Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

Category articles

General General

STAGETOOL, a novel automated approach for mouse testis histological analysis.

In Endocrinology ; h5-index 58.0

Spermatogenesis is a complex differentiation process that takes place in the seminiferous tubules. A specific organization of spermatogenic cells within the seminiferous epithelium enables a synchronous progress of germ cells at certain steps of differentiation on the spermatogenic pathway. This can be observed in testis cross-sections where seminiferous tubules can be classified into distinct stages of constant cellular composition (twelve stages in the mouse). For a detailed analysis of spermatogenesis, these stages have to be individually observed from testis cross-sections. However, the recognition of stages requires special training and expertise. Furthermore, the manual scoring is laborious considering the high number of tubule cross-sections that have to be analyzed. To facilitate the analysis of spermatogenesis, we have developed a convolutional deep neural network-based approach named "STAGETOOL". STAGETOOL analyses histological images of DAPI-stained mouse testis cross-sections at ×400 magnification, and very accurately classifies tubule cross-sections into five stage classes and cells into nine categories. STAGETOOL classification accuracy for stage classes of seminiferous tubules of a whole-testis cross-section is 99.1%. For cellular level analysis the F1 score for nine seminiferous epithelial cell types ranges 0.80-0.98. Furthermore, we show that STAGETOOL can be applied for the analysis of knockout mouse models with spermatogenic defects, as well as for automated profiling of protein expression patterns. STAGETOOL is the first fluorescent labeling-based automated method for mouse testis histological analysis that enables both stage and cell-type recognition. While STAGETOOL qualitatively parallels an experienced human histologist, it outperforms human time-wise, therefore representing a major advancement in male reproductive biology research.

Meikar Oliver, Majoral Daniel, Heikkinen Olli, Valkama Eero, Leskinen Sini, Rebane Ana, Ruusuvuori Pekka, Toppari Jorma, Mäkelä Juho-Antti, Kotaja Noora

2022-Dec-03

DAPI staining, Mouse testis histology, automated analysis, deep learning, seminiferous epithelial cycle, spermatogenesis

General General

Natural History and Real-World Data in Rare Diseases: Applications, Limitations, and Future Perspectives.

In Journal of clinical pharmacology

Rare diseases represent a highly heterogeneous group of disorders with high phenotypic and genotypic diversity within individual conditions. Due to the small numbers of people affected, there are unique challenges in understanding rare diseases and drug development for these conditions, including patient identification and recruitment, trial design, and costs. Natural history data and real-world data (RWD) play significant roles in defining and characterizing disease progression, final patient populations, novel biomarkers, genetic relationships, and treatment effects. This review provides an introduction to rare diseases, natural history data, RWD, and real-world evidence, the respective sources and applications of these data in several rare diseases. Considerations for data quality and limitations when using natural history and RWD are also elaborated. Opportunities are highlighted for cross-sector collaboration, standardized and high-quality data collection using new technologies, and more comprehensive evidence generation using quantitative approaches such as disease progression modeling, artificial intelligence, and machine learning. Advanced statistical approaches to integrate natural history data and RWD to further disease understanding and guide more efficient clinical study design and data analysis in drug development in rare diseases are also discussed.

Liu Jing, Barrett Jeffrey S, Leonardi Efthimia T, Lee Lucy, Roychoudhury Satrajit, Chen Yong, Trifillis Panayiota

2022-Dec

disease progression modeling, natural history, rare diseases, real-world data, real-world evidence

General General

AlphaFold2: A versatile tool to predict the appearance of functional adaptations in evolution: Profilin interactions in uncultured Asgard archaea: Profilin interactions in uncultured Asgard archaea.

In BioEssays : news and reviews in molecular, cellular and developmental biology

The release of AlphaFold2 (AF2), a deep-learning-aided, open-source protein structure prediction program, from DeepMind, opened a new era of molecular biology. The astonishing improvement in the accuracy of the structure predictions provides the opportunity to characterize protein systems from uncultured Asgard archaea, key organisms in evolutionary biology. Despite the accumulation in metagenomics-derived Asgard archaea eukaryotic-like protein sequences, limited structural and biochemical information have restricted the insight in their potential functions. In this review, we focus on profilin, an actin-dynamics regulating protein, which in eukaryotes, modulates actin polymerization through (1) direct actin interaction, (2) polyproline binding, and (3) phospholipid binding. We assess AF2-predicted profilin structures in their potential abilities to participate in these activities. We demonstrate that AF2 is a powerful new tool for understanding the emergence of biological functional traits in evolution.

Ponlachantra Khongpon, Suginta Wipa, Robinson Robert C, Kitaoku Yoshihito

2022-Dec-03

AlphaFold2, Asgard archaea, actin cytoskeleton, eukaryogenesis, evolution, pofilin

General General

AMP-BERT: Prediction of Antimicrobial Peptide Function Based on a BERT Model.

In Protein science : a publication of the Protein Society

Antimicrobial resistance is a growing health concern. Antimicrobial peptides (AMPs) disrupt harmful microorganisms by non-specific mechanisms, making it difficult for microbes to develop resistance. Accordingly, they are promising alternatives to traditional antimicrobial drugs. In this study, we developed an improved AMP classification model, called AMP-BERT. We propose a deep learning model with a fine-tuned BERT architecture designed to extract structural/functional information from input peptides and identify each input as AMP or non-AMP. We compared the performance of our proposed model and other machine/deep learning-based methods. Our model, AMP-BERT, yielded the best prediction results among all models evaluated with our curated external dataset. In addition, we utilized the attention mechanism in BERT to implement an interpretable feature analysis and determine the specific residues in known AMPs that contribute to peptide structure and antimicrobial function. The results show that AMP-BERT can capture the structural properties of peptides for model learning, enabling the prediction of AMPs or non-AMPs from input sequences. AMP-BERT is expected to contribute to the identification of candidate AMPs for functional validation and drug development. The code and dataset for the fine-tuning of AMP-BERT is publicly available at https://github.com/GIST-CSBL/AMP-BERT. This article is protected by copyright. All rights reserved.

Lee Hansol, Lee Songyeon, Lee Ingoo, Nam Hojung

2022-Dec-03

Antimicrobial peptides, BERT, Transformer, antimicrobial resistance, deep learning, drug discovery, machine learning, sequence classification

General General

PHEVIR: an artificial intelligence algorithm that predicts the molecular role of pathogens in complex human diseases.

In Scientific reports ; h5-index 158.0

Infectious diseases are known to cause a wide variety of post-infection complications. However, it's been challenging to identify which diseases are most associated with a given pathogen infection. Using the recently developed LeMeDISCO approach that predicts comorbid diseases associated with a given set of putative mode of action (MOA) proteins and pathogen-human protein interactomes, we developed PHEVIR, an algorithm which predicts the corresponding human disease comorbidities of 312 viruses and 57 bacteria. These predictions provide an understanding of the molecular bases of complications and means of identifying appropriate drug targets to treat them. As an illustration of its power, PHEVIR is applied to identify putative driver pathogens and corresponding human MOA proteins for Type 2 diabetes, atherosclerosis, Alzheimer's disease, and inflammatory bowel disease. Additionally, we explore the origins of the oncogenicity/oncolyticity of certain pathogens and the relationship between heart disease and influenza. The full PHEVIR database is available at https://sites.gatech.edu/cssb/phevir/ .

Zhou Hongyi, Astore Courtney, Skolnick Jeffrey

2022-Dec-03

General General

Volumetric imaging of fast cellular dynamics with deep learning enhanced bioluminescence microscopy.

In Communications biology

Bioluminescence microscopy is an appealing alternative to fluorescence microscopy, because it does not depend on external illumination, and consequently does neither produce spurious background autofluorescence, nor perturb intrinsically photosensitive processes in living cells and animals. The low photon emission of known luciferases, however, demands long exposure times that are prohibitive for imaging fast biological dynamics. To increase the versatility of bioluminescence microscopy, we present an improved low-light microscope in combination with deep learning methods to image extremely photon-starved samples enabling subsecond exposures for timelapse and volumetric imaging. We apply our method to image subcellular dynamics in mouse embryonic stem cells, epithelial morphology during zebrafish development, and DAF-16 FoxO transcription factor shuttling from the cytoplasm to the nucleus under external stress. Finally, we concatenate neural networks for denoising and light-field deconvolution to resolve intracellular calcium dynamics in three dimensions of freely moving Caenorhabditis elegans.

Morales-Curiel Luis Felipe, Gonzalez Adriana Carolina, Castro-Olvera Gustavo, Lin Li-Chun Lynn, El-Quessny Malak, Porta-de-la-Riva Montserrat, Severino Jacqueline, Morera Laura Battle, Venturini Valeria, Ruprecht Verena, Ramallo Diego, Loza-Alvarez Pablo, Krieg Michael

2022-Dec-03

General General

Tree species composition mapping with dimension reduction and post-classification using very high-resolution hyperspectral imaging.

In Scientific reports ; h5-index 158.0

Tree species' composition of forests is essential in forest management and nature conservation. We aimed to identify the tree species structure of a floodplain forest area using a hyperspectral image. We proposed an efficient novel strategy including the testing of three dimension reduction (DR) methods: Principal Component Analysis, Minimum Noise Fraction (MNF) and Indipendent Component Analysis with five machine learning (ML) algorithms (Maximum Likelihood Classifier, Support Vector Classification, Support Vector Machine, Random Forest and Artificial Neural Network) to find the most accurate outcome; altogether 300 models were calculated. Post-classification was applied by combining the multiresolution segmentation and filtering. MNF was the most efficient DR technique, and at least 7 components were needed to gain an overall accuracy (OA) of > 75%. Forty-five models had > 80% OAs; MNF was 43, and the Maximum Likelihood was 19 times among these models. Best classification belonged to MNF with 10 components and Maximum Likelihood classifier with the OA of 83.3%. Post-classification increased the OA to 86.1%. We quantified the differences among the possible DR and ML methods, and found that even > 10% worse model can be found using popular standard procedures related to the best results. Our workflow calls the attention of careful model selection to gain accurate maps.

Likó Szilárd Balázs, Bekő László, Burai Péter, Holb Imre J, Szabó Szilárd

2022-Dec-03

General General

Machine-learning-based ground sink susceptibility evaluation using underground pipeline data in Korean urban area.

In Scientific reports ; h5-index 158.0

Ground subsidence caused by natural factors, including groundwater, has been extensively researched. However, there have been few studies on ground sink caused mainly by artifacts, including underground pipelines in urban areas. This paper proposes a method of predicting ground sink susceptibility caused by underground pipelines. Underground pipeline data, drilling data, and 77 points of ground sink occurrence were collected for five 1 × 1 km urban areas. Furthermore, three ground sink conditioning factors (GSCFs) (pipe deterioration, diameter, and length) were identified by correlation analysis. Pipe deterioration showed the highest correlation with ground sink occurrence, followed by pipe length and pipe diameter in that order. Next, four machine learning methods [multinomial logistic regression (MLR), decision tree (DT) classifier, random forest (RF) classifier, and gradient boosting (GB) classifier] were applied. The results show that GB classifier had the highest accuracy of 0.7432, whereas the accuracy of RF classifier was 0.7407; thus, GB classifier was not significantly more accurate. RF classifier showed the highest reliability (0.84, 0.70, 0.87) according to the area under the receiver operating characteristic (AUC-ROC) curve. Ground sink susceptibility maps (GSSMs) of the five regions in an urban area were created using RF classifier, which performed the best overall.

Park Jun Hwan, Kang Junggoo, Kang Jaemo, Mun Duhwan

2022-Dec-03

General General

Evaluation of six machine learning classification algorithms in pig breed identification using SNPs array data.

In Animal genetics

Breed identification utilizing multiple information sources and methods is widely applicated in the field of animal genetics and breeding. Simultaneously, with the development of artificial intelligence, the integration of high-throughput genomic data and machine learning techniques is increasingly used for breed identification. In this context, we used 654 individuals from 15 pig breeds, evaluating the performance of machine learning and stacking ensemble learning classifiers, as well as the function of feature selection and anomaly detection in different scenarios. Our results showed that, when using a training set of 16 individuals per breed and 32 features (SNPs), the accuracy of breed identification with feature selection (eXtreme Gradient Boosting, XGBoost) could exceed 95.00% (nine breeds), and was improved by 7.04% over the results with random selection. For stacking ensemble learning, feature selection methods (including random selection method) were used before different base learners. When these base learners' training set had 16 individuals per breed and 32 features, the accuracy of stacking ensemble learning improved by 9.24% over the best base learner (nine breeds), but did not significantly increase the advantage over the models with XGBoost feature selection. When using a training set of 16 individuals and 512 features per breed, breed identification with anomaly detection (local outlier factor, LOF) and random selection could achieve an accuracy of 89.06% (15 breeds). These results show that machine learning could be an effective tool for breed identification and this study will also provide useful information for the application of machine learning in animal genetics and breeding.

Liu Ruiqi, Xu Zhiting, Teng Jinyan, Pan Xiangchun, Lin Qing, Cai Xiaodian, Diao Shuqi, Feng Xueyan, Yuan Xiaolong, Li Jiaqi, Zhang Zhe

2022-Dec-02

anomaly detection, breed identification, feature selection, machine learning, stacking ensemble

General General

Bootstrapping random forest and CHAID for prediction of white spot disease among shrimp farmers.

In Scientific reports ; h5-index 158.0

Technology is playing an important role is healthcare particularly as it relates to disease prevention and detection. This is evident in the COVID-19 era as different technologies were deployed to test, detect and track patients and ensure COVID-19 protocol compliance. The White Spot Disease (WSD) is a very contagious disease caused by virus. It is widespread among shrimp farmers due to its mode of transmission and source. Considering the growing concern about the severity of the disease, this study provides a predictive model for diagnosis and detection of WSD among shrimp farmers using visualization and machine learning algorithms. The study made use of dataset from Mendeley repository. Machine learning algorithms; Random Forest classification and CHAID were applied for the study, while Python was used for implementation of algorithms and for visualization of results. The results achieved showed high prediction accuracy (98.28%) which is an indication of the suitability of the model for accurate prediction of the disease. The study would add to growing knowledge about use of technology to manage White Spot Disease among shrimp farmers and ensure real-time prediction during and post COVID-19.

Edeh Michael Onyema, Dalal Surjeet, Obagbuwa Ibidun Christiana, Prasad B V V Siva, Ninoria Shalini Zanzote, Wajid Mohd Anas, Adesina Ademola Olusola

2022-Dec-03

Radiology Radiology

Developing current procedural terminology codes that describe the work performed by machines.

In NPJ digital medicine

The "Taxonomy of Artificial Intelligence for Medical Services and Procedures" became part of the Current Procedural Terminology (CPT®) code set effective January 1, 2022. It provides a framework for discrete and differentiable CPT codes which; are consistent with the features of the devices' output, characterize interaction between the device and the physician or other qualified health care professional, and foster appropriate payment. Descriptors include "Assistive", "Augmentative", and "Autonomous". As software increasingly augments the provision of medical services the taxonomy will foster consistent language in coding enabling patient, provider, and payer access to the benefits of innovation.

Frank Richard A, Jarrin Robert, Pritzker Jordan, Abramoff Michael D, Repka Michael X, Baird Pat D, Marlene Grenon S, Mahoney Megan Ruth, Mattison John E, Silva Ezequiel

2022-Dec-03

Cardiology Cardiology

Gene expression associations with body mass index in the Multi-Ethnic Study of Atherosclerosis.

In International journal of obesity (2005)

BACKGROUND/OBJECTIVES : Obesity, defined as excessive fat accumulation that represents a health risk, is increasing in adults and children, reaching global epidemic proportions. Body mass index (BMI) correlates with body fat and future health risk, yet differs in prediction by fat distribution, across populations and by age. Nonetheless, few genetic studies of BMI have been conducted in ancestrally diverse populations. Gene expression association with BMI was assessed in the Multi-Ethnic Study of Atherosclerosis (MESA) in four self-identified race and ethnicity (SIRE) groups to identify genes associated with obesity.

SUBJECTS/METHODS : RNA-sequencing was performed on 1096 MESA participants (37.8% white, 24.3% Hispanic, 28.4% African American, and 9.5% Chinese American) and linear models were used to assess the association of expression from each gene for its effect on BMI, adjusting for age, sex, sequencing center, study site, five expression and four genetic principal components in each self-identified race group. Sample-size-weighted meta-analysis was performed to identify genes with BMI-associated expression across ancestry groups.

RESULTS : Within individual SIRE groups, there were zero to three genes whose expression is significantly (p < 1.97 × 10-6) associated with BMI. Across all groups, 45 genes were identified by meta-analysis whose expression was significantly associated with BMI, explaining 29.7% of BMI variation. The 45 genes are expressed in a variety of tissues and cell types and are enriched for obesity-related processes including erythrocyte function, oxygen binding and transport, and JAK-STAT signaling.

CONCLUSIONS : We have identified genes whose expression is significantly associated with obesity in a multi-ethnic cohort. We have identified novel genes associated with BMI as well as confirmed previously identified genes from earlier genetic analyses. These novel genes and their biological pathways represent new targets for understanding the biology of obesity as well as new therapeutic intervention to reduce obesity and improve global public health.

Vargas Luciana B, Lange Leslie A, Ferrier Kendra, Aguet François, Ardlie Kristin, Gabriel Stacey, Gupta Namrata, Smith Joshua D, Blackwell Thomas W, Ding Jingzhong, Durda Peter, Tracy Russell P, Liu Yongmei, Taylor Kent D, Craig Johnson W, Rich Stephen S, Rotter Jerome I, Lange Ethan M, Konigsberg Iain R

2022-Dec-03

General General

An artificial neural network explains how bats might use vision for navigation.

In Communications biology

Animals navigate using various sensory information to guide their movement. Miniature tracking devices now allow documenting animals' routes with high accuracy. Despite this detailed description of animal movement, how animals translate sensory information to movement is poorly understood. Recent machine learning advances now allow addressing this question with unprecedented statistical learning tools. We harnessed this power to address visual-based navigation in fruit bats. We used machine learning and trained a convolutional neural network to navigate along a bat's route using visual information that would have been available to the real bat, which we collected using a drone. We show that a simple feed-forward network can learn to guide the agent towards a goal based on sensory input, and can generalize its learning both in time and in space. Our analysis suggests how animals could potentially use visual input for navigation and which features might be useful for this purpose.

Goldshtein Aya, Akrish Shimon, Giryes Raja, Yovel Yossi

2022-Dec-03

oncology Oncology

Prediction of distant metastasis in esophageal cancer using a radiomics-clinical model.

In European journal of medical research

BACKGROUND : Distant metastasis, which occurs at a rate of 25% in patients with esophageal cancer (EC), has a poor prognosis, with previous studies reporting an overall survival of only 3-10 months. However, few studies have been conducted to predict distant metastasis in EC, owing to a dearth of reliable biomarkers. The purpose of this study was to develop and validate an accurate model for predicting distant metastasis in patients with EC.

METHODS : A total of 299 EC patients were enrolled and randomly assigned to a training cohort (n = 207) and a validation cohort (n = 92). Logistic univariate and multivariate regression analyses were used to identify clinical independent predictors and create a clinical nomogram. Radiomic features were extracted from contrast-enhanced computed tomography (CT) images taken prior to treatment, and least absolute shrinkage and selection operator (Lasso) regression was used to screen the associated features, which were then used to develop a radiomic signature. Based on the screened features, four machine learning algorithms were used to build radiomics models. The joint nomogram with radiomic signature and clinically independent risk factors was developed using the logical regression algorithm. All models were validated and compared by discrimination, calibration, reclassification, and clinical benefit.

RESULTS : Multivariable analyses revealed that age, N stage, and degree of pathological differentiation were independent predictors of distant metastasis, and a clinical nomogram incorporating these factors was established. A radiomic signature was developed by a set of sixteen features chosen from 851 radiomic features. The joint nomogram incorporating clinical factors and radiomic signature performed better [AUC(95% CI) 0.827(0.742-0.912)] than the clinical nomogram [AUC(95% CI) 0.731(0.626-0.836)] and radiomics predictive models [AUC(95% CI) 0.754(0.652-0.855), LR algorithms]. Calibration and decision curve analyses revealed that the radiomics-clinical nomogram outperformed the other models. In comparison with the clinical nomogram, the joint nomogram's NRI was 0.114 (95% CI 0.075-0.345), and its IDI was 0.071 (95% CI 0.030-0.112), P = 0.001.

CONCLUSIONS : We developed and validated the first radiomics-clinical nomogram for distant metastasis in EC which may aid clinicians in identifying patients at high risk of distant metastasis.

Zhu Chao, Mu Fengchun, Wang Songping, Qiu Qingtao, Wang Shuai, Wang Linlin

2022-Dec-03

General General

A probabilistic computational framework for the prediction of corrosion-induced cracking in large structures.

In Scientific reports ; h5-index 158.0

Corrosion can initiate cracking that leads to structural integrity reduction. Quantitative corrosion assessment is challenging, and the modeling of corrosion-induced crack initiation is essential for model-based corrosion reliability analysis of various structures. This paper proposes a probabilistic computational analysis framework for corrosion-to-crack transitions by integrating a phase-field model with machine learning and uncertainty quantification. An electro-chemo-mechanical phase-field model is modified to predict pitting corrosion evolution, in which stress is properly coupled into the electrode chemical potential. A crack initiation criterion based on morphology is proposed to quantify the pit-to-cracking transition. A spatiotemporal surrogate modeling method is developed to facilitate this, consisting of a Convolution Neural Network (CNN) to map corrosion morphology to latent spaces, and a Gaussian Process regression model with a nonlinear autoregressive exogenous model (NARX) architecture for prediction of corrosion dynamics in the latent space over time. It enables the real-time prediction of corrosion morphology and crack initiation behaviors (whether, when, and where the corrosion damage triggers the crack initiation), and thus makes it possible for probabilistic analysis, with uncertainty quantified. Examples at various stress and corrosion conditions are presented to demonstrate the proposed computational framework.

Qian Guofeng, Tantratian Karnpiwat, Chen Lei, Hu Zhen, Todd Michael D

2022-Dec-03

General General

Bootstrapping random forest and CHAID for prediction of white spot disease among shrimp farmers.

In Scientific reports ; h5-index 158.0

Technology is playing an important role is healthcare particularly as it relates to disease prevention and detection. This is evident in the COVID-19 era as different technologies were deployed to test, detect and track patients and ensure COVID-19 protocol compliance. The White Spot Disease (WSD) is a very contagious disease caused by virus. It is widespread among shrimp farmers due to its mode of transmission and source. Considering the growing concern about the severity of the disease, this study provides a predictive model for diagnosis and detection of WSD among shrimp farmers using visualization and machine learning algorithms. The study made use of dataset from Mendeley repository. Machine learning algorithms; Random Forest classification and CHAID were applied for the study, while Python was used for implementation of algorithms and for visualization of results. The results achieved showed high prediction accuracy (98.28%) which is an indication of the suitability of the model for accurate prediction of the disease. The study would add to growing knowledge about use of technology to manage White Spot Disease among shrimp farmers and ensure real-time prediction during and post COVID-19.

Edeh Michael Onyema, Dalal Surjeet, Obagbuwa Ibidun Christiana, Prasad B V V Siva, Ninoria Shalini Zanzote, Wajid Mohd Anas, Adesina Ademola Olusola

2022-Dec-03

General General

EyeT4Empathy: Dataset of foraging for visual information, gaze typing and empathy assessment.

In Scientific data

We present a dataset of eye-movement recordings collected from 60 participants, along with their empathy levels, towards people with movement impairments. During each round of gaze recording, participants were divided into two groups, each one completing one task. One group performed a task of free exploration of structureless images, and a second group performed a task consisting of gaze typing, i.e. writing sentences using eye-gaze movements on a card board. The eye-tracking data recorded from both tasks is stored in two datasets, which, besides gaze position, also include pupil diameter measurements. The empathy levels of participants towards non-verbal movement-impaired people were assessed twice through a questionnaire, before and after each task. The questionnaire is composed of forty questions, extending a established questionnaire of cognitive and affective empathy. Finally, our dataset presents an opportunity for analysing and evaluating, among other, the statistical features of eye-gaze trajectories in free-viewing as well as how empathy is reflected in eye features.

Lencastre Pedro, Bhurtel Samip, Yazidi Anis, E Mello Gustavo B M, Denysov Sergiy, Lind Pedro G

2022-Dec-03

Surgery Surgery

Noninvasive prediction of axillary lymph node status in breast cancer using promoter profiling of circulating cell-free DNA.

In Journal of translational medicine

BACKGROUND : Lymph node metastasis (LNM) is one of the most important factors affecting the prognosis of breast cancer. The accurate evaluation of lymph node status is useful to predict the outcomes of patients and guide the choice of cancer treatment. However, there is still lack of a low-cost non-invasive method to assess the status of axillary lymph node (ALN). Gene expression signature has been used to assess lymph node metastasis status of breast cancer. In addition, nucleosome footprint of cell-free DNA (cfDNA) carries gene expression information of its original tissues, so it may be used to evaluate the axillary lymph node status in breast cancer.

METHODS : In this study, we found that the cfDNA nucleosome footprints between the ALN-positive patients and ALN-negative patients showed different patterns by implementing whole-genome sequencing (WGS) to detect 15 ALN-positive and 15 ALN-negative patients. In order to further evaluate its potential for assessing ALN status, we developed a classifier with multiple machine learning models by using 330 WGS data of cfDNA from 162 ALN-positive and 168 ALN-negative samples to distinguish these two types of patients.

RESULTS : We found that the promoter profiling between the ALN-positive patients and ALN-negative patients showed distinct patterns. In addition, we observed 1071 genes with differential promoter coverage and their functions were closely related to tumorigenesis. We found that the predictive classifier based on promoter profiling with a support vector machine model, named PPCNM, produced the largest area under the curve of 0.897 (95% confidence interval 0.86-0.93).

CONCLUSIONS : These results indicate that promoter profiling can be used to distinguish ALN-positive patients from ALN-negative patients, which may be helpful to guide the choice of cancer treatment.

Guo Zhi-Wei, Liu Qing, Yang Xu, Cai Geng-Xi, Han Bo-Wei, Huang Li-Min, Li Chun-Xi, Liang Zhi-Kun, Zhai Xiang-Ming, Lin Li, Li Kun, Zhang Min, Liu Tian-Cai, Pan Rui-Lin, Wu Ying-Song, Yang Xue-Xi

2022-Dec-03

Breast cancer, Cell-free DNA, Lymph node metastasis, Promoter profiling, Whole-genome sequencing

General General

Cervical pre-cancerous lesion detection: development of smartphone-based VIA application using artificial intelligence.

In BMC research notes

OBJECTIVE : Visual inspection of cervix after acetic acid application (VIA) has been considered an alternative to Pap smear in resource-limited settings, like Indonesia. However, VIA results mainly depend on examiner's experience and with the lack of comprehensive training of healthcare workers, VIA accuracy keeps declining. We aimed to develop an artificial intelligence (AI)-based Android application that can automatically determine VIA results in real time and may be further developed as a health care support system in cervical cancer screening.

RESULT : A total of 199 women who underwent VIA test was studied. Images of cervix before and after VIA test were taken with smartphone, then evaluated and labelled by experienced oncologist as VIA positive or negative. Our AI model training pipeline consists of 3 steps: image pre-processing, feature extraction, and classifier development. Out of the 199 data, 134 were used as train-validation data and the remaining 65 data were used as test data. The trained AI model generated a sensitivity of 80%, specificity of 96.4%, accuracy of 93.8%, precision of 80%, and ROC/AUC of 0.85 (95% CI 0.66-1.0). The developed AI-based Android application may potentially aid cervical cancer screening, especially in low resource settings.

Harsono Ali Budi, Susiarno Hadi, Suardi Dodi, Owen Louis, Fauzi Hilman, Kireina Jessica, Wahid Rizki Amalia, Carolina Johanna Sharon, Mantilidewi Kemala Isnainiasih, Hidayat Yudi Mulyana

2022-Dec-03

Artificial intelligence, Cervical cancer screening, Image processing, Low-resource settings, VIA

Surgery Surgery

Morbidity and Mortality Associated With Blood Transfusions in Elective Adult Cardiac Surgery.

In Journal of cardiothoracic and vascular anesthesia ; h5-index 35.0

OBJECTIVES : Perioperative transfusion thresholds have garnered increasing scrutiny as restrictive strategies have been shown to be noninferior. The study authors used data from a statewide academic collaborative to test the association between transfusion and 30-day mortality.

DESIGN : All adult patients undergoing coronary artery bypass grafting (CABG) and/or valve surgeries between 2013 and 2019 in the authors' Academic Cardiac Surgery Consortium were examined. The relationship between the number of overall packed red blood cell (pRBC) and coagulation product (CP) (fresh frozen plasma, cryoprecipitate, platelets) transfusions on 30-day mortality was evaluated. Multivariate regression was used to evaluate predictors of transfusion and study endpoints. Machine learning (ML) models also were developed to predict 30-day mortality and rank transfusion-related features by relative importance.

SETTING : At an Academic Cardiac Surgery Consortium of 5 institutions.

PARTICIPANTS : Patients ≥18 years old undergoing CABG and/or valve surgeries.

MEASUREMENTS AND MAIN RESULTS : Of the 7,762 patients (median hematocrit [HCT] 39%, IQR 35%-43%) who were included in the final study cohort, >40% were transfused at least 1 unit of pRBC or CP. In adjusted analyses, higher preoperative HCT was associated with reduced odds of mortality (adjusted odds ratio [aOR] 0.95, 95% CI 0.92-0.98), renal failure (aOR 0.95, 95% CI 0.92-0.98), and prolonged mechanical ventilation (aOR 0.97, 95% CI 0.95-0.99). In contrast, perioperative transfusions were associated with increased 30-day mortality after adjustment for preoperative HCT and other baseline features. The ML models were able to predict 30-day mortality with an area under the curve of 0.814-to-0.850, with perioperative transfusions displaying the highest feature importance.

CONCLUSIONS : The present analysis found increasing HCT to be associated with a lower incidence of mortality. The study authors also found a direct dose-response association between transfusions and all study endpoints examined.

Sanaiha Yas, Hadaya Joseph, Verma Arjun, Shemin Richard J, Madani Michael, Young Nilas, Deuse Tobias, Sun Jack, Benharash Peyman

2022-Nov-17

coronary artery bypass, health care economics and organizations, heat valve prosthesis implantation, outcome assessment, health care, quality of health care

General General

Psychological stress recognition from heart rate variability parameters based on field programmable gate arrays.

In The Review of scientific instruments

Psychological stress is a big threat to people's health. Early detection of psychological stress is important. The design of a stress recognition device based on the ECG (electrocardiograph) signal is presented in this paper. The device features intelligence, precision, portability, fast response, and low power consumption. In the design, the ECG signals are acquired by the AD8232 ECG module and processed by a low power consumption FPGA (Field Programmable Gated Array) development board PYNQ-Z2. Meanwhile, a modified Deep Forest model named Aw-Deep Forest (Adaptive Weight Deep Forest) is proposed. The Aw-Deep Forest has better performance than the Deep Forest model because it improves the fitting quality of the forests. By implementing the Aw-Deep Forest model on the FPGA, the device can assess people's state of psychological stress by analyzing the HRV (heart rate variability) parameters from ECG data. This paper mainly introduces the detailed process of ECG signal collecting, filtering, analog signal to digital signal conversion, HRV parameter analysis, and psychological stress recognition with Aw-Deep Forest. The final accuracy is 81.39%.

Wang Jian, Wang Houqin, Luo Yuemei, Tang Hongying, Mao Hongwei, Bi Shubo

2022-Nov-01

General General

COVID-DSNet: A novel deep convolutional neural network for detection of coronavirus (SARS-CoV-2) cases from CT and Chest X-Ray images.

In Artificial intelligence in medicine ; h5-index 34.0

COVID-19 (SARS-CoV-2), which causes acute respiratory syndrome, is a contagious and deadly disease that has devastating effects on society and human life. COVID-19 can cause serious complications, especially in patients with pre-existing chronic health problems such as diabetes, hypertension, lung cancer, weakened immune systems, and the elderly. The most critical step in the fight against COVID-19 is the rapid diagnosis of infected patients. Computed Tomography (CT), chest X-ray (CXR), and RT-PCR diagnostic kits are frequently used to diagnose the disease. However, due to difficulties such as the inadequacy of RT-PCR test kits and false negative (FN) results in the early stages of the disease, the time-consuming examination of medical images obtained from CT and CXR imaging techniques by specialists/doctors, and the increasing workload on specialists, it is challenging to detect COVID-19. Therefore, researchers have suggested searching for new methods in COVID- 19 detection. In analysis studies with CT and CXR radiography images, it was determined that COVID-19-infected patients experienced abnormalities related to COVID-19. The anomalies observed here are the primary motivation for artificial intelligence researchers to develop COVID-19 detection applications with deep convolutional neural networks. Here, convolutional neural network-based deep learning algorithms from artificial intelligence technologies with high discrimination capabilities can be considered as an alternative approach in the disease detection process. This study proposes a deep convolutional neural network, COVID-DSNet, to diagnose typical pneumonia (bacterial, viral) and COVID-19 diseases from CT, CXR, hybrid CT + CXR images. In the multi-classification study with the CT dataset, 97.60 % accuracy and 97.60 % sensitivity values were obtained from the COVID-DSNet model, and 100 %, 96.30 %, and 96.58 % sensitivity values were obtained in the detection of typical, common pneumonia and COVID-19, respectively. The proposed model is an economical, practical deep learning network that data scientists can benefit from and develop. Although it is not a definitive solution in disease diagnosis, it may help experts as it produces successful results in detecting pneumonia and COVID-19.

Reis Hatice Catal, Turk Veysel

2022-Dec

COVID-DSNet, Chest CT-scan images, Chest X-ray images, Depthwise separable convolution, SARS-CoV-2

General General

IDT: An incremental deep tree framework for biological image classification.

In Artificial intelligence in medicine ; h5-index 34.0

Nowadays, breast and cervical cancers are respectively the first and fourth most common causes of cancer death in females. It is believed that, automated systems based on artificial intelligence would allow the early diagnostic which increases significantly the chances of proper treatment and survival. Although Convolutional Neural Networks (CNNs) have achieved human-level performance in object classification tasks, the regular growing of the amount of medical data and the continuous increase of the number of classes make them difficult to learn new tasks without being re-trained from scratch. Nevertheless, fine tuning and transfer learning in deep models are techniques that lead to the well-known catastrophic forgetting problem. In this paper, an Incremental Deep Tree (IDT) framework for biological image classification is proposed to address the catastrophic forgetting of CNNs allowing them to learn new classes while maintaining acceptable accuracies on the previously learnt ones. To evaluate the performance of our approach, the IDT framework is compared against with three popular incremental methods, namely iCaRL, LwF and SupportNet. The experimental results on MNIST dataset achieved 87 % of accuracy and the obtained values on the BreakHis, the LBC and the SIPaKMeD datasets are promising with 92 %, 98 % and 93 % respectively.

Mousser Wafa, Ouadfel Salima, Taleb-Ahmed Abdelmalik, Kitouni Ilham

2022-Dec

Biological image classification, Breast cancer, Catastrophic forgetting, Cervical cancer, Convolutional neural networks, Incremental learning

General General

Medical resource allocation planning by integrating machine learning and optimization models.

In Artificial intelligence in medicine ; h5-index 34.0

Patients' waiting time is a major issue in the Canadian healthcare system. The planning for resource allocation impacts patients' waiting time in medicare settings. This research focuses on the reduction of patients' waiting time by providing better planning for radiological resource allocation and efficient workload distribution. Resource allocation planning is directly related to the number of patient-arrival and it is hard to predict such uncertain parameters in the future time frame. The number of patient-arrival also varies across different modalities and different timeframes which makes the patient-arrival prediction challenging. In this research, a new three-phase solution framework is proposed where a new multi-target machine learning technique is integrated with an optimization model. In the first phase, a novel Ensemble of Pruned Regressor Chain (EPRC) model is developed and trained offline to predict uncertain parameters, such as patients' arrival. The proposed model is then compared with two popular multi-target prediction methods to evaluate the model's accuracy. In the second phase, the trained model is deployed in the real-time environment to forecast patients' arrival, miss Turn Around Time (miss-TAT) rate, and probable workload count. The forecasted data is used in phase three where a new multi-objective optimization model is developed to determine workload allocation. The Weighted-sum method is used to get efficient solutions. The proposed model is deployed in a Canadian healthcare company and evaluated using real-time healthcare data. It is observed in terms of accuracy, the proposed EPRC model performed 10.81 % better compared to the other multi-target models considered in this study. It is also noticed that the forecasting results have a direct impact on the workload distribution, where the proposed model decreases the total workload by approximately 25 %. Besides, the result shows the efficient workload distribution provided by the proposed framework can reduce the average patients' waiting time by 8.17 %.

Mizan Tasquia, Taghipour Sharareh

2022-Dec

Machine learning, Multi-objective optimization, Multi-target forecasting, Resource allocation planning, Workload distribution

Public Health Public Health

A non-invasive machine learning mechanism for early disease recognition on Twitter: The case of anemia.

In Artificial intelligence in medicine ; h5-index 34.0

Social media sites, such as Twitter, provide the means for users to share their stories, feelings, and health conditions during the disease course. Anemia, the most common type of blood disorder, is recognized as a major public health problem all over the world. Yet very few studies have explored the potential of recognizing anemia from online posts. This study proposed a novel mechanism for recognizing anemia based on the associations between disease symptoms and patients' emotions posted on the Twitter platform. We used k-means and Latent Dirichlet Allocation (LDA) algorithms to group similar tweets and to identify hidden disease topics. Both disease emotions and symptoms were mapped using the Apriori algorithm. The proposed approach was evaluated using a number of classifiers. A higher prediction accuracy of 98.96 % was achieved using Sequential Minimal Optimization (SMO). The results revealed that fear and sadness emotions are dominant among anemic patients. The proposed mechanism is the first of its kind to diagnose anemia using textual information posted on social media sites. It can advance the development of intelligent health monitoring systems and clinical decision-support systems.

Sarsam Samer Muthana, Al-Samarraie Hosam, Alzahrani Ahmed Ibrahim, Shibghatullah Abdul Samad

2022-Dec

Anemia recognition, Health monitoring systems, Lexicon-based approach, Machine learning, Twitter

General General

COVID-DSNet: A novel deep convolutional neural network for detection of coronavirus (SARS-CoV-2) cases from CT and Chest X-Ray images.

In Artificial intelligence in medicine ; h5-index 34.0

COVID-19 (SARS-CoV-2), which causes acute respiratory syndrome, is a contagious and deadly disease that has devastating effects on society and human life. COVID-19 can cause serious complications, especially in patients with pre-existing chronic health problems such as diabetes, hypertension, lung cancer, weakened immune systems, and the elderly. The most critical step in the fight against COVID-19 is the rapid diagnosis of infected patients. Computed Tomography (CT), chest X-ray (CXR), and RT-PCR diagnostic kits are frequently used to diagnose the disease. However, due to difficulties such as the inadequacy of RT-PCR test kits and false negative (FN) results in the early stages of the disease, the time-consuming examination of medical images obtained from CT and CXR imaging techniques by specialists/doctors, and the increasing workload on specialists, it is challenging to detect COVID-19. Therefore, researchers have suggested searching for new methods in COVID- 19 detection. In analysis studies with CT and CXR radiography images, it was determined that COVID-19-infected patients experienced abnormalities related to COVID-19. The anomalies observed here are the primary motivation for artificial intelligence researchers to develop COVID-19 detection applications with deep convolutional neural networks. Here, convolutional neural network-based deep learning algorithms from artificial intelligence technologies with high discrimination capabilities can be considered as an alternative approach in the disease detection process. This study proposes a deep convolutional neural network, COVID-DSNet, to diagnose typical pneumonia (bacterial, viral) and COVID-19 diseases from CT, CXR, hybrid CT + CXR images. In the multi-classification study with the CT dataset, 97.60 % accuracy and 97.60 % sensitivity values were obtained from the COVID-DSNet model, and 100 %, 96.30 %, and 96.58 % sensitivity values were obtained in the detection of typical, common pneumonia and COVID-19, respectively. The proposed model is an economical, practical deep learning network that data scientists can benefit from and develop. Although it is not a definitive solution in disease diagnosis, it may help experts as it produces successful results in detecting pneumonia and COVID-19.

Reis Hatice Catal, Turk Veysel

2022-Dec

COVID-DSNet, Chest CT-scan images, Chest X-ray images, Depthwise separable convolution, SARS-CoV-2

Surgery Surgery

Breast cancer detection and classification in mammogram using a three-stage deep learning framework based on PAA algorithm.

In Artificial intelligence in medicine ; h5-index 34.0

In recent years, deep learning has been used to develop an automatic breast cancer detection and classification tool to assist doctors. In this paper, we proposed a three-stage deep learning framework based on an anchor-free object detection algorithm, named the Probabilistic Anchor Assignment (PAA) to improve diagnosis performance by automatically detecting breast lesions (i.e., mass and calcification) and further classifying mammograms into benign or malignant. Firstly, a single-stage PAA-based detector roundly finds suspicious breast lesions in mammogram. Secondly, we designed a two-branch ROI detector to further classify and regress these lesions that aim to reduce the number of false positives. Besides, in this stage, we introduced a threshold-adaptive post-processing algorithm with dense breast information. Finally, the benign or malignant lesions would be classified by an ROI classifier which combines local-ROI features and global-image features. In addition, considering the strong correlation between the task of detection head of PAA and the task of whole mammogram classification, we added an image classifier that utilizes the same global-image features to perform image classification. The image classifier and the ROI classifier jointly guide to enhance the feature extraction ability and further improve the performance of classification. We integrated three public datasets of mammograms (CBIS-DDSM, INbreast, MIAS) to train and test our model and compared our framework with recent state-of-the-art methods. The results show that our proposed method can improve the diagnostic efficiency of radiologists by automatically detecting and classifying breast lesions and classifying benign and malignant mammograms.

Jiang Jiale, Peng Junchuan, Hu Chuting, Jian Wenjing, Wang Xianming, Liu Weixiang

2022-Dec

Breast cancer, Breast lesion detection, Deep learning, Object detection algorithm, Whole mammogram classification

General General

Mining context-aware resource profiles in the presence of multitasking.

In Artificial intelligence in medicine ; h5-index 34.0

Healthcare organisations are becoming increasingly aware of the need to improve their care processes and to manage their scarce resources efficiently to secure high-quality care standards. As these processes are knowledge-intensive and heavily depend on human resources, a comprehensive understanding of the complex relationship between processes and resources is indispensable for efficient resource management. Organisational mining, a subfield of Process Mining, reveals insights into how (human) resources organise their work based on analysing process execution data recorded in Health Information Systems (HIS). This can be used to, e.g., discover resource profiles which are groups of resources performing similar activity instances, providing an extensive overview of resource behaviour within healthcare organisations. Healthcare managers can employ these insights to allocate their resources efficiently, e.g., by improving the scheduling and staffing of nurses. Existing resource profiling algorithms are limited in their ability to apprehend the complex relationship between processes and resources because they do not take into account the context in which activities were executed, particularly in the context of multitasking. Therefore, this paper introduces ResProMin-MT to discover context-aware resource profiles in the presence of multitasking. In contrast to the state-of-the-art, ResProMin-MT is capable of taking into account more complex contextual activity dimensions, such as activity durations and the degree of multitasking by resources. We demonstrate the feasibility of our method within a real-life healthcare context, validated by medical domain experts.

van Hulzen Gerhardus A W M, Li Chiao-Yun, Martin Niels, van Zelst Sebastiaan J, Depaire Benoît

2022-Dec

Context-aware process mining, Healthcare processes, Multitasking, Organisational mining, Process mining, Resource profiles

General General

An explainable deep learning-based algorithm with an attention mechanism for predicting the live birth potential of mouse embryos.

In Artificial intelligence in medicine ; h5-index 34.0

In assisted reproductive technology (ART), embryos produced by in vitro fertilization (IVF) are graded according to their live birth potential, and high-grade embryos are preferentially transplanted. However, rates of live birth following clinical ART remain low worldwide. Grading is based on the embryo shape at a limited number of stages and does not consider the shape of embryos and intracellular structures, e.g., nuclei, at various stages important for normal embryogenesis. Here, we developed a Normalized Multi-View Attention Network (NVAN) that directly predicts live birth potential from the nuclear structure in live-cell fluorescence images of mouse embryos from zygote to across a wide range of stages. The input is morphological features of cell nuclei, which were extracted as multivariate time-series data by using the segmentation algorithm for mouse embryos. The classification accuracy of our method (83.87%) greatly exceeded that of existing machine-learning methods and that of visual inspection by embryo culture specialists. Our method also has a new attention mechanism that allows us to determine which values of multivariate time-series data, used to describe nuclear morphology, were the basis for the prediction. By visualizing the features that contributed most to the prediction of live birth potential, we found that the size and shape of the nucleus at the morula stage and at the time of cell division were important for live birth prediction. We anticipate that our method will help ART and developmental engineering as a new basic technology for IVF embryo selection.

Tokuoka Yuta, Yamada Takahiro G, Mashiko Daisuke, Ikeda Zenki, Kobayashi Tetsuya J, Yamagata Kazuo, Funahashi Akira

2022-Dec

Assisted reproductive technology, Attention-based recurrent neural networks, Developmental biology, Embryogenesis, Live-cell imaging, Time-series classification

General General

The applications of machine learning in HIV neutralizing antibodies research-A systematic review.

In Artificial intelligence in medicine ; h5-index 34.0

Machine learning algorithms play an essential role in bioinformatics and allow exploring the vast and noisy biological data in unrivaled ways. This paper is a systematic review of the applications of machine learning in the study of HIV neutralizing antibodies. This significant and vast research domain can pave the way to novel treatments and to a vaccine. We selected the relevant papers by investigating the available literature from the Web of Science and PubMed databases in the last decade. The computational methods are applied in neutralization potency prediction, neutralization span prediction against multiple viral strains, antibody-virus binding sites detection, enhanced antibodies design, and the study of the antibody-induced immune response. These methods are viewed from multiple angles spanning data processing, model description, feature selection, evaluation, and sometimes paper comparisons. The algorithms are diverse and include supervised, unsupervised, and generative types. Both classical machine learning and modern deep learning were taken into account. The review ends with our ideas regarding future research directions and challenges.

Dănăilă Vlad-Rareş, Avram Speranţa, Buiu Cătălin

2022-Dec

Clustering, Data preprocessing, Deep learning, Epitope detection, Feature selection, Generative algorithms, HIV antibody, Machine learning, Neural network, Neutralization breadth, Neutralization potency, Unsupervised learning

Radiology Radiology

SurvivalCNN: A deep learning-based method for gastric cancer survival prediction using radiological imaging data and clinicopathological variables.

In Artificial intelligence in medicine ; h5-index 34.0

Radiological images have shown promising effects in patient prognostication. Deep learning provides a powerful approach for in-depth analysis of imaging data and integration of multi-modal data for modeling. In this work, we propose SurvivalCNN, a deep learning structure for cancer patient survival prediction using CT imaging data and non-imaging clinical data. In SurvivalCNN, a supervised convolutional neural network is designed to extract volumetric image features, and radiomics features are also integrated to provide potentially different imaging information. Within SurvivalCNN, a novel multi-thread multi-layer perceptron module, namely, SurvivalMLP, is proposed to perform survival prediction from censored survival data. We evaluate the proposed SurvivalCNN framework on a large clinical dataset of 1061 gastric cancer patients for both overall survival (OS) and progression-free survival (PFS) prediction. We compare SurvivalCNN to three different modeling methods and examine the effects of various sets of data/features when used individually or in combination. With five-fold cross validation, our experimental results show that SurvivalCNN achieves averaged concordance index 0.849 and 0.783 for predicting OS and PFS, respectively, outperforming the compared state-of-the-art methods and the clinical model. After future validation, the proposed SurvivalCNN model may serve as a clinical tool to improve gastric cancer patient survival estimation and prognosis analysis.

Hao Degan, Li Qiong, Feng Qiu-Xia, Qi Liang, Liu Xi-Sheng, Arefan Dooman, Zhang Yu-Dong, Wu Shandong

2022-Dec

Deep learning, Gastric cancer, Medical image, Multi-modal data, Survival prediction

General General

Deep variational graph autoencoders for novel host-directed therapy options against COVID-19.

In Artificial intelligence in medicine ; h5-index 34.0

The COVID-19 pandemic has been keeping asking urgent questions with respect to therapeutic options. Existing drugs that can be repurposed promise rapid implementation in practice because of their prior approval. Conceivably, there is still room for substantial improvement, because most advanced artificial intelligence techniques for screening drug repositories have not been exploited so far. We construct a comprehensive network by combining year-long curated drug-protein/protein-protein interaction data on the one hand, and most recent SARS-CoV-2 protein interaction data on the other hand. We learn the structure of the resulting encompassing molecular interaction network and predict missing links using variational graph autoencoders (VGAEs), as a most advanced deep learning technique that has not been explored so far. We focus on hitherto unknown links between drugs and human proteins that play key roles in the replication cycle of SARS-CoV-2. Thereby, we establish novel host-directed therapy (HDT) options whose utmost plausibility is confirmed by realistic simulations. As a consequence, many of the predicted links are likely to be crucial for the virus to thrive on the one hand, and can be targeted with existing drugs on the other hand.

Ray Sumanta, Lall Snehalika, Mukhopadhyay Anirban, Bandyopadhyay Sanghamitra, Schönhuth Alexander

2022-Dec

COVID-19, Host directed therapy, Molecular interaction network, Node2Vec, Variational graph autoEncoder

General General

Segmentation of human aorta using 3D nnU-net-oriented deep learning.

In The Review of scientific instruments

Computed tomography angiography (CTA) has become the main imaging technique for cardiovascular diseases. Before performing the transcatheter aortic valve intervention operation, segmenting images of the aortic sinus and nearby cardiovascular tissue from enhanced images of the human heart is essential for auxiliary diagnosis and guiding doctors to make treatment plans. This paper proposes a nnU-Net (no-new-Net) framework based on deep learning (DL) methods to segment the aorta and the heart tissue near the aortic valve in cardiac CTA images, and verifies its accuracy and effectiveness. A total of 130 sets of cardiac CTA image data (88 training sets, 22 validation sets, and 20 test sets) of different subjects have been used for the study. The advantage of the nnU-Net model is that it can automatically perform preprocessing and data augmentation according to the input image data, can dynamically adjust the network structure and parameter configuration, and has a high model generalization ability. Experimental results show that the DL method based on nnU-Net can accurately and effectively complete the segmentation task of cardiac aorta and cardiac tissue near the root on the cardiac CTA dataset, and achieves an average Dice similarity coefficient of 0.9698 ± 0.0081. The actual inference segmentation effect basically meets the preoperative needs of the clinic. Using the DL method based on the nnU-Net model solves the problems of low accuracy in threshold segmentation, bad segmentation of organs with fuzzy edges, and poor adaptability to different patients' cardiac CTA images. nnU-Net will become an excellent DL technology in cardiac CTA image segmentation tasks.

Li Feng, Sun Lianzhong, Lam Kwok-Yan, Zhang Songbo, Sun Zhongming, Peng Bao, Xu Hongzeng, Zhang Libo

2022-Nov-01

General General

Deep variational graph autoencoders for novel host-directed therapy options against COVID-19.

In Artificial intelligence in medicine ; h5-index 34.0

The COVID-19 pandemic has been keeping asking urgent questions with respect to therapeutic options. Existing drugs that can be repurposed promise rapid implementation in practice because of their prior approval. Conceivably, there is still room for substantial improvement, because most advanced artificial intelligence techniques for screening drug repositories have not been exploited so far. We construct a comprehensive network by combining year-long curated drug-protein/protein-protein interaction data on the one hand, and most recent SARS-CoV-2 protein interaction data on the other hand. We learn the structure of the resulting encompassing molecular interaction network and predict missing links using variational graph autoencoders (VGAEs), as a most advanced deep learning technique that has not been explored so far. We focus on hitherto unknown links between drugs and human proteins that play key roles in the replication cycle of SARS-CoV-2. Thereby, we establish novel host-directed therapy (HDT) options whose utmost plausibility is confirmed by realistic simulations. As a consequence, many of the predicted links are likely to be crucial for the virus to thrive on the one hand, and can be targeted with existing drugs on the other hand.

Ray Sumanta, Lall Snehalika, Mukhopadhyay Anirban, Bandyopadhyay Sanghamitra, Schönhuth Alexander

2022-Dec

COVID-19, Host directed therapy, Molecular interaction network, Node2Vec, Variational graph autoEncoder

General General

Ubiquitous and smart healthcare monitoring frameworks based on machine learning: A comprehensive review.

In Artificial intelligence in medicine ; h5-index 34.0

During the COVID-19 pandemic, the patient care delivery paradigm rapidly shifted to remote technological solutions. Rising rates of life expectancy of older people, and deaths due to chronic diseases (CDs) such as cancer, diabetes and respiratory disease pose many challenges to healthcare. While the feasibility of Remote Patient Monitoring (RPM) with a Smart Healthcare Monitoring (SHM) framework was somewhat questionable before the COVID-19 pandemic, it is now a proven commodity and is on its way to becoming ubiquitous. More health organizations are adopting RPM to enable CD management in the absence of individual monitoring. The current studies on SHM have reviewed the applications of IoT and/or Machine Learning (ML) in the domain, their architecture, security, privacy and other network related issues. However, no study has analyzed the AI and ubiquitous computing advances in SHM frameworks. The objective of this research is to identify and map key technical concepts in the SHM framework. In this context an interesting and meaningful classification of the research articles surveyed for this work is presented. The comprehensive and systematic review is based on the "Preferred Reporting Items for Systematic Review and Meta-Analysis" (PRISMA) approach. A total of 2540 papers were screened from leading research archives from 2016 to March 2021, and finally, 50 articles were selected for review. The major advantages, developments, distinctive architectural structure, components, technical challenges and possibilities in SHM are briefly discussed. A review of various recent cloud and fog computing based architectures, major ML implementation challenges, prospects and future trends is also presented. The survey primarily encourages the data driven predictive analytics aspects of healthcare and the development of ML models for health empowerment.

Motwani Anand, Shukla Piyush Kumar, Pawar Mahesh

2022-Dec

Big data, Chronic diseases, Cloud computing, Cognitive computing, Data analytics, Edge computing, Internet-of-things, Machine learning, Remote patient monitoring, Smart healthcare monitoring, Ubiquitous computing

General General

Development of AI classification model for angiosome-wise interpretive substantiation of plantar feet thermal asymmetry in type 2 diabetic subjects using infrared thermograms.

In Journal of thermal biology

Diabetic Foot Syndrome (DFS) is the prime impetus for most of the lower extremity complications among the diabetic subjects. DFS is characterized by aberrant variations in plantar foot temperature distribution while healthy subjects exhibit a symmetric thermal pattern between the contralateral and ipsilateral plantar feet. Thus, "asymmetry analysis" of foot thermal distribution is contributory in assessment of overall foot health of diabetic subjects. The study, aims to classify symmetric and asymmetric foot regions angiosome-wise, by comparing minimal number of color image features - color moments and Dissimilarity Index. Further, the asymmetric foot regions are assessed for identifying the hotspots within such angiosomes of the patients that characterize the possibility of onset of diabetic foot ulcer. The color feature based machine learning model developed, achieved an accuracy of 98% for a 10-fold cross validation, test accuracy of 96.07% and 0.96 F1-score thereby convincing that the chosen features are amplest and conducive in the asymmetry analysis. The developed model was validated for generalization by testing on a public benchmark dataset, in which the model achieved 92.5% accuracy and 0.91 F1 score.

Evangeline N Christy, Srinivasan S, Suresh E

2022-Dec

Artificial intelligence, Diabetic foot syndrome, Feature extraction, Hotspot identification, Infrared thermogram

General General

An exploratory experiment using temperature drop curve features to identify activity information of duck eggs at mid-incubation.

In Journal of thermal biology

To address the problem that duck egg mortality is not easily detected at mid-incubation, this paper explored a method to detect mid-incubation egg activity information based on temperature drop curve (TDC) features. In this paper, we used a thermal infrared camera to obtain continuous thermal images of death fertilized duck eggs (DFDE) on the 16th day of incubation and alive fertilized duck eggs (AFDE) hatched for 16-19 days in a 20 °C environment. By observing the temperature drop curve of egg surface, we extracted and visualized five features that could reflect the activity information of duck eggs. And we used K-Nearest Neighbor (KNN), Naive Bayesian (NB) and Support Vector Machine (SVM) to establish the activity information detection models for different incubation days. The results showed that KNN could better distinguish the activity of eggs at the 16th and the 17th day of incubation, with F1-score of 85.43% and 85.98%, respectively. The SVM showed better results at the 18th and the 19th day of incubation, with F1-score of 90.57% and 96.3%, respectively. The experimental results demonstrated that the activity detection method based on the temperature drop curve features in this paper could efficiently and nondestructively detect the activity information of mid-incubation duck eggs, which provided a technical foundation for detecting the activity information of duck eggs at mid-incubation.

Liu Youfu, Xiao Deqin, Liu Yalan, Zhou Jiaxin, Zhao Shengqiu

2022-Dec

Curve features extraction, Duck eggs, Machine learning, Mid-incubation, Temperature drop curve, Thermal infrared camera

General General

Review of Biochar Production via Crop Residue Pyrolysis: Development and Perspectives.

In Bioresource technology

Worldwide surge in crop residue generation has necessitated developing strategies for their sustainable disposal. Pyrolysis has been widely adopted to convert crop residue into biochar with bio-oil and gas being two co-products. The review adopts a whole system philosophy and systematically summarises up-to-date knowledge of crop residue pyrolysis processes, influential factors, and biochar applications. Essential process design tools for biochar production e.g., cost-benefit analysis, life cycle assessment, and machine learning methods are also reviewed, which has often been overlooked in prior reviews Important aspects include (a) correlating techno-economics of biochar production with crop residue compositions, (b) process operating conditions and management strategies, (c) biochar applications includes soil amendment, fuel displacement, catalytic usage, etc. (d) data-driven modelling techniques, (e) properties of biochar, and (f) climate change mitigation. Overall, the review will support the development of application-oriented process pipelines for crop residue-based biochar.

Li Yize, Gupta Rohit, Zhang Qiaozhi, You Siming

2022-Nov-30

Agricultural waste, Compositions, Machine Learning, Resource Recovery, Sustainable Development

General General

Simulation of integrated anaerobic digestion-gasification systems using machine learning models.

In Bioresource technology

In this study, the anaerobic digestion model M-ADM1 was integrated with the gasification model T-ANN to form a set of integrated models that can efficiently simulate the biomass AD-GS integration technology. Biogas slurry is used as feedstocks to prepare biogas slurry fertilizer. Solid residue is used feedstocks for gasification reactions. Biogas and syngas from the gasification of solid residue are used for energy. In this process, carbon emission is regarded as an important index for the comprehensive evaluation and optimization of AD-GS integration process. This study found that when the anaerobic digestion duration was 0 to 15 days, the carbon emission reduction increased rapidly. The amount of carbon emission reduction peaks on day 15. The value of carbon emission reduction is 0.1828 gCO2eq. In addition, when FEAG reached the maximum value at 15 days of anaerobic digestion, the decreasing trend of FEAG rate change value started to become significant.

Ge Yadong, Tao Junyu, Wang Zhi, Chen Chao, Liang Rui, Mu Lan, Ruan Haihua, Rodríguez Yon Yakelin, Yan Beibei, Chen Guanyi

2022-Nov-30

Anaerobic digestion, Biogas slurry, Carbon emission, Gasification, Solid residue

General General

Exposing and understanding synergistic effects in co-pyrolysis of biomass and plastic waste via machine learning.

In Bioresource technology

During co-pyrolysis of biomass with plastic waste, bio-oil yields (BOY) could be either induced or reduced significantly via synergistic effects (SE). However, investigating/ interpreting the SE and BOY in multidimensional domains is complicated and limited. This work applied XGBoost machine-learning and Shapley additive explanation (SHAP) to develop interpretable/ explainable models for predicting BOY and SE from co-pyrolysis of biomass and plastic waste using 26 input features. Imbalanced training datasets were improved by synthetic minority over-sampling technique. The prediction accuracy of XGBoost models was nearly 0.90 R2 for BOY while greater than 0.85 R2 for SE. By SHAP, individual impact and interaction of input features on the XGBoost models can be achieved. Although reaction temperature and biomass-to-plastic ratio were the top two important features, overall contributions of feedstock characteristics were more than 60 % in the system of co-pyrolysis. The finding provides a better understanding of co-pyrolysis and a way of further improvements.

Prasertpong Prapaporn, Onsree Thossaporn, Khuenkaeo Nattawut, Tippayawong Nakorn, Lauterbach Jochen

2022-Nov-30

AI, Bioenergy, Mixed biomass, Regression, Waste-to-energy

General General

Machine learning assisted predicting and engineering specific surface area and total pore volume of biochar.

In Bioresource technology

Biochar produced from pyrolysis of biomass is a platform porous carbon material that have been widely used in many areas. Specific surface area (SSA) and total pore volume (TPV) are decisive to biochar application in hydrogen uptake, CO2 adsorption, and organic pollutant removal, etc. Engineering biochar by traditional experimental methods is time-consuming and laborious. Machine learning (ML) was used to effectively aid the prediction and engineering of biochar properties. The prediction of biochar yield, SSA, and TPV was achieved via random forest (RF) and gradient boosting regression (GBR) with test R2 of 0.89-0.94. ML model interpretation indicates pyrolysis temperature, biomass ash, and volatile matter were the most important features to the three targets. Pyrolysis parameters and biomass mixing ratios for biochar production were optimized via three-target GBR model, and the optimum schemes to obtain high SSA and TPV were experimentally verified, indicating the great potential of ML for biochar engineering.

Li Hailong, Ai Zejian, Yang Lihong, Zhang Weijin, Yang Zequn, Peng Haoyi, Leng Lijian

2022-Nov-30

Bio-char, Biomass pyrolysis, Machine learning, Porous carbon material, Specific surface area, Total pore volume

General General

Automation and artificial intelligence in filamentous fungi-based bioprocesses: A review.

In Bioresource technology

By utilizing their powerful metabolic versatility, filamentous fungi can be utilized in bioprocesses aimed at achieving circular economy. With the current digital transformation within the biomanufacturing sector, the interest of automating the fungi-based systems has intensified. The purpose of this paper was therefore to review the potentials connected to the use of automation and artificial intelligence in fungi-based systems. Automation is characterized by the substitution of manual tasks with mechanized tools. Artificial intelligence is, on the other hand, a domain within computer science that aims at designing tools and machines with the capacity to execute functions that would usually require human aptitude. Process flexibility, enhanced data reliability and increased productivity are some of the benefits of integrating automation and artificial intelligence in fungi-based bioprocesses. One of the existing gaps that requires further investigation is the use of such data-based technologies in the production of food from fungi.

Wainaina Steven, Taherzadeh Mohammad J

2022-Nov-30

Filamentous fungi, Machine learning, Process control, Robotic systems, Smart sensors

General General

Off the deep end: what can deep learning do for the gene expression field?

In The Journal of biological chemistry

After a COVID-related hiatus, the fifth biennial symposium on Evolution and Core Processes in Gene Regulation met at the Stowers Institute in Kansas City, Missouri July 21-24, 2022. This symposium, sponsored by the American Society for Biochemistry and Molecular Biology (ASBMB), featured experts in gene regulation and evolutionary biology. Topic areas covered enhancer evolution, the cis-regulatory code, and regulatory variation, with an overall focus on bringing the power of deep learning to decipher DNA sequence information. Deep learning (DL) is a machine learning method that uses neural networks to learn complex rules that make predictions about diverse types of data. When DL models are trained to predict genomic data from DNA sequence information, their high prediction accuracy allows the identification of impactful genetic variants within and across species. In addition, the learned sequence rules can be extracted from the model and provide important clues about the mechanistic underpinnings of the cis-regulatory code.

Raicu Ana-Maria, Fay Justin C, Rohner Nicolas, Zeitlinger Julia, Arnosti David N

2022-Nov-30

General General

Convolutional neural network for high-resolution wetland mapping with open data: Variable selection and the challenges of a generalizable model.

In The Science of the total environment

Landscape scale wetland conservation requires accurate, up-to-date wetland maps. The most useful approaches to creating such maps are automated, spatially generalizable, temporally repeatable, and can be applied at large spatial scales. However, mapping wetlands with predictive models is challenging due to the highly variable characteristics of wetlands in both space and time. Currently, most approaches are limited by coarse resolution, commercial data, and geographic specificity. Here, we trained a deep learning model and evaluate its ability to automatically map wetlands at landscape scale in a variety of geographies. We trained a U-Net architecture to map wetlands at 1-meter spatial resolution with the following remotely sensed covariates: multispectral data from the National Agriculture Imagery Program and the Sentinel-2 satellite system, and two LiDAR-derived datasets, intensity and geomorphons. The full model mapped wetlands accurately (94 % accuracy, 96.5 % precision, 95.2 % AUC) at 1-meter resolution. Post hoc model evaluation showed that the model correctly predicted wetlands even in areas that had incorrect label/training data, which penalized the recall rate (90.2 %). Applying the model in a new geography resulted in poor performance (precision = ~80 %, recall = 48 %). However, limited retraining in this geography improved model performance substantially, demonstrating an effective means to create a spatially generalizable model. We demonstrate wetlands can be mapped at high-resolution (1 m) using free data and efficient deep-learning models that do not require manual feature engineering. Including LiDAR and geomorphons as input data improved model accuracy by 2 %, and where these data are unavailable a simpler model can efficiently map wetlands. Given the dynamic nature of wetlands and the important ecosystem services they provide, high-resolution mapping can be a game changer in terms of informing restoration and development decisions.

Mainali Kumar, Evans Mike, Saavedra David, Mills Emily, Madsen Becca, Minnemeyer Susan

2022-Nov-30

Deep learning, Geomorphon, LiDAR, Model transferability, Remote sensing, U-Net

Public Health Public Health

Nondestructive and multiplex differentiation of pathogenic microorganisms from spoilage microflora on seafood using paper chromogenic array and neural network.

In Food research international (Ottawa, Ont.)

Non-destructive detection of human foodborne pathogens is critical to ensuring food safety and public health. Here, we report a new method using a paper chromogenic array coupled with a machine learning neural network (PCA-NN) to detect viable pathogens in the presence of background microflora and spoilage microbe in seafood via volatile organic compounds sensing. Morganella morganii and Shewanella putrefaciens were used as the model pathogen and spoilage bacteria. The study evaluated microbial detection in monoculture and cocktail multiplex detection. The accuracy of PCA-NN detection was first assessed on standard media and later validated on cod and salmon as real seafood models with pathogenic and spoilage bacteria, as well as background microflora. In this study PCA-NN method successfully identified pathogenic microorganisms from microflora with or without the prevalent spoilage microbe, Shewanella putrefaciens in seafood, with accuracies ranging from 90% to 99%. This approach has the potential to advance smart packaging by achieving nondestructive pathogen surveillance on food without enrichment, incubation, or other sample preparation.

Yang Manyun, Luo Yaguang, Sharma Arnav, Jia Zhen, Wang Shilong, Wang Dayang, Lin Sophia, Perreault Whitney, Purohit Sonia, Gu Tingting, Dillow Hyden, Liu Xiaobo, Yu Hengyong, Zhang Boce

2022-Dec

Amine, Machine learning, Neural network, Paper chromogenic array, Pathogen, Seafood

General General

Ubiquitous and smart healthcare monitoring frameworks based on machine learning: A comprehensive review.

In Artificial intelligence in medicine ; h5-index 34.0

During the COVID-19 pandemic, the patient care delivery paradigm rapidly shifted to remote technological solutions. Rising rates of life expectancy of older people, and deaths due to chronic diseases (CDs) such as cancer, diabetes and respiratory disease pose many challenges to healthcare. While the feasibility of Remote Patient Monitoring (RPM) with a Smart Healthcare Monitoring (SHM) framework was somewhat questionable before the COVID-19 pandemic, it is now a proven commodity and is on its way to becoming ubiquitous. More health organizations are adopting RPM to enable CD management in the absence of individual monitoring. The current studies on SHM have reviewed the applications of IoT and/or Machine Learning (ML) in the domain, their architecture, security, privacy and other network related issues. However, no study has analyzed the AI and ubiquitous computing advances in SHM frameworks. The objective of this research is to identify and map key technical concepts in the SHM framework. In this context an interesting and meaningful classification of the research articles surveyed for this work is presented. The comprehensive and systematic review is based on the "Preferred Reporting Items for Systematic Review and Meta-Analysis" (PRISMA) approach. A total of 2540 papers were screened from leading research archives from 2016 to March 2021, and finally, 50 articles were selected for review. The major advantages, developments, distinctive architectural structure, components, technical challenges and possibilities in SHM are briefly discussed. A review of various recent cloud and fog computing based architectures, major ML implementation challenges, prospects and future trends is also presented. The survey primarily encourages the data driven predictive analytics aspects of healthcare and the development of ML models for health empowerment.

Motwani Anand, Shukla Piyush Kumar, Pawar Mahesh

2022-Dec

Big data, Chronic diseases, Cloud computing, Cognitive computing, Data analytics, Edge computing, Internet-of-things, Machine learning, Remote patient monitoring, Smart healthcare monitoring, Ubiquitous computing

General General

Machine Learning for Lung Cancer Diagnosis, Treatment, and Prognosis.

In Genomics, proteomics & bioinformatics

The recent development of imaging and sequencing technologies enables systematic advances in the clinical study of lung cancer. Meanwhile, the human mind is limited in effectively handling and fully utilizing the accumulation of such enormous amounts of data. Machine learning-based approaches play a critical role in integrating and analyzing these large and complex datasets, which have extensively characterized lung cancer through the use of different perspectives from these accrued data. In this article, we provide an overview of machine learning-based approaches that strengthen the varying aspects of lung cancer diagnosis and therapy, including early detection, auxiliary diagnosis, prognosis prediction, and immunotherapy practice. Moreover, we highlight the challenges and opportunities for future applications of machine learning in lung cancer.

Li Yawei, Wu Xin, Yang Ping, Jiang Guoqian, Luo Yuan

2022-Nov-30

-omics dataset, Feature extraction, Imaging dataset, Immunotherapy, Prediction

General General

Predicting depression and anxiety of Chinese population during COVID-19 in psychological evaluation data by XGBoost.

In Journal of affective disorders ; h5-index 79.0

BACKGROUND : Due to the onset of sudden stress, COVID-19 has greatly impacted the incidence of depression and anxiety. However, challenges still exist in identifying high-risk groups for depression and anxiety during COVID-19. Studies have identified how resilience and social support can be employed as effective predictors of depression and anxiety. This study aims to select the best combination of variables from measures of resilience, social support, and alexithymia for predicting depression and anxiety.

METHODS : The eXtreme Gradient Boosting (XGBoost1) model was applied to a dataset including data on 29,841 participants that was collected during the COVID-19 pandemic. Discriminant analyses on groups of participants with depression (DE2), anxiety (AN3), comorbid depression and anxiety (DA4), and healthy controls (HC5), were performed. All variables were selected according to their importance for classification. Further, analyses were performed with selected features to determine the best variable combination.

RESULTS : The mean accuracies achieved by three classification tasks, DE vs HC, AN vs HC, and DA vs HC, were 0.78, 0.77, and 0.89. Further, the combination of 19 selected features almost exhibited the same performance as all 56 variables (accuracies = 0.75, 0.75, and 0.86).

CONCLUSIONS : Resilience, social support, and some demographic data can accurately distinguish DE, AN, and DA from HC. The results can be used to inform screening practices for depression and anxiety. Additionally, the model performance of a limited scale including only 19 features indicates that using a simplified scale is feasible.

Tian Zhanxiao, Qu Wei, Zhao Yanli, Zhu Xiaolin, Wang Zhiren, Tan Yunlong, Jiang Ronghuan, Tan Shuping

2022-Nov-30

Anxiety, COVID-19 pandemic, Depression, Machine learning, Resilience, Social support

General General

Depression recognition using a proposed speech chain model fusing speech production and perception features.

In Journal of affective disorders ; h5-index 79.0

BACKGROUND : Increasing depression patients puts great pressure on clinical diagnosis. Audio-based diagnosis is a helpful auxiliary tool for early mass screening. However, current methods consider only speech perception features, ignoring patients' vocal tract changes, which may partly result in the poor recognition.

METHODS : This work proposes a novel machine speech chain model for depression recognition (MSCDR) that can capture text-independent depressive speech representation from the speaker's mouth to the listener's ear to improve recognition performance. In the proposed MSCDR, linear predictive coding (LPC) and Mel-frequency cepstral coefficients (MFCC) features are extracted to describe the processes of speech generation and of speech perception, respectively. Then, a one-dimensional convolutional neural network and a long short-term memory network sequentially capture intra- and inter-segment dynamic depressive features for classification.

RESULTS : We tested the MSCDR on two public datasets with different languages and paradigms, namely, the Distress Analysis Interview Corpus-Wizard of Oz and the Multi-modal Open Dataset for Mental-disorder Analysis. The accuracy of the MSCDR on the two datasets was 0.77 and 0.86, and the average F1 score was 0.75 and 0.86, which were better than the other existing methods. This improvement reveals the complementarity of speech production and perception features in carrying depressive information.

LIMITATIONS : The sample size was relatively small, which may limit the application in clinical translation to some extent.

CONCLUSION : This experiment proves the good generalization ability and superiority of the proposed MSCDR and suggests that the vocal tract changes in patients with depression deserve attention for audio-based depression diagnosis.

Du Minghao, Liu Shuang, Wang Tao, Zhang Wenquan, Ke Yufeng, Chen Long, Ming Dong

2022-Nov-30

Audio, Auxiliary diagnosis, Deep learning, Depression, Feature fusion

General General

Integrative analysis to identify shared mechanisms between schizophrenia and bipolar disorder and their comorbidities.

In Progress in neuro-psychopharmacology & biological psychiatry

Schizophrenia and bipolar disorder are characterized by highly similar neuropsychological signatures, implying shared neurobiological mechanisms between these two disorders. These disorders also have comorbidities, such as type 2 diabetes mellitus (T2DM). To date, an understanding of the mechanisms that mediate the link between these two disorders remains incomplete. In this work, we identify and investigate shared patterns across multiple schizophrenia, bipolar disorder and T2DM gene expression datasets through multiple strategies. Firstly, we investigate dysregulation patterns at the gene-level and compare our findings against disease-specific knowledge graphs (KGs). Secondly, we analyze the concordance of co-expression patterns across datasets to identify disease-specific as well as common pathways. Thirdly, we examine enriched pathways across datasets and disorders to identify common biological mechanisms between them. Lastly, we investigate the correspondence of shared genetic variants between these two disorders and T2DM as well as the disease-specific KGs. In conclusion, our work reveals several shared candidate genes and pathways, particularly those related to the immune system, such as TNF signaling pathway, IL-17 signaling pathway and NF-kappa B signaling pathway and nervous system, such as dopaminergic synapse and GABAergic synapse, which we propose mediate the link between schizophrenia and bipolar disorder and its shared comorbidity, T2DM.

Bharadhwaj Vinay Srinivas, Mubeen Sarah, Sargsyan Astghik, Jose Geena Mariya, Geissler Stefan, Hofmann-Apitius Martin, Domingo-Fernández Daniel, Kodamullil Alpha Tom

2022-Nov-30

Bipolar disorder, Gene expression, Psychiatric disorders, Schizophrenia, Transcriptomic

General General

Deep learning for hetero-homo conversion in channel-domain for phase aberration correction in ultrasound imaging.

In Ultrasonics

Echo imaging in ultrasound computed tomography (USCT) using the synthetic aperture technique is performed with the assumption that the speed of sound is constant in the system. However, tissue heterogeneity causes a mismatch between the predicted arrival time and the actual arrival time of the echo signal, which will result in phase aberration, leading to the quality degradation of the reconstructed B-mode image. The conventional correction methods that use the correlation of each different channel require the presence of strong point scatterers and involve the problem of local solutions due to excessive correction. In this study, we propose a novel approach to correcting the signal distortion due to sound speed heterogeneity using a deep neural network (DNN). The DNN was trained to convert the distorted radio frequency (RF) inputs for the heterogeneous medium to the distortion-free RF outputs for the homogeneous medium. The network with U-net architecture using ResNet-34 as a backbone was trained using the hetero-homo corresponding channel-domain RF data generated via numerical simulations. The trained network performed phase aberration correction in the channel-domain RF, with the B-mode images reconstructed with the corrected RF demonstrating a higher contrast and an improved resolution compared with uncorrected cases. It was also demonstrated that the DNN model is robust to both varied reflection intensities and varied sound speed heterogeneities. The successful results demonstrated that the proposed DNN-based method is effective for phase aberration correction in US imaging.

Koike Tatsuki, Tomii Naoki, Watanabe Yoshiki, Azuma Takashi, Takagi Shu

2022-Nov-19

Channel-domain RF, Image reconstruction, Numerical simulation, Phase aberration correction, Ultrasound computed tomography

General General

Data science techniques in biomolecular force field development.

In Current opinion in structural biology

Recent advances in data science are impacting the development of classical force fields. Here we review some ideas and techniques from data science that have been used in force field development, including database construction, atom typing, and machine learning potentials. We highlight how new tools such as active learning and automatic differentiation are facilitating the generation of target data and the direct fitting with macroscopic observables. Philosophical changes on how force field models should be built and used are also discussed. It's inspiring that more accurate biomolecular force fields can be developed with the aid of data science techniques.

Ding Ye, Yu Kuang, Huang Jing

2022-Nov-30

Data Science, Force Field, Machine Learning, Molecular Dynamics Simulation, Molecular Modeling

Internal Medicine Internal Medicine

Prediction of type 2 diabetes using genome-wide polygenic risk score and metabolic profiles: A machine learning analysis of population-based 10-year prospective cohort study.

In EBioMedicine

BACKGROUND : Previous work on predicting type 2 diabetes by integrating clinical and genetic factors has mostly focused on the Western population. In this study, we use genome-wide polygenic risk score (gPRS) and serum metabolite data for type 2 diabetes risk prediction in the Asian population.

METHODS : Data of 1425 participants from the Korean Genome and Epidemiology Study (KoGES) Ansan-Ansung cohort were used in this study. For gPRS analysis, genotypic and clinical information from KoGES health examinee (n = 58,701) and KoGES cardiovascular disease association (n = 8105) sub-cohorts were included. Linkage disequilibrium analysis identified 239,062 genetic variants that were used to determine the gPRS, while the metabolites were selected using the Boruta algorithm. We used bootstrapped cross-validation to evaluate logistic regression and random forest (RF)-based machine learning models. Finally, associations of gPRS and selected metabolites with the values of homeostatic model assessment of beta-cell function (HOMA-B) and insulin resistance (HOMA-IR) were further estimated.

FINDINGS : During the follow-up period (8.3 ± 2.8 years), 331 participants (23.2%) were diagnosed with type 2 diabetes. The areas under the curves of the RF-based models were 0.844, 0.876, and 0.883 for the model using only demographic and clinical factors, model including the gPRS, and model with both gPRS and metabolites, respectively. Incorporation of additional parameters in the latter two models improved the classification by 11.7% and 4.2% respectively. While gPRS was significantly associated with HOMA-B value, most metabolites had a significant association with HOMA-IR value.

INTERPRETATION : Incorporating both gPRS and metabolite data led to enhanced type 2 diabetes risk prediction by capturing distinct etiologies of type 2 diabetes development. An RF-based model using clinical factors, gPRS, and metabolites predicted type 2 diabetes risk more accurately than the logistic regression-based model.

FUNDING : This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korean government (MEST) (No. 2019M3E5D1A02070863 and 2022R1C1C1005458). This work was also supported by the 2020 Research Fund (1.200098.01) of UNIST (Ulsan National Institute of Science & Technology).

Hahn Seok-Ju, Kim Suhyeon, Choi Young Sik, Lee Junghye, Kang Jihun

2022-Nov-30

East Asian, Genome-wide polygenic risk score, KoGES, Machine learning, Serum metabolites, Type 2 diabetes

Dermatology Dermatology

SSD-KD: A self-supervised diverse knowledge distillation method for lightweight skin lesion classification using dermoscopic images.

In Medical image analysis

Skin cancer is one of the most common types of malignancy, affecting a large population and causing a heavy economic burden worldwide. Over the last few years, computer-aided diagnosis has been rapidly developed and make great progress in healthcare and medical practices due to the advances in artificial intelligence, particularly with the adoption of convolutional neural networks. However, most studies in skin cancer detection keep pursuing high prediction accuracies without considering the limitation of computing resources on portable devices. In this case, the knowledge distillation (KD) method has been proven as an efficient tool to help improve the adaptability of lightweight models under limited resources, meanwhile keeping a high-level representation capability. To bridge the gap, this study specifically proposes a novel method, termed SSD-KD, that unifies diverse knowledge into a generic KD framework for skin disease classification. Our method models an intra-instance relational feature representation and integrates it with existing KD research. A dual relational knowledge distillation architecture is self-supervised trained while the weighted softened outputs are also exploited to enable the student model to capture richer knowledge from the teacher model. To demonstrate the effectiveness of our method, we conduct experiments on ISIC 2019, a large-scale open-accessed benchmark of skin diseases dermoscopic images. Experiments show that our distilled MobileNetV2 can achieve an accuracy as high as 85% for the classification tasks of 8 different skin diseases with minimal parameters and computing requirements. Ablation studies confirm the effectiveness of our intra- and inter-instance relational knowledge integration strategy. Compared with state-of-the-art knowledge distillation techniques, the proposed method demonstrates improved performance. To the best of our knowledge, this is the first deep knowledge distillation application for multi-disease classification on the large-scale dermoscopy database. Our codes and models are available at https://github.com/enkiwang/Portable-Skin-Lesion-Diagnosis.

Wang Yongwei, Wang Yuheng, Cai Jiayue, Lee Tim K, Miao Chunyan, Wang Z Jane

2022-Nov-13

Deep learning, Dermoscopy, Knowledge distillation, Skin cancer detection

Surgery Surgery

Teeth U-Net: A segmentation model of dental panoramic X-ray images for context semantics and contrast enhancement.

In Computers in biology and medicine

BACKGROUND AND OBJECTIVE : It is very significant in orthodontics and restorative dentistry that the teeth are segmented from dental panoramic X-ray images. Nevertheless, there are some problems in panoramic X-ray images of teeth, such as blurred interdental boundaries, low contrast between teeth and alveolar bone.

METHODS : In this paper, The Teeth U-Net model is proposed in this paper to resolve these problems. This paper makes the following contributions: Firstly, a Squeeze-Excitation Module is utilized in the encoder and the decoder. And proposing a dense skip connection between encoder and decoder to reduce the semantic gap. Secondly, due to the irregular shape of the teeth and the low contrast of the dental panoramic X-ray images. A Multi-scale Aggregation attention Block (MAB) in the bottleneck layer is designed to resolve this problem, which can effectively extract teeth shape features and fuse multi-scale features adaptively. Thirdly, in order to capture dental feature information in a larger field of perception, this paper designs a Dilated Hybrid self-Attentive Block (DHAB) at the bottleneck layer. This module effectively suppresses the task-irrelevant background region information without increasing the network parameters. Finally, the effectiveness of the algorithm is validated using a clinical dental panoramic X-ray image datasets.

RESULTS : The results of the three comparison experiments are shown that Accuracy, Precision, Recall, Dice, Volumetric Overlap Error and Relative Volume Difference for dental panoramic X-ray teeth segmentation are 98.53%, 95.62%, 94.51%, 94.28%, 88.92% and 95.97% by the proposed model respectively.

CONCLUSION : The proposed modules complement each other in processing every detail of the dental panoramic X-ray images, which can effectively improve the efficiency of preoperative preparation and postoperative evaluation, and promote the application of dental panoramic X-ray in medical image segmentation. There are more accuracy about Teeth U-Net than others model in dental panoramic X-ray teeth segmentation. That is very important to clinical doctors to cure in orthodontics and restorative dentistry.

Hou Senbao, Zhou Tao, Liu Yuncan, Dang Pei, Lu Huiling, Shi Hongbin

2022-Nov-12

Context semantics, Contrast enhancement, Deep learning, Dental panoramic X-ray images, Medical auxiliary diagnosis

General General

Differential diagnosis of systemic lupus erythematosus and Sjögren's syndrome using machine learning and multi-omics data.

In Computers in biology and medicine

Systemic lupus erythematosus and primary Sjogren's syndrome are complex systemic autoimmune diseases that are often misdiagnosed. In this article, we demonstrate the potential of machine learning to perform differential diagnosis of these similar pathologies using gene expression and methylation data from 651 individuals. Furthermore, we analyzed the impact of the heterogeneity of these diseases on the performance of the predictive models, discovering that patients assigned to a specific molecular cluster are misclassified more often and affect to the overall performance of the predictive models. In addition, we found that the samples characterized by a high interferon activity are the ones predicted with more accuracy, followed by the samples with high inflammatory activity. Finally, we identified a group of biomarkers that improve the predictions compared to using the whole data and we validated them with external studies from other tissues and technological platforms.

Martorell-Marugán Jordi, Chierici Marco, Jurman Giuseppe, Alarcón-Riquelme Marta E, Carmona-Sáez Pedro

2022-Nov-28

Bioinformatics, Classification and association rules, Clustering, Health, Machine learning, Modeling and prediction

General General

Prediction of Aspergillus parasiticus inhibition and aflatoxin mitigation in red pepper flakes treated by pulsed electric field treatment using machine learning and neural networks.

In Food research international (Ottawa, Ont.)

Presence of aflatoxins in agricultural products is a worldwide problem. Because of their high heat stability and resistance to most of the food processing technologies, aflatoxin degradation is still a big challenge. Thus, efficacy of pulsed electric fields (PEF) by energies ranging from 0.97 to 17.28 J was tested to determine changes in quality properties in red pepper flakes, mitigation of aflatoxins, inactivation of aflatoxin producing Aspergillus parasiticus, reduction in aflatoxin mutagenity, and modelling of A. parasiticus inactivation in addition to aflatoxin mitigation. Maximum inactivation rate of 64.37 % with 17.28 J was encountered on the mean initial A. parasiticus count. A 99.88, 99.47, 97.75, and 99.58 % reductions were obtained on the mean initial AfG1, AfG2, AfB1, and AfB2 concentrations. PEF treated samples by 0.97, 1.36, 5.76, and 17.28 J at 1 μg/plate, 0.97, 1.92, 7.78, 10.80 J at 10 μg/plate, and 0.97, 1.92, 2.92, 4.08, 5.76, 4.86, 6.80, 9.60, 10.80, and 10.89 J at 100 μg/plate were not mutagenic. Modelling with gradient boosting regression tree (GBRT), random forest regression (RFR), and artificial neural network (ANN) provided the lowest RMSE and highest R2 value for GBRT model for the predicted inactivation of A. parasiticus, whereas ANN model provided the lowest RMSE and highest R2 for predicted mitigation of AfG1, AfB1, and AfB2. PEF treatment possess a viable alternative for aflatoxin degradation with reduced mutagenity and without adverse effect on quality properties of red pepper flakes.

Akdemir Evrendilek Gulsun, Bulut Nurullah, Atmaca Bahar, Uzuner Sibel

2022-Dec

Aflatoxin, Machine learning, Mutagenity, Pulsed electric fields, Red pepper flakes

General General

Predicting depression and anxiety of Chinese population during COVID-19 in psychological evaluation data by XGBoost.

In Journal of affective disorders ; h5-index 79.0

BACKGROUND : Due to the onset of sudden stress, COVID-19 has greatly impacted the incidence of depression and anxiety. However, challenges still exist in identifying high-risk groups for depression and anxiety during COVID-19. Studies have identified how resilience and social support can be employed as effective predictors of depression and anxiety. This study aims to select the best combination of variables from measures of resilience, social support, and alexithymia for predicting depression and anxiety.

METHODS : The eXtreme Gradient Boosting (XGBoost1) model was applied to a dataset including data on 29,841 participants that was collected during the COVID-19 pandemic. Discriminant analyses on groups of participants with depression (DE2), anxiety (AN3), comorbid depression and anxiety (DA4), and healthy controls (HC5), were performed. All variables were selected according to their importance for classification. Further, analyses were performed with selected features to determine the best variable combination.

RESULTS : The mean accuracies achieved by three classification tasks, DE vs HC, AN vs HC, and DA vs HC, were 0.78, 0.77, and 0.89. Further, the combination of 19 selected features almost exhibited the same performance as all 56 variables (accuracies = 0.75, 0.75, and 0.86).

CONCLUSIONS : Resilience, social support, and some demographic data can accurately distinguish DE, AN, and DA from HC. The results can be used to inform screening practices for depression and anxiety. Additionally, the model performance of a limited scale including only 19 features indicates that using a simplified scale is feasible.

Tian Zhanxiao, Qu Wei, Zhao Yanli, Zhu Xiaolin, Wang Zhiren, Tan Yunlong, Jiang Ronghuan, Tan Shuping

2022-Nov-30

Anxiety, COVID-19 pandemic, Depression, Machine learning, Resilience, Social support

General General

The use of machine learning methods to predict sperm quality in Holstein bulls.

In Theriogenology ; h5-index 37.0

The aim of this study was to develop prediction models for total sperm motility, morphological abnormalities and sperm output based on 1,551 ejaculate records of 58 Holstein bulls. The data was collected from September 2019 to November 2020 in a single artificial insemination (AI) center located in Eastern Germany. Factors considered for the prediction models include barn climate conditions, semen collector, number of false mounts, libido, semen collection frequency, breed and age (10-74 months). In this study, the prediction models Lasso, Group Lasso and Gradient Boosting were evaluated. The best model for each sperm quality parameter was chosen using cross validation. The models were estimated with five algorithms for sperm motility and sperm morphology and three algorithms for the number of total sperm per ejaculate (sperm output). For sperm motility and morphology a binary classification algorithm was applied, reaching an accuracy of over 80% for all models. For sperm output, no such classification was used and the only variable selected by all three algorithms was age. Furthermore, for sperm morphology, climate variables were frequently selected. Additionally, network diagrams from Group Lasso show the interdependencies between the major variable groups influencing sperm motility and morphology. In conclusion, the implementation of such prediction tools could help AI centers to optimize management factors and stabilize bull semen production in the future.

Hürland M, Kuhlgatz D A, Kuhlgatz C, Osmers J H, Jung M, Schulze M

2022-Nov-23

General General

Using unique molecular identifiers to improve allele calling in low-template mixtures.

In Forensic science international. Genetics

PCR artifacts are an ever-present challenge in sequencing applications. These artifacts can seriously limit the analysis and interpretation of low-template samples and mixtures, especially with respect to a minor contributor. In medicine, molecular barcoding techniques have been employed to decrease the impact of PCR error and to allow the examination of low-abundance somatic variation. In principle, it should be possible to apply the same techniques to the forensic analysis of mixtures. To that end, several short tandem repeat loci were selected for targeted sequencing, and a bioinformatic pipeline for analyzing the sequence data was developed. The pipeline notes the relevant unique molecular identifiers (UMIs) attached to each read and, using machine learning, filters the noise products out of the set of potential alleles. To evaluate this pipeline, DNA from pairs of individuals were mixed at different ratios (1-1, 1-9) and sequenced with different starting amounts of DNA (10, 1 and 0.1 ng). Naïvely using the information in the molecular barcodes led to increased performance, with the machine learning resulting in an additional benefit. In concrete terms, using the UMI data results in less noise for a given amount of drop out. For instance, if thresholds are selected that filter out a quarter of the true alleles, using read counts accepts 2381 noise alleles and using raw UMI counts accepts 1726 noise alleles, while the machine learning approach only accepts 307.

Crysup Benjamin, Mandape Sammed, King Jonathan L, Muenzler Melissa, Kapema Kapema Bupe, Woerner August E

2022-Nov-24

DNA Mixtures, Machine Learning, Massively Parallel Sequencing, Molecular Barcodes, Stutter

General General

A comprehensive survey of deep learning research on medical image analysis with focus on transfer learning.

In Clinical imaging

This survey aims to identify commonly used methods, datasets, future trends, knowledge gaps, constraints, and limitations in the field to provide an overview of current solutions used in medical image analysis in parallel with the rapid developments in transfer learning (TL). Unlike previous studies, this survey grouped the last five years of current studies for the period between January 2017 and February 2021 according to different anatomical regions and detailed the modality, medical task, TL method, source data, target data, and public or private datasets used in medical imaging. Also, it provides readers with detailed information on technical challenges, opportunities, and future research trends. In this way, an overview of recent developments is provided to help researchers to select the most effective and efficient methods and access widely used and publicly available medical datasets, research gaps, and limitations of the available literature.

Atasever Sema, Azginoglu Nuh, Terzi Duygu Sinanc, Terzi Ramazan

2022-Nov-12

Deep learning, Medical images analysis, Review, Taxonomy, Transfer learning

Surgery Surgery

Integration of genome-scale data identifies candidate sleep regulators.

In Sleep

STUDY OBJECTIVES : Genetics impacts sleep, yet, the molecular mechanisms underlying sleep regulation remain elusive. In this study, we built machine learning models to predict sleep genes based on their similarity to genes that are known to regulate sleep.

METHODS : We trained a prediction model on thousands of published datasets, representing circadian, immune, sleep deprivation, and many other processes, using a manually curated list of 109 sleep genes.

RESULTS : Our predictions fit with prior knowledge of sleep regulation and identified key genes and pathways to pursue in follow-up studies. As an example, we focused on the NF-κB pathway and showed that chronic activation of NF-κB in a genetic mouse model impacted the sleep-wake patterns.

CONCLUSION : Our study highlights the power of machine learning in integrating prior knowledge and genome-wide data to study genetic regulation of complex behaviors such as sleep.

Lee Yin Yeng, Endale Mehari, Wu Gang, Ruben Marc D, Francey Lauren J, Morris Andrew R, Choo Natalie Y, Anafi Ron C, Smith David F, Liu Andrew C, Hogenesch John B

2022-Dec-03

genetics, genome-scale data integration, machine learning, sleep regulation

General General

Transforming epilepsy research: a systematic review on natural language processing applications.

In Epilepsia

Despite improved ancillary investigations in epilepsy care, patients' narratives remain indispensable for diagnosing and treatment monitoring. This wealth of information is typically stored in electronic health records and accumulated in medical journals in an unstructured manner, thereby restricting complete utilization in clinical decision-making. To this end, clinical researchers increasing apply natural language processing (NLP) - a branch of artificial intelligence - as it removes ambiguity, derives context and imbues standardized meaning from free-narrative clinical texts. This systematic review presents an overview of the current NLP applications in epilepsy and discusses the opportunities and drawbacks of NLP alongside its future implications. We searched the PubMed and Embase databases with a "natural language processing" and "epilepsy" query (March 4th , 2022) and included original research articles describing the application of NLP techniques for textual analysis in epilepsy. Twenty-six studies were included. Fifty-eight percent of these studies used NLP to classify clinical records into predefined categories, improving patient identification and treatment decisions. Other applications of NLP had structured clinical information retrieval from electronic health records, scientific papers, and online posts of patients. Challenges and opportunities of NLP applications for enhancing epilepsy care and research are discussed. The field could further benefit from NLP by replicating successes in other healthcare domains, such as NLP-aided quality evaluation for clinical decision making, outcome prediction, and clinical record summarization.

Yew Arister N J, Schraagen Marijn, Otte Willem M, van Diessen Eric

2022-Dec-03

Pathology Pathology

Clinical evaluation of malignancy diagnosis of rare thyroid carcinomas by an artificial intelligent automatic diagnosis system.

In Endocrine

PURPOSE : To evaluate the application value of a generally trained artificial intelligence (AI) automatic diagnosis system in the malignancy diagnosis of rare thyroid carcinomas, such as follicular thyroid carcinoma, medullary thyroid carcinoma, primary thyroid lymphoma and anaplastic thyroid carcinoma and compare the diagnostic performance with radiologists of different experience levels.

METHODS : We retrospectively studied 342 patients with 378 thyroid nodules that included 196 rare malignant nodules by using postoperative pathology as the gold standard, and compared the diagnostic performances of three radiologists (one junior, one mid-level, one senior) and that of AI automatic diagnosis system.

RESULTS : The accuracy of the AI system in malignancy diagnosis was 0.825, which was significantly higher than that of all three radiologists and higher than the best radiologist in this study by a margin of 0.097 with P-value of 2.252 × 10-16. The mid-level radiologist and senior radiologist had higher sensitivity (0.857 and 0.959) than that of the AI system (0.847) at the cost of having much lower specificity (0.533, 0.478 versus 0.802). The junior radiologist showed relatively balanced sensitivity and specificity (0.816 and 0.549) but both were lower than that of the AI system.

CONCLUSIONS : The generally trained AI automatic diagnosis system showed high accuracy in the differential diagnosis of begin nodules and rare malignancy nodules. It may assist radiologists for screening of rare malignancy nodules that even senior radiologists are not acquainted with.

Wang Yuan, Xu Lei, Lu Wenliang, Kong Xiangkai, Shi Kaiyuan, Wang Liping, Kong Dexing

2022-Dec-03

AI automatic diagnosis system, Radiologists, Rare thyroid carcinomas, Ultrasonic

General General

A New Risk Score to Predict Intensive Care Unit Admission for Patients with Acute Pancreatitis 48 Hours After Admission: Multicenter Study.

In Digestive diseases and sciences ; h5-index 53.0

AIMS : The objective of this study was to develop and validate an easy-to-use risk score (APRS) to predict which patients with acute pancreatitis (AP) will need intensive care unit (ICU) treatment within 48 h post-hospitalization on the basis of the ubiquitously available clinical records.

METHODS : Patients with acute pancreatitis were retrospectively included from three independent institutions (RM cohort, 5280; TJ cohort, 262; SN cohort, 196), with 56 candidate variables collected within 48 h post-hospitalization. The RM cohort was randomly divided into a training set (N = 4220) and a test set (N = 1060). The most predictive features were extracted by LASSO from the RM cohort and entered into multivariate analysis. APRS was constructed using the coefficients of the statistically significant variables weighted by the multivariable logistic regression model. The APRS was validated by RM, TJ, and SN cohorts. The C-statistic was employed to evaluate the APRS's discrimination. DeLong test was used to compare area under the receiver operating characteristic curve (AUC) differences.

RESULTS : A total of 5738 patients with AP were enrolled. Eleven variables were selected by LASSO and entered into multivariate analysis. APRS was inferred using the above five factors (pleural effusion, ALT/AST, ALB/GLB, urea, and glucose) weighted by their regression coefficients in the multivariable logistic regression model. The C-statistics of APRS were 0.905 (95% CI 0.82-0.98) and 0.889 (95% CI 0.81-0.96) in RM and TJ validation. An online APRS web-based calculator was constructed to assist the clinician to earlier assess the clinical outcomes of patients with AP.

CONCLUSION : APRS could effectively stratify patients with AP into high and low risk of ICU admission within 48 h post-hospitalization, offering clinical value in directing management and personalize therapeutic selection for patients with AP.

Yuan Lei, Shen Lei, Ji Mengyao, Wen Xinyu, Wang Shuo, Huang Pingxiao, Li Yong, Xu Jun

2022-Dec-03

Acute pancreatitis, Intensive care unit, Precision medicine, Risk score, Stratification

General General

Electrical energy recovery from wastewater: prediction with machine learning algorithms.

In Environmental science and pollution research international

Wind, solar, biomass, tidal, etc. are renewable energy sources obtained from natural sources. Among these resources, biomass can be characterized as a significant energy source. Today, the process of producing biogas from waste and turning it into electrical energy has become more popular. So, clean, sustainable, and eco-friendly energy is generated as the waste is managed and converted into electrical energy. The estimation of the electrical energy that will be produced by wastewater recovery using machine learning (ML) algorithms is vital and has not yet been investigated. Thus, this study fills this gap. In this study, it is aimed to predict the electrical energy recovery potential of the sewage sludge of Kahramanmaraş Advanced Biological Wastewater Treatment Plant (KABWWTP) (Turkey), through incineration and anaerobic digestion. For this aim, 6 distinct ML algorithms including linear regression (LR), extreme gradient boosting (XGB), Gaussian process regression (GPR), ridge regression (RR), Lasso regression (LASReg), and Bayesian ridge regression (BR) have been used. Another novelty in this study is the restricted number of input parameters. That is, the electrical energy (output parameter) is predicted using only 3 distinct input parameters (gas flow, conductivity, and TSS). With a MAPE value of 1.032, the XGB method has been determined as the most successful model. Heat mapping and correlation analyses are used to evaluate the relationship between these parameters. Performance results are presented in tables and graphs.

Kerem Alper, Yuce Ekrem

2022-Dec-03

Biogass, Electrical energy recovery, Machine learning, Prediction, Renewable energy, Wastewater

Radiology Radiology

Automated detection and analysis of subdural hematomas using a machine learning algorithm.

In Journal of neurosurgery ; h5-index 64.0

OBJECTIVE : Machine learning algorithms have shown groundbreaking results in neuroimaging. Herein, the authors evaluate the performance of a newly developed convolutional neural network (CNN) to detect and quantify the thickness, volume, and midline shift (MLS) of subdural hematoma (SDH) from noncontrast head CT (NCHCT).

METHODS : NCHCT studies performed for the evaluation of head trauma in consecutive patients between July 2018 and April 2021 at a single institution were retrospectively identified. Ground truth determination of SDH, thickness, and MLS was established by the neuroradiology report. The primary outcome was performance of the CNN in detecting SDH in an external validation set, as measured using area under the receiver operating characteristic curve analysis. Secondary outcomes included accuracy for thickness, volume, and MLS.

RESULTS : Among 263 cases with valid NCHCT according to the study criteria, 135 patients (51%) were male, the mean (± standard deviation) age was 61 ± 23 years, and 70 patients were diagnosed with SDH on neuroradiologist evaluation. The median SDH thickness was 11 mm (IQR 6 mm), and 16 patients had a median MLS of 5 mm (IQR 2.25 mm). In the independent data set, the CNN performed well, with sensitivity of 91.4% (95% CI 82.3%-96.8%), specificity of 96.4% (95% CI 92.7%-98.5%), and accuracy of 95.1% (95% CI 91.7%-97.3%); sensitivity for the subgroup with an SDH thickness above 10 mm was 100%. The maximum thickness mean absolute error was 2.75 mm (95% CI 2.14-3.37 mm), whereas the MLS mean absolute error was 0.93 mm (95% CI 0.55-1.31 mm). The Pearson correlation coefficient computed to determine agreement between automated and manual segmentation measurements was 0.97 (95% CI 0.96-0.98).

CONCLUSIONS : The described Viz.ai SDH CNN performed exceptionally well at identifying and quantifying key features of SDHs in an independent validation imaging data set.

Colasurdo Marco, Leibushor Nir, Robledo Ariadna, Vasandani Viren, Luna Zean Aaron, Rao Abhijit S, Garcia Roberto, Srinivasan Visish M, Sheth Sunil A, Avni Naama, Madziva Moleen, Berejick Mor, Sirota Goni, Efrati Aielet, Meisel Avraham, Shaltoni Hashem, Kan Peter

2022-Sep-30

AI, CT, artificial intelligence, hemorrhage, subdural, technology, trauma

oncology Oncology

The efficacy of a machine learning algorithm for assessing tumour components as a prognostic marker of surgically resected stage IA lung adenocarcinoma.

In Japanese journal of clinical oncology

BACKGROUND : The importance of the stromal components in tumour progression has been discussed widely, but their prognostic role in small size tumours with lepidic components is not fully understood. Applying digital tissue image analysis to whole-slide imaging may enhance the accuracy and reproducibility of pathological assessment. This study aimed to evaluate the prognostic value of tumour components of lung adenocarcinoma by measuring the dimensions of the tumour consisting elements separately, using a machine learning algorithm.

METHODS : Between September 2002 and December 2016, 317 patients with surgically resected, pathological stage IA adenocarcinoma with lepidic components were analysed. We assessed the whole tumour area, including the lepidic components, and measured the epithelium, collagen, elastin areas and alveolar air space. We analysed the prognostic impact of each tumour component.

RESULTS : The dimensions of the epithelium and collagen areas were independent significant risk factors for recurrence-free survival (hazard ratio, 8.38; 95% confidence interval, 1.14-61.88; P = 0.037, and hazard ratio, 2.58; 95% confidence interval, 1.14-5.83; P = 0.022, respectively). According to the subgroup analysis when combining the epithelium and collagen areas as risk factors, patients with tumours consisting of both large epithelium and collagen areas showed significantly poor prognoses (P = 0.002).

CONCLUSIONS : We assessed tumour components using a machine learning algorithm to stratify the post-operative prognosis of surgically resected stage IA adenocarcinomas. This method might guide the selection of patients with a high risk of recurrence.

Terada Yukihiro, Isaka Mitsuhiro, Kawata Takuya, Mizuno Kiyomichi, Muramatsu Koji, Katsumata Shinya, Konno Hayato, Nagata Toshiyuki, Mizuno Tetsuya, Serizawa Masakuni, Ono Akira, Sugino Takashi, Shimizu Kimihiro, Ohde Yasuhisa

2022-Dec-02

lung adenocarcinoma, machine learning, prognosis, tumour components, whole-slide imaging

General General

Application of deblur technology for improving the clarity of digital subtractive angiography.

In Interventional neuroradiology : journal of peritherapeutic neuroradiology, surgical procedures and related neurosciences

BACKGROUND : Digital subtraction angiography (DSA) is most commonly used in vessel disease examinations and treatments. We aimed to develop a novel deep learning-based method to deblur the large focal spot DSA images, so as to obtain a clearer and sharper cerebrovascular DSA image.

METHODS : The proposed network cascaded several residual dense blocks (RDBs), which contain dense connected layers and local residual learning. Several loss functions for image restoration were investigated. Our training set consisted of 52 paired images of angiography with more than 350,000 cropped patches. The testing set included 10 body phantoms and 80 clinical images of different types of diseases for subjective evaluation. All test images were acquired using a large focal spot, and phantom images were simultaneously acquired using a micro focal spot as ground-truth. Peak-to-noise ratio (PSNR) and structural similarity (SSIM) were determined for quantitative analysis. The deblurring results were compared with the original data, and the image quality was subjectively evaluated and graded by two clinicians.

RESULTS : For quantitative analysis of phantom images, the average PSNR/SSIM based on the deep-learning approach (35.34/0.9566) was better than that of large focal spot images (30.64/0.9163). For subjective evaluation of 80 clinical patient images, image quality in all types of cerebrovascular diseases was also improved based on a deep-learning approach (p < 0.001).

CONCLUSIONS : Deep learning-based focal spot deblur algorithm can efficiently improve DSA image quality for better visualization of blood vessels and lesions in the image.

Geng Jiewen, Zhang Pu, Xu Yan, Huang Yan, He Siyu, Wang Yadong, He Chuan, Zhang Hongqi

2022-Dec-01

Residual dense network, arteriovenous malformation, deblur, digital subtraction angiography

Radiology Radiology

External validation of an MR-based radiomic model predictive of locoregional control in oropharyngeal cancer.

In European radiology ; h5-index 62.0

OBJECTIVES : To externally validate a pre-treatment MR-based radiomics model predictive of locoregional control in oropharyngeal squamous cell carcinoma (OPSCC) and to assess the impact of differences between datasets on the predictive performance.

METHODS : Radiomic features, as defined in our previously published radiomics model, were extracted from the primary tumor volumes of 157 OPSCC patients in a different institute. The developed radiomics model was validated using this cohort. Additionally, parameters influencing performance, such as patient subgroups, MRI acquisition, and post-processing steps on prediction performance will be investigated. For this analysis, matched subgroups (based on human papillomavirus (HPV) status of the tumor, T-stage, and tumor subsite) and a subgroup with only patients with 4-mm slice thickness were studied. Also the influence of harmonization techniques (ComBat harmonization, quantile normalization) and the impact of feature stability across observers and centers were studied. Model performances were assessed by area under the curve (AUC), sensitivity, and specificity.

RESULTS : Performance of the published model (AUC/sensitivity/specificity: 0.74/0.75/0.60) drops when applied on the validation cohort (AUC/sensitivity/specificity: 0.64/0.68/0.60). The performance of the full validation cohort improves slightly when the model is validated using a patient group with comparable HPV status of the tumor (AUC/sensitivity/specificity: 0.68/0.74/0.60), using patients acquired with a slice thickness of 4 mm (AUC/sensitivity/specificity: 0.67/0.73/0.57), or when quantile harmonization was performed (AUC/sensitivity/specificity: 0.66/0.69/0.60).

CONCLUSION : The previously published model shows its generalizability and can be applied on data acquired from different vendors and protocols. Harmonization techniques and subgroup definition influence performance of predictive radiomics models.

KEY POINTS : • Radiomics, a noninvasive quantitative image analysis technique, can support the radiologist by enhancing diagnostic accuracy and/or treatment decision-making. • A previously published model shows its generalizability and could be applied on data acquired from different vendors and protocols.

Bos Paula, Martens Roland M, de Graaf Pim, Jasperse Bas, van Griethuysen Joost J M, Boellaard Ronald, Leemans C René, Beets-Tan Regina G H, van de Wiel Mark A, van den Brekel Michiel W M, Castelijns Jonas A

2022-Dec-03

Machine learning, Magnetic resonance imaging, Oropharyngeal neoplasms, Prognosis, Treatment outcome

Ophthalmology Ophthalmology

Transforming ophthalmology in the digital century-new care models with added value for patients.

In Eye (London, England) ; h5-index 41.0

Ophthalmology faces many challenges in providing effective and meaningful eye care to an ever-increasing group of people. Even health systems that have so far been able to cope with the quantitative patient increase, due to their funding and the availability of highly qualified professionals, and improvements in practice routine efficiency, will be pushed to their limits. Further pressure on care will also be caused by new active substances for the largest group of patients with AMD, the so-called dry form. Treatment availability for this so far untreated group will increase the volume of patients 2-3 times. Without the adaptation of the care structures, this quantitative and qualitative expansion in therapy will inevitably lead to an undersupply.There is increasing scientific evidence that significant efficiency gains in the care of chronic diseases can be achieved through better networking of stakeholders in the healthcare system and greater patient involvement. Digitalization can make an important contribution here. Many technological solutions have been developed in recent years and the time is now ready to exploit this potential. The exceptional setting during the SARS-CoV-2 pandemic has shown many that new technology is available safely, quickly, and effectively. The emergency has catalyzed innovation processes and shown for post-pandemic time after that we are equipped to tackle the challenges in ophthalmic healthcare - ultimately for the benefit of patients and society.

Faes Livia, Maloca Peter M, Hatz Katja, Wolfensberger Thomas J, Munk Marion R, Sim Dawn A, Bachmann Lucas M, Schmid Martin K

2022-Dec-03

Radiology Radiology

Preoperative MR radiomics based on high-resolution T2-weighted images and amide proton transfer-weighted imaging for predicting lymph node metastasis in rectal adenocarcinoma.

In Abdominal radiology (New York)

OBJECTIVES : Lymph node (LN) metastasis is an important prognostic factor in rectal cancer (RC). However, accurate identification of LN metastasis can be challenged for radiologists. The aim of our study was to assess the utility of MRI radiomics based on T2-weighted images (T2WI) and amide proton transfer-weighted (APTw) images for predicting LN metastasis in RC preoperatively.

METHODS : A total of 125 patients with pathologically confirmed rectal adenocarcinoma (RA) from January 2019 to June 2021 who underwent preoperative MR were enrolled in this retrospective study. Radiomics features were extracted from high-resolution T2WI and APTw images of primary tumor. The most relevant radiomics and clinical features were selected using correlation and multivariate logistic analysis. Radiomics models were built using five machine learning algorithms including support vector machine (SVM), logical regression (LR), k- nearest neighbor (KNN), naive bayes (NB), and random forest (RF). The best algorithm was selected for further establish the clinical- radiomics model. The receiver operating characteristic curve (ROC) analysis was used to assess the performance of radiomics and clinical-radiomics model for predicting LN metastasis.

RESULTS : The LR classifier had the best prediction performance, with AUCs of 0.983 (95% CI 0.957-1.000), 0.864 (95% CI 0.729-0.972), 0.851 (95% CI 0.713-0.940) on the training set, validation, and test sets, respectively. In terms of prediction, the clinical-radiomics combined model outperformed the radiomics model. The AUCs of the clinical-radiomics combined model in the validation and test sets were 0.900 (95% CI 0.785-0.986), and 0.929 (95% CI 0.721-0.943), respectively.

CONCLUSION : The radiomics model based on high-resolution T2WI and APTw images can predict LN metastasis accurately in patients with RA.

Wei Qiurong, Yuan Wenjing, Jia Ziqi, Chen Jialiang, Li Ling, Yan Zhaoxian, Liao Yuting, Mao Liting, Hu Shaowei, Liu Xian, Chen Weicui

2022-Dec-02

Amide proton transferweighted imaging, Lymph node metastasis, Magnetic resonance imaging, Radiomic, Rectal adenocarcinoma

Radiology Radiology

Automated detection of intracranial large vessel occlusions using Viz.ai software: Experience in a large, integrated stroke network.

In Brain and behavior

BACKGROUND AND PURPOSE : Endovascular thrombectomy is an evidence-based treatment for large vessel occlusion (LVO) stroke. Commercially available artificial intelligence has been designed to detect the presence of an LVO on computed tomography angiogram (CTA). We compared Viz.ai-LVO (San Francisco, CA, USA) to CTA interpretation by board-certified neuroradiologists (NRs) in a large, integrated stroke network.

METHODS : From January 2021 to December 2021, we compared Viz.ai detection of an internal carotid artery (ICA) or middle cerebral artery first segment (MCA-M1) occlusion to the gold standard of CTA interpretation by board-certified NRs for all code stroke CTAs. On a monthly basis, sensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value (NPV) were calculated. Trend analyses were conducted to evaluate for any improvement of LVO detection by the software over time.

RESULTS : 3851 patients met study inclusion criteria, of whom 220 (5.7%) had an ICA or MCA-M1 occlusion per NR. Sensitivity and specificity were 78.2% (95% CI 72%-83%) and 97% (95% CI 96%-98%), respectively. PPV was 61% (95% CI 55%-67%), NPV 99% (95% CI 98%-99%), and accuracy was 95.9% (95% CI 95.3%-96.5%). Neither specificity or sensitivity improved over time in the trend analysis.

CONCLUSIONS : Viz.ai-LVO has high specificity and moderately high sensitivity to detect an ICA or proximal MCA occlusion. The software has the potential to streamline code stroke workflows and may be particularly impactful when emergency access to NRs or vascular neurologists is limited.

Karamchandani Rahul R, Helms Anna Maria, Satyanarayana Sagar, Yang Hongmei, Clemente Jonathan D, Defilipp Gary, Strong Dale, Rhoten Jeremy B, Asimos Andrew W

2022-Dec-01

Viz.ai, artificial intelligence, large vessel occlusion

General General

Intelligent route to design efficient CO2 reduction electrocatalysts using ANFIS optimized by GA and PSO.

In Scientific reports ; h5-index 158.0

Recently, electrochemical reduction of CO2 into value-added fuels has been noticed as a promising process to decrease CO2 emissions. The development of such technology is strongly depended upon tuning the surface properties of the applied electrocatalysts. Considering the high cost and time-consuming experimental investigations, computational methods, particularly machine learning algorithms, can be the appropriate approach for efficiently screening the metal alloys as the electrocatalysts. In doing so, to represent the surface properties of the electrocatalysts numerically, d-band theory-based electronic features and intrinsic properties obtained from density functional theory (DFT) calculations were used as descriptors. Accordingly, a dataset containg 258 data points was extracted from the DFT method to use in machine learning method. The primary purpose of this study is to establish a new model through machine learning methods; namely, adaptive neuro-fuzzy inference system (ANFIS) combined with particle swarm optimization (PSO) and genetic algorithm (GA) for the prediction of *CO (the key intermediate) adsorption energy as the efficiency metric. The developed ANFIS-PSO and ANFIS-GA showed excellent performance with RMSE of 0.0411 and 0.0383, respectively, the minimum errors reported so far in this field. Additionally, the sensitivity analysis showed that the center and the filling of the d-band are the most determining parameters for the electrocatalyst surface reactivity. The present study conveniently indicates the potential and value of machine learning in directing the experimental efforts in alloy system electrocatalysts for CO2 reduction.

Gheytanzadeh Majedeh, Baghban Alireza, Habibzadeh Sajjad, Jabbour Karam, Esmaeili Amin, Mashhadzadeh Amin Hamed, Mohaddespour Ahmad

2022-Dec-02

oncology Oncology

Metal artifact reduction in kV CT images throughout two-step sequential deep convolutional neural networks by combining multi-modal imaging (MARTIAN).

In Scientific reports ; h5-index 158.0

This work attempted to construct a new metal artifact reduction (MAR) framework in kilo-voltage (kV) computed tomography (CT) images by combining (1) deep learning and (2) multi-modal imaging, defined as MARTIAN (Metal Artifact Reduction throughout Two-step sequentIAl deep convolutional neural Networks). Most CNNs under supervised learning require artifact-free images to artifact-contaminated images for artifact correction. Mega-voltage (MV) CT is insensitive to metal artifacts, unlike kV CT due to different physical characteristics, which can facilitate the generation of artifact-free synthetic kV CT images throughout the first network (Network 1). The pairs of true kV CT and artifact-free kV CT images after post-processing constructed a subsequent network (Network 2) to conduct the actual MAR process. The proposed framework was implemented by GAN from 90 scans for head-and-neck and brain radiotherapy and validated with 10 independent cases against commercial MAR software. The artifact-free kV CT images following Network 1 and post-processing led to structural similarity (SSIM) of 0.997, and mean-absolute-error (MAE) of 10.2 HU, relative to true kV CT. Network 2 in charge of actual MAR successfully suppressed metal artifacts, relative to commercial MAR, while retaining the detailed imaging information, yielding the SSIM of 0.995 against 0.997 from the commercial MAR.

Kim Hojin, Yoo Sang Kyun, Kim Dong Wook, Lee Ho, Hong Chae-Seon, Han Min Cheol, Kim Jin Sung

2022-Dec-02

Surgery Surgery

Application of machine learning in the diagnosis of vestibular disease.

In Scientific reports ; h5-index 158.0

Machine learning is considered a potential aid to support human decision making in disease prediction. In this study, we determined the utility of various machine learning algorithms in classifying peripheral vestibular (PV) and non-PV diseases based on the results of equilibrium function tests. A total of 1009 patients who had undergone our standardized neuro-otological examinations were recruited. We applied five supervised machine learning algorithms (random forest, adaboost, gradient boosting, support vector machine, and logistic regression). After preprocessing the data, optimizing the hyperparameters using GridSearchCV, and performing a final evaluation on the test set using scikit-learn, we evaluated the predictive capability using various performance metrics, namely, accuracy, F1-score, area under the receiver operating characteristic curve, precision, recall, and Matthews correlation coefficient (MCC). All five machine learning algorithms yielded satisfactory results; the accuracy of the algorithms ranged from 76 to 79%, with the support vector machine classifier having the highest accuracy. In cases where the predictions of the five models were consistent, the accuracy of the PV diagnostic results was improved to 83%, whereas it increased to 85% for the non-PV diagnostic results. Future research should increase the number of patients and optimize the classification methods to obtain the highest diagnostic accuracy.

Anh Do Tram, Takakura Hiromasa, Asai Masatsugu, Ueda Naoko, Shojaku Hideo

2022-Dec-02

General General

CNN-based object detection and growth estimation of plum fruit (Prunus mume) using RGB and depth imaging techniques.

In Scientific reports ; h5-index 158.0

Modern people who value healthy eating habits have shown increasing interest in plum (Prunus mume) fruits, primarily owing to their nutritiousness and proven efficacy. As consumption increases, it becomes important to monitor work to prevent Prunus mume fruits from falling out. Moreover, determining the growth status of Prunus mume is also crucial and is attracting increasing attention. In this study, convolutional neural network (CNN)-based deep learning object detection was developed using RGBD images collected from Prunus mume farms. These RGBD images consider various environments, including the depth information of objects in the outdoor field. A faster region-based convolutional neural network (R-CNN), EfficientDet, Retinanet, and Single Shot Multibox Detector (SSD) were applied for detection, and the performance of all models was estimated by comparing their respective computing speeds and average precisions (APs). The test results show that the EfficientDet model is the most accurate, and SSD MobileNet is the fastest among the four models. In addition, the algorithm was developed to acquire the growth status of P. mume fruits by applying the coordinates and score values of bounding boxes to the depth map. Compared to the diameters of the artificial Prunus mume fruits used as the experimental group, the calculated diameters were very similar to those of the artificial objects. Collectively, the results demonstrate that the CNN-based deep learning Prunus mume detection and growth estimation method can be applied to real farmlands.

Kim EungChan, Hong Suk-Ju, Kim Sang-Yeon, Lee Chang-Hyup, Kim Sungjay, Kim Hyuck-Joo, Kim Ghiseok

2022-Dec-02

Radiology Radiology

Classification and visual explanation for COVID-19 pneumonia from CT images using triple learning.

In Scientific reports ; h5-index 158.0

This study presents a novel framework for classifying and visualizing pneumonia induced by COVID-19 from CT images. Although many image classification methods using deep learning have been proposed, in the case of medical image fields, standard classification methods are unable to be used in some cases because the medical images that belong to the same category vary depending on the progression of the symptoms and the size of the inflamed area. In addition, it is essential that the models used be transparent and explainable, allowing health care providers to trust the models and avoid mistakes. In this study, we propose a classification method using contrastive learning and an attention mechanism. Contrastive learning is able to close the distance for images of the same category and generate a better feature space for classification. An attention mechanism is able to emphasize an important area in the image and visualize the location related to classification. Through experiments conducted on two-types of classification using a three-fold cross validation, we confirmed that the classification accuracy was significantly improved; in addition, a detailed visual explanation was achieved comparison with conventional methods.

Kato Sota, Oda Masahiro, Mori Kensaku, Shimizu Akinobu, Otake Yoshito, Hashimoto Masahiro, Akashi Toshiaki, Hotta Kazuhiro

2022-Dec-02

General General

ResNet-32 and FastAI for diagnoses of ductal carcinoma from 2D tissue slides.

In Scientific reports ; h5-index 158.0

Carcinoma is a primary source of morbidity in women globally, with metastatic disease accounting for most deaths. Its early discovery and diagnosis may significantly increase the odds of survival. Breast cancer imaging is critical for early identification, clinical staging, management choices, and treatment planning. In the current study, the FastAI technology is used with the ResNet-32 model to precisely identify ductal carcinoma. ResNet-32 is having few layers comparted to majority of its counterparts with almost identical performance. FastAI offers a rapid approximation toward the outcome for deep learning models via GPU acceleration and a faster callback mechanism, which would result in faster execution of the model with lesser code and yield better precision in classifying the tissue slides. Residual Network (ResNet) is proven to handle the vanishing gradient and effective feature learning better. Integration of two computationally efficient technologies has yielded a precision accuracy with reasonable computational efforts. The proposed model has shown considerable efficiency in the evaluating parameters like sensitivity, specificity, accuracy, and F1 Score against the other dominantly used deep learning models. These insights have shown that the proposed approach might assist practitioners in analyzing Breast Cancer (BC) cases appropriately, perhaps saving future complications and death. Clinical and pathological analysis and predictive accuracy have been improved with digital image processing.

Praveen S Phani, Srinivasu Parvathaneni Naga, Shafi Jana, Wozniak Marcin, Ijaz Muhammad Fazal

2022-Dec-02

General General

China's Gridded Manufacturing Dataset.

In Scientific data

The growth of the manufacturing industry is the engine of rapid economic growth in developing regions. Characterizing the geographical distribution of manufacturing firms is critically important for scientists and policymakers. However, data on the manufacturing industry used in previous studies either have a low spatial resolution (or fuzzy classification) or high-resolution information is lacking. Here, we propose a map point-of-interest classification method based on machine learning technology and build a dataset of the distribution of Chinese manufacturing firms called the Gridded Manufacturing Dataset. This dataset includes the number and type of manufacturing firms at a 0.01° latitude by 0.01° longitude scale. It includes all manufacturing firms (classified into seven categories) in China in 2015 (4.56 million) and 2019 (6.19 million). This dataset can be used to characterize temporal and spatial patterns in the distribution of manufacturing firms as well as reveal the mechanisms underlying the development of the manufacturing industry and changes in regional economic policies.

Fan Chenjing, Huang Xinran, Zhou Lin, Gai Zhenyu, Zhu Chaoyang, Zhang Haole

2022-Dec-02

General General

Prediction of fluid oil and gas volumes of shales with a deep learning model and its application to the Bakken and Marcellus shales.

In Scientific reports ; h5-index 158.0

The fluid oil and gas volumes (S1) retained within the shales are one of the most important parameter of producible fluid oil and gas saturations of shales together with total organic carbon content. The S1 volumes can directly be obtained by Rock-Eval pyrolysis analysis. However, it is time consuming and not practical to obtain samples from all intervals of all wells in any shale play. S1 volumes prediction with a deep learning (DL) model have increasingly became important with the booming exploration and development of shale oil and gas resources. S1 volumes of shales are controlled by organic matter richness, type and maturity together with reservoir quality and adsorption capacity which are mainly effected by age, depth, organic content, maturity and mineralogy. A dataset consisting of 331 samples from 19 wells of various locations of the world-class organic-rich shales of the Niobrara, Eagle Ford, Barnett, Haynesville, Woodford, Vaca Muerta and Dadaş has been used to determination of a DL model for S1 volumes prediction using Python 3 programing environment with Tensorflow and Keras open-source libraries. The DL model that contains 5 dense layers and, 1024, 512, 256, 128 and 128 neurons has been predicted S1 volumes of shales as high as R2 = 0.97 from the standard petroleum E&P activities. The DL model has also successfully been applied to S1 volumes prediction of the Bakken and Marcellus shales of the North America. The prediction of the S1 volumes show that the shales have lower to higher reservoir quality and, oil and gas production rate that are well-matches with former studies.

Şen Şamil

2022-Dec-02

General General

Reference panel guided topological structure annotation of Hi-C data.

In Nature communications ; h5-index 260.0

Accurately annotating topological structures (e.g., loops and topologically associating domains) from Hi-C data is critical for understanding the role of 3D genome organization in gene regulation. This is a challenging task, especially at high resolution, in part due to the limited sequencing coverage of Hi-C data. Current approaches focus on the analysis of individual Hi-C data sets of interest, without taking advantage of the facts that (i) several hundred Hi-C contact maps are publicly available, and (ii) the vast majority of topological structures are conserved across multiple cell types. Here, we present RefHiC, an attention-based deep learning framework that uses a reference panel of Hi-C datasets to facilitate topological structure annotation from a given study sample. We compare RefHiC against tools that do not use reference samples and find that RefHiC outperforms other programs at both topological associating domain and loop annotation across different cell types, species, and sequencing depths.

Zhang Yanlin, Blanchette Mathieu

2022-Dec-02

General General

N-Omniglot, a large-scale neuromorphic dataset for spatio-temporal sparse few-shot learning.

In Scientific data

Few-shot learning (learning with a few samples) is one of the most important cognitive abilities of the human brain. However, the current artificial intelligence systems meet difficulties in achieving this ability. Similar challenges also exist for biologically plausible spiking neural networks (SNNs). Datasets for traditional few-shot learning domains provide few amounts of temporal information. And the absence of neuromorphic datasets has hindered the development of few-shot learning for SNNs. Here, to the best of our knowledge, we provide the first neuromorphic dataset for few-shot learning using SNNs: N-Omniglot, based on the Dynamic Vision Sensor. It contains 1,623 categories of handwritten characters, with only 20 samples per class. N-Omniglot eliminates the need for a neuromorphic dataset for SNNs with high spareness and tremendous temporal coherence. Additionally, the dataset provides a powerful challenge and a suitable benchmark for developing SNNs algorithms in the few-shot learning domain due to the chronological information of strokes. We also provide the improved nearest neighbor, convolutional network, SiameseNet, and meta-learning algorithm in the spiking version for verification.

Li Yang, Dong Yiting, Zhao Dongcheng, Zeng Yi

2022-Dec-02

Cardiology Cardiology

The Role of Endoscopic Ultrasound in Hepatology.

In Gut and liver

Endoscopic ultrasound (EUS) has been an indispensable and widely used diagnostic tool in several medical fields, including gastroenterology, cardiology, and urology, due to its diverse therapeutic and diagnostic applications. Many studies show that it is effective and safe in patients with liver conditions where conventional endoscopy or cross-sectional imaging are inefficient or when surgical interventions pose high risks. In this article, we present a review of the current literature for the different diagnostic and therapeutic applications of EUS in liver diseases and their complications and discuss the potential future application of artificial intelligence analysis of EUS.

Alqahtani Saleh A, Ausloos Floriane, Park Ji Seok, Jang Sunguk

2022-Dec-02

Endoscopic ultrasound, Liver diseases, Portal hypertension

General General

The HA4M dataset: Multi-Modal Monitoring of an assembly task for Human Action recognition in Manufacturing.

In Scientific data

This paper introduces the Human Action Multi-Modal Monitoring in Manufacturing (HA4M) dataset, a collection of multi-modal data relative to actions performed by different subjects building an Epicyclic Gear Train (EGT). In particular, 41 subjects executed several trials of the assembly task, which consists of 12 actions. Data were collected in a laboratory scenario using a Microsoft® Azure Kinect which integrates a depth camera, an RGB camera, and InfraRed (IR) emitters. To the best of authors' knowledge, the HA4M dataset is the first multi-modal dataset about an assembly task containing six types of data: RGB images, Depth maps, IR images, RGB-to-Depth-Aligned images, Point Clouds and Skeleton data. These data represent a good foundation to develop and test advanced action recognition systems in several fields, including Computer Vision and Machine Learning, and application domains such as smart manufacturing and human-robot collaboration.

Cicirelli Grazia, Marani Roberto, Romeo Laura, Domínguez Manuel García, Heras Jónathan, Perri Anna G, D’Orazio Tiziana

2022-Dec-02

General General

Deciphering clinical abbreviations with a privacy protecting machine learning system.

In Nature communications ; h5-index 260.0

Physicians write clinical notes with abbreviations and shorthand that are difficult to decipher. Abbreviations can be clinical jargon (writing "HIT" for "heparin induced thrombocytopenia"), ambiguous terms that require expertise to disambiguate (using "MS" for "multiple sclerosis" or "mental status"), or domain-specific vernacular ("cb" for "complicated by"). Here we train machine learning models on public web data to decode such text by replacing abbreviations with their meanings. We report a single translation model that simultaneously detects and expands thousands of abbreviations in real clinical notes with accuracies ranging from 92.1%-97.1% on multiple external test datasets. The model equals or exceeds the performance of board-certified physicians (97.6% vs 88.7% total accuracy). Our results demonstrate a general method to contextually decipher abbreviations and shorthand that is built without any privacy-compromising data.

Rajkomar Alvin, Loreaux Eric, Liu Yuchen, Kemp Jonas, Li Benny, Chen Ming-Jun, Zhang Yi, Mohiuddin Afroz, Gottweis Juraj

2022-Dec-02

General General

Improved model quality assessment using sequence and structural information by enhanced deep neural networks.

In Briefings in bioinformatics

Protein model quality assessment plays an important role in protein structure prediction, protein design and drug discovery. In this work, DeepUMQA2, a substantially improved version of DeepUMQA for protein model quality assessment, is proposed. First, sequence features containing protein co-evolution information and structural features reflecting family information are extracted to complement model-dependent features. Second, a novel backbone network based on triangular multiplication update and axial attention mechanism is designed to enhance information exchange between inter-residue pairs. On CASP13 and CASP14 datasets, the performance of DeepUMQA2 increases by 20.5 and 20.4% compared with DeepUMQA, respectively (measured by top 1 loss). Moreover, on the three-month CAMEO dataset (11 March to 04 June 2022), DeepUMQA2 outperforms DeepUMQA by 15.5% (measured by local AUC0,0.2) and ranks first among all competing server methods in CAMEO blind test. Experimental results show that DeepUMQA2 outperforms state-of-the-art model quality assessment methods, such as ProQ3D-LDDT, ModFOLD8, and DeepAccNet and DeepUMQA2 can select more suitable best models than state-of-the-art protein structure methods, such as AlphaFold2, RoseTTAFold and I-TASSER, provided themselves.

Liu Jun, Zhao Kailong, Zhang Guijun

2022-Dec-02

deep learning, homologous template, model quality assessment, multiple sequence alignment

General General

Succinylated lysine residue prediction revisited.

In Briefings in bioinformatics

Lysine succinylation is a kind of post-translational modification (PTM) that plays a crucial role in regulating the cellular processes. Aberrant succinylation may cause inflammation, cancers, metabolism diseases and nervous system diseases. The experimental methods to detect succinylation sites are time-consuming and costly. This thus calls for computational models with high efficacy, and attention has been given in the literature to develop such models, albeit with only moderate success in the context of different evaluation metrics. One crucial aspect in this context is the biochemical and physicochemical properties of amino acids, which appear to be useful as features for such computational predictors. However, some of the existing computational models did not use the biochemical and physicochemical properties of amino acids. In contrast, some others used them without considering the inter-dependency among the properties. The combinations of biochemical and physicochemical properties derived through our optimization process achieve better results than the results achieved by combining all the properties. We propose three deep learning architectures: CNN+Bi-LSTM (CBL), Bi-LSTM+CNN (BLC) and their combination (CBL_BLC). We find that CBL_BLC outperforms the other two. Ensembling of different models successfully improves the results. Notably, tuning the threshold of the ensemble classifiers further improves the results. Upon comparing our work with other existing works on two datasets, we successfully achieve better sensitivity and specificity by varying the threshold value.

Ahmed Shehab Sarar, Rifat Zaara Tasnim, Rahman M Saifur, Rahman M Sohel

2022-Dec-02

Deep Learning, Genetic algorithm, Post-translational modification, Succinylation

Radiology Radiology

A CT-Based Deep Learning Radiomics Nomogram to Predict Histological Grades of Head and Neck Squamous Cell Carcinoma.

In Academic radiology

RATIONALE AND OBJECTIVES : Accurate pretreatment assessment of histological differentiation grade of head and neck squamous cell carcinoma (HNSCC) is crucial for prognosis evaluation. This study aimed to construct and validate a contrast-enhanced computed tomography (CECT)-based deep learning radiomics nomogram (DLRN) to predict histological differentiation grades of HNSCC.

MATERIALS AND METHODS : A total of 204 patients with HNSCC who underwent CECT scans were enrolled in this study. The participants recruited from two hospitals were split into a training set (n=124, 74 well/moderately differentiated and 50 poorly differentiated) of patients from one hospital and an external test set of patients from the other hospital (n=80, 49 well/moderately differentiated and 31 poorly differentiated). CECT-based manually-extracted radiomics (MER) features and deep learning (DL) features were extracted and selected. The selected MER features and DL features were then combined to construct a DLRN via multivariate logistic regression. The predictive performance of the DLRN was assessed using ROCs and decision curve analysis (DCA).

RESULTS : Three MER features and seven DL features were finally selected. The DLRN incorporating the selected MER and DL features showed good predictive value for the histological differentiation grades of HNSCC (well/moderately differentiated vs. poorly differentiated) in both the training (AUC, 0.878) and test (AUC, 0.822) sets. DCA demonstrated that the DLRN was clinically useful for predicting histological differentiation grades of HNSCC.

CONCLUSION : A CECT-based DLRN was constructed to predict histological differentiation grades of HNSCC. The DLRN showed good predictive efficacy and might be useful for prognostic evaluation of patients with HNSCC.

Zheng Ying-Mei, Che Jun-Yi, Yuan Ming-Gang, Wu Zeng-Jie, Pang Jing, Zhou Rui-Zhi, Li Xiao-Li, Dong Cheng

2022-Nov-30

Deep learning, Head and neck squamous cell carcinoma, Radiomics, Tomography, X-ray computed

General General

Human Decision Making in an AI Driven Future in Health: Protocols for Comparative Analysis and Simulation.

In JMIR research protocols ; h5-index 26.0

BACKGROUND : Health care can broadly be divided into two domains: clinical health services and complex health services, i.e., non-clinical health services such as health policy and health regulation. Artificial Intelligence (AI) is transforming both these areas. Currently, humans are leaders, managers, and decision makers in complex health services. However, with the rise of AI, the time has come to ask whether humans will continue to have meaningful decision-making roles in this domain. Further, rationality has long dominated this space. What role will intuition play?

OBJECTIVE : The objective is to establish a protocol of protocols to be used in the proposed research, which aims to explore whether humans will continue in meaningful decision-making roles in complex health services in an AI-driven future.

METHODS : This paper describes a set of protocols for the proposed research, which is designed as a four-step project across two phases. This paper describes the protocols for each step: (i) The protocol for a scoping review to identify and map human attributes that influence decision-making in complex health services.The research question focuses on the attributes that influence human decision-making in this context as reported in the literature. (ii) The protocol for a scoping review to identify and map AI attributes that influence decision-making in complex health services. The research question focuses on attributes that influence AI decision-making in this context as reported in the literature . (iii) The protocol for a comparative analysis: A narrative comparison, followed by a mathematical comparison, of the two sets of attributes - human and AI. This analysis will investigate whether humans have one or more unique attributes that could influence decision-making for the better. (iv) The protocol for the simulation of a non-clinical environment in health regulation and policy into which virtual human and AI decision-makers (agents) are introduced. The virtual human and AI will be based on the human and AI attributes identified in the scoping reviews. The simulation will explore, observe and document how humans interact with AI, and whether humans are likely to compete, cooperate, or converge with AI.

RESULTS : The results will be presented in tabular form, visually intuitive formats, and - in the case of the simulation - multimedia formats as well.

CONCLUSIONS : This paper provides a roadmap for the proposed research. It also provides an example of a protocol of protocols for methods used in complex health research. While there are established guidelines for a priori protocols for scoping reviews, there is a paucity of guidance on establishing a protocol of protocols. This paper takes the first step towards building a scaffolding for future guidelines in this regard.

Doreswamy Nandini, Horstmanshof Louise

2022-Nov-30

General General

Generative Adversarial Networks for Modeling Clinical Biomarker Profiles with Race/Ethnicity.

In British journal of clinical pharmacology ; h5-index 58.0

AIMS : Modeling biomarker profiles for under-represented race/ethnicity groups are challenging because the underlying studies frequently do not have sufficient participants from these groups. The aim was to investigate generative adversarial networks (GANs), an artificial intelligence (AI) technology that enables realistic simulations of complex patterns, for modeling clinical biomarker profiles of under-represented groups.

METHODS : GANs consist of generator and discriminator neural networks that operate in tandem. GAN architectures were developed for modeling univariate and joint distributions of a panel of 16 diabetes-relevant biomarkers from the National Health and Nutrition Examination Survey (NHANES), which contains laboratory and clinical biomarker data from a population-based sample of individuals of all ages, racial groups, and ethnicities. Conditional GANs were used to model biomarker profiles for race/ethnicity categories. GAN performance was assessed by comparing GAN outputs to test data.

RESULTS : The biomarkers exhibited non-normal distributions and varied in their bivariate correlation patterns. Univariate distributions were modeled with generator and discriminator neural networks consisting of two dense layers with rectified linear unit-activation. The distributions of GAN-generated biomarkers were similar to the test data distributions. The joint distributions of the biomarker panel in the GAN-generated data were dispersed and overlapped with the joint distribution of the test data as assessed by three multi-dimensional projection methods. Conditional GANs satisfactorily modeled the joint distribution of the biomarker panel in the Black, Hispanic, White, and "Other" race/ethnicity categories.

CONCLUSIONS : GAN are a promising AI approach for generating virtual patient data with realistic biomarker distributions for under-represented race/ethnicity groups.

Nair Rahul, Mohan Deen Dayal, Frank Sandra, Setlur Srirangaraj, Govindaraju Venugopal, Ramanathan Murali

2022-Dec-02

AI, Artificial intelligence, biomarkers, generative adversarial networks

General General

Ensemble learning for the detection of pli-de-passages in the superior temporal sulcus.

In NeuroImage ; h5-index 117.0

The surface of the cerebral cortex is very convoluted, with a large number of folds, the cortical sulci. These folds are extremely variable from one individual to another, and this large variability is a problem for many applications in neuroscience and brain imaging. In particular, sulcal geometry (shape) and sulcal topology (branches, number of pieces) are very variable. "Plis de passages" (PPs) or "annectant gyri" can explain part of the topological variability, namely why sulci have a variable number of pieces across subjects. The concept of PPs was first introduced by Gratiolet (1854) to describe transverse gyri that interconnect both sides of a sulcus, that are frequently buried in the depth of sulci, and that are sometimes apparent on the cortical surface, hence seemingly interrupting the course of sulci and separating them in several pieces. Nevertheless, the difficulty of identifying PPs and the lack of systematic methods to automatically detect them has limited their use. However, based on a recent characterization of PPs in the superior temporal sulcus, we present here a method to automatically detect PPs in the superior temporal sulcus. Local morphology within the sulcus is characterized using cortical surface profiling, and the three-dimensional PP recognition problem is performed as a two-dimensional image classification problem with class-imbalance. This is solved by using an ensemble support vector machine model (EnsSVM) with a rebalancing strategy. Cross validation and quantitative experimental results on an external dataset show the effectiveness and robustness of our approach.

Song Tianqi, Bodin Clémentine, Coulon Olivier

2022-Nov-29

Cerebral Cortex, Cortical folding, Machine learning, Plis de passage, SVM

General General

A lightweight network for COVID-19 detection in X-ray images.

In Methods (San Diego, Calif.)

The Novel Coronavirus 2019 (COVID-19) is a global pandemic which has a devastating impact. Due to its quick transmission, a prominent challenge in confronting this pandemic is the rapid diagnosis. Currently, the commonly-used diagnosis is the specific molecular tests aided with the medical imaging modalities such as chest X-ray (CXR). However, with the large demand, the diagnoses of CXR are time-consuming and laborious. Deep learning is promising for automatically diagnosing COVID-19 to ease the burden on medical systems. At present, the most applied neural networks are large, which hardly satisfy the rapid yet inexpensive requirements of COVID-19 detection. To reduce huge computation and memory demands, in this paper, we focus on implementing lightweight networks for COVID-19 detection in CXR. Concretely, we first augment data based on clinical visual features of CXR from expertise. Then, according to the fact that all the input data are CXR, we design a targeted four-layer network with either 11×11 or 3×3 kernels to recognize regional features and detail features. A pruning criterion based on the weights importance is also proposed to further prune the network. Experiments on a public COVID-19 dataset validate the effectiveness and efficiency of the proposed method.

Shi Yong, Tang Anda, Xiao Yang, Niu Lingfeng

2022-Nov-29

COVID-19 detection, network pruning, neural network

General General

Images Reconstruction from functional magnetic resonance imaging Patterns Based on the Improved Deep Generative Multiview Model.

In Neuroscience

Reconstructing visual stimulus images from the brain activity signals is an important research task in the field of brain decoding. Many methods of reconstructing visual stimulus images mainly focus on how to use deep learning to classify the brain activities measured by functional magnetic resonance imaging or identify visual stimulus images. Accurate reconstruction of visual stimulus images by using deep learning still remains challenging. This paper proposes an improved deep generative multiview model to further promote the accuracy of reconstructing visual stimulus images. Firstly, an encoder based on residual-in-residual dense blocks is designed to fit the deep and multiview visual features of human natural state, and extract the features of visual stimulus images. Secondly, the structure of original decoder is extended to a deeper network in the deep generative multiview model, which makes the features obtained by each deconvolution layer more distinguishable. Finally, we configure the parameters of the optimizer and compare the performance of various optimizers under different parameter values, and then the one with the best performance is chosen and adopted to the whole model. The performance evaluations conducted on two publicly available datasets demonstrate that the improved model has more accurate reconstruction effectiveness than the original deep generative multiview model.

Pan Hongguang, Fu Yunpeng, Li Zhuoyi, Wen Fan, Hu Jianchen, Wu Bo

2022-Nov-29

Brain-computer interface, deep learning, image reconstruction, residual-in-residual dense blocks

Internal Medicine Internal Medicine

Chest X-ray-based opportunistic screening of sarcopenia using deep learning.

In Journal of cachexia, sarcopenia and muscle

BACKGROUND : Early detection and management of sarcopenia is of clinical importance. We aimed to develop a chest X-ray-based deep learning model to predict presence of sarcopenia.

METHODS : Data of participants who visited osteoporosis clinic at Severance Hospital, Seoul, South Korea, between January 2020 and June 2021 were used as derivation cohort as split to train, validation and test set (65:15:20). A community-based older adults cohort (KURE) was used as external test set. Sarcopenia was defined based on Asian Working Group 2019 guideline. A deep learning model was trained to predict appendicular lean mass (ALM), handgrip strength (HGS) and chair rise test performance from chest X-ray images; then the machine learning model (SARC-CXR score) was built using the age, sex, body mass index and chest X-ray predicted muscle parameters along with estimation uncertainty values.

RESULTS : Mean age of the derivation cohort (n = 926; women n = 700, 76%; sarcopenia n = 141, 15%) and the external test (n = 149; women n = 95, 64%; sarcopenia n = 18, 12%) cohort was 61.4 and 71.6 years, respectively. In the internal test set (a hold-out set, n = 189, from the derivation cohort) and the external test set (n = 149), the concordance correlation coefficient for ALM prediction was 0.80 and 0.76, with an average difference of 0.18 ± 2.71 and 0.21 ± 2.28, respectively. Gradient-weight class activation mapping for deep neural network models to predict ALM and HGS commonly showed highly weight pixel values at bilateral lung fields and part of the cardiac contour. SARC-CXR score showed good discriminatory performance for sarcopenia in both internal test set [area under the receiver-operating characteristics curve (AUROC) 0.813, area under the precision-recall curve (AUPRC) 0.380, sensitivity 0.844, specificity 0.739, F1-score 0.540] and external test set (AUROC 0.780, AUPRC 0.440, sensitivity 0.611, specificity 0.855, F1-score 0.458). Among SARC-CXR model features, predicted low ALM from chest X-ray was the most important predictor of sarcopenia based on SHapley Additive exPlanations values. Higher estimation uncertainty of HGS contributed to elevate the predicted risk of sarcopenia. In internal test set, SARC-CXR score showed better discriminatory performance than SARC-F score (AUROC 0.813 vs. 0.691, P = 0.029).

CONCLUSIONS : Chest X-ray-based deep leaning model improved detection of sarcopenia, which merits further investigation.

Ryu Jin, Eom Sujeong, Kim Hyeon Chang, Kim Chang Oh, Rhee Yumie, You Seng Chan, Hong Namki

2022-Dec-01

Appendicular lean mass, Artificial intelligence, Chest X-ray-based deep learning model, Chest radiograph, Sarcopenia

General General

Develop a hybrid machine learning model for promoting microbe iomass production.

In Bioresource technology

Since the cultivation condition of microbe biomass production (mycelia yield) involves a variety of factors, it's a laborious process to obtain the optimal cultivation condition of Antrodia cinnamomea (A. cinnamomea). This study proposed a hybrid machine learning approach (i.e., ANFIS-NM) to identify the potent factors and optimize the cultivation conditions of A. cinnamomea based on a 32 fractional factorial design with seven factors. The results indicate that the ANFIS-NM approach successfully identified three key factors (i.e., glucose, potato dextrose broth, and agar) and significantly boosted mycelia yield. The interpretability of ANFIS rules made the cultivation conditions visually interpretable. Subsequently, a three-factor five-level central composite design was used to probe the optimal yield. This study demonstrates the proposed hybrid machine learning approach could significantly reduce the time consumption in laboratory cultivation and increase mycelia yield that meets SDGs 7 and 12, hitting a new milestone for biomass production.

Kow Pu-Yun, Lu Mei-Kuang, Lee Meng-Hsin, Lu Wei-Bin, Chang Fi-John

2022-Nov-29

Adaptive Neuro-Fuzzy Inference System (ANFIS), Antrodia cinnamomea, Artificial Neural Network (ANN), Biomass, Response Surface Methodology (RSM)

General General

Gene nceA encodes a Ni/Co-sensing transcription factor to regulate metal efflux in Corynebacterium glutamicum.

In Metallomics : integrated biometal science

The function of Corynebacterium glutamicum ORF NCgl2684 (named nceA in this study), which was annotated to encode a metalloregulator, was assessed using physiological, genetic, and biochemical approaches. Cells with deleted-nceA (ΔnceA) showed a resistant phenotype to NiSO4 and CoSO4 and showed faster growth in minimal medium containing 20 μM NiSO4 or 10 μM CoSO4 than both the wild-type and nceA-overexpressing (P180-nceA) cells. In the ΔnceA strain, the transcription of the downstream-located ORF NCgl2685 (nceB), annotated to encode efflux protein, was increased approximately four-fold, whereas gene transcription decreased down to 30% level in the P180-nceA strain. The transcription of the nceA and nceB genes were stimulated, even when as little as 5 nM NiSO4 was added to the growth medium. Protein NceA was able to bind DNA comprising the promoter region (from -14 to + 18) of the nceA-nceB operon. The protein-DNA interaction was abolished in the presence of 20 μM NiSO4, 50 μM CoSO4, or 50 μM CdSO4. Although manganese induced the transcription of the nceA and nceB genes, it failed to interrupt protein-DNA interaction. Simultaneously, the P180-nceA cells showed increased sensitivity to oxidants such as menadione, hydrogen peroxide, and cumene hydroperoxide, but not diamide. Collectively, our data show that NceA is a nickel- and cobalt-sensing transcriptional regulator that controls the transcription of the probable efflux protein-encoding nceB. The genes are able to suppress intracellular levels of nickel to prevent reactions, which can cause oxidative damage to cellular components.

Choi Won-Woo, Jeong Haeri, Kim Younhee, Lee Heung-Shick

2022-Dec-02

\n Corynebacterium glutamicum, cobalt, efflux, nickel, transcriptional regulator

General General

A Bibliometric and Visualized Analysis of Liver Fibrosis From 2002 to 2022.

In Journal of gastroenterology and hepatology ; h5-index 51.0

Fibrosis of the liver is a degenerative alteration that occurs in the majority of chronic liver disorders. Further progression can lead to cirrhosis, liver failure, and hepatocellular carcinoma, which can seriously affect the health and lives of patients. The field of liver fibrosis research has flourished in the last 20 years, with approximately 9,000 articles retrieved from the Web of Science Core Collection database alone. In order to identify future research hotspots and potential paths in a thorough and scientifically reliable manner, it is important to organize and visualize the research on this topic from a holistic and very general perspective. This study used bibliometric analysis with CiteSpace and VOSviewer software to provide a quantitative analysis, hotspot mining, and commentary of articles published in the field of liver fibrosis over the last 20 years. This bibliometric analysis contains a total of 8,994 articles with 45,667 authors from 6,872 institutions in 97 countries, published in 1,371 journals and citing 156,309 references. The literature volume has steadily increased over the last 20 years. Research has focused on gastroenterology & hepatology, pharmacology & pharmacy, and medicine, research & experimental areas. We found that the pathological mechanisms, diagnostic and quantitative methods, etiology, and anti-fibrotic strategies constitute the knowledge structure of liver fibrosis. Finding mechanisms for liver fibrosis regression, identifying precise non-invasive diagnostic and prognostic biomarkers, and creating efficient liver fibrosis patient treatments are the main goals of current research.

Zhao Qianqian, Liang Luhua, Zhai Fei, Ling Guixia, Xiang Rongwu, Jiang Xiwei

2022-Dec-02

Bibliometrics, CiteSpace, Liver fibrosis, VOSviwer

Radiology Radiology

CT radiomics for differentiating oncocytoma from renal cell carcinomas: Systematic review and meta-analysis.

In Clinical imaging

BACKGROUND : Radiomics is a type of quantitative analysis that provides a more objective approach to detecting tumor subtypes using medical imaging. The goal of this paper is to conduct a comprehensive assessment of the literature on computed tomography (CT) radiomics for distinguishing renal cell carcinomas (RCCs) from oncocytoma.

METHODS : From February 15th 2012 to 2022, we conducted a broad search of the current literature using the PubMed/MEDLINE, Google scholar, Cochrane Library, Embase, and Web of Science. A meta-analysis of radiomics studies concentrating on discriminating between oncocytoma and RCCs was performed, and the risk of bias was assessed using the Quality Assessment of Diagnostic Accuracy Studies method. The pooled sensitivity, specificity, and diagnostic odds ratio were evaluated via a random-effects model, which was applied for the meta-analysis. This study is registered with PROSPERO (CRD42022311575).

RESULTS : After screening the search results, we identified 6 studies that utilized radiomics to distinguish oncocytoma from other renal tumors; there were a total of 1064 lesions in 1049 patients (288 oncocytoma lesions vs 776 RCCs lesions). The meta-analysis found substantial heterogeneity among the included studies, with pooled sensitivity and specificity of 0.818 [0.619-0.926] and 0.808 [0.537-0.938], for detecting different subtypes of RCCs (clear cell RCC, chromophobe RCC, and papillary RCC) from oncocytoma. Also, a pooled sensitivity and specificity of 0.83 [0.498-0.960] and 0.92 [0.825-0.965], respectively, was found in detecting oncocytoma from chromophobe RCC specifically.

CONCLUSIONS : According to this study, CT radiomics has a high degree of accuracy in distinguishing RCCs from RO, including chromophobe RCCs from RO. Radiomics algorithms have the potential to improve diagnosis in scenarios that have traditionally been ambiguous. However, in order for this modality to be implemented in the clinical setting, standardization of image acquisition and segmentation protocols as well as inter-institutional sharing of software is warranted.

Dehghani Firouzabadi Fatemeh, Gopal Nikhil, Homayounieh Fatemeh, Anari Pouria Yazdian, Li Xiaobai, Ball Mark, Jones Elizabeth C, Samimi Safa, Turkbey Evrim, Malayeri Ashkan A

2022-Nov-17

Chromophobe RCC, Clear cell RCC, Machine learning, Oncocytoma, Papillary RCC, Renal cell carcinoma, Systematic review

General General

A novel approach for estimating and predicting uncertainty in water quality index model using machine learning approaches.

In Water research

With the significant increase in WQI applications worldwide and lack of specific application guidelines, accuracy and reliability of WQI models is a major issue. It has been reported that WQI models produce significant uncertainties during the various stages of their application including: (i) water quality indicator selection, (ii) sub-index (SI) calculation, (iii) water quality indicator weighting and (iv) aggregation of sub-indices to calculate the overall index. This research provides a robust statistically sound methodology for assessment of WQI model uncertainties. Eight WQI models are considered. The Monte Carlo simulation (MCS) technique was applied to estimate model uncertainty, while the Gaussian Process Regression (GPR) algorithm was utilised to predict uncertainties in the WQI models at each sampling site. The sub-index functions were found to contribute to considerable uncertainty and hence affect the model reliability - they contributed 12.86% and 10.27% of uncertainty for summer and winter applications, respectively. Therefore, the selection of sub-index function needs to be made with care. A low uncertainty of less than 1% was produced by the water quality indicator selection and weighting processes. Significant statistical differences were found between various aggregation functions. The weighted quadratic mean (WQM) function was found to provide a plausible assessment of water quality of coastal waters at reduced uncertainty levels. The findings of this study also suggest that the unweighted root means squared (RMS) aggregation function could be potentially also used for assessment of coastal water quality. Findings from this research could inform a range of stakeholders including decision-makers, researchers, and agencies responsible for water quality monitoring, assessment and management.

Uddin Md Galal, Nash Stephen, Rahman Azizur, Olbert Agnieszka I

2022-Nov-25

Cork harbour, Gaussian processes regression, Monte Carlo simulation, Uncertainty, Water quality index

General General

Continual learning with attentive recurrent neural networks for temporal data classification.

In Neural networks : the official journal of the International Neural Network Society

Continual learning is an emerging research branch of deep learning, which aims to learn a model for a series of tasks continually without forgetting knowledge obtained from previous tasks. Despite receiving a lot of attention in the research community, temporal-based continual learning techniques are still underutilized. In this paper, we address the problem of temporal-based continual learning by allowing a model to continuously learn on temporal data. To solve the catastrophic forgetting problem of learning temporal data in task incremental scenarios, in this research, we propose a novel method based on attentive recurrent neural networks, called Temporal Teacher Distillation (TTD). TTD solves the catastrophic forgetting problem in an attentive recurrent neural network based on three hypotheses, namely Rotation Hypothesis, Redundant Hypothesis, and Recover Hypothesis. Rotation Hypothesis and Redundant hypotheses could cause the attention shift phenomenon, which degrades the model performance on the learned tasks. Moreover, not considering the Recover Hypothesis increases extra memory usage in continuously training different tasks. Therefore, the proposed TTD based on the above hypotheses complements the inadequacy of the existing methods for temporal-based continual learning. For evaluating the performance of our proposed method in task incremental setting, we use a public dataset, WIreless Sensor Data Mining (WISDM), and a synthetic dataset, Split-QuickDraw-100. According to experimental results, the proposed TTD significantly outperforms state-of-the-art methods by up to 14.6% and 45.1% in terms of accuracy and forgetting measures, respectively. To the best of our knowledge, this is the first work that studies continual learning in real-world incremental categories for temporal data classification with attentive recurrent neural networks and provides the proper application-oriented scenario.

Yin Shao-Yu, Huang Yu, Chang Tien-Yu, Chang Shih-Fang, Tseng Vincent S

2022-Nov-11

Continual learning, Deep learning, Recurrent neural networks, Temporal data classification

Surgery Surgery

Setting up of a machine learning algorithm for the identification of severe liver fibrosis profile in the general US population cohort.

In International journal of medical informatics ; h5-index 49.0

BACKGROUND : The progress of digital transformation in clinical practice opens the door to transforming the current clinical line for liver disease diagnosis from a late-stage diagnosis approach to an early-stage based one. Early diagnosis of liver fibrosis can prevent the progression of the disease and decrease liver-related morbidity and mortality. We developed here a machine learning (ML) algorithm containing standard parameters that can identify liver fibrosis in the general US population.

MATERIALS AND METHODS : Starting from a public database (National Health and Nutrition Examination Survey, NHANES), representative of the American population with 7265 eligible subjects (control population n = 6828, with Fibroscan values E < 9.7 KPa; target population n = 437 with Fibroscan values E ≥ 9.7 KPa), we set up an SVM algorithm able to discriminate for individuals with liver fibrosis among the general US population. The algorithm set up involved the removal of missing data and a sampling optimization step to managing the data imbalance (only ∼ 5 % of the dataset is the target population).

RESULTS : For the feature selection, we performed an unbiased analysis, starting from 33 clinical, anthropometric, and biochemical parameters regardless of their previous application as biomarkers of liver diseases. Through PCA analysis, we identified the 26 more significant features and then used them to set up a sampling method on an SVM algorithm. The best sampling technique to manage the data imbalance was found to be oversampling through the SMOTE-NC. For final model validation, we utilized a subset of 300 individuals (150 with liver fibrosis and 150 controls), subtracted from the main dataset prior to sampling. Performances were evaluated on multiple independent runs.

CONCLUSIONS : We provide proof of concept of an ML clinical decision support tool for liver fibrosis diagnosis in the general US population. Though the presented ML model represents at this stage only a prototype, in the future, it might be implemented and potentially applied to program broad screenings for liver fibrosis.

Hassoun Samir, Bruckmann Chiara, Ciardullo Stefano, Perseghin Gianluca, Di Gaudio Francesca, Broccolo Francesco

2022-Nov-25

Imbalanced dataset, Liver fibrosis, Machine learning, NHANES, Oversampling techniques

Public Health Public Health

External validation of prediction models for patient-reported outcome measurements collected using the selfBACK mobile app.

In International journal of medical informatics ; h5-index 49.0

BACKGROUND : External validation is essential in examining the disparities in the training and validation cohorts during the development of prediction models, especially when the application domain is healthcare-oriented. Currently, the use of prediction models in healthcare research aimed at utilising the under-explored potential of patient-reported outcome measurements (PROMs) is limited, and few are validated using external datasets.

OBJECTIVE : To validate the machine learning prediction models developed in our previous work [29] for predicting four pain-related patient-reported outcomes from the selfBACK clinical trial datasets.

METHODS : We evaluate the validity of three pre-trained prediction models based on three methods- Case-Based Reasoning, Support Vector Regression, and XGBoost Regression-using an external dataset that contains PROMs collected from patients with non-specific neck and or low back pain using the selfBACK mobile application.

RESULTS : Overall, the predictive power was low, except for prediction of one of the outcomes. The results indicate that while the predictions are far from immaculate in either case, the models show ability to generalise and predict outcomes for a new dataset.

CONCLUSION : External validation of the prediction models presents modest results and highlights the individual differences and need for external validation of prediction models in clinical settings. There is need for further development in this area of machine learning application and patient-centred care.

Verma Deepika, Bach Kerstin, Mork Paul Jarle

2022-Nov-26

Case-based reasoning, Low-back pain, Machine learning, Neck pain, Outcome prediction, Patient-reported outcome measurements, Self-reported measures

Internal Medicine Internal Medicine

Vascular age acquired from the pulse signal: A new index to screen early vascular aging.

In Computers in biology and medicine

BACKGROUND : Chronological age (CA) has been adopted as an important independent risk factor in cardiovascular risk assessment. However, different individuals with same CA may have distinct actual vascular aging due to various lifestyles. Therefore, it is difficult to fully describe the difference of actual vascular aging by CA.

OBJECTIVE : This study proposes a new index vascular age (VA) to avoid the limitations of CA.

METHOD : In this work, VA refers to the sum of CA and lifestyle impact (AgeLI). Firstly, we take the pulse signal features and CA as independent variables and dependent variable respectively, and adopt cross validation to train Support Vector Regression model. Then we acquire the predicted chronological age (PA) of all subjects with the model. Secondly, we obtain the function model between CA and PA, and calculate the expectation of PA (ePA) for each subject. Simultaneously, we take the difference between PA and ePA as the estimated value of AgeLI to further calculate VA. Finally, in order to evaluate the effectiveness of VA, we compare the correlations between CA, PA, VA and 8 objective indices such as augmentation index, pulse transit time, diastolic augmentation index, etc. RESULTS: In general, VA and PA are closer to these 8 objective indices than CA. Moreover, VA is also superior to PA in vascular aging evaluation.

CONCLUSION : The VA suggested in this study emphasizes the difference of vascular aging in same CA group, which can better reflect the actual vascular aging than CA and PA.

Tang Qingfeng, Pan Zhiqiang, Tao Changlong, Jiang Jing, Su Benyue, An Hui, Liu Guodong

2022-Nov-26

Chronological age, Lifestyle impact, Pulse signal, Support vector regression, Vascular age

General General

From sMRI to task-fMRI: A unified geometric deep learning framework for cross-modal brain anatomo-functional mapping.

In Medical image analysis

Achieving predictions of brain functional activation patterns/task-fMRI maps from its underlying anatomy is an important yet challenging problem. Once successful, it will not only open up new ways to understand how brain anatomy influences functional organization of the brain, but also provide new technical support for the clinical use of anatomical information to guide the localization of cortical functional areas. However, due to the non-Euclidean complex architecture of brain anatomy and the inherent low signal-to-noise ratio (SNR) properties of fMRI signals, the key challenge in building such a cross-modal brain anatomo-functional mapping is how to effectively learn the context-aware information of brain anatomy and overcome the interference of noise-containing task-fMRI labels on the learning process. In this work, we propose a Unified Geometric Deep Learning framework (BrainUGDL) to perform the cross-modal brain anatomo-functional mapping task. Considering that both global and local structures of brain anatomy have an impact on brain functions from their respective perspectives, we innovatively propose the novel Global Graph Encoding (GGE) unit and Local Graph Attention (LGA) unit embedded into two parallel branches, focusing on learning the high-level global and local context information, respectively. Specifically, GGE learns the global context information of each mesh vertex by building and encoding global interactions, and LGA learns the local context information of each mesh vertex by selectively aggregating patch structure enhanced features from its spatial neighbors. The information learnt from the two branches is then fused to form a comprehensive representation of brain anatomical features for final brain function predictions. To address the inevitable measurement noise in task-fMRI labels, we further elaborate a novel uncertainty-filtered learning mechanism, which enables BrainUGDL to realize revised learning from the noise-containing labels through the estimated uncertainty. Experiments across seven open task-fMRI datasets from human connectome project (HCP) demonstrate the superiority of BrainUGDL. To our best knowledge, our proposed BrainUGDL is the first to achieve the prediction of individual task-fMRI maps solely based on brain sMRI data.

Zhu Zhiyuan, Huang Taicheng, Zhen Zonglei, Wang Boyu, Wu Xia, Li Shuo

2022-Nov-07

Brain anatomo-functional mapping, Geometric deep learning, Task-fMRI, sMRI

General General

Attitudes toward dementia screening and influential factors in older adults in China.

In Psychogeriatrics : the official journal of the Japanese Psychogeriatric Society

BACKGROUND : Dementia will likely be an ongoing concern for future generations, and according to the World Health Organization, two-thirds of dementia cases are missed diagnoses. We aimed to explore the attitudes of older adults toward dementia screening and the related influencing factors.

METHODS : A multicentre cross-sectional study was conducted. Data were collected using questionnaires between 2020 December and 2021 June from five provinces in China. The study included older adults aged 60 years or older, living in China. A sociodemographic questionnaire and the Perceptions Regarding Investigational Screening for Memory in Primary Care scale were used to assess attitudes toward and influencing factors of dementia screening.

RESULTS : A total of 279 participants completed the questionnaires. The results revealed housing status as a positive factor in the acceptance dimension, while high income was the primary positive factor in the benefits of screening dimension. Having religious beliefs, low income, and never participating in social activities were positive factors for the stigma dimension. Widowed marital status and participation in social activities were negative factors for the independence dimension, while having religious beliefs positively influenced the suffering dimension.

CONCLUSIONS : This study showed that participants held a relatively positive attitude toward dementia screening, although they had concerns about stigma and negative impact on independence. Further studies are required to develop intervention strategies to help older adults improve their attitudes and quality of life, promote cognitive health, and facilitate healthy ageing.

Xue Bing, Luo Chang, Luo Xianwu

2022-Dec-01

attitudes, cross-sectional, dementia screening, multicentre, older adults

Ophthalmology Ophthalmology

Transforming ophthalmology in the digital century-new care models with added value for patients.

In Eye (London, England) ; h5-index 41.0

Ophthalmology faces many challenges in providing effective and meaningful eye care to an ever-increasing group of people. Even health systems that have so far been able to cope with the quantitative patient increase, due to their funding and the availability of highly qualified professionals, and improvements in practice routine efficiency, will be pushed to their limits. Further pressure on care will also be caused by new active substances for the largest group of patients with AMD, the so-called dry form. Treatment availability for this so far untreated group will increase the volume of patients 2-3 times. Without the adaptation of the care structures, this quantitative and qualitative expansion in therapy will inevitably lead to an undersupply.There is increasing scientific evidence that significant efficiency gains in the care of chronic diseases can be achieved through better networking of stakeholders in the healthcare system and greater patient involvement. Digitalization can make an important contribution here. Many technological solutions have been developed in recent years and the time is now ready to exploit this potential. The exceptional setting during the SARS-CoV-2 pandemic has shown many that new technology is available safely, quickly, and effectively. The emergency has catalyzed innovation processes and shown for post-pandemic time after that we are equipped to tackle the challenges in ophthalmic healthcare - ultimately for the benefit of patients and society.

Faes Livia, Maloca Peter M, Hatz Katja, Wolfensberger Thomas J, Munk Marion R, Sim Dawn A, Bachmann Lucas M, Schmid Martin K

2022-Dec-03

General General

An interpretable machine learning approach based on DNN, SVR, Extra Tree, and XGBoost models for predicting daily pan evaporation.

In Journal of environmental management

Evaporation is an important hydrological process in the water cycle, especially for water bodies. Machine Learning (ML) models have become accurate and powerful tools in predicting pan evaporation. Meanwhile, the "black-box" character and the consistency with the physical process can decrease the practical implication of ML models. To overcome such limitations, we attempt to develop an interpretable based-ML framework to predict daily pan evaporation using Extra Tree, XGBoost, SVR, and Deep Neural Network (DNN) ML models using hourly climate datasets. To that end, we integrated and employed the Shapely Additive explanations (SHAP), Sobol-based sensitivity analysis, and Local Interpretable Model-agnostic Explanations (LIME) to evaluate the interpretability of the models in predicting daily pan evaporation, at Sidi Mohammed Ben Abdellah (SMBA) weather station, in Morocco. The validation results of the models showed that the developed models are accurate in reproducing the daily pan evaporation with NSE ranging from 0.76 to 0.83 during the validation phase. Furthermore, the interpretability results of the ML models showed that the air temperature (Ta), solar radiation (Rs), followed by relative humidity (H) are the most important climate variables with inflection points of the Ta_median, Ta_mean, Rs_sum, H_mean, and w_std are 17.42 °C, 17.65 °C, 3.8 kw.m-2, 69.59%, and 1.25 m s-1, sequentially. Overall, the interpretability of the models showed a good consistency of the ML models with the real hydro-climatic process of evaporation in a semi-arid environment. Hence, the proposed methodology is powerful in enhancing the reliability and transparency of the developed models for predicting daily pan evaporation. Finally, the proposed approach is new insights to reduce the ''Black-Box'' character of ML models in hydrological studies.

El Bilali Ali, Abdeslam Taleb, Ayoub Nafii, Lamane Houda, Ezzaouini Mohamed Abdellah, Elbeltagi Ahmed

2022-Nov-29

Climate variables, Interpretable machine learning, LIME, SHAP, Sobol index

General General

Age-related brain atrophy is not a homogenous process: Different functional brain networks associate differentially with aging and blood factors.

In Proceedings of the National Academy of Sciences of the United States of America

Aging is characterized by a progressive loss of brain volume at an estimated rate of 5% per decade after age 40. While these morphometric changes, especially those affecting gray matter and atrophy of the temporal lobe, are predictors of cognitive performance, the strong association with aging obscures the potential parallel, but more specific role, of individual subject physiology. Here, we studied a cohort of 554 human subjects who were monitored using structural MRI scans and blood immune protein concentrations. Using machine learning, we derived a cytokine clock (CyClo), which predicted age with good accuracy (Mean Absolute Error = 6 y) based on the expression of a subset of immune proteins. These proteins included, among others, Placenta Growth Factor (PLGF) and Vascular Endothelial Growth Factor (VEGF), both involved in angiogenesis, the chemoattractant vascular cell adhesion molecule 1 (VCAM-1), the canonical inflammatory proteins interleukin-6 (IL-6) and tumor necrosis factor alpha (TNFα), the chemoattractant IP-10 (CXCL10), and eotaxin-1 (CCL11), previously involved in brain disorders. Age, sex, and the CyClo were independently associated with different functionally defined cortical networks in the brain. While age was mostly correlated with changes in the somatomotor system, sex was associated with variability in the frontoparietal, ventral attention, and visual networks. Significant canonical correlation was observed for the CyClo and the default mode, limbic, and dorsal attention networks, indicating that immune circulating proteins preferentially affect brain processes such as focused attention, emotion, memory, response to social stress, internal evaluation, and access to consciousness. Thus, we identified immune biomarkers of brain aging which could be potential therapeutic targets for the prevention of age-related cognitive decline.

Markov Nikola T, Lindbergh Cutter A, Staffaroni Adam M, Perez Kevin, Stevens Michael, Nguyen Khiem, Murad Natalia F, Fonseca Corrina, Campisi Judith, Kramer Joel, Furman David

2022-Dec-06

aging, brain aging, cytokine clock, cytokines, gray matter volume

General General

A Review of Emerging Electromagnetic-Acoustic Sensing Techniques for Healthcare Monitoring.

In IEEE transactions on biomedical circuits and systems ; h5-index 39.0

Conventional electromagnetic (EM) sensing techniques such as radar and LiDAR are widely used for remote sensing, vehicle applications, weather monitoring, and clinical monitoring. Acoustic techniques such as sonar and ultrasound sensors are also used for consumer applications, such as ranging and in vivo medical/healthcare applications. It has been of long-term interest to doctors and clinical practitioners to realize continuous healthcare monitoring in hospitals and/or homes. Physiological and biopotential signals in real-time serve as important health indicators to predict and prevent serious illness. Emerging electromagnetic-acoustic (EMA) sensing techniques synergistically combine the merits of EM sensing with acoustic imaging to achieve comprehensive detection of physiological and biopotential signals. Further, EMA enables complementary fusion sensing for challenging healthcare settings, such as real-world long-term monitoring of treatment effects at home or in remote environments. This article reviews various examples of EMA sensing instruments, including implementation, performance, and application from the perspectives of circuits to systems. The novel and significant applications to healthcare are discussed. Three types of EMA sensors are presented: (1) Chip-based radar sensors for health status monitoring, (2) Thermo-acoustic sensing instruments for biomedical applications, and (3) Photoacoustic (PA) sensing and imaging systems, including dedicated reconstruction algorithms were reviewed from time-domain, frequency-domain, time-reversal, and model-based solutions. The future of EMA techniques for continuous healthcare with enhanced accuracy supported by artificial intelligence (AI) is also presented.

Fang Zhongyuan, Gao Fei, Jin Haoran, Liu Siyu, Wang Wensong, Zhang Ruochong, Zheng Zesheng, Xiao Xuan, Tang Kai, Lou Liheng, Tang Kea-Tiong, Chen Jie, Zheng Yuanjin

2022-Dec-02

General General

Segmentation-free PVC for Cardiac SPECT using a Densely-connected Multi-dimensional Dynamic Network.

In IEEE transactions on medical imaging ; h5-index 74.0

In nuclear imaging, limited resolution causes partial volume effects (PVEs) that affect image sharpness and quantitative accuracy. Partial volume correction (PVC) methods incorporating high-resolution anatomical information from CT or MRI have been demonstrated to be effective. However, such anatomical-guided methods typically require tedious image registration and segmentation steps. Accurately segmented organ templates are also hard to obtain, particularly in cardiac SPECT imaging, due to the lack of hybrid SPECT/CT scanners with high-end CT and associated motion artifacts. Slight mis-registration/missegmentation would result in severe degradation in image quality after PVC. In this work, we develop a deep-learning-based method for fast cardiac SPECT PVC without anatomical information and associated organ segmentation. The proposed network involves a densely-connected multi-dimensional dynamic mechanism, allowing the convolutional kernels to be adapted based on the input images, even after the network is fully trained. Intramyocardial blood volume (IMBV) is introduced as an additional clinical-relevant loss function for network optimization. The proposed network demonstrated promising performance on 28 canine studies acquired on a GE Discovery NM/CT 570c dedicated cardiac SPECT scanner with a 64-slice CT using Technetium-99m-labeled red blood cells. This work showed that the proposed network with densely-connected dynamic mechanism produced superior results compared with the same network without such mechanism. Results also showed that the proposed network without anatomical information could produce images with statistically comparable IMBV measurements to the images generated by anatomical-guided PVC methods, which could be helpful in clinical translation.

Xie Huidong, Liu Zhao, Shi Luyao, Greco Kathleen, Chen Xiongchao, Zhou Bo, Feher Attila, Stendahl John C, Boutagy Nabil, Kyriakides Tassos C, Wang Ge, Sinusas Albert J, Liu Chi

2022-Dec-02

Pathology Pathology

Computer Vision Based on a Modular Neural Network for Automatic Assessment of Physical Therapy Rehabilitation Activities.

In IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society

Physical rehabilitation techniques during the treatment of clinical pathology are one of the most challenging areas for the medical structure, patients, and families. In large and continental countries, remote monitoring of this treatment is essential. However, equipment and medical follow-up during exercises still have high costs. With the improvement of computer vision and machine learning techniques, some computational, less expensive alternatives have been proposed in the literature. However, monitoring patients during physical rehabilitation exercises with the help of artificial intelligence by a health professional, especially from the capture of visual signals, is still a challenge and poorly explored in the scientific-technological literature. This work aims to propose a new methodology based on computer vision and machine learning for remote tracking of the body joints of patients during physiotherapy rehabilitation exercises. As a new contribution, this work presents a modular neural network architecture composed of two modules: one for detecting physical exercises and another for measuring how much is correct. Another contribution is a strategy for expanding databases, considering that generic databases for this type of exercise are rare on the internet. The results showed that both modules obtained more than 90% of accuracy in recognition and their respective validation.

Francisco Joao A, Rodrigues Paulo Sergio

2022-Dec-02

General General

Super-resolution image display using diffractive decoders.

In Science advances

High-resolution image projection over a large field of view (FOV) is hindered by the restricted space-bandwidth product (SBP) of wavefront modulators. We report a deep learning-enabled diffractive display based on a jointly trained pair of an electronic encoder and a diffractive decoder to synthesize/project super-resolved images using low-resolution wavefront modulators. The digital encoder rapidly preprocesses the high-resolution images so that their spatial information is encoded into low-resolution patterns, projected via a low SBP wavefront modulator. The diffractive decoder processes these low-resolution patterns using transmissive layers structured using deep learning to all-optically synthesize/project super-resolved images at its output FOV. This diffractive image display can achieve a super-resolution factor of ~4, increasing the SBP by ~16-fold. We experimentally validate its success using 3D-printed diffractive decoders that operate at the terahertz spectrum. This diffractive image decoder can be scaled to operate at visible wavelengths and used to design large SBP displays that are compact, low power, and computationally efficient.

Işıl Çağatay, Mengu Deniz, Zhao Yifan, Tabassum Anika, Li Jingxi, Luo Yi, Jarrahi Mona, Ozcan Aydogan

2022-Dec-02

General General

Public Trust in Artificial Intelligence Applications in Mental Health Care: Topic Modeling Analysis.

In JMIR human factors

BACKGROUND : Mental disorders (MDs) impose heavy burdens on health care (HC) systems and affect a growing number of people worldwide. The use of mobile health (mHealth) apps empowered by artificial intelligence (AI) is increasingly being resorted to as a possible solution.

OBJECTIVE : This study adopted a topic modeling (TM) approach to investigate the public trust in AI apps in mental health care (MHC) by identifying the dominant topics and themes in user reviews of the 8 most relevant mental health (MH) apps with the largest numbers of reviewers.

METHODS : We searched Google Play for the top MH apps with the largest numbers of reviewers, from which we selected the most relevant apps. Subsequently, we extracted data from user reviews posted from January 1, 2020, to April 2, 2022. After cleaning the extracted data using the Python text processing tool spaCy, we ascertained the optimal number of topics, drawing on the coherence scores and used latent Dirichlet allocation (LDA) TM to generate the most salient topics and related terms. We then classified the ascertained topics into different theme categories by plotting them onto a 2D plane via multidimensional scaling using the pyLDAvis visualization tool. Finally, we analyzed these topics and themes qualitatively to better understand the status of public trust in AI apps in MHC.

RESULTS : From the top 20 MH apps with the largest numbers of reviewers retrieved, we chose the 8 (40%) most relevant apps: (1) Wysa: Anxiety Therapy Chatbot; (2) Youper Therapy; (3) MindDoc: Your Companion; (4) TalkLife for Anxiety, Depression & Stress; (5) 7 Cups: Online Therapy for Mental Health & Anxiety; (6) BetterHelp-Therapy; (7) Sanvello; and (8) InnerHour. These apps provided 14.2% (n=559), 11.0% (n=431), 13.7% (n=538), 8.8% (n=356), 14.1% (n=554), 11.9% (n=468), 9.2% (n=362), and 16.9% (n=663) of the collected 3931 reviews, respectively. The 4 dominant topics were topic 4 (cheering people up; n=1069, 27%), topic 3 (calming people down; n=1029, 26%), topic 2 (helping figure out the inner world; n=963, 25%), and topic 1 (being an alternative or complement to a therapist; n=870, 22%). Based on topic coherence and intertopic distance, topics 3 and 4 were combined into theme 3 (dispelling negative emotions), while topics 2 and 1 remained 2 separate themes: theme 2 (helping figure out the inner world) and theme 1 (being an alternative or complement to a therapist), respectively. These themes and topics, though involving some dissenting voices, reflected an overall high status of trust in AI apps.

CONCLUSIONS : This is the first study to investigate the public trust in AI apps in MHC from the perspective of user reviews using the TM technique. The automatic text analysis and complementary manual interpretation of the collected data allowed us to discover the dominant topics hidden in a data set and categorize these topics into different themes to reveal an overall high degree of public trust. The dissenting voices from users, though only a few, can serve as indicators for health providers and app developers to jointly improve these apps, which will ultimately facilitate the treatment of prevalent MDs and alleviate the overburdened HC systems worldwide.

Shan Yi, Ji Meng, Xie Wenxiu, Lam Kam-Yiu, Chow Chi-Yin

2022-Dec-02

AI application, Google Play, artificial intelligence, digital health, eHealth, health app: mHealth, mental disorder, mental health, mental health care, mental illness, mobile health, public opinion, public trust, term, theme, topic, topic modeling, user feedback, user review, visualization

Public Health Public Health

Risks, Epidemics, and Prevention Measures of Infectious Diseases in Major Sports Events: Scoping Review.

In JMIR public health and surveillance

BACKGROUND : Major sports events are the focus of the world. However, the gathering of crowds during these events creates huge risks of infectious diseases transmission, posing a significant public health threat.

OBJECTIVE : The aim of this study was to systematically review the epidemiological characteristics and prevention measures of infectious diseases at major sports events.

METHODS : The procedure of this scoping review followed Arksey and O'Malley's five-step methodological framework. Electronic databases, including PubMed, Web of Science, Scopus, and Embase, were searched systematically. The general information (ie, publication year, study type) of each study, sports events' features (ie, date and host location), infectious diseases' epidemiological characteristics (ie, epidemics, risk factors), prevention measures, and surveillance paradigm were extracted, categorized, and summarized.

RESULTS : A total of 24,460 articles were retrieved from the databases and 358 studies were included in the final data synthesis based on selection criteria. A rapid growth of studies was found over recent years. The number of studies investigating epidemics and risk factors for sports events increased from 16/254 (6.3%) before 2000 to 201/254 (79.1%) after 2010. Studies focusing on prevention measures of infectious diseases accounted for 85.0% (238/280) of the articles published after 2010. A variety of infectious diseases have been reported, including respiratory tract infection, gastrointestinal infection, vector-borne infection, blood-borne infection, and water-contact infection. Among them, respiratory tract infections were the most concerning diseases (250/358, 69.8%). Besides some routine prevention measures targeted at risk factors of different diseases, strengthening surveillance was highlighted in the literature. The surveillance system appeared to have gone through three stages of development, including manual archiving, network-based systems, and automated intelligent platforms.

CONCLUSIONS : This critical summary and collation of previous empirical evidence is meaningful to provide references for holding major sports events. It is essential to improve the surveillance techniques for timely detection of the emergence of epidemics and to improve risk perception in future practice.

Yan Xiangyu, Fang Yian, Li Yongjie, Jia Zhongwei, Zhang Bo

2022-Dec-02

epidemic, major sports event, prevention, risk factor, scoping review, surveillance

Public Health Public Health

Prediction of elevated groundwater fluoride across India using multi-model approach: insights on the influence of geologic and environmental factors.

In Environmental science and pollution research international

Elevated fluoride in groundwater is a severe problem in India due to its extensive occurrence and detrimental health impacts on the large population that thrives on groundwater. Although fluoride is primarily a geogenic pollutant, existing model-based studies lack the amalgamation of the influence of geologic factors, specifically tectonics, for identifying groundwater fluoride distribution. This drawback encourages the present study to investigate the association of the tectonic framework with fluoride in a multi-model approach. We have applied three machine learning models (random forest, boosted regression tree, and logistic regression) to predict elevated groundwater fluoride based on fluoride measurements across India. The random forest model outperformed other models with an accuracy of 93%. Tectonics was found to be one of the most important predictors alongside "depth to water table." Two major areas of high risk identified were the northwest parts and the south-southeast cratonic peninsular region. The random forest model also performed significantly well over the validation dataset. We estimate that nearly 257 million people are exposed to elevated fluoride risk in India. We endeavor that the findings of our study would be an effective tool for identifying the areas at risk of elevated fluoride and also assist in undertaking effective groundwater management strategies.

Sarkar Soumyajit, Mukherjee Abhijit, Chakraborty Madhumita, Quamar Md Tahseen, Duttagupta Srimanti, Bhattacharya Animesh

2022-Dec-02

Fluoride, Groundwater contamination, Machine learning, Population, Exposure, Random forest, Tectonics

General General

Using artificial intelligence to improve pain assessment and pain management: a scoping review.

In Journal of the American Medical Informatics Association : JAMIA

CONTEXT : Over 20% of US adults report they experience pain on most days or every day. Uncontrolled pain has led to increased healthcare utilization, hospitalization, emergency visits, and financial burden. Recognizing, assessing, understanding, and treating pain using artificial intelligence (AI) approaches may improve patient outcomes and healthcare resource utilization. A comprehensive synthesis of the current use and outcomes of AI-based interventions focused on pain assessment and management will guide the development of future research.

OBJECTIVES : This review aims to investigate the state of the research on AI-based interventions designed to improve pain assessment and management for adult patients. We also ascertain the actual outcomes of Al-based interventions for adult patients.

METHODS : The electronic databases searched include Web of Science, CINAHL, PsycINFO, Cochrane CENTRAL, Scopus, IEEE Xplore, and ACM Digital Library. The search initially identified 6946 studies. After screening, 30 studies met the inclusion criteria. The Critical Appraisals Skills Programme was used to assess study quality.

RESULTS : This review provides evidence that machine learning, data mining, and natural language processing were used to improve efficient pain recognition and pain assessment, analyze self-reported pain data, predict pain, and help clinicians and patients to manage chronic pain more effectively.

CONCLUSIONS : Findings from this review suggest that using AI-based interventions has a positive effect on pain recognition, pain prediction, and pain self-management; however, most reports are only pilot studies. More pilot studies with physiological pain measures are required before these approaches are ready for large clinical trial.

Zhang Meina, Zhu Linzee, Lin Shih-Yin, Herr Keela, Chi Chih-Lin, Demir Ibrahim, Dunn Lopez Karen, Chi Nai-Ching

2022-Dec-02

artificial intelligence, pain, pain assessment, pain control, pain management

General General

Machine learning and experimental validation to construct a metastasis-related gene signature and ceRNA network for predicting osteosarcoma prognosis.

In Journal of orthopaedic surgery and research

OBJECTIVE : Osteosarcoma (OS) is more common in adolescents and significantly harmful, and the survival rate is considerably low, especially in patients with metastatic OS. The identification of effective biomarkers and associated regulatory mechanisms, which predict OS occurrence and development as well as improve prognostic accuracy, will help develop more refined protocols for OS treatment.

METHODS : In this study, genes showing differential expression in metastatic and non-metastatic types of OS were identified, and the ones affecting OS prognosis were screened from among these. Following this, the functions and pathways associated with the genes were explored via enrichment analysis, and an effective predictive signature was constructed using Cox regression based on the machine learning algorithm, least absolute shrinkage and selection operator (LASSO). Next, a correlative competing endogenous RNA (ceRNA) regulatory axis was constructed after verification by bioinformatics analysis and luciferase reporter gene experiments conducted based on the prognostic signature.

RESULTS : Overall, 251 differentially expressed genes were identified and screened using bioinformatics and double luciferase reporter gene experiments. An effective prognostic signature was constructed based on 15 genes associated with OS metastasis, and upstream non-coding RNAs were identified to construct the "NBR2/miR-129-5p/FKBP11" regulatory axis based on the ceRNA networks, which helped identify candidate biomarkers for the OS clinical diagnosis and treatment, drug research, and prognostic prediction, among other applications. The findings of this study provide a novel strategy for determining the mechanism underlying OS occurrence and development and the appropriate treatment.

Liao Yong, Liu Qingsong, Xiao Chunxia, Zhou Jihui

2022-Dec-01

Competing endogenous RNA network, Experimental validation of dual luciferase reporter gene, Machine learning, Metastasis-related gene signature, Osteosarcoma

Radiology Radiology

Classification and visual explanation for COVID-19 pneumonia from CT images using triple learning.

In Scientific reports ; h5-index 158.0

This study presents a novel framework for classifying and visualizing pneumonia induced by COVID-19 from CT images. Although many image classification methods using deep learning have been proposed, in the case of medical image fields, standard classification methods are unable to be used in some cases because the medical images that belong to the same category vary depending on the progression of the symptoms and the size of the inflamed area. In addition, it is essential that the models used be transparent and explainable, allowing health care providers to trust the models and avoid mistakes. In this study, we propose a classification method using contrastive learning and an attention mechanism. Contrastive learning is able to close the distance for images of the same category and generate a better feature space for classification. An attention mechanism is able to emphasize an important area in the image and visualize the location related to classification. Through experiments conducted on two-types of classification using a three-fold cross validation, we confirmed that the classification accuracy was significantly improved; in addition, a detailed visual explanation was achieved comparison with conventional methods.

Kato Sota, Oda Masahiro, Mori Kensaku, Shimizu Akinobu, Otake Yoshito, Hashimoto Masahiro, Akashi Toshiaki, Hotta Kazuhiro

2022-Dec-02

General General

DeepCellEss: Cell line-specific essential protein prediction with attention-based interpretable deep learning.

In Bioinformatics (Oxford, England)

MOTIVATION : Protein essentiality is usually accepted to be a conditional trait and strongly affected by cellular environments. However, existing computational methods often do not take such characteristics into account, preferring to incorporate all available data and train a general model for all cell lines. In addition, the lack of model interpretability limits further exploration and analysis of essential protein predictions.

RESULTS : In this study, we proposed DeepCellEss, a sequence-based interpretable deep learning framework for cell line-specific essential protein predictions. DeepCellEss utilizes convolutional neural network and bidirectional long short-term memory to learn short- and long-range latent information from protein sequences. Further, a multi-head self-attention mechanism is used to provide residue-level model interpretability. For model construction, we collected extremely large-scale benchmark datasets across 323 cell lines. Extensive computational experiments demonstrate that DeepCellEss yields effective prediction performance for different cell lines, and outperforms existing sequence-based methods as well as network-based centrality measures. Finally, we conducted some case studies to illustrate the necessity of considering specific cell lines and the superiority of DeepCellEss. We believe that DeepCellEss can serve as a useful tool for predicting essential proteins across different cell lines.

AVAILABILITY : The DeepCellEss web server is available at http://csuligroup.com:8000/DeepCellEss. The source code can be obtained from https://github.com/CSUBioGroup/DeepCellEss.

SUPPLEMENTARY INFORMATION : Supplementary data are available at Bioinformatics online.

Li Yiming, Zeng Min, Zhang Fuhao, Wu Fang-Xiang, Li Min

2022-Dec-02

General General

A faster way to model neuronal circuitry.

In eLife

Artificial neural networks could pave the way for efficiently simulating large-scale models of neuronal networks in the nervous system.

Davison Andrew P, Appukuttan Shailesh

2022-Dec-02

NMDA, artificial neural net, computational model, cortex, deep learning, neuroscience, none

General General

Development of In Silico Models for Predicting Potential Time-Dependent Inhibitors of Cytochrome P450 3A4.

In Molecular pharmaceutics ; h5-index 60.0

Cytochrome P450 3A4 (CYP3A4) is one of the major drug metabolizing enzymes in the human body and metabolizes ∼30-50% of clinically used drugs. Inhibition of CYP3A4 must always be considered in the development of new drugs. Time-dependent inhibition (TDI) is an important P450 inhibition type that could cause undesired drug-drug interactions. Therefore, identification of CYP3A4 TDI by a rapid convenient way is of great importance to any new drug discovery effort. Here, we report the development of in silico classification models for prediction of potential CYP3A4 time-dependent inhibitors. On the basis of the CYP3A4 TDI data set that we manually collected from literature and databases, both conventional machine learning and deep learning models were constructed. The comparisons of different sampling strategies, molecular representations, and machine-learning algorithms showed the benefits of a balanced data set and the deep-learning model featured by GraphConv. The generalization ability of the best model was tested by screening an external data set, and the prediction results were validated by biological experiments. In addition, several structural alerts that are relevant to CYP3A4 time-dependent inhibitors were identified via information gain and frequency analysis. We anticipate that our effort would be useful for identification of potential CYP3A4 time-dependent inhibitors in drug discovery and design.

Xu Minjie, Lu Zhou, Wu Zengrui, Gui Minyan, Liu Guixia, Tang Yun, Li Weihua

2022-Dec-02

CYP3A4, deep learning, in silico models, machine learning, time-dependent inhibitors

General General

Computer-aided classification of colorectal segments during colonoscopy: a deep learning approach based on images of a magnetic endoscopic positioning device.

In Scandinavian journal of gastroenterology

OBJECTIVE : Assessment of the anatomical colorectal segment of polyps during colonoscopy is important for treatment and follow-up strategies, but is largely operator dependent. This feasibility study aimed to assess whether, using images of a magnetic endoscope imaging (MEI) positioning device, a deep learning approach can be useful to objectively divide the colorectum into anatomical segments.

METHODS : Models based on the VGG-16 based convolutional neural network architecture were developed to classify the colorectum into anatomical segments. These models were pre-trained on ImageNet data and further trained using prospectively collected data of the POLAR study in which endoscopists were using MEI (3930 still images and 90,151 video frames). Five-fold cross validation with multiple runs was used to evaluate the overall diagnostic accuracies of the models for colorectal segment classification (divided into a 5-class and 2-class colorectal segment division). The colorectal segment assignment by endoscopists was used as the reference standard.

RESULTS : For the 5-class colorectal segment division, the best performing model correctly classified the colorectal segment in 753 of the 1196 polyps, corresponding to an overall accuracy of 63%, sensitivity of 63%, specificity of 89% and kappa of 0.47. For the 2-class colorectal segment division, 1112 of the 1196 polyps were correctly classified, corresponding to an accuracy of 93%, sensitivity of 93%, specificity of 90% and kappa of 0.82.

CONCLUSION : The diagnostic performance of a deep learning approach for colorectal segment classification based on images of a MEI device is yet suboptimal (clinicaltrials.gov: NCT03822390).

Houwen Britt B S L, Hartendorp Fons, Giotis Ioanis, Hazewinkel Yark, Fockens Paul, Walstra Taco R, Dekker Evelien

2022-Dec-02

Artificial intelligence, colonoscopy, colorectal cancer, colorectal polyps, optical diagnosis

General General

Neurosurgery inpatient outcome prediction for discharge planning with deep learning and transfer learning.

In British journal of neurosurgery ; h5-index 24.0

INTRODUCTION : Deep learning may be able to assist with the prediction of neurosurgical inpatient outcomes. The aims of this study were to investigate deep learning and transfer learning in the prediction of several inpatient outcomes including timing of discharge and discharge destination.

METHOD : Data were collected on consecutive neurosurgical admissions from existing databases over a 15-month period. Following pre-processing artificial neural networks were applied to admission notes and ward round notes to predict four inpatient outcomes. Models were developed on the training dataset, before being tested on a hold-out test dataset and a validation dataset.

RESULTS : 1341 individual admissions were included in the study. Using transfer learning and an artificial neural network an area under the receiver operator curve (AUC) of 0.81 and 0.80 on the derivation and validation datasets was able to be achieved for the prediction of discharge within the next 48 hours using daily ward round notes. This result is in comparison to an AUC of 0.71 and 0.68 using an artificial neural network without transfer learning for the same outcome. When the artificial neural network with transfer learning was applied to the other outcomes AUC of 0.72, 0.93 and 0.83 was achieved on the validation datasets for predicting discharge within the next 7 days, survival to discharge and discharge to home as a destination.

CONCLUSIONS : Deep learning may predict inpatient neurosurgery outcomes from free-text medical data. Recurrent predictions with ward round notes enable the use of information obtained throughout hospital admissions in these estimates.

Lam Lydia, Lam Antoinette, Bacchi Stephen, Abou-Hamden Amal

2022-Dec-02

Artificial intelligence, length of stay, machine learning, predictive analytics

General General

Using deep-learning predictions of inter-residue distances for model validation.

In Acta crystallographica. Section D, Structural biology

Determination of protein structures typically entails building a model that satisfies the collected experimental observations and its deposition in the Protein Data Bank. Experimental limitations can lead to unavoidable uncertainties during the process of model building, which result in the introduction of errors into the deposited model. Many metrics are available for model validation, but most are limited to consideration of the physico-chemical aspects of the model or its match to the experimental data. The latest advances in the field of deep learning have enabled the increasingly accurate prediction of inter-residue distances, an advance which has played a pivotal role in the recent improvements observed in the field of protein ab initio modelling. Here, new validation methods are presented based on the use of these precise inter-residue distance predictions, which are compared with the distances observed in the protein model. Sequence-register errors are particularly clearly detected and the register shifts required for their correction can be reliably determined. The method is available in the ConKit package (https://www.conkit.org).

Sánchez Rodríguez Filomeno, Chojnowski Grzegorz, Keegan Ronan M, Rigden Daniel J

2022-Dec-01

AlphaFold2, ConKit, conkit-validate, inter-residue distances, model validation

General General

Artificial intelligence facilitates measuring reflux episodes and postreflux swallow-induced peristaltic wave index from impedance-pH studies in patients with reflux disease.

In Neurogastroenterology and motility : the official journal of the European Gastrointestinal Motility Society

BACKGROUND/AIM : Reflux episodes and postreflux swallow-induced peristaltic wave (PSPW) index are useful impedance parameters that can augment the diagnosis of gastroesophageal reflux disease (GERD). However, manual analysis of pH-impedance tracings is time consuming, resulting in limited use of these novel impedance metrics. This study aims to evaluate whether a supervised learning artificial intelligence (AI) model is useful to identify reflux episodes and PSPW index.

METHODS : Consecutive patients underwent 24-h impedance-pH monitoring were enrolled for analysis. Multiple AI and machine learning with a deep residual net model for image recognition were explored based on manual interpretation of reflux episodes and PSPW according to criteria from the Wingate Consensus. Intraclass correlation coefficients (ICCs) were used to measure the strength of inter-rater agreement of data between manual and AI interpretations.

RESULTS : We analyzed 106 eligible patients with 7939 impedance events, of whom 38 patients with pathological acid exposure time (AET) and 68 patients with physiological AET. On the manual interpretation, patients with pathological AET had more reflux episodes and lower PSPW index than those with physiological AET. Overall accuracy of AI identification for reflux episodes and PSPW achieved 87% and 82%, respectively. Inter-rater agreements between AI and manual interpretations achieved excellent for individual numbers of reflux episodes and PSPW index (ICC = 0.965 and ICC = 0.921).

CONCLUSIONS : AI has the potential to accurately and efficiently measure impedance metrics including reflux episodes and PSPW index. AI can be a reliable adjunct for measuring novel impedance metrics for GERD in the near future.

Wong Ming-Wun, Liu Min-Xiang, Lei Wei-Yi, Liu Tso-Tsai, Yi Chih-Hsun, Hung Jui-Sheng, Liang Shu-Wei, Lin Lin, Tseng Chiu-Wang, Wang Jen-Hung, Wu Ping-An, Chen Chien-Lin

2022-Dec-02

artificial intelligence, gastroesophageal reflux disease, impedance-pH monitoring, postreflux swallow-induced peristaltic wave index, reflux episodes

oncology Oncology

Intraoperative Cytological Diagnosis of Brain Tumors: A Preliminary Study Using Deep Learning Model.

In Cytopathology : official journal of the British Society for Clinical Cytology

BACKGROUND : Intraoperative pathological diagnosis of central nervous system (CNS) tumors is essential in neuro-oncology to plan the patient management. Frozen section slides and cytological preparations provide architectural and cellular details analyzed by the pathologists to reach an intraoperative diagnosis. With the progress in artificial intelligence and machine learning fields, AI systems have significant potential in providing highly accurate real-time diagnosis in cytopathology.

OBJECTIVE : To investigate the efficiency of machine learning models in intraoperative cytological diagnosis of CNS tumors.

MATERIALS AND METHODS : We trained a deep neural network to classify 4 major brain biopsied lesions for intraoperative tissue diagnosis. Overall, 205 medical images were obtained from squash smear slides of histologically correlated cases, with 18 high-grade and 11 low-grade gliomas, 17 metastatic carcinomas, and 9 non-neoplastic pathological brain tissues. The neural network model was trained and evaluated using 5-fold cross-validation.

RESULTS : The model achieved 95% and 97% diagnostic accuracy on the patch-level classification and patient-level classification tasks, respectively.

CONCLUSIONS : We conclude that deep learning-based classification of cytological preparations may be a promising complementary method for rapid and accurate intraoperative diagnosis of CNS tumors.

Ozer Erdener, Bilecen Ali Enver, Ozer Nur Basak, Yanikoglu Berrin

2022-Dec-02

artificial intelligence, brain tumor, cytopathology, deep learning, intraoperative diagnosis, neural networks

General General

Deep generative modeling and clustering of single cell Hi-C data.

In Briefings in bioinformatics

Deciphering 3D genome conformation is important for understanding gene regulation and cellular function at a spatial level. The recent advances of single cell Hi-C technologies have enabled the profiling of the 3D architecture of DNA within individual cell, which allows us to study the cell-to-cell variability of 3D chromatin organization. Computational approaches are in urgent need to comprehensively analyze the sparse and heterogeneous single cell Hi-C data. Here, we proposed scDEC-Hi-C, a new framework for single cell Hi-C analysis with deep generative neural networks. scDEC-Hi-C outperforms existing methods in terms of single cell Hi-C data clustering and imputation. Moreover, the generative power of scDEC-Hi-C could help unveil the differences of chromatin architecture across cell types. We expect that scDEC-Hi-C could shed light on deepening our understanding of the complex mechanism underlying the formation of chromatin contacts.

Liu Qiao, Zeng Wanwen, Zhang Wei, Wang Sicheng, Chen Hongyang, Jiang Rui, Zhou Mu, Zhang Shaoting

2022-Dec-01

3D genome, deep learning, single cell, unsupervised learning

Radiology Radiology

Application of 18F-fluorodeoxyglucose PET/CT radiomic features and machine learning to predict early recurrence of non-small cell lung cancer after curative-intent therapy.

In Nuclear medicine communications

OBJECTIVE : To predict the recurrence of non-small cell lung cancer (NSCLC) within 2 years after curative-intent treatment using a machine-learning approach with PET/CT-based radiomics.

PATIENTS AND METHODS : A total of 77 NSCLC patients who underwent pretreatment 18F-fluorodeoxyglucose PET/CT were retrospectively analyzed. Five clinical features (age, sex, tumor stage, tumor histology, and smoking status) and 48 radiomic features extracted from primary tumors on PET were used for binary classifications. These were ranked, and a subset of useful features was selected based on Gini coefficient scores in terms of associations with relapsed status. Areas under the receiver operating characteristics curves (AUC) were yielded by six machine-learning algorithms (support vector machine, random forest, neural network, naive Bayes, logistic regression, and gradient boosting). Model performances were compared and validated via random sampling.

RESULTS : A PET/CT-based radiomic model was developed and validated for predicting the recurrence of NSCLC during the first 2 years after curation. The most important features were SD and variance of standardized uptake value, followed by low-intensity short-zone emphasis and high-intensity zone emphasis. The naive Bayes model with the 15 best-ranked features displayed the best performance (AUC: 0.816). Prediction models using the five best PET-derived features outperformed those using five clinical variables.

CONCLUSION : The machine learning model using PET-derived radiomic features showed good performance for predicting the recurrence of NSCLC during the first 2 years after a curative intent therapy. PET/CT-based radiomic features may help clinicians improve the risk stratification of relapsed NSCLC.

Park Soon Bin, Kim Ki-Up, Park Young Woo, Hwang Jung Hwa, Lim Chae Hong

2022-Dec-02

General General

Named entity recognition of Chinese electronic medical records based on a hybrid neural network and medical MC-BERT.

In BMC medical informatics and decision making ; h5-index 38.0

BACKGROUND : Named entity recognition (NER) of electronic medical records is an important task in clinical medical research. Although deep learning combined with pretraining models performs well in recognizing entities in clinical texts, because Chinese electronic medical records have a special text structure and vocabulary distribution, general pretraining models cannot effectively incorporate entities and medical domain knowledge into representation learning; separate deep network models lack the ability to fully extract rich features in complex texts, which negatively affects the named entity recognition of electronic medical records.

METHODS : To better represent electronic medical record text, we extract the text's local features and multilevel sequence interaction information to improve the effectiveness of electronic medical record named entity recognition. This paper proposes a hybrid neural network model based on medical MC-BERT, namely, the MC-BERT + BiLSTM + CNN + MHA + CRF model. First, MC-BERT is used as the word embedding model of the text to obtain the word vector, and then BiLSTM and CNN obtain the feature information of the forward and backward directions of the word vector and the local context to obtain the corresponding feature vector. After merging the two feature vectors, they are sent to multihead self-attention (MHA) to obtain multilevel semantic features, and finally, CRF is used to decode the features and predict the label sequence.

RESULTS : The experiments show that the F1 values of our proposed hybrid neural network model based on MC-BERT reach 94.22%, 86.47%, and 92.28% on the CCKS-2017, CCKS-2019 and cEHRNER datasets, respectively. Compared with the general-domain BERT-based BiLSTM + CRF, our F1 values increased by 0.89%, 1.65% and 2.63%. Finally, we analyzed the effect of an unbalanced number of entities in the electronic medical records on the results of the NER experiment.

Chen Peng, Zhang Meng, Yu Xiaosheng, Li Songpu

2022-Dec-01

BERT model, Chinese electronic medical record, Hybrid neural network, Named entity recognition

General General

A lightweight network for COVID-19 detection in X-ray images.

In Methods (San Diego, Calif.)

The Novel Coronavirus 2019 (COVID-19) is a global pandemic which has a devastating impact. Due to its quick transmission, a prominent challenge in confronting this pandemic is the rapid diagnosis. Currently, the commonly-used diagnosis is the specific molecular tests aided with the medical imaging modalities such as chest X-ray (CXR). However, with the large demand, the diagnoses of CXR are time-consuming and laborious. Deep learning is promising for automatically diagnosing COVID-19 to ease the burden on medical systems. At present, the most applied neural networks are large, which hardly satisfy the rapid yet inexpensive requirements of COVID-19 detection. To reduce huge computation and memory demands, in this paper, we focus on implementing lightweight networks for COVID-19 detection in CXR. Concretely, we first augment data based on clinical visual features of CXR from expertise. Then, according to the fact that all the input data are CXR, we design a targeted four-layer network with either 11×11 or 3×3 kernels to recognize regional features and detail features. A pruning criterion based on the weights importance is also proposed to further prune the network. Experiments on a public COVID-19 dataset validate the effectiveness and efficiency of the proposed method.

Shi Yong, Tang Anda, Xiao Yang, Niu Lingfeng

2022-Nov-29

COVID-19 detection, network pruning, neural network

General General

Intramuscular EMG feature extraction and evaluation at different arm positions and hand postures based on a statistical criterion method.

In Proceedings of the Institution of Mechanical Engineers. Part H, Journal of engineering in medicine

Prostheses control using electromyography signals have shown promising aspects in various fields including rehabilitation sciences and assistive technology controlled devices. Pattern recognition and machine learning methods have been observed to play a significant role in evaluating features and classifying different limb motions for enhanced prosthetic executions. This paper proposes feature extraction and evaluation method using intramuscular electromyography (iEMG) signals at different arm positions and hand postures based on the RES Index value statistical criterion method. Sixteen-time domain features were selected for the study at two main circumstances; fixed arm position (FAP) and fixed hand posture (FHP). Eight healthy male participants (30.62 ± 3.87 years) were asked to execute five motion classes including hand grip, hand open, rest, hand extension, and hand flexion at four different arm positions that comprise of 0°, 45°, 90°, and 135°. The classification process is accomplished via the application of the k-nearest neighbor (KNN) classifier. Then RES index was calculated to investigate the optimal features based on the proposed statistical criterion method. From the RES Index, we concluded that Variance (VAR) is the best feature while WAMP, Zero Crossing (ZC), and Slope Sign Change (SSC) are the worst ones in FAP conditions. On the contrary, we concluded that Average Amplitude Change (AAC) is the best feature while WAMP and Simple Square Integral (SSI) resulted in least RES Index values for FHP conditions. The proposed study has possible iEMG based applications such as assistive control devices, robotics. Also, working with the frequency domain features encapsulates the future scope of the study.

Asghar Ali, Khan Saad Jawaid, Azim Fahad, Shakeel Choudhary Sobhan, Hussain Amatullah, Niazi Imran Khan

2022-Dec-01

Statistical analysis [medical], arm positions, feature extraction, hand postures, intramuscular EMG

General General

A novel hybrid walk-forward ensemble optimization for time series cryptocurrency prediction.

In Heliyon

Cryptocurrency is an advanced digital currency that is secured by encryption, making it nearly impossible to forge or duplicate. Many cryptocurrencies are blockchain-based with decentralized networks. The prediction of cryptocurrency prices is a very difficult task because of the absence of an appropriate analytical basis to substantiate their claims. Cryptocurrencies are also dependent on several variables, such as technical advancement, internal competition, market pressure, economic concerns, security, and political considerations. This paper proposed the hybrid walk-forward ensemble optimization technique and applied it to predict the daily prices of fifteen cryptocurrencies, such as Cardano (ADA-USD), Bitcoin (BTC-USD), Dogecoin (DOGE-USD), Ethereum Classic (ETC-USD), Chainlink (LINK-USD), Litecoin (LTC-USD), NEO (NEO-USD), Tron (TRX-USD), Tether (USDT-USD), NEM (XEM-USD), Stellar (XLM-USD), Ripple (XRP-USD), and Tezos (XTZ-USD). A performance comparison of these cryptocurrencies was done using classical statistical models, machine learning algorithms, and deep learning algorithms on different cryptocurrency time series. Simulation results show that our proposed model performed better in terms of cryptocurrency prediction accuracy compared to the classical statistical model and machine and deep learning algorithms used in this paper.

Oyewola David Opeoluwa, Dada Emmanuel Gbenga, Ndunagu Juliana Ngozi

2022-Nov

BlockChain, Cryptocurrency, Gated recurrent unit, Optimization, Walk-forward

General General

Therapists and psychotherapy side effects in China: A machine learning-based study.

In Heliyon

OBJECTIVE : Side effects in the psychotherapy are sometimes unavoidable. Therapists play a significant role in the side effects of psychotherapy, but there have been few quantitative studies on the mechanisms by which therapists contribute to them.

METHODS : We designed the psychotherapy Side Effects Questionnaire-Therapist Version (PSEQ-T) and released it online through an official WeChat account, where 530 therapists participated in the cross-sectional analysis. The therapists were classified into groups with and without perceptions of clients' side effects. A number of features were selected to distinguish the therapists by category. Six machine learning-based algorithms were selected and trained by our dataset to build classification models. We leveraged the Shapley Additive exPlanations (SHAP) method to quantify the importance of each feature to the therapist categories.

RESULTS : Our study demonstrated the following: (1) Of the therapists, 316 perceived clients' side effects in psychotherapy, with a 59.6% incidence of side effects; the most common type was "make the clients or patients feel bad" (49.8%). (2) A Random Forest-based machine-learning classifier offered the best predictive performance to distinguish the therapists with and without perceptions of clients' side effects, with an F1 score of 0.722 and an AUC value of 0.717. (3) "Therapists' psychological activity" was the most relevant feature for distinguishing the therapist category.

CONCLUSIONS : Our study revealed that the therapist's mastery of the limitations of psychotherapy technology and theory, especially the awareness and construction of their psychological states, was the most critical factor in predicting the therapist's perception of the side effects of psychotherapy.

Yao Lijun, Xu Zhiwei, Zhao Xudong, Chen Yang, Liu Liang, Fu Xiaoming, Chen Fazhan

2022-Nov

Artificial intelligence, Machine learning, Psychotherapy, Side effects, Therapist

General General

The promise of the metaverse in mental health: the new era of MEDverse.

In Heliyon

Since Mark Zuckerberg's announcement about the development of new three-dimensional virtual worlds for social communication, a great debate has been raised about the promise of such a technology. The metaverse, a term formed by combining meta and universe, could open a new era in mental health, mainly in psychological disorders, where the creation of a full-body illusion via digital avatar could promote healthcare and personal well-being. Patients affected by body dysmorphism symptoms (i.e., eating disorders), social deficits (i.e. autism) could greatly benefit from this kind of technology. However, it is not clear which advantage the metaverse would have in treating psychological disorders with respect to the well-known and effective virtual reality (VR) exposure therapy. Indeed, in the last twenty years, a plethora of studies have demonstrated the effectiveness of VR technology in reducing symptoms of pain, anxiety, stress, as well as, in improving cognitive and social skills. We hypothesize that the metaverse will offer more opportunities, such as a more complex, virtual realm where sensory inputs, and recurrent feedback, mediated by a "federation" of multiple technologies - e.g., artificial intelligence, tangible interfaces, Internet of Things and blockchain, can be reinterpreted for facilitating a new kind of communication overcoming self-body representation. However, nowadays a clear starting point does not exist. For this reason, it is worth defining a theoretical framework for applying this new kind of technology in a social neuroscience context for developing accurate solutions to mental health in the future.

Cerasa Antonio, Gaggioli Andrea, Marino Flavia, Riva Giuseppe, Pioggia Giovanni

2022-Nov

Autism, Body dysmorphism disorders, Mental disorders, Metaverse

Public Health Public Health

Pharmacogenomics driven decision support prototype with machine learning: A framework for improving patient care.

In Frontiers in big data

INTRODUCTION : A growing number of healthcare providers make complex treatment decisions guided by electronic health record (EHR) software interfaces. Many interfaces integrate multiple sources of data (e.g., labs, pharmacy, diagnoses) successfully, though relatively few have incorporated genetic data.

METHOD : This study utilizes informatics methods with predictive modeling to create and validate algorithms to enable informed pharmacogenomic decision-making at the point of care in near real-time. The proposed framework integrates EHR and genetic data relevant to the patient's current medications including decision support mechanisms based on predictive modeling. We created a prototype with EHR and linked genetic data from the Department of Veterans Affairs (VA), the largest integrated healthcare system in the US. The EHR data included diagnoses, medication fills, and outpatient clinic visits for 2,600 people with HIV and matched uninfected controls linked to prototypic genetic data (variations in single or multiple positions in the DNA sequence). We then mapped the medications that patients were prescribed to medications defined in the drug-gene interaction mapping of the Clinical Pharmacogenomics Implementation Consortium's (CPIC) level A (i.e., sufficient evidence for at least one prescribing action) guidelines that predict adverse events. CPIC is a National Institute of Health funded group of experts who develop evidence based pharmacogenomic guidelines. Preventable adverse events (PAE) can be defined as a harmful outcome from an intervention that could have been prevented. For this study, we focused on potential PAEs resulting from a medication-gene interaction.

RESULTS : The final model showed AUC scores of 0.972 with an F1 score of 0.97 with genetic data as compared to 0.766 and 0.73 respectively, without genetic data integration.

DISCUSSION : Over 98% of people in the cohort were on at least one medication with CPIC level a guideline in their lifetime. We compared predictive power of machine learning models to detect a PAE between five modeling methods: Random Forest, Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), K Nearest neighbors (KNN), and Decision Tree. We found that XGBoost performed best for the prototype when genetic data was added to the framework and improved prediction of PAE. We compared area under the curve (AUC) between the models in the testing dataset.

Kidwai-Khan Farah, Rentsch Christopher T, Pulk Rebecca, Alcorn Charles, Brandt Cynthia A, Justice Amy C

2022

clinical decision support, data framework, machine learning, pharmacogenomics, prototype

Dermatology Dermatology

Machine Learning for Diagnosis of Systemic Lupus Erythematosus: A Systematic Review and Meta-Analysis.

In Computational intelligence and neuroscience

BACKGROUND : Application of machine learning (ML) for identification of systemic lupus erythematosus (SLE) has been recently drawing increasing attention, while there is still lack of evidence-based support.

METHODS : Systematic review and meta-analysis are conducted to evaluate its diagnostic accuracy and application prospect. PubMed, Embase, Cochrane Library, and Web of Science libraries are searched, in combination with manual searching and literature retrospection, for studies regarding machine learning for identifying SLE and neuropsychiatric systemic lupus erythematosus (NPSLE). Quality Assessment of Diagnostic Accuracy Studies (QUADA-2) is applied to assess the quality of included studies. Diagnostic accuracy of the SLE model and NPSLE model is assessed using the bivariate fixed-effect model, and the data are pooled. Summary receiver operator characteristic curve (SROC) is plotted, and area under the curve (AUC) is calculated.

RESULTS : Eighteen (18) studies are included, in which ten (10) focused on SLE and eight (8) on NPSLE. The AUC of SLE identification is 0.95, the sensitivity is 0.90, the specificity is 0.89, the PLR is 8.4, the NLR is 0.12, and the DOR is 73. AUC of NPSLE identification is 0.89, the sensitivity is 0.83, the specificity is 0.83, the PLR is 5.0, the NLR is 0.20, and the DOR is 25.

CONCLUSION : Machine learning presented remarkable performance in identification of SLE and NPSLE. Based on the convenience for inclusion factor collection and non-invasiveness of detection, machine learning is expected to be widely applied in clinical practice to assist medical decision making.

Zhou Yuan, Wang Meng, Zhao Shasha, Yan Yan

2022

General General

Deep Learning Model for the Image Fusion and Accurate Classification of Remote Sensing Images.

In Computational intelligence and neuroscience

Deep learning is widely used for the classification of images that have various attributes. Image data are used to extract colour, texture, form, and local features. These features are combined in feature-level image fusion to create a merged remote sensing image. A trained depth belief network (DBN) processes and divides fusion images, while a Softmax classifier determines the land type. As tested, the proposed approach can categorise all types of land. Traditional methods of detecting distant sensing photographs have limitations that can be overcome by using convolutional neural networks (CNN). Traditional techniques are incapable of combining deep learning elements while doing badly in classification. After PCA decreases data dimensionality, deep learning is applied to generate effective features that employ deep learning after PCA has reduced the dimensionality of the data. Principal component analysis is commonly used because of its effectiveness in attaining linear dimension reduction. It may be used on its own or as a starting point for further study into various different dimensionality reduction approaches. Data can be altered by remapping onto a new set of orthogonal axes using a process known as projection-based principal component analysis. Following remote sensing of land resources, the pictures were classified using a support vector machine. Euroset satellite images are used to assess the suggested approach. Accuracy and kappa have both increased. It was accurate and within 95.83 % of the planned figures. The classification findings' kappa value and reasoning time were 95.87 % and 128 milliseconds, respectively. Both the model's performance and the classification effect are excellent.

Mary S Roselin, Pachar Sunita, Srivastava Prabhat Kumar, Malik Medhavi, Sharma Avani, G Almutiri Tariq, Atal Zabihullah

2022

General General

Plastic Eating Enzymes: A Step Towards Sustainability.

In Indian journal of microbiology

The large-scale usage of petro-chemical-based plastics has proved to be a significant source of environmental pollution due to their non-biodegradable nature. Microbes-based enzymes such as esterases, cutinases, and lipases have shown the ability to degrade synthetic plastic. However, the degradation of plastics by enzymes is primarily limited by the unavailability of a robust enzymatic system, i.e., low activity and stability towards plastic degradation. Recently, the machine learning strategy involved structure-based and deep neural networks show desirable potential to generate functional, active stable, and tolerant polyethylene terephthalate (PET) degrading enzyme (FAST-PETase). FAST-PETase showed the highest PET hydrolytic activity among known enzymes or their variants and degraded broad ranges of plastics. The development of a closed-loop circular economy-based system of plastic degradation to monomers by FAST-PETase followed by the re-polymerization of monomers into clean plastics can be a more sustainable approach. As an alternative to synthetic plastics, diverse microbes can produce polyhydroxyalkanoates, and their degradation by microbes has been well-established. This article discusses recent updates in the enzymatic degradation of plastics for sustainable development.

Patel Sanjay K S, Lee Jung-Kul

2022-Dec

Bio-degradation process, Machine learning strategy, Plastic degrading enzyme, Polyhydroxyalkanoates, Synthetic plastic

Dermatology Dermatology

Advances in microbial metagenomics and artificial intelligence analysis in forensic identification.

In Frontiers in microbiology

Microorganisms, which are widely distributed in nature and human body, show unique application value in forensic identification. Recent advances in high-throughput sequencing technology and significant reductions in analysis costs have markedly promoted the development of forensic microbiology and metagenomics. The rapid progression of artificial intelligence (AI) methods and computational approaches has shown their unique application value in forensics and their potential to address relevant forensic questions. Here, we summarize the current status of microbial metagenomics and AI analysis in forensic microbiology, including postmortem interval inference, individual identification, geolocation, and tissue/fluid identification.

He Qing, Niu Xueli, Qi Rui-Qun, Liu Min

2022

artificial intelligence, forensic microbiology, forensic science, machine learning, microbial forensics, microbiome

Cardiology Cardiology

Development of artificial neural network models for paediatric critical illness in South Africa.

In Frontiers in pediatrics

OBJECTIVES : Failures in identification, resuscitation and appropriate referral have been identified as significant contributors to avoidable severity of illness and mortality in South African children. In this study, artificial neural network models were developed to predict a composite outcome of death before discharge from hospital or admission to the PICU. These models were compared to logistic regression and XGBoost models developed on the same data in cross-validation.

DESIGN : Prospective, analytical cohort study.

SETTING : A single centre tertiary hospital in South Africa providing acute paediatric services.

PATIENTS : Children, under the age of 13 years presenting to the Paediatric Referral Area for acute consultations.

OUTCOMES : Predictive models for a composite outcome of death before discharge from hospital or admission to the PICU.

INTERVENTIONS : None.

MEASUREMENTS AND MAIN RESULTS : 765 patients were included in the data set with 116 instances (15.2%) of the study outcome. Models were developed on three sets of features. Two derived from sequential floating feature selection (one inclusive, one parsimonious) and one from the Akaike information criterion to yield 9 models. All developed models demonstrated good discrimination on cross-validation with mean ROC AUCs greater than 0.8 and mean PRC AUCs greater than 0.53. ANN1, developed on the inclusive feature-et demonstrated the best discrimination with a ROC AUC of 0.84 and a PRC AUC of 0.64 Model calibration was variable, with most models demonstrating weak calibration. Decision curve analysis demonstrated that all models were superior to baseline strategies, with ANN1 demonstrating the highest net benefit.

CONCLUSIONS : All models demonstrated satisfactory performance, with the best performing model in cross-validation being an ANN model. Given the good performance of less complex models, however, these models should also be considered, given their advantage in ease of implementation in practice. An internal validation study is now being conducted to further assess performance with a view to external validation.

Pienaar Michael A, Sempa Joseph B, Luwes Nicolaas, George Elizabeth C, Brown Stephen C

2022

children, critical care, machine learning, neural networks, severity of illness, triage

Internal Medicine Internal Medicine

An improved workflow for accurate and robust healthcare environmental surveillance using metagenomics.

In Microbiome

BACKGROUND : Effective surveillance of microbial communities in the healthcare environment is increasingly important in infection prevention. Metagenomics-based techniques are promising due to their untargeted nature but are currently challenged by several limitations: (1) they are not powerful enough to extract valid signals out of the background noise for low-biomass samples, (2) they do not distinguish between viable and nonviable organisms, and (3) they do not reveal the microbial load quantitatively. An additional practical challenge towards a robust pipeline is the inability to efficiently allocate sequencing resources a priori. Assessment of sequencing depth is generally practiced post hoc, if at all, for most microbiome studies, regardless of the sample type. This practice is inefficient at best, and at worst, poor sequencing depth jeopardizes the interpretation of study results. To address these challenges, we present a workflow for metagenomics-based environmental surveillance that is appropriate for low-biomass samples, distinguishes viability, is quantitative, and estimates sequencing resources.

RESULTS : The workflow was developed using a representative microbiome sample, which was created by aggregating 120 surface swabs collected from a medical intensive care unit. Upon evaluating and optimizing techniques as well as developing new modules, we recommend best practices and introduce a well-structured workflow. We recommend adopting liquid-liquid extraction to improve DNA yield and only incorporating whole-cell filtration when the nonbacterial proportion is large. We suggest including propidium monoazide treatment coupled with internal standards and absolute abundance profiling for viability assessment and involving cultivation when demanding comprehensive profiling. We further recommend integrating internal standards for quantification and additionally qPCR when we expect poor taxonomic classification. We also introduce a machine learning-based model to predict required sequencing effort from accessible sample features. The model helps make full use of sequencing resources and achieve desired outcomes. Video Abstract CONCLUSIONS: This workflow will contribute to more accurate and robust environmental surveillance and infection prevention. Lessons gained from this study will also benefit the continuing development of methods in relevant fields.

Shen Jiaxian, McFarland Alexander G, Blaustein Ryan A, Rose Laura J, Perry-Dow K Allison, Moghadam Anahid A, Hayden Mary K, Young Vincent B, Hartmann Erica M

2022-Dec-02

Environmental surveillance, Infection prevention, Low biomass, Machine learning, Metagenomics, Quantification, Sequencing depth prediction, Viability

General General

Res-SE-ConvNet: A Deep Neural Network for Hypoxemia Severity Prediction for Hospital In-Patients Using Photoplethysmograph Signal.

In IEEE journal of translational engineering in health and medicine

Determining the severity level of hypoxemia, the scarcity of saturated oxygen (SpO2) in the human body, is very important for the patients, a matter which has become even more significant during the outbreak of Covid-19 variants. Although the widespread usage of Pulse Oximeter has helped the doctors aware of the current level of SpO2 and thereby determine the hypoxemia severity of a particular patient, the high sensitivity of the device can lead to the desensitization of the care-givers, resulting in slower response to actual hypoxemia event. There has been research conducted for the detection of severity level using various parameters and bio-signals and feeding them in a machine learning algorithm. However, in this paper, we have proposed a new residual-squeeze-excitation-attention based convolutional network (Res-SE-ConvNet) using only Photoplethysmography (PPG) signal for the comfortability of the patient. Unlike the other methods, the proposed method has outperformed the standard state-of-art methods as the result shows 96.5% accuracy in determining 3 class severity problems with 0.79 Cohen Kappa score. This method has the potential to aid the patients in receiving the benefit of an automatic and faster clinical decision support system, thus handling the severity of hypoxemia.

Mahmud Talha Ibn, Imran Sheikh Asif, Shahnaz Celia

2022

Saturated oxygen, attention, deep learning, excitation, feature map

General General

Artificial intelligence applied to omics data in liver diseases: Enhancing clinical predictions.

In Frontiers in artificial intelligence

Rapid development of biotechnology has led to the generation of vast amounts of multi-omics data, necessitating the advancement of bioinformatics and artificial intelligence to enable computational modeling to diagnose and predict clinical outcome. Both conventional machine learning and new deep learning algorithms screen existing data unbiasedly to uncover patterns and create models that can be valuable in informing clinical decisions. We summarized published literature on the use of AI models trained on omics datasets, with and without clinical data, to diagnose, risk-stratify, and predict survivability of patients with non-malignant liver diseases. A total of 20 different models were tested in selected studies. Generally, the addition of omics data to regular clinical parameters or individual biomarkers improved the AI model performance. For instance, using NAFLD fibrosis score to distinguish F0-F2 from F3-F4 fibrotic stages, the area under the curve (AUC) was 0.87. When integrating metabolomic data by a GMLVQ model, the AUC drastically improved to 0.99. The use of RF on multi-omics and clinical data in another study to predict progression of NAFLD to NASH resulted in an AUC of 0.84, compared to 0.82 when using clinical data only. A comparison of RF, SVM and kNN models on genomics data to classify immune tolerant phase in chronic hepatitis B resulted in AUC of 0.8793-0.8838 compared to 0.6759-0.7276 when using various serum biomarkers. Overall, the integration of omics was shown to improve prediction performance compared to models built only on clinical parameters, indicating a potential use for personalized medicine in clinical setting.

Baciu Cristina, Xu Cherry, Alim Mouaid, Prayitno Khairunnadiya, Bhat Mamatha

2022

artificial intelligence, clinical outcome prediction, liver disease, machine learning, omics data

General General

A comprehensive survey on computational learning methods for analysis of gene expression data.

In Frontiers in molecular biosciences

Computational analysis methods including machine learning have a significant impact in the fields of genomics and medicine. High-throughput gene expression analysis methods such as microarray technology and RNA sequencing produce enormous amounts of data. Traditionally, statistical methods are used for comparative analysis of gene expression data. However, more complex analysis for classification of sample observations, or discovery of feature genes requires sophisticated computational approaches. In this review, we compile various statistical and computational tools used in analysis of expression microarray data. Even though the methods are discussed in the context of expression microarrays, they can also be applied for the analysis of RNA sequencing and quantitative proteomics datasets. We discuss the types of missing values, and the methods and approaches usually employed in their imputation. We also discuss methods of data normalization, feature selection, and feature extraction. Lastly, methods of classification and class discovery along with their evaluation parameters are described in detail. We believe that this detailed review will help the users to select appropriate methods for preprocessing and analysis of their data based on the expected outcome.

Bhandari Nikita, Walambe Rahee, Kotecha Ketan, Khare Satyajeet P

2022

deep learning, explainable techniques, feature selection, gene expression, interpretation, machine learning, microarray, missing value imputation

General General

GAPCNN with HyPar: Global Average Pooling convolutional neural network with novel NNLU activation function and HYBRID parallelism.

In Frontiers in computational neuroscience

With the increasing demand for deep learning in the last few years, CNNs have been widely used in many applications and have gained interest in classification, regression, and image recognition tasks. The training of these deep neural networks is compute-intensive and takes days or even weeks to train the model from scratch. The compute-intensive nature of these deep neural networks sometimes limits the practical implementation of CNNs in real-time applications. Therefore, the computational speedup in these networks is of utmost importance, which generates interest in CNN training acceleration. Much research is going on to meet the computational requirement and make it feasible for real-time applications. Because of its simplicity, data parallelism is used primarily, but it performs badly sometimes. In most cases, researchers prefer model parallelism to data parallelism, but it is not always the best choice. Therefore, in this study, we implement a hybrid of both data and model parallelism to improve the computational speed without compromising accuracy. There is only a 1.5% accuracy drop in our proposed study with an increased speed up of 3.62X. Also, a novel activation function Normalized Non-linear Activation Unit NNLU is proposed to introduce non-linearity in the model. The activation unit is non-saturated and helps avoid the model's over-fitting. The activation unit is free from the vanishing gradient problem. Also, the fully connected layer in the proposed CNN model is replaced by the Global Average Pooling layers (GAP) to enhance the model's accuracy and computational performance. When tested on a bio-medical image dataset, the model achieves an accuracy of 98.89% and requires a training time of only 1 s. The model categorizes medical images into different categories of glioma, meningioma, and pituitary tumor. The model is compared with existing state-of-art techniques, and it is observed that the proposed model outperforms others in classification accuracy and computational speed. Also, results are observed for different optimizers', different learning rates, and various epoch numbers.

Habib Gousia, Qureshi Shaima

2022

ADAM, AMsgrad, CNN, Global Average Pooling, NNLU, SGD, hybrid parallelism, max-pooling

General General

Retracted: A Coordinated and Optimized Mechanism of Artificial Intelligence for Student Management by College Counselors Based on Big Data.

In Computational and mathematical methods in medicine

[This retracts the article DOI: 10.1155/2021/1725490.].

Methods In Medicine Computational And Mathematical

2022

General General

An Intelligent Motor Assessment Method Utilizing a Bi-Lateral Virtual-Reality Task for Stroke Rehabilitation on Upper Extremity.

In IEEE journal of translational engineering in health and medicine

Virtual reality (VR) has been widely adopted by therapists to provide rich motor training tasks. Time series data of motion trajectory accompanied with the interaction of VR system may contain important clues in regard to the assessment of motor function, however, clinical evaluation scales such as Fugl-Meyer Assessment (FMA), Wolf Motor Function Test (WMFT), and Test D'évaluation Des Membres Supérieurs Des Personnes Âgées (TEMPA) are highly depended in clinic. Further, there is not yet an assessment method that simultaneously consider motion trajectory and clinical evaluation scales. The objective of this study is to establish an evidence-based assessment model by machine-learning method that integrated motion trajectory of a VR task with clinical evaluation scales. In this study, a VR system for upper-limb motor training was proposed for stroke rehabilitation. Clinical trials with 20 stroke patients were performed. A variety of motor indicators that derived via motion trajectory were proposed. The correlations between motor indicators and clinical evaluation scales were examined. Further, motor indicators were integrated with evaluation scales to develop a machine-learning based model that represents an evidence-based motor assessment approach. Clinical evaluation scales, FMA, TEMPA and WMFT, were significantly progressed. A few motor indicators were found significantly correlated with clinical evaluation scales. The accuracy of machine-learning based assessment model was up to 86%. The proposed VR system is validated to be effective in motor rehabilitation. Motor indicators derived from motor trajectory were with potential for clinical motor assessment. Machine learning could be a promising tool to perform automatic assessment. Clinical and Translational Impact Statement-A VR task for motor rehabilitation was exanimated via clinical trials. Integrating motor indices with clinical assessment, a machine-learning model with accuracy of 86% was developed to evaluate motor function.

Chung Chia-Ru, Su Mu-Chun, Lee Si-Huei, Wu Eric Hsiao-Kuang, Tang Li-Hsien, Yeh Shih-Ching

2022

Stroke rehabilitation, machine learning, motor training, virtual reality

General General

Res-SE-ConvNet: A Deep Neural Network for Hypoxemia Severity Prediction for Hospital In-Patients Using Photoplethysmograph Signal.

In IEEE journal of translational engineering in health and medicine

Determining the severity level of hypoxemia, the scarcity of saturated oxygen (SpO2) in the human body, is very important for the patients, a matter which has become even more significant during the outbreak of Covid-19 variants. Although the widespread usage of Pulse Oximeter has helped the doctors aware of the current level of SpO2 and thereby determine the hypoxemia severity of a particular patient, the high sensitivity of the device can lead to the desensitization of the care-givers, resulting in slower response to actual hypoxemia event. There has been research conducted for the detection of severity level using various parameters and bio-signals and feeding them in a machine learning algorithm. However, in this paper, we have proposed a new residual-squeeze-excitation-attention based convolutional network (Res-SE-ConvNet) using only Photoplethysmography (PPG) signal for the comfortability of the patient. Unlike the other methods, the proposed method has outperformed the standard state-of-art methods as the result shows 96.5% accuracy in determining 3 class severity problems with 0.79 Cohen Kappa score. This method has the potential to aid the patients in receiving the benefit of an automatic and faster clinical decision support system, thus handling the severity of hypoxemia.

Mahmud Talha Ibn, Imran Sheikh Asif, Shahnaz Celia

2022

Saturated oxygen, attention, deep learning, excitation, feature map

General General

Association between the C-reactive protein to albumin ratio and adverse clinical prognosis in patients with young stroke.

In Frontiers in neurology

BACKGROUND : The inflammatory response plays an important role in ischemic stroke, and the incidence of stroke in young adults has increased rapidly in recent years. The C-reactive protein-to-albumin ratio (CAR) is a new index that reflects the overall inflammatory status of patients with major diseases; however, no studies have reported the relationship between CAR and young stroke.

METHODS : The participants' baseline characteristics and laboratory examination results, including CAR, were obtained at admission. The modified Rankin Scale (mRS) scores at the 30-day and 90-day follow-ups were obtained from all patients. All the participants included in the study were classified into four groups according to CAR quartiles (Q1-Q4). Logistic regression was used to analyze the relationship between different CAR levels and adverse outcomes (mRS 3-6 and mRS 2-6). We also plotted receiver operating characteristic curves of CAR for adverse clinical outcomes and calculated the area under the curve and cutoff values.

RESULTS : A total of 630 patients with young stroke were enrolled in the study. In the multivariate logistic regression model, at the 30-day follow-up, the Q3 and Q4 (significantly increased CAR) groups showed an elevated risk of mRS score of 2-6 (odds ratio [OR]: 2.94; 95% confidence interval [CI]: 1.40-6.16, p < 0.01; OR: 4.01; 95% CI: 1.88-8.91, p < 0.01). At the 90-day follow-up, the Q3 and Q4 groups still showed an elevated risk of an mRS score of 2-6 (Q3, OR: 2.76; 95% CI: 1.30-5.86, p < 0.01; Q4, OR: 2.63; 95% CI: 1.22-5.65, p < 0.01).

CONCLUSION : A significantly increased CAR was independently associated with an increased risk of adverse outcomes in young patients with stroke.

Du Yang, Zhang Jia, Li Ning, Guo Jiahuan, Liu Xinmin, Bian Liheng, Zhao Xingquan, Liu Yanfang

2022

C-reactive protein to albumin ratio, inflammation, prognosis, stroke in young adults, young stroke

Public Health Public Health

Machine-learning prediction for hospital length of stay using a French medico-administrative database.

In Journal of market access & health policy

INTRODUCTION : Prolonged Hospital Length of Stay (PLOS) is an indicator of deteriorated efficiency in Quality of Care. One goal of public health management is to reduce PLOS by identifying its most relevant predictors. The objective of this study is to explore Machine Learning (ML) models that best predict PLOS.

METHODS : Our dataset was collected from the French Medico-Administrative database (PMSI) as a retrospective cohort study of all discharges in the year 2015 from a large university hospital in France (APHM). The study outcomes were LOS transformed into a binary variable (long vs. short LOS) according to the 90th percentile (14 days). Logistic regression (LR), classification and regression trees (CART), random forest (RF), gradient boosting (GB) and neural networks (NN) were applied to the collected data. The predictive performance of the models was evaluated using the area under the ROC curve (AUC).

RESULTS : Our analysis included 73,182 hospitalizations, of which 7,341 (10.0%) led to PLOS. The GB classifier was the most performant model with the highest AUC (0.810), superior to all the other models (all p-values <0.0001). The performance of the RF, GB and NN models (AUC ranged from 0.808 to 0.810) was superior to that of the LR model (AUC = 0.795); all p-values <0.0001. In contrast, LR was superior to CART (AUC = 0.786), p < 0.0001. The variable most predictive of the PLOS was the destination of the patient after hospitalization to other institutions. The typical clinical profile of these patients (17.5% of the sample) was the elderly patient, admitted in emergency, for a trauma, a neurological or a cardiovascular pathology, more often institutionalized, with more comorbidities notably mental health problems, dementia and hemiplegia.

DISCUSSION : The integration of ML, particularly the GB algorithm, may be useful for health-care professionals and bed managers to better identify patients at risk of PLOS. These findings underscore the need to strengthen hospitals through targeted allocation to meet the needs of an aging population.

Jaotombo Franck, Pauly Vanessa, Fond Guillaume, Orleans Veronica, Auquier Pascal, Ghattas Badih, Boyer Laurent

2023

Machine learning, health services research, neural network, prediction, public health

Cardiology Cardiology

Identification of decompensation episodes in chronic heart failure patients based solely on heart sounds.

In Frontiers in cardiovascular medicine

Decompensation episodes in chronic heart failure patients frequently result in unplanned outpatient or emergency room visits or even hospitalizations. Early detection of these episodes in their pre-symptomatic phase would likely enable the clinicians to manage this patient cohort with the appropriate modification of medical therapy which would in turn prevent the development of more severe heart failure decompensation thus avoiding the need for heart failure-related hospitalizations. Currently, heart failure worsening is recognized by the clinicians through characteristic changes of heart failure-related symptoms and signs, including the changes in heart sounds. The latter has proven to be largely unreliable as its interpretation is highly subjective and dependent on the clinicians' skills and preferences. Previous studies have indicated that the algorithms of artificial intelligence are promising in distinguishing the heart sounds of heart failure patients from those of healthy individuals. In this manuscript, we focus on the analysis of heart sounds of chronic heart failure patients in their decompensated and recompensated phase. The data was recorded on 37 patients using two types of electronic stethoscopes. Using a combination of machine learning approaches, we obtained up to 72% classification accuracy between the two phases, which is better than the accuracy of the interpretation by cardiologists, which reached 50%. Our results demonstrate that machine learning algorithms are promising in improving early detection of heart failure decompensation episodes.

Susič David, Poglajen Gregor, Gradišek Anton

2022

artificial intelligence-AI, cardiac decompensation, classification, decompensation detection, heart failiure, heart sound, machine learing, phonocardiogram (PCG)

General General

Construction of artificial neural network diagnostic model and analysis of immune infiltration for periodontitis.

In Frontiers in genetics ; h5-index 62.0

Background: Periodontitis is a chronic inflammatory disease leading to tooth loss in severe cases, and early diagnosis is essential for periodontitis prevention. This study aimed to construct a diagnostic model for periodontitis using a random forest algorithm and an artificial neural network (ANN). Methods: Gene expression data of two large cohorts of patients with periodontitis, GSE10334 and GSE16134, were downloaded from the Gene Expression Omnibus database. We screened for differentially expressed genes in the GSE10334 cohort, identified key periodontitis biomarkers using a Random Forest algorithm, and constructed a classification artificial neural network model, using receiver operating characteristic curves to evaluate its diagnostic utility. Furthermore, patients with periodontitis were classified using a consensus clustering algorithm. The immune infiltration landscape was assessed using CIBERSOFT and single-sample Gene Set Enrichment Analysis. Results: A total of 153 differentially expressed genes were identified, of which 42 were downregulated. We utilized 13 key biomarkers to establish a periodontitis diagnostic model. The model had good predictive performance, with an area under the receiver operative characteristic curve (AUC) of 0.945. The independent cohort (GSE16134) was used to further validate the model's accuracy, showing an area under the receiver operative characteristic curve of 0.900. The proportion of plasma cells was highest in samples from patients with period ontitis, and 13 biomarkers were closely related to immunity. Two molecular subgroups were defined in periodontitis, with one cluster suggesting elevated levels of immune infiltration and immune function. Conclusion: We successfully identified key biomarkers of periodontitis using machine learning and developed a satisfactory diagnostic model. Our model may provide a valuable reference for the prevention and early detection of periodontitis.

Xiang Junwei, Huang Wenkai, He Yaodong, Li Yunshan, Wang Yuanyin, Chen Ran

2022

biomarkers, gene expression, machine learning, neural networks, periodontitis

General General

Analysis of the effect of an artificial intelligence chatbot educational program on non-face-to-face classes: a quasi-experimental study.

In BMC medical education

BACKGROUND : Education and training are needed for nursing students using artificial intelligence-based educational programs. However, few studies have assessed the effect of using chatbots in nursing education.

OBJECTIVES : This study aimed to develop and examine the effect of an artificial intelligence chatbot educational program for promoting nursing skills related to electronic fetal monitoring in nursing college students during non-face-to-face classes during the COVID-19 pandemic.

DESIGN : This quasi-experimental study used a nonequivalent control group non-synchronized pretest-posttest design.

METHODS : The participants were 61 junior students from a nursing college located in G province of South Korea. Data were collected between November 3 and 16, 2021, and analyzed using independent t-tests.

RESULTS : The experimental group-in which the artificial intelligence chatbot program was applied-did not show statistically significant differences in knowledge (t = -0.58, p = .567), clinical reasoning competency (t = 0.75, p = .455), confidence (t = 1.13, p = .264), and feedback satisfaction (t = 1.72, p = .090), compared with the control group; however, its participants' interest in education (t = 2.38, p = .020) and self-directed learning (t = 2.72, p = .006) were significantly higher than those in the control group.

CONCLUSION : The findings of our study highlighted the potential of artificial intelligence chatbot programs as an educational assistance tool to promote nursing college students' interest in education and self-directed learning. Moreover, such programs can be effective in enhancing nursing students' skills in non-face-to face-situations caused by the ongoing COVID-19 pandemic.

Han Jeong-Won, Park Junhee, Lee Hanna

2022-Dec-01

Artificial intelligence, Chatbot program, Clinical reasoning, Data processing, Education, Nursing

General General

Analysis of the effect of an artificial intelligence chatbot educational program on non-face-to-face classes: a quasi-experimental study.

In BMC medical education

BACKGROUND : Education and training are needed for nursing students using artificial intelligence-based educational programs. However, few studies have assessed the effect of using chatbots in nursing education.

OBJECTIVES : This study aimed to develop and examine the effect of an artificial intelligence chatbot educational program for promoting nursing skills related to electronic fetal monitoring in nursing college students during non-face-to-face classes during the COVID-19 pandemic.

DESIGN : This quasi-experimental study used a nonequivalent control group non-synchronized pretest-posttest design.

METHODS : The participants were 61 junior students from a nursing college located in G province of South Korea. Data were collected between November 3 and 16, 2021, and analyzed using independent t-tests.

RESULTS : The experimental group-in which the artificial intelligence chatbot program was applied-did not show statistically significant differences in knowledge (t = -0.58, p = .567), clinical reasoning competency (t = 0.75, p = .455), confidence (t = 1.13, p = .264), and feedback satisfaction (t = 1.72, p = .090), compared with the control group; however, its participants' interest in education (t = 2.38, p = .020) and self-directed learning (t = 2.72, p = .006) were significantly higher than those in the control group.

CONCLUSION : The findings of our study highlighted the potential of artificial intelligence chatbot programs as an educational assistance tool to promote nursing college students' interest in education and self-directed learning. Moreover, such programs can be effective in enhancing nursing students' skills in non-face-to face-situations caused by the ongoing COVID-19 pandemic.

Han Jeong-Won, Park Junhee, Lee Hanna

2022-Dec-01

Artificial intelligence, Chatbot program, Clinical reasoning, Data processing, Education, Nursing

General General

On the application of population-based structural health monitoring in aerospace engineering.

In Frontiers in robotics and AI

One of the major obstacles to the widespread uptake of data-based Structural Health Monitoring so far, has been the lack of damage-state data for the (mostly high-value) structures of interest. To address this issue, a methodology for sharing data and models between structures has been developed-Population-Based Structural Health Monitoring (PBSHM). PBSHM works on the principle that, if populations of structures are sufficiently similar, or share sections which can be considered similar, then data and models can be shared between them for use in diagnostic inference. The PBSHM methodology therefore relies on two key components: firstly, identifying whether structures are sufficiently similar for successful transfer of diagnostics; this is achieved by the use of an abstract representation of structures. Secondly, machine learning techniques are exploited to effectively transfer information between the structures in a way that improves damage detection and classification across the whole population. Although PBSHM has been conceived to deal with large and general classes of structures, much of the detailed developments presented so far have concerned bridges; the aim of this paper is to provide similarly detailed discussions in the aerospace context. The overview here will examine data transfer between aircraft components, as well as illustrating how one might construct an abstract representation of a full aircraft.

Brennan Daniel S, Gosliga Julian, Gardner Paul, Mills Robin S, Worden Keith

2022

aerospace engineering, data-based structural health monitoring, fleet-based monitoring, irreducible element modelling, knowledge transfer, machine learning, population-based structural health monitoring, transfer learning

General General

Retracted: The Construction of Sports Health Management Model Based on Deep Learning.

In Applied bionics and biomechanics

[This retracts the article DOI: 10.1155/2022/5194665.].

And Biomechanics Applied Bionics

2022

General General

Tacrolimus pharmacokinetics in pediatric nephrotic syndrome: A combination of population pharmacokinetic modelling and machine learning approaches to improve individual prediction.

In Frontiers in pharmacology

Background and Aim: Tacrolimus (TAC) is a first-line immunosuppressant for the treatment of refractory nephrotic syndrome (RNS), but the pharmacokinetics of TAC varies widely among individuals, and there is still no accurate model to predict the pharmacokinetics of TAC in RNS. Therefore, this study aimed to combine population pharmacokinetic (PPK) model and machine learning algorithms to develop a simple and accurate prediction model for TAC. Methods: 139 children with RNS from August 2013 to December 2018 were included, and blood samples of TAC trough and partial peak concentrations were collected. The blood concentration of TAC was determined by enzyme immunoassay; CYP3A5 was genotyped by polymerase chain reaction-restriction fragment length polymorphism method; MYH9, LAMB2, ACTN4 and other genotypes were determined by MALDI-TOF MS method; PPK model was established by nonlinear mixed-effects method. Based on this, six machine learning algorithms, including eXtreme Gradient Boosting (XGBoost), Random Forest (RF), Extra-Trees, Gradient Boosting Decision Tree (GBDT), Adaptive boosting (AdaBoost) and Lasso, were used to establish the machine learning model of TAC clearance. Results: A one-compartment model of first-order absorption and elimination adequately described the pharmacokinetics of TAC. Age, co-administration of Wuzhi capsules, CYP3A5 *3/*3 genotype and CTLA4 rs4553808 genotype were significantly affecting the clearance of TAC. Among the six machine learning models, the Lasso algorithm model performed the best (R2 = 0.42). Conclusion: For the first time, a clearance prediction model of TAC in pediatric patients with RNS was established using PPK combined with machine learning, by which the individual clearance of TAC can be predicted more accurately, and the initial dose of administration can be optimized to achieve the goal of individualized treatment.

Huang Qiongbo, Lin Xiaobin, Wang Yang, Chen Xiujuan, Zheng Wei, Zhong Xiaoli, Shang Dewei, Huang Min, Gao Xia, Deng Hui, Li Jiali, Zeng Fangling, Mo Xiaolan

2022

gene polymorphisms, machine learning, pediatric nephrotic syndrome, population pharmacokinetic, tacrolimus

General General

Characterization of Epithelial-Mesenchymal Transition Identifies a Gene Signature for Predicting Clinical Outcomes and Therapeutic Responses in Bladder Cancer.

In Disease markers

PURPOSE : The complex etiological variables and high heterogeneity of bladder cancer (BC) make prognostic prediction challenging. We aimed to develop a robust and promising gene signature using advanced machine learning methods for predicting the prognosis and therapy responses of BC patients.

METHODS : The single-sample gene set enrichment analysis (ssGSEA) algorithm and univariable Cox regression were used to identify the primary risk hallmark among the various cancer hallmarks. Machine learning methods were then combined with survival and differential gene expression analyses to construct a novel prognostic signature, which would be validated in two additional independent cohorts. Moreover, relationships between this signature and therapy responses were also identified. Functional enrichment analysis and immune cell estimation were also conducted to provide insights into the potential mechanisms of BC.

RESULTS : Epithelial-mesenchymal transition (EMT) was identified as the primary risk factor for the survival of BC patients (HR=1.43, 95% CI: 1.26-1.63). A novel EMT-related gene signature was constructed and validated in three independent cohorts, showing stable and accurate performance in predicting clinical outcomes. Furthermore, high-risk patients had poor prognoses and multivariable Cox regression analysis revealed this to be an independent risk factor for patient survival. CD8+ T cells, Tregs, and M2 macrophages were found abundantly in the tumor microenvironment of high-risk patients. Moreover, it was anticipated that high-risk patients would be more sensitive to chemotherapeutic drugs, while low-risk patients would benefit more from immunotherapy.

CONCLUSIONS : We successfully identified and validated a novel EMT-related gene signature for predicting clinical outcomes and therapy responses in BC patients, which may be useful in clinical practice for risk stratification and individualized treatment.

Wang Yicun, Zhang Hao, Hu Xiaopeng

2022

General General

Machine learning assisted dynamic phenotypes and genomic variants help understand the ecotype divergence in rapeseed.

In Frontiers in plant science

Three ecotypes of rapeseed, winter, spring, and semi-winter, have been formed to enable the plant to adapt to different geographic areas. Although several major loci had been found to contribute to the flowering divergence, the genomic footprints and associated dynamic plant architecture in the vegetative growth stage underlying the ecotype divergence remain largely unknown in rapeseed. Here, a set of 41 dynamic i-traits and 30 growth-related traits were obtained by high-throughput phenotyping of 171 diverse rapeseed accessions. Large phenotypic variation and high broad-sense heritability were observed for these i-traits across all developmental stages. Of these, 19 i-traits were identified to contribute to the divergence of three ecotypes using random forest model of machine learning approach, and could serve as biomarkers to predict the ecotype. Furthermore, we analyzed genomic variations of the population, QTL information of all dynamic i-traits, and genomic basis of the ecotype differentiation. It was found that 213, 237, and 184 QTLs responsible for the differentiated i-traits overlapped with the signals of ecotype divergence between winter and spring, winter and semi-winter, and spring and semi-winter, respectively. Of which, there were four common divergent regions between winter and spring/semi-winter and the strongest divergent regions between spring and semi-winter were found to overlap with the dynamic QTLs responsible for the differentiated i-traits at multiple growth stages. Our study provides important insights into the divergence of plant architecture in the vegetative growth stage among the three ecotypes, which was contributed to by the genetic differentiation, and might contribute to environmental adaption and yield improvement.

Feng Hui, Guo Chaocheng, Li Zongyi, Gao Yuan, Zhang Qinghua, Geng Zedong, Wang Jing, Chen Guoxing, Liu Kede, Li Haitao, Yang Wanneng

2022

dynamic phenotyping, ecotype, machine learning, quantitative trait loci, rapeseed

Radiology Radiology

Automated lesion detection of breast cancer in [18F] FDG PET/CT using a novel AI-Based workflow.

In Frontiers in oncology

UNLABELLED : Applications based on artificial intelligence (AI) and deep learning (DL) are rapidly being developed to assist in the detection and characterization of lesions on medical images. In this study, we developed and examined an image-processing workflow that incorporates both traditional image processing with AI technology and utilizes a standards-based approach for disease identification and quantitation to segment and classify tissue within a whole-body [18F]FDG PET/CT study.

METHODS : One hundred thirty baseline PET/CT studies from two multi-institutional preoperative clinical trials in early-stage breast cancer were semi-automatically segmented using techniques based on PERCIST v1.0 thresholds and the individual segmentations classified as to tissue type by an experienced nuclear medicine physician. These classifications were then used to train a convolutional neural network (CNN) to automatically accomplish the same tasks.

RESULTS : Our CNN-based workflow demonstrated Sensitivity at detecting disease (either primary lesion or lymphadenopathy) of 0.96 (95% CI [0.9, 1.0], 99% CI [0.87,1.00]), Specificity of 1.00 (95% CI [1.0,1.0], 99% CI [1.0,1.0]), DICE score of 0.94 (95% CI [0.89, 0.99], 99% CI [0.86, 1.00]), and Jaccard score of 0.89 (95% CI [0.80, 0.98], 99% CI [0.74, 1.00]).

CONCLUSION : This pilot work has demonstrated the ability of AI-based workflow using DL-CNNs to specifically identify breast cancer tissue as determined by [18F]FDG avidity in a PET/CT study. The high sensitivity and specificity of the network supports the idea that AI can be trained to recognize specific tissue signatures, both normal and disease, in molecular imaging studies using radiopharmaceuticals. Future work will explore the applicability of these techniques to other disease types and alternative radiotracers, as well as explore the accuracy of fully automated and quantitative detection and response assessment.

Leal Jeffrey P, Rowe Steven P, Stearns Vered, Connolly Roisin M, Vaklavas Christos, Liu Minetta C, Storniolo Anna Maria, Wahl Richard L, Pomper Martin G, Solnes Lilja B

2022

PERCIST v1.0, artificial intelligence, breast cancer, deep learning, machine learning

Pathology Pathology

Data-driven support to decision-making in molecular tumour boards for lymphoma: A design science approach.

In Frontiers in oncology

BACKGROUND : The increasing amount of molecular data and knowledge about genomic alterations from next-generation sequencing processes together allow for a greater understanding of individual patients, thereby advancing precision medicine. Molecular tumour boards feature multidisciplinary teams of clinical experts who meet to discuss complex individual cancer cases. Preparing the meetings is a manual and time-consuming process.

PURPOSE : To design a clinical decision support system to improve the multimodal data interpretation in molecular tumour board meetings for lymphoma patients at Karolinska University Hospital, Stockholm, Sweden. We investigated user needs and system requirements, explored the employment of artificial intelligence, and evaluated the proposed design with primary stakeholders.

METHODS : Design science methodology was used to form and evaluate the proposed artefact. Requirements elicitation was done through a scoping review followed by five semi-structured interviews. We used UML Use Case diagrams to model user interaction and UML Activity diagrams to inform the proposed flow of control in the system. Additionally, we modelled the current and future workflow for MTB meetings and its proposed machine learning pipeline. Interactive sessions with end-users validated the initial requirements based on a fictive patient scenario which helped further refine the system.

RESULTS : The analysis showed that an interactive secure Web-based information system supporting the preparation of the meeting, multidisciplinary discussions, and clinical decision-making could address the identified requirements. Integrating artificial intelligence via continual learning and multimodal data fusion were identified as crucial elements that could provide accurate diagnosis and treatment recommendations.

IMPACT : Our work is of methodological importance in that using artificial intelligence for molecular tumour boards is novel. We provide a consolidated proof-of-concept system that could support the end-to-end clinical decision-making process and positively and immediately impact patients.

CONCLUSION : Augmenting a digital decision support system for molecular tumour boards with retrospective patient material is promising. This generates realistic and constructive material for human learning, and also digital data for continual learning by data-driven artificial intelligence approaches. The latter makes the future system adaptable to human bias, improving adequacy and decision quality over time and over tasks, while building and maintaining a digital log.

Rodríguez Ruiz Núria, Abd Own Sulaf, Ekström Smedby Karin, Eloranta Sandra, Koch Sabine, Wästerlid Tove, Krstic Aleksandra, Boman Magnus

2022

artificial intelligence, clinical decision support system, lymphoma, molecular tumour board, multimodal data, next-generation sequencing, precision medicine

General General

An Acute Kidney Injury Prediction Model for 24-hour Ultramarathon Runners.

In Journal of human kinetics

Acute kidney injury (AKI) is frequently seen in ultrarunners, and in this study, an AKI prediction model for 24-hour ultrarunners was built based on the runner's prerace blood, urine, and body composition data. Twenty-two ultrarunners participated in the study. The risk of acquiring AKI was evaluated by a support vector machine (SVM) model, which is a statistical model commonly used for classification tasks. The inputs of the SVM model were the data collected 1 hour before the race, and the output of the SVM model was the decision of acquiring AKI. Our best AKI prediction model achieved accuracy of 96% in training and 90% in cross-validation tests. In addition, the sensitivity and specificity of the model were 90% and 100%, respectively. In accordance with the AKI prediction model components, ultra-runners are suggested to have high muscle mass and undergo regular ultra-endurance sports training to reduce the risk of acquiring AKI after participating in a 24-hour ultramarathon.

Hsu Po-Ya, Hsu Yi-Chung, Liu Hsin-Li, Fong Kao Wei, Lin Kuan-Yu

2022-Oct

acute kidney injury, extreme sports, injury prevention, machine learning

Radiology Radiology

Artificial intelligence in gastric cancer: applications and challenges.

In Gastroenterology report

Gastric cancer (GC) is one of the most common malignant tumors with high mortality. Accurate diagnosis and treatment decisions for GC rely heavily on human experts' careful judgments on medical images. However, the improvement of the accuracy is hindered by imaging conditions, limited experience, objective criteria, and inter-observer discrepancies. Recently, the developments of machine learning, especially deep-learning algorithms, have been facilitating computers to extract more information from data automatically. Researchers are exploring the far-reaching applications of artificial intelligence (AI) in various clinical practices, including GC. Herein, we aim to provide a broad framework to summarize current research on AI in GC. In the screening of GC, AI can identify precancerous diseases and assist in early cancer detection with endoscopic examination and pathological confirmation. In the diagnosis of GC, AI can support tumor-node-metastasis (TNM) staging and subtype classification. For treatment decisions, AI can help with surgical margin determination and prognosis prediction. Meanwhile, current approaches are challenged by data scarcity and poor interpretability. To tackle these problems, more regulated data, unified processing procedures, and advanced algorithms are urgently needed to build more accurate and robust AI models for GC.

Cao Runnan, Tang Lei, Fang Mengjie, Zhong Lianzhen, Wang Siwen, Gong Lixin, Li Jiazheng, Dong Di, Tian Jie

2022

artificial intelligence, computed tomography, endoscopy, gastric cancer, pathology, radiomics

General General

TSHVNet: Simultaneous Nuclear Instance Segmentation and Classification in Histopathological Images Based on Multiattention Mechanisms.

In BioMed research international ; h5-index 102.0

Accurate nuclear instance segmentation and classification in histopathologic images are the foundation of cancer diagnosis and prognosis. Several challenges are restricting the development of accurate simultaneous nuclear instance segmentation and classification. Firstly, the visual appearances of different category nuclei could be similar, making it difficult to distinguish different types of nuclei. Secondly, it is thorny to separate highly clustering nuclear instances. Thirdly, rare current studies have considered the global dependencies among diverse nuclear instances. In this article, we propose a novel deep learning framework named TSHVNet which integrates multiattention modules (i.e., Transformer and SimAM) into the state-of-the-art HoVer-Net for the sake of a more accurate nuclear instance segmentation and classification. Specifically, the Transformer attention module is employed on the trunk of the HoVer-Net to model the long-distance relationships of diverse nuclear instances. The SimAM attention modules are deployed on both the trunk and branches to apply the 3D channel and spatial attention to assign neurons with appropriate weights. Finally, we validate the proposed method on two public datasets: PanNuke and CoNSeP. The comparison results have shown the outstanding performance of the proposed TSHVNet network among the state-of-art methods. Particularly, as compared to the original HoVer-Net, the performance of nuclear instance segmentation evaluated by the PQ index has shown 1.4% and 2.8% increases on the CoNSeP and PanNuke datasets, respectively, and the performance of nuclear classification measured by F1_score has increased by 2.4% and 2.5% on the CoNSeP and PanNuke datasets, respectively. Therefore, the proposed multiattention-based TSHVNet is of great potential in simultaneous nuclear instance segmentation and classification.

Chen Yuli, Jia Yuhang, Zhang Xinxin, Bai Jiayang, Li Xue, Ma Miao, Sun Zengguo, Pei Zhao

2022

Surgery Surgery

Automatic Detection of Horner Syndrome by Using Facial Images.

In Journal of healthcare engineering

Horner syndrome is a clinical constellation that presents with miosis, ptosis, and facial anhidrosis. It is important as a warning sign of the damaged oculosympathetic chain, potentially with serious causes. However, the diagnosis of Horner syndrome is operator dependent and subjective. This study aims to present an objective method that can recognize Horner sign from facial photos and verify its accuracy. A total of 173 images were collected, annotated, and divided into training and testing groups. Two types of classifiers were trained (two-stage classifier and one-stage classifier). The two-stage method utilized the MediaPipe face mesh to estimate the coordinates of landmarks and generate facial geometric features accordingly. Then, ten machine learning classifiers were trained based on this. The one-stage classifier was trained based on one of the latest algorithms, YOLO v5. The performance of the classifier was evaluated by the diagnosis accuracy, sensitivity, and specificity. For the two-stage model, the MediaPipe successfully detected 92.2% of images in the testing group, and the Decision Tree Classifier presented the highest accuracy (0.790). The sensitivity and specificity of this classifier were 0.432 and 0.970, respectively. As for the one-stage classifier, the accuracy, sensitivity, and specificity were 0.65, 0.51, and 0.84, respectively. The results of this study proved the possibility of automatic detection of Horner syndrome from images. This tool could work as a second advisor for neurologists by reducing subjectivity and increasing accuracy in diagnosing Horner syndrome.

Fan Jingyuan, Qin Bengang, Gu Fanbin, Wang Zhaoyang, Liu Xiaolin, Zhu Qingtang, Yang Jiantao

2022

Public Health Public Health

Data-driven identification of post-acute SARS-CoV-2 infection subphenotypes.

In Nature medicine ; h5-index 170.0

The post-acute sequelae of SARS-CoV-2 infection (PASC) refers to a broad spectrum of symptoms and signs that are persistent, exacerbated or newly incident in the period after acute SARS-CoV-2 infection. Most studies have examined these conditions individually without providing evidence on co-occurring conditions. In this study, we leveraged the electronic health record data of two large cohorts, INSIGHT and OneFlorida+, from the national Patient-Centered Clinical Research Network. We created a development cohort from INSIGHT and a validation cohort from OneFlorida+ including 20,881 and 13,724 patients, respectively, who were SARS-CoV-2 infected, and we investigated their newly incident diagnoses 30-180 days after a documented SARS-CoV-2 infection. Through machine learning analysis of over 137 symptoms and conditions, we identified four reproducible PASC subphenotypes, dominated by cardiac and renal (including 33.75% and 25.43% of the patients in the development and validation cohorts); respiratory, sleep and anxiety (32.75% and 38.48%); musculoskeletal and nervous system (23.37% and 23.35%); and digestive and respiratory system (10.14% and 12.74%) sequelae. These subphenotypes were associated with distinct patient demographics, underlying conditions before SARS-CoV-2 infection and acute infection phase severity. Our study provides insights into the heterogeneity of PASC and may inform stratified decision-making in the management of PASC conditions.

Zhang Hao, Zang Chengxi, Xu Zhenxing, Zhang Yongkang, Xu Jie, Bian Jiang, Morozyuk Dmitry, Khullar Dhruv, Zhang Yiye, Nordvig Anna S, Schenck Edward J, Shenkman Elizabeth A, Rothman Russell L, Block Jason P, Lyman Kristin, Weiner Mark G, Carton Thomas W, Wang Fei, Kaushal Rainu

2022-Dec-01

General General

Evaluation of roadside air quality using deep learning models after the application of the diesel vehicle policy (Euro 6).

In Scientific reports ; h5-index 158.0

Euro 6 is the latest vehicle emission standards for pollutants such as CO, NO2 and PM, that all new vehicles must comply, and it was introduced in September 2015 in South Korea. This study examined the effect of Euro 6 by comparing the measured pollutant concentrations after 2016 (Euro 6-era) to the estimated concentrations without Euro 6. The concentration without Euro 6 was estimated by first modeling the air quality using various environmental factors related to diesel vehicles, meteorological conditions, temporal information such as date and precursors in 2002-2015 (pre-Euro 6-era), and then applying the model to predict the concentration after 2016. In this study, we used both recurrent neural network (RNN) and random forest (RF) algorithms to model the air quality and showed that RNN can achieve higher R2 (0.634 ~ 0.759 depending on pollutants) than RF, making it more suitable for air quality modeling. According to our results, the measured concentrations during 2016-2019 were lower than the concentrations predicted using RNN by - 1.2%, - 3.4%, and - 4.8% for CO, NO2 and PM10. Such reduction can be attributed to the result of Euro 6.

Hwang Hyemin, Choi Sung Rak, Lee Jae Young

2022-Dec-01

Radiology Radiology

Chronic Mild Traumatic Brain Injury: Aberrant Static and Dynamic Connectomic Features Identified Through Machine Learning Model Fusion.

In Neuroinformatics

Traumatic Brain Injury (TBI) is a frequently occurring condition and approximately 90% of TBI cases are classified as mild (mTBI). However, conventional MRI has limited diagnostic and prognostic value, thus warranting the utilization of additional imaging modalities and analysis procedures. The functional connectomic approach using resting-state functional MRI (rs-fMRI) has shown great potential and promising diagnostic capabilities across multiple clinical scenarios, including mTBI. Additionally, there is increasing recognition of a fundamental role of brain dynamics in healthy and pathological cognition. Here, we undertake an in-depth investigation of mTBI-related connectomic disturbances and their emotional and cognitive correlates. We leveraged machine learning and graph theory to combine static and dynamic functional connectivity (FC) with regional entropy values, achieving classification accuracy up to 75% (77, 74 and 76% precision, sensitivity and specificity, respectively). As compared to healthy controls, the mTBI group displayed hypoconnectivity in the temporal poles, which correlated positively with semantic (r = 0.43, p < 0.008) and phonemic verbal fluency (r = 0.46, p < 0.004), while hypoconnectivity in the right dorsal posterior cingulate correlated positively with depression symptom severity (r = 0.54, p < 0.0006). These results highlight the importance of residual FC in these regions for preserved cognitive and emotional function in mTBI. Conversely, hyperconnectivity was observed in the right precentral and supramarginal gyri, which correlated negatively with semantic verbal fluency (r=-0.47, p < 0.003), indicating a potential ineffective compensatory mechanism. These novel results are promising toward understanding the pathophysiology of mTBI and explaining some of its most lingering emotional and cognitive symptoms.

Simos Nicholas J, Manolitsi Katina, Luppi Andrea I, Kagialis Antonios, Antonakakis Marios, Zervakis Michalis, Antypa Despina, Kavroulakis Eleftherios, Maris Thomas G, Vakis Antonios, Stamatakis Emmanuel A, Papadaki Efrosini

2022-Dec-02

Depression, Functional Connectivity, Traumatic Brain Injury, Verbal Fluency, fMRI

General General

Hybrid the long short-term memory with whale optimization algorithm and variational mode decomposition for monthly evapotranspiration estimation.

In Scientific reports ; h5-index 158.0

The sustainability of artificial sand-binding vegetation is determined by the water balance between evapotranspiration (ET) and precipitation in desert regions. Consequently, accurately estimating ET is a critical prerequisite for determing the types and spatial distribution of artificial vegetation in different sandy areas. For this purpose, a novel hybrid estimation model was proposed to estimate monthly ET by coupling the deep learning long short term memory (LSTM) with variational mode decomposition (VMD) and whale optimization algorithm (WOA) (i.e., VMD-WOA-LSTM) to estimate the monthly ET in the southeast margins of Tengger Desert. The superiority of LSTM was selected due to its capability of automatically extracting the nonlinear and nonstationary features from sequential data, WOA was employed to optimize the hyperparameters of LSTM, and VMD was used to extract the intrinsic traits of ET time series. The estimating results of VMD-WOA-LSTM has been compared with actual ET and estimation of other hybrid models in terms of standard performance metrics. The results reveale that VMD-WOA-LSTM provide more accurate and reliable estimating results than that of LSTM, the support vector machine (SVM), and the variants of those models. Therefore, VMD-WOA-LSTM could be recommended as an essential auxiliary method to estimate ET in desert regions.

Fu Tonglin, Li Xinrong

2022-Dec-01

Radiology Radiology

Prediction of left lobe hypertrophy after right lobe radioembolization of the liver using a clinical data model with external validation.

In Scientific reports ; h5-index 158.0

In cirrhotic patients with hepatocellular carcinoma (HCC), right-sided radioembolization (RE) with Yttrium-90-loaded microspheres is an established palliative therapy and can be considered a "curative intention" treatment when aiming for sequential tumor resection. To become surgical candidate, hypertrophy of the left liver lobe to > 40% (future liver remnant, FLR) is mandatory, which can develop after RE. The amount of radiation-induced shrinkage of the right lobe and compensatory hypertrophy of the left lobe is difficult for clinicians to predict. This study aimed to utilize machine learning to predict left lobe liver hypertrophy in patients with HCC and cirrhosis scheduled for right lobe RE, with external validation. The results revealed that machine learning can accurately predict relative and absolute volume changes of the left liver lobe after right lobe RE. This prediction algorithm could help to estimate the chances of conversion from palliative RE to curative major hepatectomy following significant FLR hypertrophy.

Theysohn Jens M, Demircioglu Aydin, Kleditzsch Malte, Ludwig Johannes M, Weber Manuel, Umutlu Lale, Li Yan, Kircher Malte, Lapa Constantin, Buck Andreas, Koehler Michael, Wildgruber Moritz, Lange Christian M, Palard Xavier, Garin Etienne, Herrmann Ken, Forsting Michael, Nensa Felix

2022-Dec-01

General General

Future tree survival in European forests depends on understorey tree diversity.

In Scientific reports ; h5-index 158.0

Climate change heavily threatens forest ecosystems worldwide and there is urgent need to understand what controls tree survival and forests stability. There is evidence that biodiversity can enhance ecosystem stability (Loreau and de Mazancourt in Ecol Lett 16:106-115, 2013; McCann in Nature 405:228-233, 2000), however it remains largely unclear whether this also holds for climate change and what aspects of biodiversity might be most important. Here we apply machine learning to outputs of a flexible-trait Dynamic Global Vegetation Model to unravel the effects of enhanced functional tree trait diversity and its sub-components on climate-change resistance of temperate forests ( http://www.pik-potsdam.de/~billing/video/Forest_Resistance_LPJmLFIT.mp4 ). We find that functional tree trait diversity enhances forest resistance. We explain this with 1. stronger complementarity effects (~ 25% importance) especially improving the survival of trees in the understorey of up to + 16.8% (± 1.6%) and 2. environmental and competitive filtering of trees better adapted to future climate (40-87% importance). We conclude that forests containing functionally diverse trees better resist and adapt to future conditions. In this context, we especially highlight the role of functionally diverse understorey trees as they provide the fundament for better survival of young trees and filtering of resistant tree individuals in the future.

Billing Maik, Thonicke Kirsten, Sakschewski Boris, von Bloh Werner, Walz Ariane

2022-Dec-01

General General

A Dataset with Multibeam Forward-Looking Sonar for Underwater Object Detection.

In Scientific data

Multibeam forward-looking sonar (MFLS) plays an important role in underwater detection. There are several challenges to the research on underwater object detection with MFLS. Firstly, the research is lack of available dataset. Secondly, the sonar image, generally processed at pixel level and transformed to sector representation for the visual habits of human beings, is disadvantageous to the research in artificial intelligence (AI) areas. Towards these challenges, we present a novel dataset, the underwater acoustic target detection (UATD) dataset, consisting of over 9000 MFLS images captured using Tritech Gemini 1200ik sonar. Our dataset provides raw data of sonar images with annotation of 10 categories of target objects (cube, cylinder, tyres, etc). The data was collected from lake and shallow water. To verify the practicality of UATD, we apply the dataset to the state-of-the-art detectors and provide corresponding benchmarks for its accuracy and efficiency.

Xie Kaibing, Yang Jian, Qiu Kang

2022-Dec-01

General General

UPRLIMET: UPstream Regional LiDAR Model for Extent of Trout in stream networks.

In Scientific reports ; h5-index 158.0

Predicting the edges of species distributions is fundamental for species conservation, ecosystem services, and management decisions. In North America, the location of the upstream limit of fish in forested streams receives special attention, because fish-bearing portions of streams have more protections during forest management activities than fishless portions. We present a novel model development and evaluation framework, wherein we compare 26 models to predict upper distribution limits of trout in streams. The models used machine learning, logistic regression, and a sophisticated nested spatial cross-validation routine to evaluate predictive performance while accounting for spatial autocorrelation. The model resulting in the best predictive performance, termed UPstream Regional LiDAR Model for Extent of Trout (UPRLIMET), is a two-stage model that uses a logistic regression algorithm calibrated to observations of Coastal Cutthroat Trout (Oncorhynchus clarkii clarkii) occurrence and variables representing hydro-topographic characteristics of the landscape. We predict trout presence along reaches throughout a stream network, and include a stopping rule to identify a discrete upper limit point above which all stream reaches are classified as fishless. Although there is no simple explanation for the upper distribution limit identified in UPRLIMET, four factors, including upstream channel length above the point of uppermost fish, drainage area, slope, and elevation, had highest importance. Across our study region of western Oregon, we found that more of the fish-bearing network is on private lands than on state, US Bureau of Land Mangement (BLM), or USDA Forest Service (USFS) lands, highlighting the importance of using spatially consistent maps across a region and working across land ownerships. Our research underscores the value of using occurrence data to develop simple, but powerful, prediction tools to capture complex ecological processes that contribute to distribution limits of species.

Penaluna Brooke E, Burnett Jonathan D, Christiansen Kelly, Arismendi Ivan, Johnson Sherri L, Griswold Kitty, Holycross Brett, Kolstoe Sonja H

2022-Dec-01

General General

An integrated resource for functional and structural connectivity of the marmoset brain.

In Nature communications ; h5-index 260.0

Comprehensive integration of structural and functional connectivity data is required to model brain functions accurately. While resources for studying the structural connectivity of non-human primate brains already exist, their integration with functional connectivity data has remained unavailable. Here we present a comprehensive resource that integrates the most extensive awake marmoset resting-state fMRI data available to date (39 marmoset monkeys, 710 runs, 12117 mins) with previously published cellular-level neuronal tracing data (52 marmoset monkeys, 143 injections) and multi-resolution diffusion MRI datasets. The combination of these data allowed us to (1) map the fine-detailed functional brain networks and cortical parcellations, (2) develop a deep-learning-based parcellation generator that preserves the topographical organization of functional connectivity and reflects individual variabilities, and (3) investigate the structural basis underlying functional connectivity by computational modeling. This resource will enable modeling structure-function relationships and facilitate future comparative and translational studies of primate brains.

Tian Xiaoguang, Chen Yuyan, Majka Piotr, Szczupak Diego, Perl Yonatan Sanz, Yen Cecil Chern-Chyi, Tong Chuanjun, Feng Furui, Jiang Haiteng, Glen Daniel, Deco Gustavo, Rosa Marcello G P, Silva Afonso C, Liang Zhifeng, Liu Cirong

2022-Dec-01

General General

Machine learning modeling practices to support the principles of AI and ethics in nutrition research.

In Nutrition & diabetes

BACKGROUND : Nutrition research is relying more on artificial intelligence and machine learning models to understand, diagnose, predict, and explain data. While artificial intelligence and machine learning models provide powerful modeling tools, failure to use careful and well-thought-out modeling processes can lead to misleading conclusions and concerns surrounding ethics and bias.

METHODS : Based on our experience as reviewers and journal editors in nutrition and obesity, we identified the most frequently omitted best practices from statistical modeling and how these same practices extend to machine learning models. We next addressed areas required for implementation of machine learning that are not included in commercial software packages.

RESULTS : Here, we provide a tutorial on best artificial intelligence and machine learning modeling practices that can reduce potential ethical problems with a checklist and guiding principles to aid nutrition researchers in developing, evaluating, and implementing artificial intelligence and machine learning models in nutrition research.

CONCLUSION : The quality of AI/ML modeling in nutrition research requires iterative and tailored processes to mitigate against potential ethical problems or to predict conclusions that are free of bias.

Thomas Diana M, Kleinberg Samantha, Brown Andrew W, Crow Mason, Bastian Nathaniel D, Reisweber Nicholas, Lasater Robert, Kendall Thomas, Shafto Patrick, Blaine Raymond, Smith Sarah, Ruiz Daniel, Morrell Christopher, Clark Nicholas

2022-Dec-02

Radiology Radiology

Comparative analysis of popular predictors for difficult laryngoscopy using hybrid intelligent detection methods.

In Heliyon

Difficult laryngoscopy is associated with airway injury, and asphyxia. There are no guidelines or gold standards for detecting difficult laryngoscopy. There are many opinions on which predictors to use to detect difficult laryngoscopy exposure, and no comprehensively unified comparative analysis has been conducted. The efficacy and accuracy of deep learning (DL)-based models and machine learning (ML)-based models for predicting difficult laryngoscopy need to be evaluated and compared, under the circumstance that the flourishing of deep neural networks (DNN) has increasingly left ML less concentrated and uncreative. For the first time, the performance of difficult laryngoscopy prediction for a dataset of 671 patients, under single index and integrated multiple indicators was consistently verified under seven ML-based models and four DL-based approaches. The top dog was a simple traditional machine learning model, Naïve Bayes, outperforming DL-based models, the best test accuracy is 86.6%, the F1 score is 0.908, and the average precision score is 0.837. Three radiological variables of difficult laryngoscopy were all valuable separately and combinedly and the ranking was presented. There is no significant difference in performance among the three radiological indicators individually (83.06% vs. 83.20% vs. 83.33%) and comprehensively (83.74%), suggesting that anesthesiologists can flexibly choose appropriate measurement indicators according to the actual situation to predict difficult laryngoscopy. Adaptive spatial interaction was imposed to the model to boost the performance of difficult laryngoscopy prediction with preoperative cervical spine X-ray.

Liu Xiaoxiao, Flanagan Colin, Fang Jingchao, Lei Yiming, McGrath Launcelot, Wang Jun, Guo Xiangyang, Guo Jiangzhen, McGrath Harry, Han Yongzheng

2022-Nov

Airway management, Anesthesiology, Difficult laryngoscopy, Laryngoscope exposure, Machine learning

Radiology Radiology

Clinical-radiomics predictors to identify the suitability of transarterial chemoembolization treatment in intermediate-stage hepatocellular carcinoma: A multicenter study.

In Hepatobiliary & pancreatic diseases international : HBPD INT

BACKGROUND : Although transarterial chemoembolization (TACE) is the first-line therapy for intermediate-stage hepatocellular carcinoma (HCC), it is not suitable for all patients. This study aimed to determine how to select patients who are not suitable for TACE as the first treatment choice.

METHODS : A total of 243 intermediate-stage HCC patients treated with TACE at three centers were retrospectively enrolled, of which 171 were used for model training and 72 for testing. Radiomics features were screened using the Spearman correlation analysis and the least absolute shrinkage and selection operator (LASSO) algorithm. Subsequently, a radiomics model was established using extreme gradient boosting (XGBoost) with 5-fold cross-validation. The Shapley additive explanations (SHAP) method was used to visualize the radiomics model. A clinical model was constructed using univariate and multivariate logistic regression. The combined model comprising the radiomics signature and clinical factors was then established. This model's performance was evaluated by discrimination, calibration, and clinical application. Generalization ability was evaluated by the testing cohort. Finally, the model was used to analyze overall and progression-free survival of different groups.

RESULTS : A third of the patients (81/243) were unsuitable for TACE treatment. The combined model had a high degree of accuracy as it identified TACE-unsuitable cases, at a sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) of 0.759, 0.885, 0.906 [95% confidence interval (CI): 0.859-0.953] in the training and 0.826, 0.776, and 0.894 (95% CI: 0.815-0.972) in the testing cohort, respectively.

CONCLUSIONS : The high degree of accuracy of our clinical-radiomics model makes it clinically useful in identifying intermediate-stage HCC patients who are unsuitable for TACE treatment.

Wang Dan-Dan, Zhang Jin-Feng, Zhang Lin-Han, Niu Meng, Jiang Hui-Jie, Jia Fu-Cang, Feng Shi-Ting

2022-Nov-22

Hepatocellular carcinoma, Machine learning, Prediction, Radiomics, Transarterial chemoembolization

General General

Machine learning in bioprocess development: from promise to practice.

In Trends in biotechnology

Fostered by novel analytical techniques, digitalization, and automation, modern bioprocess development provides large amounts of heterogeneous experimental data, containing valuable process information. In this context, data-driven methods like machine learning (ML) approaches have great potential to rationally explore large design spaces while exploiting experimental facilities most efficiently. Herein we demonstrate how ML methods have been applied so far in bioprocess development, especially in strain engineering and selection, bioprocess optimization, scale-up, monitoring, and control of bioprocesses. For each topic, we will highlight successful application cases, current challenges, and point out domains that can potentially benefit from technology transfer and further progress in the field of ML.

Helleckes Laura M, Hemmerich Johannes, Wiechert Wolfgang, von Lieres Eric, Grünberger Alexander

2022-Nov-28

bioprocess development, machine learning, process analytical technology, process control, process scale-up, strain selection

General General

Underwater-art: Expanding information perspectives with text templates for underwater acoustic target recognition.

In The Journal of the Acoustical Society of America

Underwater acoustic target recognition is an intractable task due to the complex acoustic source characteristics and sound propagation patterns. Limited by insufficient data and narrow information perspective, recognition models based on deep learning seem far from satisfactory in practical underwater scenarios. Although underwater acoustic signals are severely influenced by distance, channel depth, or other factors, annotations of relevant information are often nonuniform, incomplete, and hard to use. In this work, the proposal is to implement underwater acoustic recognition based on templates made up of rich relevant information (UART). The templates are designed to integrate relevant information from different perspectives into descriptive natural language. UART adopts an audio-spectrogram-text trimodal contrastive learning framework, which endows UART with the ability to guide the learning of acoustic representations by descriptive natural language. These experiments reveal that UART has better recognition capability and generalization performance than traditional paradigms. Furthermore, the pretrained UART model could provide superior prior knowledge for the recognition model in the scenario without any auxiliary annotation.

Xie Yuan, Ren Jiawei, Xu Ji

2022-Nov

General General

Fast grid-free strength mapping of multiple sound sources from microphone array data using a Transformer architecture.

In The Journal of the Acoustical Society of America

Conventional microphone array methods for the characterization of sound sources that require a focus-grid are, depending on the grid resolution, either computationally demanding or limited in reconstruction accuracy. This paper presents a deep learning method for grid-free source characterization using a Transformer architecture that is exclusively trained with simulated data. Unlike previous grid-free model architectures, the presented approach requires a single model to characterize an unknown number of ground-truth sources. The model predicts a set of source components, spatially arranged in clusters. Integration over the predicted cluster components allows for the determination of the strength for each ground-truth source individually. Fast and accurate source mapping performance of up to ten sources at different frequencies is demonstrated and strategies to reduce the training effort at neighboring frequencies are given. A comparison with the established grid-based CLEAN-SC and a probabilistic sparse Bayesian learning method on experimental data emphasizes the validity of the approach.

Kujawski Adam, Sarradj Ennes

2022-Nov

Surgery Surgery

Predicting Overall Survival Using Machine Learning Algorithms in Oral Cavity Squamous Cell Carcinoma.

In Anticancer research

BACKGROUND/AIM : Machine learning (ML) models are often modelled to predict cancer prognosis but rarely consider spatial factors in a region. Hence this study explored machine learning algorithms utilising Local Government Areas (LGAs) in Queensland, Australia to spatially predict 3- and 5-year prognosis of oral cancer patients and provide clinical interpretability of the predicted outcome made by the ML model.

PATIENTS AND METHODS : Data from a total of 3,841 oral cancer patients were retrieved from the Queensland Cancer Registry (QCR). Synthesizing minority oversampling technique together with edited nearest neighbours (SMOTE-ENN) was used to pre-process unbalanced datasets. Five ML models: logistic regression, random forest classifier, XGBoost, Gaussian Naïve Bayes and Voting Classifier were trained. Predictive features were age, sex, LGAs, tumour site and differentiation. Outcomes were 3- and 5-year overall survival of patients. Model performances on test set were evaluated using area under the curve and F1 scores. SHapley Additive exPlanations (SHAP) method was applied to the best performing model for model interpretation of the predicted outcome.

RESULTS : The Voting Classifier was the best performing model with F1 score of 0.58 and 0.64 for 3- and 5-year overall survival, respectively. Age was the most important feature in the Voting Classifier in 3- and 5-year prognosis prediction. LGAs at diagnosis was the top 3 predictive feature for both 3- and 5-year models.

CONCLUSION : The Voting Classifier demonstrated the best overall performance in classifying both 3- and 5-year overall survival of oral cancer patients in Queensland. SHAP method provided clinical understanding of the predictive features of the Voting Classifier.

Tan Jia Yan, Adeoye John, Thomson Peter, Sharma Dileep, Ramamurthy Poornima, Choi Siu-Wai

2022-Dec

Oral cavity cancer, SHapley values, interpretability, machine learning, prognosis

Pathology Pathology

A Machine Learning Approach Using PET/CT-based Radiomics for Prediction of PD-L1 Expression in Non-small Cell Lung Cancer.

In Anticancer research

BACKGROUND/AIM : We explored the prediction of programmed cell death ligand 1 (PD-L1) expression level in non-small cell lung cancer using a machine learning approach with positron emission tomography/computed tomography (PET/CT)-based radiomics.

PATIENTS AND METHODS : A total of 312 patients (189 adenocarcinomas, 123 squamous cell carcinomas) who underwent F-18 fluorodeoxyglucose PET/CT were retrospectively analysed. Imaging biomarkers with 46 CT and 48 PET radiomic features were extracted from segmented tumours on PET and CT images using the LIFEx package. Radiomic features were ranked, and the top five best feature subsets were selected using the Gini index based on associations with PD-L1 expression in at least 50% of tumour cells. The areas under the receiver operating characteristic curves (AUCs) of binary classifications afforded by several machine learning algorithms (random forest, neural network, Naïve Bayes, logistic regression, adaptive boosting, stochastic gradient descent, support vector machine) were compared. The model performances were tested by 10-fold cross validation.

RESULTS : We developed and validated a PET/CT-based radiomic model predicting PD-L1 expression levels in lung cancer. Long run high grey-level emphasis, homogeneity, mean Hounsfield unit, long run emphasis from CT, and maximum standardised uptake value from PET were the five best feature subsets for positive PD-L1 expression. The Naïve Bayes model (AUC=0.712), with a sensitivity of 75.3% and specificity of 58.2%, outperformed all other classifiers. It was followed by the neural network model (AUC=0.711), random forest (AUC=0.700), logistic regression (AUC=0.673) and adaptive boosting (AUC=0.604).

CONCLUSION : PET/CT-based radiomic features may help clinicians identify tumours with positive PD-L1 expression in a non-invasive manner using machine learning algorithms.

Lim Chae Hong, Koh Young Wha, Hyun Seung Hyup, Lee Su Jin

2022-Dec

Non-small cell lung cancer, PD-L1, PET/CT, machine learning, texture analysis

Pathology Pathology

Chronological Change in EPHA2 Protein Expression Is Associated With Recurrence of Bladder Cancer.

In Anticancer research

BACKGROUND/AIM : Bladder cancer is the most common urinary tract cancer. Patients diagnosed with advanced T-stage/muscle-invasive bladder cancer through transurethral resection of bladder tumors (TURBT) are treated with total radical cystectomy; however, there is a high chance of recurrence. Nevertheless, markers for predicting this recurrence are not currently available. Here, we evaluated the chronological change of ephrin type-A receptor 2 (EPHA2) expression, a molecule known for its role in cell adhesion, to predict bladder cancer recurrence after cystectomy, using TURBT and cystectomy specimens.

MATERIALS AND METHODS : An immunostaining evaluation method that combines whole-slide images and image analysis software was developed to quantify and evaluate stainability objectively. We assessed the correlation between EPHA2 expression and bladder cancer recurrence using this novel immunostaining method and chronological changes in target protein expression in TURBT and radical cystectomy samples.

RESULTS : In TURBT specimens, the number of cases with a high N-terminal/C-terminal EPHA2 ratio in the group with recurrence was significantly higher than in the non-recurrent group (p=0.019). The number of cases with a high level of C-terminal EPHA2 positivity in the radical cystectomy specimen when compared to the TURBT specimen obtained from the same patient was significantly higher in the recurrent group than in the non-recurrent group (p=0.0034).

CONCLUSION : EPHA2 appears to be a promising marker for bladder tumor recurrence after cystectomy and its evaluation may enable the selection of appropriate cases for adjuvant therapy among patients undergoing radical cystectomy. Further studies, including mass-scale analysis, are required to confirm these results.

Koizumi Mitsuyuki, Sato Shinya, Yoshihara Mitsuyo, Nakamura Yoshiyasu, Terao Hideyuki, Okubo Yoichiro, Washimi Kota, Yoshioka Emi, Yokose Tomoyuki, Kishida Takeshi, Koshikawa Naohiko, Miyagi Yohei

2022-Dec

Bladder cancer, EPHA2, adipocytes, biomarker, cancer recurrence, machine learning

General General

Ultrasonic Texture Features for Assessing Cardiac Remodeling and Dysfunction.

In Journal of the American College of Cardiology ; h5-index 167.0

BACKGROUND : Changes in cardiac size, myocardial mass, cardiomyocyte appearance, and, ultimately, the function of the entire organ are interrelated features of cardiac remodeling that profoundly affect patient outcomes.

OBJECTIVES : This study proposes that the application of radiomics for extracting cardiac ultrasonic textural features (ultrasomics) can aid rapid, automated assessment of left ventricular (LV) structure and function without requiring manual measurements.

METHODS : This study developed machine-learning models using cardiac ultrasound images from 1,915 subjects in 3 clinical cohorts: 1) an expert-annotated cardiac point-of-care-ultrasound (POCUS) registry (n = 943, 80% training/testing and 20% internal validation); 2) a prospective POCUS cohort for external validation (n = 275); and 3) a prospective external validation on high-end ultrasound systems (n = 484). In a type 2 diabetes murine model, echocardiography of wild-type (n = 10) and Leptr-/- (n = 8) mice were assessed longitudinally at 3 and 25 weeks, and ultrasomics features were correlated with histopathological features of hypertrophy.

RESULTS : The ultrasomics model predicted LV remodeling in the POCUS and high-end ultrasound external validation studies (area under the curve: 0.78 [95% CI: 0.68-0.88] and 0.79 [95% CI: 0.73-0.86], respectively). Similarly, the ultrasomics model predicted LV remodeling was significantly associated with major adverse cardiovascular events in both cohorts (P < 0.0001 and P = 0.0008, respectively). Moreover, on multivariate analysis, the ultrasomics probability score was an independent echocardiographic predictor of major adverse cardiovascular events in the high-end ultrasound cohort (HR: 8.53; 95% CI: 4.75-32.1; P = 0.0003). In the murine model, cardiomyocyte hypertrophy positively correlated with 2 ultrasomics biomarkers (R2 = 0.57 and 0.52, Q < 0.05).

CONCLUSIONS : Cardiac ultrasomics-based biomarkers may aid development of machine-learning models that provide an expert-level assessment of LV structure and function.

Hathaway Quincy A, Yanamala Naveena, Siva Nanda K, Adjeroh Donald A, Hollander John M, Sengupta Partho P

2022-Dec-06

MACE, automated, machine-learning, mouse, radiomics, ultrasomics

General General

Usability, acceptability and feasibility of a novel technology with visual guidance with video and audio recording during newborn resuscitation: a pilot study.

In BMJ health & care informatics

OBJECTIVE : Inadequate adherence to resuscitation for non-crying infants will have poor outcome and thus rationalise a need for real-time guidance and quality improvement technology. This study assessed the usability, feasibility and acceptability of a novel technology of real-time visual guidance, with sound and video recording during resuscitation.

SETTING : A public hospital in Nepal.

DESIGN : A cross-sectional design.

INTERVENTION : The technology has an infant warmer with light, equipped with a tablet monitor, NeoBeat and upright bag and mask. The tablet records resuscitation activities, ventilation sound, heart rate and display time since birth. Healthcare providers (HCPs) were trained on the technology before piloting.

DATA COLLECTION AND ANALYSIS : HCPs who had at least 8 weeks of experience using the technology completed a questionnaire on usability, feasibility and acceptability (ranged 1-5 scale). Overall usability score was calculated (ranged 1-100 scale).

RESULTS : Among the 30 HCPs, 25 consented to the study. The usability score was good with the mean score (SD) of 68.4% (10.4). In terms of feasibility, the participants perceived that they did not receive adequate support from the hospital administration for use of the technology, mean score (SD) of 2.44 (1.56). In terms of acceptability, the information provided in the monitor, that is, time elapsed from birth was easy to understand with mean score (SD) of 4.60 (0.76).

CONCLUSION : The study demonstrates reasonable usability, feasibility and acceptability of a technological solution that records audio visual events during resuscitation and provides visual guidance to improve care.

Kc Ashish, Kong So Yeon Joyce, Basnet Omkar, Haaland Solveig Haukås, Bhattarai Pratiksha, Gomo Øystein, Gurung Rejina, Ahlsson Fredrik, Meinich-Bache Øyvind, Axelin Anna, Malla Honey, Basula Yuba Nidhi, Pathak Om Krishna, Pokharel Sunil Mani, Subedi Hira, Myklebust Helge

2022-Dec

Artificial intelligence, Decision Support Systems, Clinical, Decision Support Techniques

General General

Respiratory effort during sleep and prevalent hypertension in obstructive sleep apnoea.

In The European respiratory journal

Mechanisms underlying blood pressure changes in obstructive sleep apnoea (OSA) are incompletely understood. Increased respiratory effort (RE) is one of the main features of OSA and is associated with sympathetic overactivity, leading to increased vascular wall stiffness and remodelling. This study investigated associations between a new measure of RE (percentage of sleep time spent with increased RE based on measurement of mandibular jaw movements [MJM]; REMOV, %TST) and prevalent hypertension in adults referred for evaluation of suspected OSA. A machine learning model was built to predict hypertension from clinical data, conventional polysomnography (PSG) indices, and MJM-derived parameters (including REMOV, %TST). The model was evaluated in a training subset and a test subset. The analysis included 1127 patients, 901 (80%) in the training subset and 226 (20%) in the test subset. The prevalence of hypertension was 31% and 30%, respectively, in the training and test subsets. A risk stratification model based on eighteen input features including REMOV had good accuracy for predicting prevalent hypertension (sensitivity 0.75, specificity 0.83). Using the Shapley additive explanation (SHAP) method, REMOV was the best predictor of hypertension after clinical risk factors (age, sex, body mass index, neck circumference) and time with oxygen saturation <90%, ahead òf standard PSG metrics (including the apnoea-hypopnoea index and oxygen desaturation index). The proportion of sleep time spent with increased RE automatically derived from MJM was identified as a potential new reliable metric to predict prevalent hypertension in patients with OSA.

Martinot Jean-Benoit, Le-Dong Nhat-Nam, Malhotra Atul, Pépin Jean-Louis

2022-Dec-01

General General

Combined Mueller matrix imaging and artificial intelligence classification framework for Hepatitis B detection.

In Journal of biomedical optics

SIGNIFICANCE : The combination of polarized imaging with artificial intelligence (AI) technology has provided a powerful tool for performing an objective and precise diagnosis in medicine.

AIM : An approach is proposed for the detection of hepatitis B (HB) virus using a combined Mueller matrix imaging technique and deep learning method.

APPROACH : In the proposed approach, Mueller matrix imaging polarimetry is applied to obtain 4 × 4 Mueller matrix images of 138 HBsAg-containing (positive) serum samples and 136 HBsAg-free (negative) serum samples. The kernel estimation density results show that, of the 16 Mueller matrix elements, elements M 22 and M 33 provide the best discriminatory power between the positive and negative samples.

RESULTS : As a result, M 22 and M 33 are taken as the inputs to five different deep learning models: Xception, VGG16, VGG19, ResNet 50, and ResNet150. It is shown that the optimal classification accuracy (94.5%) is obtained using the VGG19 model with element M 22 as the input.

CONCLUSIONS : Overall, the results confirm that the proposed hybrid Mueller matrix imaging and AI framework provides a simple and effective approach for HB virus detection.

Pham Thi-Thu-Hien, Nguyen Hoang-Phuoc, Luu Thanh-Ngan, Le Ngoc-Bich, Vo Van-Toi, Huynh Ngoc-Trinh, Phan Quoc-Hung, Le Thanh-Hai

2022-Jul

HBsAg, Mueller matrix imaging, convolutional neural network, hepatitis B, polarimetry

General General

Differentiation of central disorders of hypersomnolence with manual and artificial-intelligence-derived polysomnographic measures.

In Sleep

Differentiation of central disorders of hypersomnolence (DOH) is challenging but important for patient care. This study aimed to investigate whether biomarkers derived from sleep structure evaluated both by manual scoring as well as with artificial intelligence (AI) algorithms allow distinction of patients with different DOH. We included video-polysomnography data of 40 narcolepsy type 1 (NT1), 26 narcolepsy type 2 (NT2), 23 idiopathic hypersomnia (IH) patients and 54 subjects with subjective excessive daytime sleepiness (sEDS). Sleep experts manually scored sleep stages. A previously validated AI algorithm was employed to obtain automatic hypnograms and hypnodensity graphs (where each epoch is represented as a mixture of sleep stage probabilities). One-thousand-three features describing sleep architecture and instability were extracted from manual/automatic hypnogram and hypnodensity graphs. After feature selection, random forest classifiers were trained and tested in a 5-fold-cross-validation scheme to distinguish groups pairwise (NT1-vs-NT2, NT1-vs-IH, …) and single groups from the pooled remaining ones (NT1-vs-rest, NT2-vs-rest,…). The accuracy/F1-score values obtained in the test sets were: 0.74±0.04/0.79±0.05 (NT1-vs-NT2), 0.89±0.09/0.91±0.08 (NT1-vs-IH), 0.93±0.06/0.91±0.07 (NT1-vs-sEDS), 0.88±0.04/0.80±0.07 (NT1-vs-rest), 0.65±0.10/0.70±0.09 (NT2-vs-IH), 0.72±0.12/0.60±0.10 (NT2-vs-sEDS), 0.54±0.19/0.38±0.13 (NT2-vs-rest), 0.57±0.11/0.35±0.18 (IH-vs-sEDS), 0.71±0.08/0.35±0.10 (IH-vs-rest) and 0.76±0.08/0.71±0.13 (sEDS-vs-rest). The results confirm previous findings on sleep instability in NT1 patients and show that combining manual and automatic AI-based sleep analysis could be useful for better distinction of NT2 from IH, but no precise sleep biomarker of NT2 or IH could be identified. Validation in a larger and multi-centric cohort is needed to confirm these findings.

Cesari Matteo, Egger Kristin, Stefani Ambra, Bergmann Melanie, Ibrahim Abubaker, Brandauer Elisabeth, Högl Birgit, Heidbreder Anna

2022-Dec-02

Computerized analysis, Excessive daytime sleepiness, Hypersomnia, Machine learning, Sleep instability

General General

White matter hyperintensity load is associated with premature brain aging.

In Aging ; h5-index 49.0

BACKGROUND : Brain age is an MRI-derived estimate of brain tissue loss that has a similar pattern to aging-related atrophy. White matter hyperintensities (WMHs) are neuroimaging markers of small vessel disease and may represent subtle signs of brain compromise. We tested the hypothesis that WMHs are independently associated with premature brain age in an original aging cohort.

METHODS : Brain age was calculated using machine-learning on whole-brain tissue estimates from T1-weighted images using the BrainAgeR analysis pipeline in 166 healthy adult participants. WMHs were manually delineated on FLAIR images. WMH load was defined as the cumulative volume of WMHs. A positive difference between estimated brain age and chronological age (BrainGAP) was used as a measure of premature brain aging. Then, partial Pearson correlations between BrainGAP and volume of WMHs were calculated (accounting for chronological age).

RESULTS : Brain and chronological age were strongly correlated (r(163)=0.932, p<0.001). There was significant negative correlation between BrainGAP scores and chronological age (r(163)=-0.244, p<0.001) indicating that younger participants had higher BrainGAP (premature brain aging). Chronological age also showed a positive correlation with WMH load (r(163)=0.506, p<0.001) indicating older participants had increased WMH load. Controlling for chronological age, there was a statistically significant relationship between premature brain aging and WMHs load (r(163)=0.216, p=0.003). Each additional year in brain age beyond chronological age corresponded to an additional 1.1mm3 in WMH load.

CONCLUSIONS : WMHs are an independent factor associated with premature brain aging. This finding underscores the impact of white matter disease on global brain integrity and progressive age-like brain atrophy.

Busby Natalie, Newman-Norlund Sarah, Sayers Sara, Newman-Norlund Roger, Wilson Sarah, Nemati Samaneh, Rorden Chris, Wilmskoetter Janina, Riccardi Nicholas, Roth Rebecca, Fridriksson Julius, Bonilha Leonardo

2022-Nov-30

aging, brain age, brain health, health, white matter hyperintensity

General General

Emulate Randomized Clinical Trials using Heterogeneous Treatment Effect Estimation for Personalized Treatments: Methodology Review and Benchmark.

In Journal of biomedical informatics ; h5-index 55.0

Big data and (deep) machine learning have been ambitious tools in digital medicine, but these tools focus mainly on association. Intervention in medicine is about the causal effects. The average treatment effect has long been studied as a measure of causal effect, assuming that all populations have the same effect size. However, no "one-size-fits-all" treatment seems to work in some complex diseases. Treatment effects may vary by patient. Estimating heterogeneous treatment effects (HTE) may have a high impact on developing personalized treatment. Lots of advanced machine learning models for estimating HTE have emerged in recent years, but there has been limited translational research into the real-world healthcare domain. To fill the gap, we reviewed and compared eleven recent HTE estimation methodologies, including meta-learner, representation learning models, and tree-based models. We performed a comprehensive benchmark experiment based on nationwide healthcare claim data with application to Alzheimer's disease drug repurposing. We provided some challenges and opportunities in HTE estimation analysis in the healthcare domain to close the gap between innovative HTE models and deployment to real-world healthcare problems.

Ling Yaobin, Upadhyaya Pulakesh, Chen Luyao, Jiang Xiaoqian, Kim Yejin

2022-Nov-28

Causal inference, Conditional average treatment effect, Deep learning, Drug development, Machine learning, Target trial

Public Health Public Health

Using machine learning models to predict the effects of seasonal fluxes on Plesiomonas shigelloides population density.

In Environmental pollution (Barking, Essex : 1987)

Seasonal variations (SVs) affect the population density (PD), fate, and fitness of pathogens in environmental water resources and the public health impacts. Therefore, this study is aimed at applying machine learning intelligence (MLI) to predict the impacts of SVs on P. shigelloides population density (PDP) in the aquatic milieu. Physicochemical events (PEs) and PDP from three rivers acquired via standard microbiological and instrumental techniques across seasons were fitted to MLI algorithms (linear regression (LR), multiple linear regression (MR), random forest (RF), gradient boosted machine (GBM), neural network (NN), K-nearest neighbour (KNN), boosted regression tree (BRT), extreme gradient boosting (XGB) regression, support vector regression (SVR), decision tree regression (DTR), M5 pruned regression (M5P), artificial neural network (ANN) regression (with one 10-node hidden layer (ANN10), two 6- and 4-node hidden layers (ANN64), and two 5- and 5-node hidden layers (ANN55)), and elastic net regression (ENR)) to assess the implications of the SVs of PEs on aquatic PDP. The results showed that SVs significantly influenced PDP and PEs in the water (p < 0.0001), exhibiting a site-specific pattern. While MLI algorithms predicted PDP with differing absolute flux magnitudes for the contributing variables, DTR predicted the highest PDP value of 1.707 log unit, followed by XGB (1.637 log unit), but XGB (mean-squared-error (MSE) = 0.0025; root-mean-squared-error (RMSE) = 0.0501; R2 =0.998; medium absolute deviation (MAD) = 0.0275) outperformed other models in terms of regression metrics. Temperature and total suspended solids (TSS) ranked first and second as significant factors in predicting PDP in 53.3% (8/15) and 40% (6/15), respectively, of the models, based on the RMSE loss after permutations. Additionally, season ranked third among the 7 models, and turbidity (TBS) ranked fourth at 26.7% (4/15), as the primary significant factor for predicting PDP in the aquatic milieu. The results of this investigation demonstrated that MLI predictive modelling techniques can promisingly be exploited to complement the repetitive laboratory-based monitoring of PDP and other pathogens, especially in low-resource settings, in response to seasonal fluxes and can provide insights into the potential public health risks of emerging pathogens and TSS pollution (e.g., nanoparticles and micro- and nanoplastics) in the aquatic milieu. The model outputs provide low-cost and effective early warning information to assist watershed managers and fish farmers in making appropriate decisions about water resource protection, aquaculture management, and sustainable public health protection.

Ekundayo Temitope C, Ijabadeniyi Oluwatosin A, Igbinosa Etinosa O, Okoh Anthony I

2022-Nov-28

Artificial neural network regression, Boosted regression tree, Decision tree regression, Extreme gradient boosted regression, Feature importance, Gradient boosted machine, K-nearest neighbours, M5 pruned regression, Machine intelligence, Multiple linear regression, Neural networks, Pathogen, Prediction, Predictive microbiology, Public health, Random forest, Support vector regression

General General

Tingli Dazao Decoction pretreatment ameliorates mitochondrial damage induced by oxidative stress in cardiomyocytes.

In Journal of ethnopharmacology ; h5-index 59.0

ETHNOPHARMACOLOGICAL RELEVANCE : Tingli Dazao Decoction (TLDZD) recorded in "Synopsis of Prescriptions of the Golden Chamber" is a classical prescription used for the treatment of heart failure nowadays. The studies of TLDZD were mainly focused on clinical practice where the formula was usually combined with other medicinal herbs. Chemical composition and cardiovascular pharmacological research of TLDZD were still insufficient.

AIM OF THE STUDY : This study aimed to investigate the chemical constituents of TLDZD, evaluate the effects of TLDZD on mitochondria of myocardial cells under oxidative stress, and identify its potential cardioprotective components.

MATERIALS AND METHODS : Chemical composition analysis of TLDZD was performed by ultra-performance liquid chromatography-quadrupole-time of flight-mass spectrometry. An in vitro oxidative stress model of cardiomyocytes was established by treating H9c2 cells with tert-butyl hydroperoxide (tBHP). The impact of TLDZD and its components on the production of cellular reactive oxygen species (ROS) and mitochondrial ROS (mROS), the level of malonaldehyde as well as the structure and function of mitochondria were evaluated. The effect of TLDZD on AKT/Nrf2/HO-1 signaling pathway in cardiomyocytes under oxidative stress were observed.

RESULTS : Seventy-eight compounds were characterized from TLDZD, among which flavonoids, glucosinolates and phenylpropanoids were abundant, and a small number of cardiac glycosides and alkaloids also existed in TLDZD. Pretreatment with TLDZD significantly attenuated cell death, accompanied by decreased ROS and mROS production, reduced malonaldehyde level, lower mitochondrial membrane potential and adenosine triphosphate content in H9c2 cells stimulated with tBHP. The active components were mainly flavonoids of TLZ represented by quercetin-3-O-β-D-glucose-7-O-β-D-gentiobioside. In mechanism, the cardioprotective effect of TLDZD was proved to be associated with the activation of the AKT/Nrf2/HO-1 signaling pathway.

CONCLUSIONS : The chemical profile of TLDZD was comprehensively investigated. Flavonoids with quercetin-3-O-β-D-glucose-7-O-β-D-gentiobioside as the representative, were the main component in TLDZD responsible for attenuating mitochondrial oxidative damage in cardiomyocytes.

Chen Huihui, Zhu Yue, Zhao Xiaoping, Yang Zhenzhong

2022-Nov-28

AKT/Nrf2/HO-1 signaling pathway, H9c2 cells, Mitochondria, Oxidative stress, Tingli Dazao Decoction

General General

Visual category representations in the infant brain.

In Current biology : CB

Visual categorization is a human core cognitive capacity1,2 that depends on the development of visual category representations in the infant brain.3,4,5,6,7 However, the exact nature of infant visual category representations and their relationship to the corresponding adult form remains unknown.8 Our results clarify the nature of visual category representations from electroencephalography (EEG) data in 6- to 8-month-old infants and their developmental trajectory toward adult maturity in the key characteristics of temporal dynamics,2,9 representational format,10,11,12 and spectral properties.13,14 Temporal dynamics change from slowly emerging, developing representations in infants to quickly emerging, complex representations in adults. Despite those differences, infants and adults already partly share visual category representations. The format of infants' representations is visual features of low to intermediate complexity, whereas adults' representations also encode high-complexity features. Theta band activity contributes to visual category representations in infants, and these representations are shifted to the alpha/beta band in adults. Together, we reveal the developmental neural basis of visual categorization in humans, show how information transmission channels change in development, and demonstrate the power of advanced multivariate analysis techniques in infant EEG research for theory building in developmental cognitive science.

Xie Siying, Hoehl Stefanie, Moeskops Merle, Kayhan Ezgi, Kliesch Christian, Turtleton Bert, Köster Moritz, Cichy Radoslaw M

2022-Nov-22

cognitive development, deep learning, infant cognition, multivariate analysis, object recognition, spectral characterization, visual perception

General General

Prediction of Golgi Polarity in Collectively Migrating Epithelial Cells Using Graph Neural Network.

In Cells, tissues, organs

In the stationary epithelium, the Golgi apparatus assumes an apical position, above the cell nucleus. However, during wound healing and morphogenesis, as the epithelial cells starts migrating, it relocalizes closer to the basal plane. On this plane, the position of Golgi with respect to the cell nucleus defines the organizational polarity of a migrating epithelial cell, which is crucial for an efficient collective migration. Yet, factors influencing the Golgi polarity remain elusive. Here we constructed a graph neural network-based deep learning model to systematically analyze the dependency of Golgi polarity on multiple geometric and physical factors. In spite of the complexity of a migrating epithelial monolayer, our simple model was able to predict the Golgi polarity with 75% accuracy. Moreover, the model predicted that Golgi polarity predominantly correlates with the orientation of maximum principal stress. Finally, we found that this correlation operates locally since progressive coarsening of the stress field over multiple cell-lengths reduced the stress polarity-Golgi polarity correlation as well as the predictive accuracy of the neural network model. Taken together, our results demonstrated that graph neural networks could be a powerful tool towards understanding how different physical factors influence collective cell migration. They also highlighted a previously unknown role of physical cues in defining the intracellular organization.

Khuntia Purnati, Das Tamal

2022-Dec-01

Pathology Pathology

Association of longitudinal cognitive decline with diffusion MRI in Gray Matter, Amyloid, and Tau deposition.

In Neurobiology of aging ; h5-index 69.0

Extracellular amyloid plaques in gray matter are the earliest pathological marker for Alzheimer's disease (AD), followed by abnormal tau protein accumulation. The link between diffusion changes in gray matter, amyloid and tau pathology, and cognitive decline is not well understood. We first performed cross-sectional analyses on T1-weighted imaging, diffusion MRI, and amyloid and tau PETs from the ADNI 2/3 database. We evaluated cortical volume, free-water, fractional anisotropy (FA), and amyloid and tau SUVRs in 171 cognitively normal, 103 MCI, and 44 AD individuals. When the 3 groups were combined, increasing amyloid burden was associated with reduced extracellular free-water in the entorhinal cortex and hippocampus in those with amyloid-negative status whereas increasing tau burden was associated with increased extracellular free-water regardless of amyloid status. Next, we found that for the MCI subjects, diffusion measures (free-water, FA) alone predicted MMSE score 2 years later with a high r-square value (87%), as compared to tau SUVRs (27%), T1 volume (36%), and amyloid SUVRs (75%). Diffusion measures represent a potent non-invasive marker for predicting cognitive decline.

Wang Wei-En, Chen Rob, Mayrand Robin Perry, Adjouadi Malek, Fang Ruogu, DeKosky Steven T, Duara Ranjan, Coombes Stephen A, Vaillancourt David E

2022-Nov-05

“Alzheimers disease”, Amyloid, Diffusion MRI, Free-water imaging, Machine learning, Positron emission tomography, Tau

Surgery Surgery

Butein suppresses PD-L1 expression via downregulating STAT1 in non-small cell lung cancer.

In Biomedicine & pharmacotherapy = Biomedecine & pharmacotherapie

PD-L1 (programmed cell death ligand 1) is frequently up-regulated in tumors and is critical in tumor immune escape. In addition to antibodies that block the interaction between PD-L1 and PD-1 (programmed cell death protein 1), small-molecule compounds that suppress PD-L1 expression also exhibit significant anti-tumor effects, emerging as a new strategy targeting PD-L1. By using a cell-based screening model, we found that butein, a natural chalcone compound, significantly reduced the cytoplasm and cell surface expression of PD-L1. This effect was further validated in various non-small cell lung cancer (NSCLC) cell lines and primary cells derived from clinical NSCLC tissues. Butein inhibited PD-L1 transcription, but not the half-life of PD-L1 protein. Butein reduced STAT1 level and butein-induced PD-L1 suppression was eliminated by the absence of STAT1. By co-culture system, butein improved tumor elimination by increasing the killing ability of CD8+ T cells. By in vivo study, we further confirmed that butein downregulated PD-L1 expression and improved infiltration of CD8+ T cells in tumor tissues. Taken together, our study suggested that butein could suppress the transcription of PD-L1 via downregulating STAT1, providing a theoretical basis for the application of butein in anti-tumor therapy.

Zhao Lin, Zhang Wenxin, Luan Fengming, Chen Xi, Wu Honghai, He Qiaojun, Weng Qinjie, Ding Ling, Yang Bo

2022-Nov-28

Butein, Immune cell infiltration, Natural chalcone compound, PD-L1 transcription, Total STAT1

General General

A co-evolutionary lane-changing trajectory planning method for automated vehicles based on the instantaneous risk identification.

In Accident; analysis and prevention

Lane-changing trajectory planning (LTP) is an effective concept to control automated vehicles (AVs) in mixed traffic, which can reduce traffic conflicts and improve overall traffic efficiency. To enhance the lane change safety for AVs, a co-evolutionary lane-changing trajectory planning (CLTP) method is proposed to describe the risk minimization process that co-evolves with the dynamic traffic environment in the limited literature. Firstly, the natural driving data of vehicle trajectory on the expressway provided by the High dataset are used to construct the lane-changing samples. To obtain the future traffic environment information, a deep learning neural network is adopted to capture trajectory dynamics in mobility of surrounding vehicles around a lane-changing vehicle. Secondly, the safe interaction between the subject vehicle and the surrounding vehicles is considered to establish a mathematical model for the temporal and spatial risk identification of a lane change event based on the fault tree analysis method. Subsequently, the risk minimization of lane change is considered as the objective. Based on the acceleration and deceleration overtaking rules and the trapezoidal acceleration method, the longitudinal and lateral displacement schemes during a lane change are designed. Finally, the motion parameters of longitudinal and lateral displacement are acquired to form an ideal lane change trajectory using a genetic algorithm. The results show that this method can effectively achieve higher safety of the lane-changing process, and reduce the traffic conflicts and traffic turbulence caused by dangerous lane-changing behaviors. The findings can provide theoretical support for lane change trajectory planning algorithm design of intelligent vehicles.

Wu Jiabin, Chen Xiaohua, Bie Yiming, Zhou Wei

2022-Nov-28

Intelligent vehicle, Lane change planning, Risk identification, Traffic engineering

General General

The scientific progress and prospects of artificial intelligence in digestive endoscopy: A comprehensive bibliometric analysis.

In Medicine

Artificial intelligence (AI) has been used for diagnosis and outcome prediction in clinical practice. Furthermore, AI in digestive endoscopy has attracted much attention and shown promising and stimulating results. This study aimed to determine the development trends and research hotspots of AI in digestive endoscopy by visualizing articles. Publications on AI in digestive endoscopy research were retrieved from the Web of Science Core Collection on April 25, 2022. VOSviewer and CiteSpace were used to assess and plot the research outputs. This analytical research was based on original articles and reviews. A total of 524 records of AI research in digestive endoscopy, published between 2005 and 2022, were retrieved. The number of articles has increased 27-fold from 2017 to 2021. Fifty-one countries and 994 institutions contributed to all publications. Asian countries had the highest number of publications. China, the USA, and Japan were consistently the leading driving forces and mainly contributed (26%, 21%, and 14.31%, respectively). With a solid academic reputation in this area, Japan has the highest number of citations per article. Tada Tomohiro published the most articles and received the most citations.. Gastrointestinal endoscopy published the largest number of publications, and 4 of the top 10 cited papers were published in this journal. "The Classification," "ulcerative colitis," "capsule endoscopy," "polyp detection," and "early gastric cancer" were the leading research hotspots. Our study provides systematic elaboration for researchers to better understand the development of AI in gastrointestinal endoscopy.

Gan Pei-Ling, Huang Shu, Pan Xiao, Xia Hui-Fang, Lü Mu-Han, Zhou Xian, Tang Xiao-Wei

2022-Nov-25

Public Health Public Health

Data-driven identification of post-acute SARS-CoV-2 infection subphenotypes.

In Nature medicine ; h5-index 170.0

The post-acute sequelae of SARS-CoV-2 infection (PASC) refers to a broad spectrum of symptoms and signs that are persistent, exacerbated or newly incident in the period after acute SARS-CoV-2 infection. Most studies have examined these conditions individually without providing evidence on co-occurring conditions. In this study, we leveraged the electronic health record data of two large cohorts, INSIGHT and OneFlorida+, from the national Patient-Centered Clinical Research Network. We created a development cohort from INSIGHT and a validation cohort from OneFlorida+ including 20,881 and 13,724 patients, respectively, who were SARS-CoV-2 infected, and we investigated their newly incident diagnoses 30-180 days after a documented SARS-CoV-2 infection. Through machine learning analysis of over 137 symptoms and conditions, we identified four reproducible PASC subphenotypes, dominated by cardiac and renal (including 33.75% and 25.43% of the patients in the development and validation cohorts); respiratory, sleep and anxiety (32.75% and 38.48%); musculoskeletal and nervous system (23.37% and 23.35%); and digestive and respiratory system (10.14% and 12.74%) sequelae. These subphenotypes were associated with distinct patient demographics, underlying conditions before SARS-CoV-2 infection and acute infection phase severity. Our study provides insights into the heterogeneity of PASC and may inform stratified decision-making in the management of PASC conditions.

Zhang Hao, Zang Chengxi, Xu Zhenxing, Zhang Yongkang, Xu Jie, Bian Jiang, Morozyuk Dmitry, Khullar Dhruv, Zhang Yiye, Nordvig Anna S, Schenck Edward J, Shenkman Elizabeth A, Rothman Russell L, Block Jason P, Lyman Kristin, Weiner Mark G, Carton Thomas W, Wang Fei, Kaushal Rainu

2022-Dec-01

General General

Reinforcement learning for robust stabilization of nonlinear systems with asymmetric saturating actuators.

In Neural networks : the official journal of the International Neural Network Society

We study the robust stabilization problem of a class of nonlinear systems with asymmetric saturating actuators and mismatched disturbances. Initially, we convert such a robust stabilization problem into a nonlinear-constrained optimal control problem by constructing a discounted cost function for the auxiliary system. Then, for the purpose of solving the nonlinear-constrained optimal control problem, we develop a simultaneous policy iteration (PI) in the reinforcement learning framework. The implementation of the simultaneous PI relies on an actor-critic architecture, which employs actor and critic neural networks (NNs) to separately approximate the control policy and the value function. To determine the actor and critic NNs' weights, we use the approach of weighted residuals together with the typical Monte-Carlo integration technique. Finally, we perform simulations of two nonlinear plants to validate the established theoretical claims.

Yang Xiong, Zhou Yingjiang, Gao Zhongke

2022-Nov-16

Adaptive dynamic programming, Neural network control, Reinforcement learning, Robust stabilization, Saturating actuator

General General

DANet: Semi-supervised differentiated auxiliaries guided network for video action recognition.

In Neural networks : the official journal of the International Neural Network Society

Video Action Recognition (ViAR) aims to identify the category of the human action observed in a given video. With the advent of Deep Learning (DL) techniques, noticeable performance breakthroughs have been achieved in this study. However, the success of most existing DL-based ViAR methods heavily relies on the existence of a large amount of annotated data, i.e., videos with corresponding action categories. In practice, obtaining such a desired number of annotations is often difficult due to expensive labeling costs, which may lead to significant performance degradation for these methods. To address this issue, we propose an end-to-end semi-supervised Differentiated Auxiliary guided Network (DANet) to best use a few annotated videos. Except for the common supervised learning on a few annotated videos, the DANet also involves the knowledge of multiple pre-trained auxiliary networks to optimize the ViAR network in a self-supervised way on the unannotated data by removing the annotations. Considering the tight connection between video action recognition and classical static image-based visual tasks, the abundant knowledge from the pre-trained static image-based models can be used for training the ViAR model. Specifically, the DANet is a two-branch architecture, which includes a target branch of the ViAR network, and an auxiliary branch of multiple auxiliary networks (i.e., referring to diverse off-the-shelf models of relevant image tasks). Given a limited number of annotated videos, we train the target ViAR network end-to-end in a semi-supervised way, namely, with both the supervised cross-entropy loss on annotated videos, and the per-auxiliary weighted self-supervised contrastive losses on the same videos but without using annotations. Besides, we further explore different weighted guidance of the auxiliary networks to the ViAR network to better reflect different relationships between the image-based models and the ViAR model. Finally, we conduct extensive experiments on several popular action recognition benchmarks in comparison with existing state-of-the-art methods, and the experimental results demonstrate the superiority of DANet over most of the compared methods. In particular, the DANet obviously suppresses state-of-the-art ViAR methods even with very fewer annotated videos.

Gao Guangyu, Liu Ziming, Zhang Guangjun, Li Jinyang, Qin A K

2022-Nov-17

Action recognition, Contrastive loss, Semi-supervised learning, Unannotated video

Pathology Pathology

Deep learning for computational cytology: A survey.

In Medical image analysis

Computational cytology is a critical, rapid-developing, yet challenging topic in medical image computing concerned with analyzing digitized cytology images by computer-aided technologies for cancer screening. Recently, an increasing number of deep learning (DL) approaches have made significant achievements in medical image analysis, leading to boosting publications of cytological studies. In this article, we survey more than 120 publications of DL-based cytology image analysis to investigate the advanced methods and comprehensive applications. We first introduce various deep learning schemes, including fully supervised, weakly supervised, unsupervised, and transfer learning. Then, we systematically summarize public datasets, evaluation metrics, versatile cytology image analysis applications including cell classification, slide-level cancer screening, nuclei or cell detection and segmentation. Finally, we discuss current challenges and potential research directions of computational cytology.

Jiang Hao, Zhou Yanning, Lin Yi, Chan Ronald C K, Liu Jiang, Chen Hao

2022-Nov-14

Artificial intelligence, Cancer screening, Computational cytology, Deep learning, Pathology, Survey

General General

Environmentally Stable, Stretchable, Adhesive, and Conductive Organohydrogels with Multiple Dynamic Interactions as High-Performance Strain and Temperature Sensors.

In ACS applied materials & interfaces ; h5-index 147.0

Nowadays, with the rapid development of artificial intelligence, conductive hydrogel-based sensors play an increasingly vital role in health monitoring and temperature sensing. However, the perfect integration of the environmental stability and applied performance of the hydrogel has always been a challenging and significant problem. Herein, we report an environmentally tolerant, stretchable, adhesive, self-healing conductive gel through multiple dynamic interactions in the water/glycerol/ionic liquids medium, which can be used as a high-performance strain and temperature sensor. The random copolymer poly(acrylic acid-co-acetoacetoxyethyl methacrylate) interacts with the branched poly(ethylene imine) (PEI) and Zr4+ ions via the dynamic covalent enamine bonds, coordinations, and electrostatic interactions to improve stretchable (1300%), compressible, fatigue-resistant (1000 cycles at 50% strain), and self-healing performance (95%, 24 h). The combination of water/glycerol/ionic liquids imparts the resulting gel with excellent electrical conductivity, anti-drying, and anti-freezing performance. By means of the above excellent performance, the gel could be used as the flexible strain or pressure sensor with high sensitivity and stability for the detection of the movement, expression, handwriting, pronouncing, and electrocardiogram (ECG) signals in various models. Meanwhile, the resulting gel can be assembled as the temperature sensor to trace the change of temperature accurately and steadily, which has a wide operating window (0 to 100 °C), an ultralow detection limit (0.2 °C), and high sensitivity (2.1% °C-1). It is believed that the strategy for the multifunction and high-performance gel will blaze a new trail for the smart device in health management, temperature detection, and information transmission under various environmental conditions.

Rong Liduo, Zhao Wei, Fan Yu, Zhou Zixuan, Zhan Meixiao, He Xu, Yuan Weizhong, Qian Chunhua

2022-Dec-01

adhesive conductive gel, dynamic interactions, environmental tolerance, strain or pressure sensor, temperature detection

Public Health Public Health

Development and Validation of Algorithms to Estimate Live Birth Gestational Age in Medicaid Analytic eXtract Data.

In Epidemiology (Cambridge, Mass.)

BACKGROUND : While healthcare utilization data are useful for postmarketing surveillance of drug safety in pregnancy, the start of pregnancy and gestational age at birth are often incompletely recorded or missing. Our objective was to develop and validate a claims-based live birth gestational age algorithm.

METHODS : Using the Medicaid Analytic eXtract (MAX) linked to birth certificates in three states, we developed four candidate algorithms based on: preterm codes; preterm or postterm codes; timing of prenatal care; and prediction models - using conventional regression and machine-learning approaches with a broad range of prespecified and empirically selected predictors. We assessed algorithm performance based on mean squared error (MSE) and proportion of pregnancies with estimated gestational age within 1 and 2 weeks of the gold standard, defined as the clinical or obstetric estimate of gestation on the birth certificate. We validated the best-performing algorithms against medical records in a nationwide sample. We quantified misclassification of select drug exposure scenarios due to estimated gestational age as positive predictive value (PPV), sensitivity, and specificity.

RESULTS : Among 114,117 eligible pregnancies, the random forest model with all predictors emerged as the best performing algorithm: MSE 1.5; 84.8% within 1 week and 96.3% within 2 weeks, with similar performance in the nationwide validation cohort. For all exposure scenarios, PPVs were >93.8%, sensitivities >94.3%, and specificities >99.4%.

CONCLUSIONS : We developed a highly accurate algorithm for estimating gestational age among live births in the nationwide MAX data, further supporting the value of these data for drug safety surveillance in pregnancy. See video abstract at, http://links.lww.com/EDE/B989 .

Zhu Yanmin, Thai Thuy N, Hernandez-Diaz Sonia, Bateman Brian T, Winterstein Almut G, Straub Loreen, Franklin Jessica M, Gray Kathryn J, Wyss Richard, Mogun Helen, Vine Seanna, Taylor Lockwood G, Ouellet-Hellstrom Rita, Ma Yong, Qiang Yandong, Hua Wei, Huybrechts Krista F

2023-Jan-01

General General

A Machine Learning Method for Automated Description and Workflow Analysis of First Trimester Ultrasound Scans.

In IEEE transactions on medical imaging ; h5-index 74.0

Obstetric ultrasound assessment of fetal anatomy in the first trimester of pregnancy is one of the less explored fields in obstetric sonography because of the paucity of guidelines on anatomical screening and availability of data. This paper, for the first time, examines imaging proficiency and practices of first trimester ultrasound scanning through analysis of full-length ultrasound video scans. Findings from this study provide insights to inform the development of more effective user-machine interfaces, of targeted assistive technologies, as well as improvements in workflow protocols for first trimester scanning. Specifically, this paper presents an automated framework to model operator clinical workflow from full-length routine first-trimester fetal ultrasound scan videos. The 2D+t convolutional neural network-based architecture proposed for video annotation incorporates transfer learning and spatio-temporal (2D+t) modelling to automatically partition an ultrasound video into semantically meaningful temporal segments based on the fetal anatomy detected in the video. The model results in a cross-validation A1 accuracy of 96.10%, F1 = 0.95, precision = 0.94 and recall = 0.95. Automated semantic partitioning of unlabelled video scans (n=250) achieves a high correlation with expert annotations (ρ = 0.95, p = 0.06). Clinical workflow patterns, operator skill and its variability can be derived from the resulting representation using the detected anatomy labels, order, and distribution. It is shown that nuchal translucency (NT) is the toughest standard plane to acquire and most operators struggle to localize high-quality frames. Furthermore, it is found that newly qualified operators spend 25.56% more time on key biometry tasks than experienced operators.

Yasrab Robail, Fu Zeyu, Zhao He, Lee Lok Hin, Sharma Harshita, Drukker Lior, Papageorgiou Aris T, Alison Noble J

2022-Dec-01

General General

AAU-net: An Adaptive Attention U-net for Breast Lesions Segmentation in Ultrasound Images.

In IEEE transactions on medical imaging ; h5-index 74.0

Various deep learning methods have been proposed to segment breast lesions from ultrasound images. However, similar intensity distributions, variable tumor morphologies and blurred boundaries present challenges for breast lesions segmentation, especially for malignant tumors with irregular shapes. Considering the complexity of ultrasound images, we develop an adaptive attention U-net (AAU-net) to segment breast lesions automatically and stably from ultrasound images. Specifically, we introduce a hybrid adaptive attention module (HAAM), which mainly consists of a channel self-attention block and a spatial self-attention block, to replace the traditional convolution operation. Compared with the conventional convolution operation, the design of the hybrid adaptive attention module can help us capture more features under different receptive fields. Different from existing attention mechanisms, the HAAM module can guide the network to adaptively select more robust representation in channel and space dimensions to cope with more complex breast lesions segmentation. Extensive experiments with several state-of-the-art deep learning segmentation methods on three public breast ultrasound datasets show that our method has better performance on breast lesions segmentation. Furthermore, robustness analysis and external experiments demonstrate that our proposed AAU-net has better generalization performance in the breast lesion segmentation. Moreover, the HAAM module can be flexibly applied to existing network frameworks. The source code is available on https://github.com/CGPxy/AAU-net.

Chen Gongping, Li Lei, Dai Yu, Zhang Jianxun, Yap Moi Hoon

2022-Dec-01

General General

A Compound Loss Function with Shape Aware Weight Map for Microscopy Cell Segmentation.

In IEEE transactions on medical imaging ; h5-index 74.0

Microscopy cell segmentation is a crucial step in biological image analysis and a challenging task. In recent years, deep learning has been widely used to tackle this task, with promising results. A critical aspect of training complex neural networks for this purpose is the selection of the loss function, as it affects the learning process. In the field of cell segmentation, most of the recent research in improving the loss function focuses on addressing the problem of inter-class imbalance. Despite promising achievements, more work is needed, as the challenge of cell segmentation is not only the inter-class imbalance but also the intra-class imbalance (the cost imbalance between the false positives and false negatives of the inference model), the segmentation of cell minutiae, and the missing annotations. To deal with these challenges, in this paper, we propose a new compound loss function employing a shape aware weight map. The proposed loss function is inspired by Youden's J index to handle the problem of inter-class imbalance and uses a focal cross-entropy term to penalize the intra-class imbalance and weight easy/hard samples. The proposed shape aware weight map can handle the problem of missing annotations and facilitate valid segmentation of cell minutiae. Results of evaluations on all ten 2D+time datasets from the public cell tracking challenge demonstrate 1) the superiority of the proposed loss function with the shape aware weight map, and 2) that the performance of recent deep learning-based cell segmentation methods can be improved by using the proposed compound loss function.

Zhu Yanming, Yin Xuefei, Meijering Erik

2022-Dec-01

General General

Emotion Recognition of Subjects with Hearing Impairment Based on Fusion of Facial Expression and EEG Topographic Map.

In IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society

Emotion analysis has been employed in many fields such as human-computer interaction, rehabilitation, and neuroscience. But most emotion analysis methods mainly focus on healthy controls or depression patients. This paper aims to classify the emotional expressions in individuals with hearing impairment based on EEG signals and facial expressions. Two kinds of signals were collected simultaneously when the subjects watched affective video clips, and we labeled the video clips with discrete emotional states (fear, happiness, calmness, and sadness). We extracted the differential entropy (DE) features based on EEG signals and converted DE features into EEG topographic maps (ETM). Next, the ETM and facial expressions were fused by the multichannel fusion method. Finally, a deep learning classifier CBAM_ResNet34 combined Residual Network (ResNet) and Convolutional Block Attention Module (CBAM) was used for subject-dependent emotion classification. The results show that the average classification accuracy of four emotions recognition after multimodal fusion achieves 78.32%, which is higher than 67.90% for facial expressions and 69.43% for EEG signals. Moreover, visualization by the Gradient-weighted Class Activation Mapping (Grad-CAM) of ETM showed that the prefrontal, temporal and occipital lobes were the brain regions closely related to emotional changes in individuals with hearing impairment.

Li Dahua, Liu Jiayin, Yang Yi, Hou Fazheng, Song Haotian, Song Yu, Gao Qiang, Mao Zemin

2022-Dec-01

General General

Passive tracking of underwater acoustic targets based on multi-beam LOFAR and deep learning.

In PloS one ; h5-index 176.0

Conventional passive tracking methods for underwater acoustic targets in sonar engineering generate time azimuth histogram and use it as a basis for target azimuth and tracking. Passive underwater acoustic targets only have azimuth information on the time azimuth histogram, which is easy to be lost and disturbed by ocean noise. To improve the accuracy of passive tracking, we propose to adopt the processed multi-beam Low Frequency Analysis and Recording (LOFAR) as the dataset for passive tracking. In this paper, an improved LeNet-5 convolutional neural network model (CNN) model is used to identify targets, and a passive tracking method for underwater acoustic targets based on multi-beam LOFAR and deep learning is proposed, combined with Extended Kalman Filter (EKF) to improve the tracking accuracy. The performance of the method under realistic conditions is evaluated through simulation analysis and validation using data obtained from marine experiments.

Wang Maofa, Qiu Baochun, Zhu Zefei, Ma Li, Zhou Chuanping

2022

General General

Right hemispheric white matter hyperintensities improve the prediction of spatial neglect severity in acute stroke.

In NeuroImage. Clinical

White matter hyperintensities (WMH) are frequently observed in brain scans of elderly people. They are associated with an increased risk of stroke, cognitive decline, and dementia. However, it is unknown yet if measures of WMH provide information that improve the understanding of poststroke outcome compared to only state-of-the-art stereotaxic structural lesion data. We implemented high-dimensional machine learning models, based on support vector regression, to predict the severity of spatial neglect in 103 acute right hemispheric stroke patients. We found that (1) the additional information of right hemispheric or bilateral voxel-based topographic WMH extent indeed yielded a significant improvement in predicting acute neglect severity (compared to the voxel-based stroke lesion map alone). (2) Periventricular WMH appeared more relevant for prediction than deep subcortical WMH. (3) Among different measures of WMH, voxel-based maps as measures of topographic extent allowed more accurate predictions compared to the use of traditional ordinally assessed visual rating scales (Fazekas-scale, Cardiovascular Health Study-scale). In summary, topographic WMH appear to be a valuable clinical imaging biomarker for predicting the severity of cognitive deficits and bears great potential for rehabilitation guidance of acute stroke patients.

Röhrig Lisa, Sperber Christoph, Bonilha Leonardo, Rorden Christopher, Karnath Hans-Otto

2022-Nov-11

Imaging biomarker, Leukoaraiosis, Machine learning, Spatial attention, Support vector regression, White matter lesions

Public Health Public Health

Modeling approaches for early warning and monitoring of pandemic situations as well as decision support.

In Frontiers in public health

The COVID-19 pandemic has highlighted the lack of preparedness of many healthcare systems against pandemic situations. In response, many population-level computational modeling approaches have been proposed for predicting outbreaks, spatiotemporally forecasting disease spread, and assessing as well as predicting the effectiveness of (non-) pharmaceutical interventions. However, in several countries, these modeling efforts have only limited impact on governmental decision-making so far. In light of this situation, the review aims to provide a critical review of existing modeling approaches and to discuss the potential for future developments.

Botz Jonas, Wang Danqi, Lambert Nicolas, Wagner Nicolas, Génin Marie, Thommes Edward, Madan Sumit, Coudeville Laurent, Fröhlich Holger

2022

agent-based-modeling, artificial intelligence, compartmental models, machine learning, pandemic

General General

Tai Chi increases functional connectivity and decreases chronic fatigue syndrome: A pilot intervention study with machine learning and fMRI analysis.

In PloS one ; h5-index 176.0

BACKGROUND : The latest guidance on chronic fatigue syndrome (CFS) recommends exercise therapy. Tai Chi, an exercise method in traditional Chinese medicine, is reportedly helpful for CFS. However, the mechanism remains unclear. The present longitudinal study aimed to detect the influence of Tai Chi on functional brain connectivity in CFS.

METHODS : The study recruited 20 CFS patients and 20 healthy controls to receive eight sessions of Tai Chi exercise over a period of one month. Before the Tai Chi exercise, an abnormal functional brain connectivity for recognizing CFS was generated by a linear support vector model. The prediction ability of the structure was validated with a random forest classification under a permutation test. Then, the functional connections (FCs) of the structure were analyzed in the large-scale brain network after Tai Chi exercise while taking the changes in the Fatigue Scale-14, Pittsburgh Sleep Quality Index (PSQI), and the 36-item short-form health survey (SF-36) as clinical effectiveness evaluation. The registration number is ChiCTR2000032577 in the Chinese Clinical Trial Registry.

RESULTS : 1) The score of the Fatigue Scale-14 decreased significantly in the CFS patients, and the scores of the PSQI and SF-36 changed significantly both in CFS patients and healthy controls. 2) Sixty FCs were considered significant to discriminate CFS (P = 0.000, best accuracy 90%), with 80.5% ± 9% average accuracy. 3) The FCs that were majorly related to the left frontoparietal network (FPN) and default mode network (DMN) significantly increased (P = 0.0032 and P = 0.001) in CFS patients after Tai Chi exercise. 4) The change of FCs in the left FPN and DMN were positively correlated (r = 0.40, P = 0.012).

CONCLUSION : These results demonstrated that the 60 FCs we found using machine learning could be neural biomarkers to discriminate between CFS patients and healthy controls. Tai Chi exercise may improve CFS patients' fatigue syndrome, sleep quality, and body health statement by strengthening the functional connectivity of the left FPN and DMN under these FCs. The findings promote our understanding of Tai Chi exercise's value in treating CFS.

Wu Kang, Li Yuanyuan, Zou Yihuai, Ren Yi, Wang Yahui, Hu Xiaojie, Wang Yue, Chen Chen, Lu Mengxin, Xu Lingling, Wu Linlu, Li Kuangshi

2022

Radiology Radiology

Artificial intelligence for localization of the acute ischemic stroke by non-contrast computed tomography.

In PloS one ; h5-index 176.0

A non-contrast cranial computer tomography (ncCT) is often employed for the diagnosis of the early stage of the ischemic stroke. However, the number of false negatives is high. More accurate results are obtained by an MRI. However, the MRI is not available in every hospital. Moreover, even if it is available in the clinic for the routine tests, emergency often does not have it. Therefore, this paper proposes an end-to-end framework for detection and segmentation of the brain infarct on the ncCT. The computer tomography perfusion (CTp) is used as the ground truth. The proposed ensemble model employs three deep convolution neural networks (CNNs) to process three end-to-end feature maps and a hand-craft features characterized by specific contra-lateral features. To improve the accuracy of the detected infarct area, the spatial dependencies between neighboring slices are employed at the postprocessing step. The numerical experiments have been performed on 18 ncCT-CTp paired stroke cases (804 image-pairs). The leave-one-out approach is applied for evaluating the proposed method. The model achieves 91.16% accuracy, 65.15% precision, 77.44% recall, 69.97% F1 score, and 0.4536 IoU.

Kaothanthong Natsuda, Atsavasirilert Kamin, Sarampakhul Soawapot, Chantangphol Pantid, Songsaeng Dittapong, Makhanov Stanislav

2022

General General

A novel customer churn prediction model for the telecommunication industry using data transformation methods and feature selection.

In PloS one ; h5-index 176.0

Customer churn is one of the most critical issues faced by the telecommunication industry (TCI). Researchers and analysts leverage customer relationship management (CRM) data through the use of various machine learning models and data transformation methods to identify the customers who are likely to churn. While several studies have been conducted in the customer churn prediction (CCP) context in TCI, a review of performance of the various models stemming from these studies show a clear room for improvement. Therefore, to improve the accuracy of customer churn prediction in the telecommunication industry, we have investigated several machine learning models, as well as, data transformation methods. To optimize the prediction models, feature selection has been performed using univariate technique and the best hyperparameters have been selected using the grid search method. Subsequently, experiments have been conducted on several publicly available TCI datasets to assess the performance of our models in terms of the widely used evaluation metrics, such as AUC, precision, recall, and F-measure. Through a rigorous experimental study, we have demonstrated the benefit of applying data transformation methods as well as feature selection while training an optimized CCP model. Our proposed technique improved the prediction performance by up to 26.2% and 17% in terms of AUC and F-measure, respectively.

Sana Joydeb Kumar, Abedin Mohammad Zoynul, Rahman M Sohel, Rahman M Saifur

2022

General General

Study on exercise muscle fatigue based on sEMG and ECG data fusion and temporal convolutional network.

In PloS one ; h5-index 176.0

BACKGROUND : Muscle fatigue is a crucial indicator to determine whether training is in place and to protect trainers.

PURPOSE : To make full use of morphological information of surface EMG and ECG signals in the time domain, a new idea and method for the fatigue assessment of exercise muscles based on data fusion is proposed in this paper.

METHODS : sEMG and ECG time series with the same length were obtained by signal preprocessing and sequence normalization, feature extraction of sequence tenses was realized by a deep learning network based on sequential convolution and signal fusion model of muscle fatigue evaluation was established by D-S evidence theory.

EXPERIMENT : Thirty volunteers were recruited and divided into three groups. ECG signals and sEMG signals at the biceps brachii of the right upper limb were monitored in a 20-minute exercise cycle.

RESULTS : The prediction result of TCN based on time domain signal is better than the commonly used KNN and SVM recognition algorithm, and the recognition accuracy of relaxed, excessive and fatigue by D-S fusion was 89%, 86%, 88.5%. The accuracy was 0.9055, 0.9494 and 0.9269, respectively. The recall rates of the three conditions were 0.9303, 0.9570 and 0.9435. The F-score of the three conditions was 0.8911, 0.8764 and 0.8837, respectively.

CONCLUSION : Based on time series and time series convolutional network, sEMG and ECG fusion of motor muscle recognition method can better distinguish different state information and has certain practical value in the fields of muscle evaluation, clinical diagnosis, wearable devices and so on.

Mu Dinghong, Li Fenglei, Yu Linxinying, Du Chunlin, Ge Linhua, Sun Tao

2022

General General

A novel hybrid optimization enabled robust CNN algorithm for an IoT network intrusion detection approach.

In PloS one ; h5-index 176.0

Due to the huge number of connected Internet of Things (IoT) devices within a network, denial of service and flooding attacks on networks are on the rise. IoT devices are disrupted and denied service because of these attacks. In this study, we proposed a novel hybrid meta-heuristic adaptive particle swarm optimization-whale optimizer algorithm (APSO-WOA) for optimization of the hyperparameters of a convolutional neural network (APSO-WOA-CNN). The APSO-WOA optimization algorithm's fitness value is defined as the validation set's cross-entropy loss function during CNN model training. In this study, we compare our optimization algorithm with other optimization algorithms, such as the APSO algorithm, for optimization of the hyperparameters of CNN. In model training, the APSO-WOA-CNN algorithm achieved the best performance compared to the FNN algorithm, which used manual parameter settings. We evaluated the APSO-WOA-CNN algorithm against APSO-CNN, SVM, and FNN. The simulation results suggest that APSO-WOA-CNf[N is effective and can reliably detect multi-type IoT network attacks. The results show that the APSO-WOA-CNN algorithm improves accuracy by 1.25%, average precision by 1%, the kappa coefficient by 11%, Hamming loss by 1.2%, and the Jaccard similarity coefficient by 2%, as compared to the APSO-CNN algorithm, and the APSO-CNN algorithm achieves the best performance, as compared to other algorithms.

Bahaa Ahmed, Sayed Abdalla, Elfangary Laila, Fahmy Hanan

2022

General General

Mastering the game of Stratego with model-free multiagent reinforcement learning.

In Science (New York, N.Y.)

We introduce DeepNash, an autonomous agent that plays the imperfect information game Stratego at a human expert level. Stratego is one of the few iconic board games that artificial intelligence (AI) has not yet mastered. It is a game characterized by a twin challenge: It requires long-term strategic thinking as in chess, but it also requires dealing with imperfect information as in poker. The technique underpinning DeepNash uses a game-theoretic, model-free deep reinforcement learning method, without search, that learns to master Stratego through self-play from scratch. DeepNash beat existing state-of-the-art AI methods in Stratego and achieved a year-to-date (2022) and all-time top-three ranking on the Gravon games platform, competing with human expert players.

Perolat Julien, De Vylder Bart, Hennes Daniel, Tarassov Eugene, Strub Florian, de Boer Vincent, Muller Paul, Connor Jerome T, Burch Neil, Anthony Thomas, McAleer Stephen, Elie Romuald, Cen Sarah H, Wang Zhe, Gruslys Audrunas, Malysheva Aleksandra, Khan Mina, Ozair Sherjil, Timbers Finbarr, Pohlen Toby, Eccles Tom, Rowland Mark, Lanctot Marc, Lespiau Jean-Baptiste, Piot Bilal, Omidshafiei Shayegan, Lockhart Edward, Sifre Laurent, Beauguerlange Nathalie, Munos Remi, Silver David, Singh Satinder, Hassabis Demis, Tuyls Karl

2022-Dec-02

General General

An attention-based recurrent learning model for short-term travel time prediction.

In PloS one ; h5-index 176.0

With the advent of Big Data technology and the Internet of Things, Intelligent Transportation Systems (ITS) have become inevitable for future transportation networks. Travel time prediction (TTP) is an essential part of ITS and plays a pivotal role in congestion avoidance and route planning. The novel data sources such as smartphones and in-vehicle navigation applications allow traffic conditions in smart cities to be analyzed and forecast more reliably than ever. Such a massive amount of geospatial data provides a rich source of information for TTP. Gated Recurrent Unit (GRU) has been successfully applied to traffic prediction problems due to its ability to handle long-term traffic sequences. However, the existing GRU does not consider the relationship between various historical travel time positions in the sequences for traffic prediction. We propose an attention-based GRU model for short-term travel time prediction to cope with this problem enabling GRU to learn the relevant context in historical travel time sequences and update the weights of hidden states accordingly. We evaluated the proposed model using FCD data from Beijing. To demonstrate the generalization of our proposed model, we performed a robustness analysis by adding noise obeying Gaussian distribution. The experimental results on test data indicated that our proposed model performed better than the existing deep learning time-series models in terms of Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Coefficient of Determination (R2).

Chughtai Jawad-Ur-Rehman, Haq Irfan Ul, Muneeb Muhammad

2022

General General

Intelligent personalized shopping recommendation using clustering and supervised machine learning algorithms.

In PloS one ; h5-index 176.0

Next basket recommendation is a critical task in market basket data analysis. It is particularly important in grocery shopping, where grocery lists are an essential part of shopping habits of many customers. In this work, we first present a new grocery Recommender System available on the MyGroceryTour platform. Our online system uses different traditional machine learning (ML) and deep learning (DL) algorithms, and provides recommendations to users in a real-time manner. It aims to help Canadian customers create their personalized intelligent weekly grocery lists based on their individual purchase histories, weekly specials offered in local stores, and product cost and availability information. We perform clustering analysis to partition given customer profiles into four non-overlapping clusters according to their grocery shopping habits. Then, we conduct computational experiments to compare several traditional ML algorithms and our new DL algorithm based on the use of a gated recurrent unit (GRU)-based recurrent neural network (RNN) architecture. Our DL algorithm can be viewed as an extension of DREAM (Dynamic REcurrent bAsket Model) adapted to multi-class (i.e. multi-store) classification, since a given user can purchase recommended products in different grocery stores in which these products are available. Among traditional ML algorithms, the highest average F-score of 0.516 for the considered data set of 831 customers was obtained using Random Forest, whereas our proposed DL algorithm yielded the average F-score of 0.559 for this data set. The main advantage of the presented Recommender System is that our intelligent recommendation is personalized, since a separate traditional ML or DL model is built for each customer considered. Such a personalized approach allows us to outperform the prediction results provided by general state-of-the-art DL models.

Chabane Nail, Bouaoune Achraf, Tighilt Reda, Abdar Moloud, Boc Alix, Lord Etienne, Tahiri Nadia, Mazoure Bogdan, Acharya U Rajendra, Makarenkov Vladimir

2022

Public Health Public Health

Ten quick tips for sequence-based prediction of protein properties using machine learning.

In PLoS computational biology

The ubiquitous availability of genome sequencing data explains the popularity of machine learning-based methods for the prediction of protein properties from their amino acid sequences. Over the years, while revising our own work, reading submitted manuscripts as well as published papers, we have noticed several recurring issues, which make some reported findings hard to understand and replicate. We suspect this may be due to biologists being unfamiliar with machine learning methodology, or conversely, machine learning experts may miss some of the knowledge needed to correctly apply their methods to proteins. Here, we aim to bridge this gap for developers of such methods. The most striking issues are linked to a lack of clarity: how were annotations of interest obtained; which benchmark metrics were used; how are positives and negatives defined. Others relate to a lack of rigor: If you sneak in structural information, your method is not sequence-based; if you compare your own model to "state-of-the-art," take the best methods; if you want to conclude that some method is better than another, obtain a significance estimate to support this claim. These, and other issues, we will cover in detail. These points may have seemed obvious to the authors during writing; however, they are not always clear-cut to the readers. We also expect many of these tips to hold for other machine learning-based applications in biology. Therefore, many computational biologists who develop methods in this particular subject will benefit from a concise overview of what to avoid and what to do instead.

Hou Qingzhen, Waury Katharina, Gogishvili Dea, Feenstra K Anton

2022-Dec

General General

Bilingual Language Experience and Its Effect on Conflict Adaptation in Reactive Inhibitory Control Tasks.

In Psychological science ; h5-index 93.0

We used machine-learning techniques to assess interactions between language and cognitive systems related to inhibitory control and conflict adaptation in reactive control tasks. We built theoretically driven candidate models of Simon and Number Stroop task data (N = 777 adult bilinguals ages 18-43 years living in Montréal, Canada) that differed in whether bilingual experience interacted with inhibitory control, including two forms of conflict adaptation: shorter term sequential congruency effects and longer term trial order effects. Models with continuous aspects of bilingual experience provided signal in predicting new, unmodeled data. Specifically, mixed language usage predicted trial order adaptation to conflict. This effect was restricted to Number Stroop, which overtly involves linguistic or symbolic information and relatively higher language- and response-related uncertainty. These results suggest that bilingual experience adaptively tunes aspects of the control system and offers a novel integrative modeling approach that can be used to pursue other complex individual difference questions within the psychological sciences.

Gullifer Jason W, Pivneva Irina, Whitford Veronica, Sheikh Naveed A, Titone Debra

2022-Dec-01

bilingualism, conflict adaptation, individual differences, reactive control

General General

NigraNet: An automatic framework to assess nigral neuromelanin content in early Parkinson's disease using convolutional neural network.

In NeuroImage. Clinical

BACKGROUND : Parkinson's disease (PD) demonstrates neurodegenerative changes in the substantia nigra pars compacta (SNc) using neuromelanin-sensitive (NM)-MRI. As SNc manual segmentation is prone to substantial inter-individual variability across raters, development of a robust automatic segmentation framework is necessary to facilitate nigral neuromelanin quantification. Artificial intelligence (AI) is gaining traction in the neuroimaging community for automated brain region segmentation tasks using MRI.

OBJECTIVE : Developing and validating AI-based NigraNet, a fully automatic SNc segmentation framework allowing nigral neuromelanin quantification in patients with PD using NM-MRI.

METHODS : We prospectively included 199 participants comprising 144 early-stage idiopathic PD patients (disease duration = 1.5 ± 1.0 years) and 55 healthy volunteers (HV) scanned using a 3 Tesla MRI including whole brain T1-weighted anatomical imaging and NM-MRI. The regions of interest (ROI) were delineated in all participants automatically using NigraNet, a modified U-net, and compared to manual segmentations performed by two experienced raters. The SNc volumes (Vol), volumes corrected by total intracranial volume (Cvol), normalized signal intensity (NSI) and contrast-to-noise ratio (CNR) were computed. One-way GLM-ANCOVA was performed while adjusting for age and sex as covariates. Diagnostic performance measurement was assessed using the receiver operating characteristic (ROC) analysis. Inter and intra-observer variability were estimated using Dice similarity coefficient (DSC). The agreements between methods were tested using intraclass correlation coefficient (ICC) based on a mean-rating, two-way, mixed-effects model estimates for absolute agreement. Cronbach's alpha and Bland-Altman plots were estimated to assess inter-method consistency.

RESULTS : Using both methods, Vol, Cvol, NSI and CNR measurements differed between PD and HV with an effect of sex for Cvol and CNR. ICC values between the methods demonstrated optimal agreement for Cvol and CNR (ICC > 0.9) and high reproducibility (DSC: 0.80) was also obtained. The SNc measurements also showed good to excellent consistency values (Cronbach's alpha > 0.87). Bland-Altman plots of agreement demonstrated no association of SNc ROI measurement differences between the methods and ROI average measurements while confirming that 95 % of the data points were ranging between the limits of mean difference (d ± 1.96xSD). Percentage changes between PD and HV were -27.4 % and -17.7 % for Vol, -30.0 % and -22.2 % for Cvol, -15.8 % and -14.4 % for NSI, -17.1 % and -16.0 % for CNR for automatic and manual measurements respectively. Using automatic method, in the entire dataset, we obtained the areas under the ROC curve (AUC) of 0.83 for Vol, 0.85 for Cvol, 0.79 for NSI and 0.77 for CNR whereas in the training dataset of 0.96 for Vol, 0.95 for Cvol, 0.85 for NSI and 0.85 for CNR. Disease duration correlated negatively with NSI of the patients for both the automatic and manual measurements.

CONCLUSIONS : We presented an AI-based NigraNet framework that utilizes a small MRI training dataset to fully automatize the SNc segmentation procedure with an increased precision and more reproducible results. Considering the consistency, accuracy and speed of our approach, this study could be a crucial step towards the implementation of a time-saving non-rater dependent fully automatic method for studying neuromelanin changes in clinical settings and large-scale neuroimaging studies.

Gaurav Rahul, Valabrègue Romain, Yahia-Chérif Lydia, Mangone Graziella, Narayanan Sridar, Arnulf Isabelle, Vidailhet Marie, Corvol Jean-Christophe, Lehéricy Stéphane

2022-Oct-31

Artificial Intelligence, Convolutional Neural Networks, Deep Learning, MRI, Neuromelanin, Parkinson’s Disease, Substantia Nigra

Public Health Public Health

Symptom diaries as a digital tool to detect SARS-CoV-2 infections and differentiate between prevalent variants.

In Frontiers in public health

The COVID-19 pandemic and the high numbers of infected individuals pose major challenges for public health departments. To overcome these challenges, the health department in Cologne has developed a software called DiKoMa. This software offers the possibility to track contact and index persons, but also provides a digital symptom diary. In this work, the question of whether these can also be used for diagnostic purposes will be investigated. Machine learning makes it possible to identify infections based on early symptom profiles and to distinguish between the predominant dominant variants. Focusing on the occurrence of the symptoms in the first week, a decision tree is trained for the differentiation between contact and index persons and the prevailing dominant variants (Wildtype, Alpha, Delta, and Omicron). The model is evaluated, using sex- and age-stratified cross-validation and validated by symptom profiles of the first 6 days. The variants achieve an AUC-ROC from 0.89 for Omicron and 0.6 for Alpha. No significant differences are observed for the results of the validation set (Alpha 0.63 and Omicron 0.87). The evaluation of symptom combinations using artificial intelligence can determine the individual risk for the presence of a COVID-19 infection, allows assignment to virus variants, and can contribute to the management of epidemics and pandemics on a national and international level. It can help to reduce the number of specific tests in times of low labor capacity and could help to early identify new virus variants.

Grüne Barbara, Kugler Sabine, Ginzel Sebastian, Wolff Anna, Buess Michael, Kossow Annelene, Küfer-Weiß Annika, Rüping Stefan, Neuhann Florian

2022

SARS-CoV-2, classification, digital symptom diaries, health department, machine learning, prevalent virus variants, symptom combinations

General General

Machine-learning-based prediction of pre-eclampsia using first-trimester maternal characteristics and biomarkers.

In Ultrasound in obstetrics & gynecology : the official journal of the International Society of Ultrasound in Obstetrics and Gynecology

OBJECTIVE : To evaluate the accuracy of predicting the risk of developing pre-eclampsia (PE) according to first-trimester maternal demographic characteristics, medical history and biomarkers using artificial-intelligence and machine-learning methods.

METHODS : The data were derived from prospective non-interventional screening for PE at 11-13 weeks' gestation at two maternity hospitals in the UK. The data were divided into three subsets. The first set, including 30 437 subjects, was used to develop the training process, the second set of 10 000 subjects was utilized to optimize the machine-learning hyperparameters and the third set of 20 352 subjects was coded and used for model validation. An artificial neural network was used to predict from the demographic characteristics and medical history the prior risk that was then combined with biomarker values to determine the risk of PE and preterm PE with delivery at < 37 weeks' gestation. An additional network was trained without including race as input. Biomarkers included uterine artery pulsatility index (UtA-PI), mean arterial blood pressure (MAP), placental growth factor (PlGF) and pregnancy-associated plasma protein-A. All markers were entered using raw values without conversion into standardized multiples of the median. The prediction accuracy was estimated using the area under the receiver-operating-characteristics curve (AUC). We further computed the detection rate at 10%, 20% and 40% false-positive rates (FPR). The impact of taking aspirin was also added. Shapley values were calculated to evaluate the contribution of each parameter to the prediction of risk. We used a non-parametric test to compare the expected AUC with the one obtained when we randomly scrambled the labels and kept the predictions. For the general prediction, we performed 10 000 permutations of the labels. When the AUC was higher than the one obtained in all 10 000 permutations, we reported a P-value of < 0.0001. For the race-specific analysis, we performed 1000 permutations. When the AUC was higher than the AUC in permutations, we reported a P-value of < 0.001.

RESULTS : The detection rate for preterm PE vs no PE, at a 10% FPR, was 53.3% when screening by maternal factors only, and the corresponding AUC was 0.816; these increased to 75.3% and 0.909, respectively, with the addition of biomarkers into the model. Information on race was important for the prediction accuracy; when race was not used to train the model, at a 10% FPR, the detection rate of preterm PE vs no PE decreased to 34.5-45.5% (for different races) when screening by maternal factors only and to 55.0-62.1% when biomarkers were added. The major predictors of PE were high MAP and UtA-PI, and low PlGF. The accuracy of prediction of all PE cases was lower than that for preterm PE. Aspirin use was recommended for cases who were at high risk of preterm PE. The AUC of all PE vs no PE was 0.770 when screening by maternal factors and 0.817 when the biomarkers were added; the respective detection rates, at a 10% FPR, were 41.3% and 52.9%.

CONCLUSIONS : Screening for PE using a non-linear machine-learning-based approach does not require a population-based normalization, and its performance is similar to that of logistic regression. Removing race information from the model reduces its prediction accuracy, especially for the non-white populations when only maternal factors are considered. © 2022 International Society of Ultrasound in Obstetrics and Gynecology.

Ansbacher-Feldman Z, Syngelaki A, Meiri H, Cirkin R, Nicolaides K H, Louzoun Y

2022-Dec

artificial intelligence, first trimester, machine learning, mean arterial pressure, neural network, placental growth factor, posterior risk, pre-eclampsia, prior risk, uterine artery Doppler

General General

Integration of Artificial Intelligence Into Sociotechnical Work Systems-Effects of Artificial Intelligence Solutions in Medical Imaging on Clinical Efficiency: Protocol for a Systematic Literature Review.

In JMIR research protocols ; h5-index 26.0

BACKGROUND : When introducing artificial intelligence (AI) into clinical care, one of the main objectives is to improve workflow efficiency because AI-based solutions are expected to take over or support routine tasks.

OBJECTIVE : This study sought to synthesize the current knowledge base on how the use of AI technologies for medical imaging affects efficiency and what facilitators or barriers moderating the impact of AI implementation have been reported.

METHODS : In this systematic literature review, comprehensive literature searches will be performed in relevant electronic databases, including PubMed/MEDLINE, Embase, PsycINFO, Web of Science, IEEE Xplore, and CENTRAL. Studies in English and German published from 2000 onwards will be included. The following inclusion criteria will be applied: empirical studies targeting the workflow integration or adoption of AI-based software in medical imaging used for diagnostic purposes in a health care setting. The efficiency outcomes of interest include workflow adaptation, time to complete tasks, and workload. Two reviewers will independently screen all retrieved records, full-text articles, and extract data. The study's methodological quality will be appraised using suitable tools. The findings will be described qualitatively, and a meta-analysis will be performed, if possible. Furthermore, a narrative synthesis approach that focuses on work system factors affecting the integration of AI technologies reported in eligible studies will be adopted.

RESULTS : This review is anticipated to begin in September 2022 and will be completed in April 2023.

CONCLUSIONS : This systematic review and synthesis aims to summarize the existing knowledge on efficiency improvements in medical imaging through the integration of AI into clinical workflows. Moreover, it will extract the facilitators and barriers of the AI implementation process in clinical care settings. Therefore, our findings have implications for future clinical implementation processes of AI-based solutions, with a particular focus on diagnostic procedures. This review is additionally expected to identify research gaps regarding the focus on seamless workflow integration of novel technologies in clinical settings.

TRIAL REGISTRATION : PROSPERO CRD42022303439; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=303439.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID) : PRR1-10.2196/40485.

Wenderott Katharina, Gambashidze Nikoloz, Weigl Matthias

2022-Dec-01

adoption, artificial intelligence, barrier, clinical care, clinical efficiency, diagnoses, diagnosis, diagnostic, digital health, facilitator, implementation, library science, literature review, literature search, medical librarian, narrative review, narrative synthesis, review methodology, search strategy, sociotechnical, sociotechnical work system, systematic review

Cardiology Cardiology

Interpretable Machine Learning Prediction of Drug-Induced QT Prolongation: Electronic Health Record Analysis.

In Journal of medical Internet research ; h5-index 88.0

BACKGROUND : Drug-induced long-QT syndrome (diLQTS) is a major concern among patients who are hospitalized, for whom prediction models capable of identifying individualized risk could be useful to guide monitoring. We have previously demonstrated the feasibility of machine learning to predict the risk of diLQTS, in which deep learning models provided superior accuracy for risk prediction, although these models were limited by a lack of interpretability.

OBJECTIVE : In this investigation, we sought to examine the potential trade-off between interpretability and predictive accuracy with the use of more complex models to identify patients at risk for diLQTS. We planned to compare a deep learning algorithm to predict diLQTS with a more interpretable algorithm based on cluster analysis that would allow medication- and subpopulation-specific evaluation of risk.

METHODS : We examined the risk of diLQTS among 35,639 inpatients treated between 2003 and 2018 with at least 1 of 39 medications associated with risk of diLQTS and who had an electrocardiogram in the system performed within 24 hours of medication administration. Predictors included over 22,000 diagnoses and medications at the time of medication administration, with cases of diLQTS defined as a corrected QT interval over 500 milliseconds after treatment with a culprit medication. The interpretable model was developed using cluster analysis (K=4 clusters), and risk was assessed for specific medications and classes of medications. The deep learning model was created using all predictors within a 6-layer neural network, based on previously identified hyperparameters.

RESULTS : Among the medications, we found that class III antiarrhythmic medications were associated with increased risk across all clusters, and that in patients who are noncritically ill without cardiovascular disease, propofol was associated with increased risk, whereas ondansetron was associated with decreased risk. Compared with deep learning, the interpretable approach was less accurate (area under the receiver operating characteristic curve: 0.65 vs 0.78), with comparable calibration.

CONCLUSIONS : In summary, we found that an interpretable modeling approach was less accurate, but more clinically applicable, than deep learning for the prediction of diLQTS. Future investigations should consider this trade-off in the development of methods for clinical prediction.

Simon Steven T, Trinkley Katy E, Malone Daniel C, Rosenberg Michael Aaron

2022-Dec-01

AI, EHR, ML, artificial intelligence, deep learning, drug-induced QT prolongation, electronic health records, interpretable machine learning, monitoring, prediction, predictive modeling, risk

Surgery Surgery

Current models to understand the onset and progression of scoliotic deformities in adolescent idiopathic scoliosis: a systematic review.

In Spine deformity

PURPOSE : To create an updated and comprehensive overview of the modeling studies that have been done to understand the mechanics underlying deformities of adolescent idiopathic scoliosis (AIS), to predict the risk of curve progression and thereby substantiate etiopathogenetic theories.

METHODS : In this systematic review, an online search in Scopus and PubMed together with an analysis in secondary references was done, which yielded 86 studies. The modeling types were extracted and the studies were categorized accordingly.

RESULTS : Animal modeling, together with machine learning modeling, forms the category of black box models. This category is perceived as the most clinically relevant. While animal models provide a tangible idea of the biomechanical effects in scoliotic deformities, machine learning modeling was found to be the best curve-progression predictor. The second category, that of artificial models, has, just as animal modeling, a tangible model as a result, but focusses more on the biomechanical process of the scoliotic deformity. The third category is formed by computational models, which are very popular in etiopathogenetic parameter-based studies. They are also the best in calculating stresses and strains on vertebrae, intervertebral discs, and other surrounding tissues.

CONCLUSION : This study presents a comprehensive overview of the current modeling techniques to understand the mechanics of the scoliotic deformities, predict the risk of curve progression in AIS and thereby substantiate etiopathogenetic theories. Although AIS remains to be seen as a complex and multifactorial problem, the progression of its deformity can be predicted with good accuracy. Modeling of AIS develops rapidly and may lead to the identification of risk factors and mitigation strategies in the near future. The overview presented provides a basis to follow this development.

Meiring A R, de Kater E P, Stadhouder A, van Royen B J, Breedveld P, Smit T H

2022-Dec-01

Adolescent idiopathic scoliosis, Biomechanics, Curve progression, Modeling, Pathogenesis

General General

LambdaPP: Fast and accessible protein-specific phenotype predictions.

In Protein science : a publication of the Protein Society

The availability of accurate and fast Artificial Intelligence (AI) solutions predicting aspects of proteins are revolutionizing experimental and computational molecular biology. The webserver LambdaPP aspires to supersede PredictProtein, the first internet server making AI protein predictions available in 1992. Given a protein sequence as input, LambdaPP provides easily accessible visualizations of protein 3D structure, along with predictions at the protein level (GeneOntology, subcellular location), and the residue level (binding to metal ions, small molecules, and nucleotides; conservation; intrinsic disorder; secondary structure; alpha-helical and beta-barrel transmembrane segments; signal-peptides; variant effect) in seconds. The structure prediction provided by LambdaPP - leveraging ColabFold and computed in minutes - is based on MMseqs2 multiple sequence alignments. All other feature prediction methods are based on the pLM ProtT5. Queried by a protein sequence, LambdaPP computes protein and residue predictions almost instantly for various phenotypes, including 3D structure and aspects of protein function. This article is protected by copyright. All rights reserved.

Olenyi Tobias, Marquet Céline, Heinzinger Michael, Kröger Benjamin, Nikolova Tiha, Bernhofer Michael, Sändig Philip, Schütze Konstantin, Littmann Maria, Mirdita Milot, Steinegger Martin, Dallago Christian, Rost Burkhard

2022-Dec-01

artificial intelligence, protein annotation, protein function prediction, protein language models, protein structure prediction, web server

General General

Examining AI Methods for Micro-Coaching Dialogs.

In Proceedings of the SIGCHI conference on human factors in computing systems. CHI Conference

Conversational interaction, for example through chatbots, is well-suited to enable automated health coaching tools to support self-management and prevention of chronic diseases. However, chatbots in health are predominantly scripted or rule-based, which can result in a stagnant and repetitive user experience in contrast with more dynamic, data-driven chatbots in other domains. Consequently, little is known about the tradeoffs of pursuing data-driven approaches for health chatbots. We examined multiple artificial intelligence (AI) approaches to enable micro-coaching dialogs in nutrition - brief coaching conversations related to specific meals, to support achievement of nutrition goals - and compared, reinforcement learning (RL), rule-based, and scripted approaches for dialog management. While the data-driven RL chatbot succeeded in shorter, more efficient dialogs, surprisingly the simplest, scripted chatbot was rated as higher quality, despite not fulfilling its task as consistently. These results highlight tensions between scripted and more complex, data-driven approaches for chatbots in health.

Mitchell Elliot G, Elhadad Noémie, Mamykina Lena

2022-Apr

Health coaching, chatbots, conversational agents, reinforcement learning, self-management

General General

A Flexible Iontronic Capacitive Sensing Array for Hand Gesture Recognition Using Deep Convolutional Neural Networks.

In Soft robotics

Hand gesture recognition, one of the most popular research topics in human-machine interaction, is extensively used in visual and augmented reality, sign language translation, prosthesis control, and so on. To improve the flexibility and interactivity of wearable gesture sensing interfaces, flexible electronic systems for gesture recognition have been widely studied. However, these systems are limited in terms of wearability, stability, scalability, and robustness. Herein, we report a flexible wearable hand gesture recognition system that is based on an iontronic capacitive pressure sensing array and deep convolutional neural networks. The entire capacitive array is integrated into a flexible silicone wristband and can be comfortably and conveniently wrapped around the wrist. The pressure sensing array, which is composed of an iontronic film sandwiched between two flexible screen-printed electrode arrays, exhibits a high sensitivity (775.8 kPa-1), fast response time (65 ms), and high durability (over 6000 cycles). Image processing techniques and deep convolutional neural networks are applied for sensor signal feature extraction and hand gesture recognition. Several contexts such as intertrial test (average accuracy of 99.9%), intersession rewearing (average accuracy of 93.2%), electrode shift (average accuracy of 83.2%), and different arm positions during measurement (average accuracy of 93.1%) are evaluated.

Wang Tiantong, Zhao Yunbiao, Wang Qining

2022-Nov-28

deep convolutional neural networks, flexible sensing array, hand gesture recognition, iontronic capacitive sensor

General General

Optimized Data Set and Feature Construction for Substrate Prediction of Membrane Transporters.

In Journal of chemical information and modeling

α-Helical transmembrane proteins termed membrane transporters mediate the passage of small hydrophilic substrate molecules across biological lipid bilayer membranes. Annotating the specific substrates of the dozens to hundreds of individual transporters of an organism is an important task. In the past, machine learning classifiers have been successfully trained on pan-organism data sets to predict putative substrates of transporters. Here, we critically examine the selection of an optimal data set of protein sequence features for the classification task. We focus on membrane transporters of the three model organisms Escherichia coli, Arabidopsis thaliana, and Saccharomyces cerevisiae, as well as human. We show that organism-specific classifiers can be robustly trained if at least 20 samples are available for each substrate class. If information from position-specific scoring matrices is included, such classifiers have F1 scores between 0.85 and 1.00. For the largest data set (A. thaliana), a 4-class classifier yielded an F-score of 0.97. On a pan-organism data set composed of transporters of all four organisms, amino acid and sugar transporters were predicted with an F1 score of 0.91.

Denger Andreas, Helms Volkhard

2022-Dec-01

General General

A Computational Complexity Perspective on Segmentation as a Cognitive Subcomputation.

In Topics in cognitive science

Computational feasibility is a widespread concern that guides the framing and modeling of natural and artificial intelligence. The specification of cognitive system capacities is often shaped by unexamined intuitive assumptions about the search space and complexity of a subcomputation. However, a mistaken intuition might make such initial conceptualizations misleading for what empirical questions appear relevant later on. We undertake here computational-level modeling and complexity analyses of segmentation - a widely hypothesized subcomputation that plays a requisite role in explanations of capacities across domains, such as speech recognition, music cognition, active sensing, event memory, action parsing, and statistical learning - as a case study to show how crucial it is to formally assess these assumptions. We mathematically prove two sets of results regarding computational hardness and search space size that may run counter to intuition, and position their implications with respect to existing views on the subcapacity.

Adolfi Federico, Wareham Todd, van Rooij Iris

2022-Dec-01

Computational complexity, Computational-level analysis, Modeling, Segmentation, Theory, Tractability

oncology Oncology

Different Characteristics in Gut Microbiome between Advanced Adenoma Patients and Colorectal Cancer Patients by Metagenomic Analysis.

In Microbiology spectrum

The occurrence and development of colorectal cancer (CRC) and advanced adenoma (AA) are closely related to the gut microbiome, and AA has a high cancerization progression rate to CRC. Current studies have revealed that bacteriological analysis cannot identify CRC from AA. The objective was to explore microbial targets that could identify CRC and AA from a microecological perspective and to figure out the best way to identify CRC based on fecal microbes. The metagenomic sequencing data were used to describe the gut microbiome profile and analyze the differences between microbial abundance and microbial single nucleotide polymorphism (SNP) characteristics in AA and CRC patients. It was found that there were no significant differences in the diversity between the two groups. The abundance of bacteria (e.g., Firmicutes, Clostridia, and Blautia), fungi (Hypocreales), archaea (Methanosarcina, Methanoculleus, and Methanolacinia), and viruses (Alphacoronavirus, Sinsheimervirus, and Gammaretrovirus) differed between AA and CRC patients. Multiple machine-learning algorithms were used to establish prediction models, aiming to identify CRC and AA. The accuracy of the random forest (RF) model based on the gut microbiome was 86.54%. Nevertheless, the accuracy of SNP was 92.31% in identifying CRC from AA. In conclusion, using microbial SNP was the best method to identify CRC, it was superior to using the gut microbiome, and it could provide new targets for CRC screening. IMPORTANCE There are differences in characteristic microorganisms between AA and CRC. However, current studies have indicated that bacteriological analysis cannot identify CC from AA, and thus, we wondered if there were some other targets that could be used to identify CRC from AA in the gut microbiome. The differences of SNPs in the gut microbiota of intraindividuals were significantly smaller than those of interindividuals. In addition, compared with intestinal microbes, SNP was less affected by time with certain stability. It was discovered that microbial SNP was better than the gut microbiome for identifying CRC from AA. Therefore, screening characteristic microbial SNP could provide a new research direction for identifying CRC from AA.

Han Shuwen, Zhuang Jing, Pan Yuefen, Wu Wei, Ding Kefeng

2022-Dec-01

SNP, artificial intelligence, colorectal cancer, gut microbiome, metagenomic sequencing

Cardiology Cardiology

A comparative study of pretrained language models for long clinical text.

In Journal of the American Medical Informatics Association : JAMIA

OBJECTIVE : Clinical knowledge-enriched transformer models (eg, ClinicalBERT) have state-of-the-art results on clinical natural language processing (NLP) tasks. One of the core limitations of these transformer models is the substantial memory consumption due to their full self-attention mechanism, which leads to the performance degradation in long clinical texts. To overcome this, we propose to leverage long-sequence transformer models (eg, Longformer and BigBird), which extend the maximum input sequence length from 512 to 4096, to enhance the ability to model long-term dependencies in long clinical texts.

MATERIALS AND METHODS : Inspired by the success of long-sequence transformer models and the fact that clinical notes are mostly long, we introduce 2 domain-enriched language models, Clinical-Longformer and Clinical-BigBird, which are pretrained on a large-scale clinical corpus. We evaluate both language models using 10 baseline tasks including named entity recognition, question answering, natural language inference, and document classification tasks.

RESULTS : The results demonstrate that Clinical-Longformer and Clinical-BigBird consistently and significantly outperform ClinicalBERT and other short-sequence transformers in all 10 downstream tasks and achieve new state-of-the-art results.

DISCUSSION : Our pretrained language models provide the bedrock for clinical NLP using long texts. We have made our source code available at https://github.com/luoyuanlab/Clinical-Longformer, and the pretrained models available for public download at: https://huggingface.co/yikuan8/Clinical-Longformer.

CONCLUSION : This study demonstrates that clinical knowledge-enriched long-sequence transformers are able to learn long-term dependencies in long clinical text. Our methods can also inspire the development of other domain-enriched long-sequence transformers.

Li Yikuan, Wehbe Ramsey M, Ahmad Faraz S, Wang Hanyin, Luo Yuan

2022-Nov-30

clinical natural language processing, named entity recognition, natural language inference, question answering, text classification

Pathology Pathology

Computational approaches for network-based integrative multi-omics analysis.

In Frontiers in molecular biosciences

Advances in omics technologies allow for holistic studies into biological systems. These studies rely on integrative data analysis techniques to obtain a comprehensive view of the dynamics of cellular processes, and molecular mechanisms. Network-based integrative approaches have revolutionized multi-omics analysis by providing the framework to represent interactions between multiple different omics-layers in a graph, which may faithfully reflect the molecular wiring in a cell. Here we review network-based multi-omics/multi-modal integrative analytical approaches. We classify these approaches according to the type of omics data supported, the methods and/or algorithms implemented, their node and/or edge weighting components, and their ability to identify key nodes and subnetworks. We show how these approaches can be used to identify biomarkers, disease subtypes, crosstalk, causality, and molecular drivers of physiological and pathological mechanisms. We provide insight into the most appropriate methods and tools for research questions as showcased around the aetiology and treatment of COVID-19 that can be informed by multi-omics data integration. We conclude with an overview of challenges associated with multi-omics network-based analysis, such as reproducibility, heterogeneity, (biological) interpretability of the results, and we highlight some future directions for network-based integration.

Agamah Francis E, Bayjanov Jumamurat R, Niehues Anna, Njoku Kelechi F, Skelton Michelle, Mazandu Gaston K, Ederveen Thomas H A, Mulder Nicola, Chimusa Emile R, ‘t Hoen Peter A C

2022

data integration, machine learning, multi-modal network, multi-omics, network causal inference, network diffusion/propagation

Radiology Radiology

Quantification of Radiomics features of peritumoral vasogenic edema extracted from FLAIR images in glioblastoma and isolated brain metastasis, using T1-DCE perfusion analysis.

In NMR in biomedicine ; h5-index 41.0

The peritumoral vasogenic edema (PVE) in brain tumors exhibits varied characteristics. Brain metastasis (BM) and meningioma barely have tumor cells in PVE, while Glioblastoma (GB) show tumor cell infiltration in most subjects. The purpose of this study was to investigate the PVE of these three pathologies using Radiomics features in FLAIR images, with the hypothesis that the tumor cells might influence textural variation. Ex-vivo experimentation of Radiomics analysis of T1-weighted images of the culture medium with and without suspended tumor cells was also attempted to infer the possible influence of increasing tumor cells on Radiomics features. This retrospective study involved MR images acquired using 3.0T MR machine from 83 patients having 48 GB, 21 BM and 14 Meningioma. The 93 Radiomics features were extracted from each subject's PVE mask from 3 pathologies using T1-DCE MRI. Statistically significant (<0.05, independent samples T-test) features were considered. Features maps were also computed for qualitative investigation. The same was carried out for T1-weighted cell line images but group comparison was carried using One-way ANOVA. Further, a random forest (RF) based machine learning (ML) model was designed to classify the PVE of GB and BM. The texture-based variation especially higher non-uniformity values were observed in the PVE of GB. No significance was observed between BM and Meningioma PVE. In cell line images, the culture medium had higher non-uniformity and considerably reduced with increasing cell densities in 4 features. RF model implemented with highly significant features provided improved AUC results. The possible infiltrative tumor cells in the PVE of the GB are likely influencing the texture values and are higher in comparison with BM PVE and may be of value in differentiation of solitary metastasis from GB. However, the robustness of the features needs to be investigated with larger cohort and across the scanners in future.

Suhail Parvaze P, Bhattacharjee Rupsa, Verma Yogesh Kumar, Singh Rakesh Kumar, Yadav Virendra, Singh Anup, Khanna Gaurav, Ahlawat Sunita, Trivedi Richa, Patir Rana, Vaishya Sandeep, Shah Tejas J, Gupta Rakesh K

2022-Dec-01

oncology Oncology

A Multi-scale, Multi-region and Attention Mechanism-based Deep Learning Framework for Prediction of Grading in Hepatocellular Carcinoma.

In Medical physics ; h5-index 59.0

BACKGROUND : Histopathological grading is a significant risk factor for postsurgical recurrence in hepatocellular carcinoma (HCC). Preoperative knowledge of histopathological grading could provide instructive guidance for individualized treatment decision-making in HCC management.

PURPOSE : This study aims to develop and validate a newly proposed deep learning model to predict histopathological grading in HCC with improved accuracy.

METHODS : In this dual-center study, we retrospectively enrolled 384 HCC patients with complete clinical, pathological and radiological data. Aiming to synthesize radiological information derived from both tumor parenchyma and peritumoral microenvironment regions, a modeling strategy based on a multi-scale and multi-region dense connected convolutional neural network (MSMR-DenseCNNs) was proposed to predict histopathological grading using preoperative contrast enhanced computed tomography (CT) images. Multi-scale inputs were defined as three-scale enlargement of an original minimum bounding box in width and height by given pixels, which correspondingly contained more peritumoral analysis areas with the enlargement. Multi-region inputs were defined as three regions of interest (ROIs) including a squared ROI, a precisely delineated tumor ROI, and a peritumoral tissue ROI. The DenseCNN structure was designed to consist of a shallow feature extraction layer, dense block module, and transition and attention module. The proposed MSMR-DenseCNN was pretrained by the ImageNet dataset to capture basic graphic characteristics from the images and was retrained by the collected retrospective CT images. The predictive ability of the MSMR-DenseCNN models on triphasic images was compared with a conventional radiomics model, radiological model and clinical model.

RESULTS : MSMR-DenseCNN applied to the delayed phase (DP) achieved the highest area under the curve (AUC) of 0.867 in the validation cohort for grading prediction, outperforming those on the arterial phase (AP) and portal venous phase (PVP). Fusion of the results on triphasic images did not increase the predictive ability, which underscored the role of DP for grading prediction. Compared with a single-scale and single-region network, the DP-phase based MSMR-DenseCNN model remarkably raised sensitivity from 67.4% to 75.5% with comparable specificity of 78.6%. MSMR-DenseCNN on DP defeated conventional radiomics, radiological and clinical models, where the AUCs were correspondingly 0.765, 0.695 and 0.612 in the validation cohort.

CONCLUSIONS : The MSMR-DenseCNN modeling strategy increased the accuracy for preoperative prediction of grading in HCC, and enlightens similar radiological analysis pipelines in a variety of clinical scenarios in HCC management. This article is protected by copyright. All rights reserved.

Wei Jingwei, Ji Qian, Gao Yu, Yang Xiaozhen, Guo Donghui, Gu Dongsheng, Yuan Chunwang, Tian Jie, Ding Dawei

2022-Dec-01

computed tomography, deep learning, hepatocellular carcinoma, histopathological grading, radiomics

General General

Impact of Asp/Glu-ADP-ribosylation on protein-protein interaction and protein function.

In Proteomics

PARylation plays critical roles in regulating multiple cellular processes such as DNA damage response and repair, transcription, RNA processing, and stress response. More than 300 human proteins have been found to be modified by PARylation on acidic residues, i.e., Asp (D) and Glu (E). We used the deep-learning tool AlphaFold to predict protein-protein interactions (PPIs) and their interfaces for these proteins based on coevolution signals from joint multiple sequence alignments. AlphaFold predicted 260 confident PPIs involving PARylated proteins, and about one quarter of these PPIs have D/E-PARylation sites in their predicted PPI interfaces. AlphaFold predictions offer novel insights into the mechanisms of PARylation regulations by providing structural details of the PPI interfaces. D/E-PARylation sites have a preference to occur in coil regions and disordered regions, and PPI interfaces containing D/E-PARylation sites tend to occur between short linear sequence motifs in disordered regions and globular domains. The hub protein PCNA is predicted to interact with more than 20 proteins via the common PIP box motif and the structurally variable flanking regions. D/E-PARylation sites were found in the interfaces of key components of the RNA transcription and export complex, the SF3a spliceosome complex, and H/ACA and C/D small nucleolar ribonucleoprotein complexes, suggesting that systematic PARylation have a profound effect in regulating multiple RNA-related processes such as RNA nuclear export, splicing, and modification. Finally, PARylation of SUMO2 could modulate its interaction with CHAF1A, thereby representing a potential mechanism for the cross-talk between PARylation and SUMOylation in regulation of chromatin remodeling. This article is protected by copyright. All rights reserved.

Pei Jimin, Zhang Jing, Wang Xu-Dong, Kim Chiho, Yu Yonghao, Cong Qian

2022-Dec-01

D/E-PARylation, coevolution, interaction interface, protein-protein interaction

General General

Electronic-Structure Properties from Atom-Centered Predictions of the Electron Density.

In Journal of chemical theory and computation

The electron density of a molecule or material has recently received major attention as a target quantity of machine-learning models. A natural choice to construct a model that yields transferable and linear-scaling predictions is to represent the scalar field using a multicentered atomic basis analogous to that routinely used in density fitting approximations. However, the nonorthogonality of the basis poses challenges for the learning exercise, as it requires accounting for all the atomic density components at once. We devise a gradient-based approach to directly minimize the loss function of the regression problem in an optimized and highly sparse feature space. In so doing, we overcome the limitations associated with adopting an atom-centered model to learn the electron density over arbitrarily complex data sets, obtaining very accurate predictions using a comparatively small training set. The enhanced framework is tested on 32-molecule periodic cells of liquid water, presenting enough complexity to require an optimal balance between accuracy and computational efficiency. We show that starting from the predicted density a single Kohn-Sham diagonalization step can be performed to access total energy components that carry an error of just 0.1 meV/atom with respect to the reference density functional calculations. Finally, we test our method on the highly heterogeneous QM9 benchmark data set, showing that a small fraction of the training data is enough to derive ground-state total energies within chemical accuracy.

Grisafi Andrea, Lewis Alan M, Rossi Mariana, Ceriotti Michele

2022-Dec-01

General General

Decoding degeneration: the implementation of machine learning for clinical detection of neurodegenerative disorders.

In Neural regeneration research

Machine learning represents a growing subfield of artificial intelligence with much promise in the diagnosis, treatment, and tracking of complex conditions, including neurodegenerative disorders such as Alzheimer's and Parkinson's diseases. While no definitive methods of diagnosis or treatment exist for either disease, researchers have implemented machine learning algorithms with neuroimaging and motion-tracking technology to analyze pathologically relevant symptoms and biomarkers. Deep learning algorithms such as neural networks and complex combined architectures have proven capable of tracking disease-linked changes in brain structure and physiology as well as patient motor and cognitive symptoms and responses to treatment. However, such techniques require further development aimed at improving transparency, adaptability, and reproducibility. In this review, we provide an overview of existing neuroimaging technologies and supervised and unsupervised machine learning techniques with their current applications in the context of Alzheimer's and Parkinson's diseases.

Khaliq Fariha, Oberhauser Jane, Wakhloo Debia, Mahajani Sameehan

2023-Jun

Alzheimer’s disease, Parkinson’s disease, clinical detection, deep learning, machine learning, neurodegenerative disorders, neuroimaging

Surgery Surgery

Concerns surrounding application of artificial intelligence in hip and knee arthroplasty : a review of literature and recommendations for meaningful adoption.

In The bone & joint journal ; h5-index 53.0

Literature surrounding artificial intelligence (AI)-related applications for hip and knee arthroplasty has proliferated. However, meaningful advances that fundamentally transform the practice and delivery of joint arthroplasty are yet to be realized, despite the broad range of applications as we continue to search for meaningful and appropriate use of AI. AI literature in hip and knee arthroplasty between 2018 and 2021 regarding image-based analyses, value-based care, remote patient monitoring, and augmented reality was reviewed. Concerns surrounding meaningful use and appropriate methodological approaches of AI in joint arthroplasty research are summarized. Of the 233 AI-related orthopaedics articles published, 178 (76%) constituted original research, while the rest consisted of editorials or reviews. A total of 52% of original AI-related research concerns hip and knee arthroplasty (n = 92), and a narrative review is described. Three studies were externally validated. Pitfalls surrounding present-day research include conflating vernacular ("AI/machine learning"), repackaging limited registry data, prematurely releasing internally validated prediction models, appraising model architecture instead of inputted data, withholding code, and evaluating studies using antiquated regression-based guidelines. While AI has been applied to a variety of hip and knee arthroplasty applications with limited clinical impact, the future remains promising if the question is meaningful, the methodology is rigorous and transparent, the data are rich, and the model is externally validated. Simple checkpoints for meaningful AI adoption include ensuring applications focus on: administrative support over clinical evaluation and management; necessity of the advanced model; and the novelty of the question being answered.Cite this article: Bone Joint J 2022;104-B(12):1292-1303.

Polisetty Teja S, Jain Samagra, Pang Michael, Karnuta Jaret M, Vigdorchik Jonathan M, Nawabi Danyal H, Wyles Cody C, Ramkumar Prem N

2022-Dec

Arthroplasty, Artificial intelligence, Concerns, Imaging, Knee, Machine learning, Remote monitoring, TRIPOD, Value, comorbidities, femoral components, hip, hip and knee arthroplasty, hip dislocation, joint arthroplasty, orthopaedic surgeons, radiographs

Public Health Public Health

Modeling approaches for early warning and monitoring of pandemic situations as well as decision support.

In Frontiers in public health

The COVID-19 pandemic has highlighted the lack of preparedness of many healthcare systems against pandemic situations. In response, many population-level computational modeling approaches have been proposed for predicting outbreaks, spatiotemporally forecasting disease spread, and assessing as well as predicting the effectiveness of (non-) pharmaceutical interventions. However, in several countries, these modeling efforts have only limited impact on governmental decision-making so far. In light of this situation, the review aims to provide a critical review of existing modeling approaches and to discuss the potential for future developments.

Botz Jonas, Wang Danqi, Lambert Nicolas, Wagner Nicolas, Génin Marie, Thommes Edward, Madan Sumit, Coudeville Laurent, Fröhlich Holger

2022

agent-based-modeling, artificial intelligence, compartmental models, machine learning, pandemic

Public Health Public Health

Symptom diaries as a digital tool to detect SARS-CoV-2 infections and differentiate between prevalent variants.

In Frontiers in public health

The COVID-19 pandemic and the high numbers of infected individuals pose major challenges for public health departments. To overcome these challenges, the health department in Cologne has developed a software called DiKoMa. This software offers the possibility to track contact and index persons, but also provides a digital symptom diary. In this work, the question of whether these can also be used for diagnostic purposes will be investigated. Machine learning makes it possible to identify infections based on early symptom profiles and to distinguish between the predominant dominant variants. Focusing on the occurrence of the symptoms in the first week, a decision tree is trained for the differentiation between contact and index persons and the prevailing dominant variants (Wildtype, Alpha, Delta, and Omicron). The model is evaluated, using sex- and age-stratified cross-validation and validated by symptom profiles of the first 6 days. The variants achieve an AUC-ROC from 0.89 for Omicron and 0.6 for Alpha. No significant differences are observed for the results of the validation set (Alpha 0.63 and Omicron 0.87). The evaluation of symptom combinations using artificial intelligence can determine the individual risk for the presence of a COVID-19 infection, allows assignment to virus variants, and can contribute to the management of epidemics and pandemics on a national and international level. It can help to reduce the number of specific tests in times of low labor capacity and could help to early identify new virus variants.

Grüne Barbara, Kugler Sabine, Ginzel Sebastian, Wolff Anna, Buess Michael, Kossow Annelene, Küfer-Weiß Annika, Rüping Stefan, Neuhann Florian

2022

SARS-CoV-2, classification, digital symptom diaries, health department, machine learning, prevalent virus variants, symptom combinations

General General

Recommendations for marathon runners: on the application of recommender systems and machine learning to support recreational marathon runners.

In User modeling and user-adapted interaction

Every year millions of people, from all walks of life, spend months training to run a traditional marathon. For some it is about becoming fit enough to complete the gruelling 26.2 mile (42.2 km) distance. For others, it is about improving their fitness, to achieve a new personal-best finish-time. In this paper, we argue that the complexities of training for a marathon, combined with the availability of real-time activity data, provide a unique and worthwhile opportunity for machine learning and for recommender systems techniques to support runners as they train, race, and recover. We present a number of case studies-a mix of original research plus some recent results-to highlight what can be achieved using the type of activity data that is routinely collected by the current generation of mobile fitness apps, smart watches, and wearable sensors.

Smyth Barry, Lawlor Aonghus, Berndsen Jakim, Feely Ciara

2022

Marathon running, Personalised fitness, Recommender systems

General General

Sigma70Pred: A highly accurate method for predicting sigma70 promoter in Escherichia coli K-12 strains.

In Frontiers in microbiology

Sigma70 factor plays a crucial role in prokaryotes and regulates the transcription of most of the housekeeping genes. One of the major challenges is to predict the sigma70 promoter or sigma70 factor binding site with high precision. In this study, we trained and evaluate our models on a dataset consists of 741 sigma70 promoters and 1,400 non-promoters. We have generated a wide range of features around 8,000, which includes Dinucleotide Auto-Correlation, Dinucleotide Cross-Correlation, Dinucleotide Auto Cross-Correlation, Moran Auto-Correlation, Normalized Moreau-Broto Auto-Correlation, Parallel Correlation Pseudo Tri-Nucleotide Composition, etc. Our SVM based model achieved maximum accuracy 97.38% with AUROC 0.99 on training dataset, using 200 most relevant features. In order to check the robustness of the model, we have tested our model on the independent dataset made by using RegulonDB10.8, which included 1,134 sigma70 and 638 non-promoters, and able to achieve accuracy of 90.41% with AUROC of 0.95. Our model successfully predicted constitutive promoters with accuracy of 81.46% on an independent dataset. We have developed a method, Sigma70Pred, which is available as webserver and standalone packages at https://webs.iiitd.edu.in/raghava/sigma70pred/. The services are freely accessible.

Patiyal Sumeet, Singh Nitindeep, Ali Mohd Zartab, Pundir Dhawal Singh, Raghava Gajendra P S

2022

machine learning, prokaryotic genome, promoter, sigma70 factor, transcription

General General

Next-generation proteomics of serum extracellular vesicles combined with single-cell RNA sequencing identifies MACROH2A1 associated with refractory COVID-19.

In Inflammation and regeneration

BACKGROUND : The coronavirus disease 2019 (COVID-19) pandemic is widespread; however, accurate predictors of refractory cases have not yet been established. Circulating extracellular vesicles, involved in many pathological processes, are ideal resources for biomarker exploration.

METHODS : To identify potential serum biomarkers and examine the proteins associated with the pathogenesis of refractory COVID-19, we conducted high-coverage proteomics on serum extracellular vesicles collected from 12 patients with COVID-19 at different disease severity levels and 4 healthy controls. Furthermore, single-cell RNA sequencing of peripheral blood mononuclear cells collected from 10 patients with COVID-19 and 5 healthy controls was performed.

RESULTS : Among the 3046 extracellular vesicle proteins that were identified, expression of MACROH2A1 was significantly elevated in refractory cases compared to non-refractory cases; moreover, its expression was increased according to disease severity. In single-cell RNA sequencing of peripheral blood mononuclear cells, the expression of MACROH2A1 was localized to monocytes and elevated in critical cases. Consistently, single-nucleus RNA sequencing of lung tissues revealed that MACROH2A1 was highly expressed in monocytes and macrophages and was significantly elevated in fatal COVID-19. Moreover, molecular network analysis showed that pathways such as "estrogen signaling pathway," "p160 steroid receptor coactivator (SRC) signaling pathway," and "transcriptional regulation by STAT" were enriched in the transcriptome of monocytes in the peripheral blood mononuclear cells and lungs, and they were also commonly enriched in extracellular vesicle proteomics.

CONCLUSIONS : Our findings highlight that MACROH2A1 in extracellular vesicles is a potential biomarker of refractory COVID-19 and may reflect the pathogenesis of COVID-19 in monocytes.

Kawasaki Takahiro, Takeda Yoshito, Edahiro Ryuya, Shirai Yuya, Nogami-Itoh Mari, Matsuki Takanori, Kida Hiroshi, Enomoto Takatoshi, Hara Reina, Noda Yoshimi, Adachi Yuichi, Niitsu Takayuki, Amiya Saori, Yamaguchi Yuta, Murakami Teruaki, Kato Yasuhiro, Morita Takayoshi, Yoshimura Hanako, Yamamoto Makoto, Nakatsubo Daisuke, Miyake Kotaro, Shiroyama Takayuki, Hirata Haruhiko, Adachi Jun, Okada Yukinori, Kumanogoh Atsushi

2022-Nov-30

COVID-19, Exosome, Liquid biopsy, MACROH2A1, Multi-omics, SARS-CoV-2

General General

Radiomorphological signs and clinical severity of SARS-CoV-2 lineage B.1.1.7.

In BJR open

OBJECTIVE : We aimed to assess the differences in the severity and chest-CT radiomorphological signs of SARS-CoV-2 B.1.1.7 and non-B.1.1.7 variants.

METHODS : We collected clinical data of consecutive patients with laboratory-confirmed COVID-19 and chest-CT imaging who were admitted to the Emergency Department between September 1- November 13, 2020 (non-B.1.1.7 cases) and March 1-March 18, 2021 (B.1.1.7 cases). We also examined the differences in the severity and radiomorphological features associated with COVID-19 pneumonia. Total pneumonia burden (%), mean attenuation of ground-glass opacities and consolidation were quantified using deep-learning research software.

RESULTS : The final population comprised 500 B.1.1.7 and 500 non-B.1.1.7 cases. Patients with B.1.1.7 infection were younger (58.5 ± 15.6 vs 64.8 ± 17.3; p < .001) and had less comorbidities. Total pneumonia burden was higher in the B.1.1.7 patient group (16.1% [interquartile range (IQR):6.0-34.2%] vs 6.6% [IQR:1.2-18.3%]; p < .001). In the age-specific analysis, in patients <60 years B.1.1.7 pneumonia had increased consolidation burden (0.1% [IQR:0.0-0.7%] vs 0.1% [IQR:0.0-0.2%]; p < .001), and severe COVID-19 was more prevalent (11.5% vs  4.9%; p = .032). Mortality rate was similar in all age groups.

CONCLUSION : Despite B.1.1.7 patients were younger and had fewer comorbidities, they experienced more severe disease than non-B.1.1.7 patients, however, the risk of death was the same between the two groups.

ADVANCES IN KNOWLEDGE : Our study provides data on deep-learning based quantitative lung lesion burden and clinical outcomes of patients infected by B.1.1.7 VOC. Our findings might serve as a model for later investigations, as new variants are emerging across the globe.

Simon Judit, Grodecki Kajetan, Cadet Sebastian, Killekar Aditya, Slomka Piotr, Zara Samuel James, Zsarnóczay Emese, Nardocci Chiara, Nagy Norbert, Kristóf Katalin, Vásárhelyi Barna, Müller Veronika, Merkely Béla, Dey Damini, Maurovich-Horvat Pál

2022

General General

Influence of host genotype in establishing root associated microbiome of indica rice cultivars for plant growth promotion.

In Frontiers in microbiology

Rice plants display a unique root ecosystem comprising oxic-anoxic zones, harboring a plethora of metabolic interactions mediated by its root microbiome. Since agricultural land is limited, an increase in rice production will rely on novel methods of yield enhancement. The nascent concept of tailoring plant phenotype through the intervention of synthetic microbial communities (SynComs) is inspired by the genetics and ecology of core rhizobiome. In this direction, we have studied structural and functional variations in the root microbiome of 10 indica rice varieties. The studies on α and β-diversity indices of rhizospheric root microbiome with the host genotypes revealed variations in the structuring of root microbiome as well as a strong association with the host genotypes. Biomarker discovery, using machine learning, highlighted members of class Anaerolineae, α-Proteobacteria, and bacterial genera like Desulfobacteria, Ca. Entotheonella, Algoriphagus, etc. as the most important features of indica rice microbiota having a role in improving the plant's fitness. Metabolically, rice rhizobiomes showed an abundance of genes related to sulfur oxidation and reduction, biofilm production, nitrogen fixation, denitrification, and phosphorus metabolism. This comparative study of rhizobiomes has outlined the taxonomic composition and functional diversification of rice rhizobiome, laying the foundation for the development of next-generation microbiome-based technologies for yield enhancement in rice and other crops.

Singh Arjun, Kumar Murugan, Chakdar Hillol, Pandiyan Kuppusamy, Kumar Shiv Charan, Zeyad Mohammad Tarique, Singh Bansh Narayan, Ravikiran K T, Mahto Arunima, Srivastava Alok Kumar, Saxena Anil Kumar

2022

PiCRUST, SynComs, community metagenomics, indica rice, machine learning

General General

Multiset multicover methods for discriminative marker selection.

In Cell reports methods

Markers are increasingly being used for several high-throughput data analysis and experimental design tasks. Examples include the use of markers for assigning cell types in scRNA-seq studies, for deconvolving bulk gene expression data, and for selecting marker proteins in single-cell spatial proteomics studies. Most marker selection methods focus on differential expression (DE) analysis. Although such methods work well for data with a few non-overlapping marker sets, they are not appropriate for large atlas-size datasets where several cell types and tissues are considered. To address this, we define the phenotype cover (PC) problem for marker selection and present algorithms that can improve the discriminative power of marker sets. Analysis of these sets on several marker-selection tasks suggests that these methods can lead to solutions that accurately distinguish different phenotypes in the data.

Hasanaj Euxhen, Alavi Amir, Gupta Anupam, Póczos Barnabás, Bar-Joseph Ziv

2022-Nov-21

algorithm, biomarker, cross-entropy method, gene sets, marker discovery, multiset multicover, phenotype cover, scRNA-seq, set cover

Surgery Surgery

Accurate preoperative staging and HER2 status prediction of gastric cancer by the deep learning system based on enhanced computed tomography.

In Frontiers in oncology

PURPOSE : To construct the deep learning system (DLS) based on enhanced computed tomography (CT) images for preoperative prediction of staging and human epidermal growth factor receptor 2 (HER2) status in gastric cancer patients.

METHODS : The raw enhanced CT image dataset consisted of CT images of 389 patients in the retrospective cohort, The Cancer Imaging Archive (TCIA) cohort, and the prospective cohort. DLS was developed by transfer learning for tumor detection, staging, and HER2 status prediction. The pre-trained Yolov5, EfficientNet, EfficientNetV2, Vision Transformer (VIT), and Swin Transformer (SWT) were studied. The tumor detection and staging dataset consisted of 4860 enhanced CT images and annotated tumor bounding boxes. The HER2 state prediction dataset consisted of 38900 enhanced CT images.

RESULTS : The DetectionNet based on Yolov5 realized tumor detection and staging and achieved a mean Average Precision (IoU=0.5) (mAP_0.5) of 0.909 in the external validation cohort. The VIT-based PredictionNet performed optimally in HER2 status prediction with the area under the receiver operating characteristics curve (AUC) of 0.9721 and 0.9995 in the TCIA cohort and prospective cohort, respectively. DLS included DetectionNet and PredictionNet had shown excellent performance in CT image interpretation.

CONCLUSION : This study developed the enhanced CT-based DLS to preoperatively predict the stage and HER2 status of gastric cancer patients, which will help in choosing the appropriate treatment to improve the survival of gastric cancer patients.

Guan Xiao, Lu Na, Zhang Jianping

2022

CNN, HER2 status, deep learning, gastric cancer, transformer

Pathology Pathology

Computational approaches for network-based integrative multi-omics analysis.

In Frontiers in molecular biosciences

Advances in omics technologies allow for holistic studies into biological systems. These studies rely on integrative data analysis techniques to obtain a comprehensive view of the dynamics of cellular processes, and molecular mechanisms. Network-based integrative approaches have revolutionized multi-omics analysis by providing the framework to represent interactions between multiple different omics-layers in a graph, which may faithfully reflect the molecular wiring in a cell. Here we review network-based multi-omics/multi-modal integrative analytical approaches. We classify these approaches according to the type of omics data supported, the methods and/or algorithms implemented, their node and/or edge weighting components, and their ability to identify key nodes and subnetworks. We show how these approaches can be used to identify biomarkers, disease subtypes, crosstalk, causality, and molecular drivers of physiological and pathological mechanisms. We provide insight into the most appropriate methods and tools for research questions as showcased around the aetiology and treatment of COVID-19 that can be informed by multi-omics data integration. We conclude with an overview of challenges associated with multi-omics network-based analysis, such as reproducibility, heterogeneity, (biological) interpretability of the results, and we highlight some future directions for network-based integration.

Agamah Francis E, Bayjanov Jumamurat R, Niehues Anna, Njoku Kelechi F, Skelton Michelle, Mazandu Gaston K, Ederveen Thomas H A, Mulder Nicola, Chimusa Emile R, ‘t Hoen Peter A C

2022

data integration, machine learning, multi-modal network, multi-omics, network causal inference, network diffusion/propagation

General General

High frame rate (∼3 Hz) circular photoacoustic tomography using single-element ultrasound transducer aided with deep learning.

In Journal of biomedical optics

SIGNIFICANCE : In circular scanning photoacoustic tomography (PAT), it takes several minutes to generate an image of acceptable quality, especially with a single-element ultrasound transducer (UST). The imaging speed can be enhanced by faster scanning (with high repetition rate light sources) and using multiple-USTs. However, artifacts arising from the sparse signal acquisition and low signal-to-noise ratio at higher scanning speeds limit the imaging speed. Thus, there is a need to improve the imaging speed of the PAT systems without hampering the quality of the PAT image.

AIM : To improve the frame rate (or imaging speed) of the PAT system by using deep learning (DL).

APPROACH : For improving the frame rate (or imaging speed) of the PAT system, we propose a novel U-Net-based DL framework to reconstruct PAT images from fast scanning data.

RESULTS : The efficiency of the network was evaluated on both single- and multiple-UST-based PAT systems. Both phantom and in vivo imaging demonstrate that the network can improve the imaging frame rate by approximately sixfold in single-UST-based PAT systems and by approximately twofold in multi-UST-based PAT systems.

CONCLUSIONS : We proposed an innovative method to improve the frame rate (or imaging speed) by using DL and with this method, the fastest frame rate of ∼ 3    Hz imaging is achieved without hampering the quality of the reconstructed image.

Rajendran Praveenbalaji, Pramanik Manojit

2022-Jun

circular photoacoustic tomography, deep learning, high framerate imaging, photoacoustic tomography

Surgery Surgery

Hypertriglyceridemia is associated with stroke after non-cardiac, non-neurological surgery in the older patients: A nested case-control study.

In Frontiers in aging neuroscience ; h5-index 64.0

INTRODUCTION : Geriatric postoperative stroke is a rare but serious complication after surgery. The association between hypertriglyceridemia and postoperative stroke remains controversial, especially in older patients undergoing non-cardiac, non-neurological surgery. The study aims to address this clinical dilemma.

MATERIALS AND METHODS : We conducted a nested case-control study among 9601 aged patients undergoing non-cardiac non-neurological surgery from October 2015 to 2021. A total of 22 positive cases were matched for the surgical type and time, to 88 control patients by a ratio of 1:4. The effect of hypertriglyceridemia on the occurrence of postoperative stroke within 30 days after surgery was estimated using conditional logistic regression analysis by adjusting to various potential confounders.

RESULTS : A total of 22 cases developed ischemia stroke after surgery, and compared with the non-stroke group, they had more postoperative ICU admission, longer postoperative hospitalization and higher total cost (all p < 0.05), and more patients were presenting with preoperative hypertriglyceridemia [8 (36.4%) vs. 15 (17.0%), p = 0.045]. There was a significant association between hypertriglyceridemia and postoperative stroke, with adjusted odds ratios of 6.618 (95% CI 1.286, 34.064) (p = 0.024). The above results remained robust in the sensitivity analyses.

CONCLUSION : Among older patients undergoing non-cardiac and non-neurological surgery, hypertriglyceridemia was associated with significant increased risk of postoperative stroke.

Chen Chaojin, Wen Qianyu, Ma Chuzhou, Li Xiaoyue, Huang Tengchao, Ke Jie, Gong Chulian, Hei Ziqing

2022

elderly patients, hypertriglyceridemia, non-cardiac non-neurological surgery, postoperative stroke, sensitivity analysis

General General

Brain2Pix: Fully convolutional naturalistic video frame reconstruction from brain activity.

In Frontiers in neuroscience ; h5-index 72.0

Reconstructing complex and dynamic visual perception from brain activity remains a major challenge in machine learning applications to neuroscience. Here, we present a new method for reconstructing naturalistic images and videos from very large single-participant functional magnetic resonance imaging data that leverages the recent success of image-to-image transformation networks. This is achieved by exploiting spatial information obtained from retinotopic mappings across the visual system. More specifically, we first determine what position each voxel in a particular region of interest would represent in the visual field based on its corresponding receptive field location. Then, the 2D image representation of the brain activity on the visual field is passed to a fully convolutional image-to-image network trained to recover the original stimuli using VGG feature loss with an adversarial regularizer. In our experiments, we show that our method offers a significant improvement over existing video reconstruction techniques.

Le Lynn, Ambrogioni Luca, Seeliger Katja, Güçlütürk Yağmur, van Gerven Marcel, Güçlü Umut

2022

decoding, fMRI, neural networks, vision, visual reconstruction

General General

Unraveling the impact of Lactobacillus spp. and other urinary microorganisms on the efficacy of mirabegron in female patients with overactive bladder.

In Frontiers in cellular and infection microbiology ; h5-index 53.0

OBJECTIVE : Overactive bladder (OAB) is a disease that seriously affects patients' quality of life and mental health. To address this issue, more and more researchers are examining the relationship between OAB treatment and urinary microecology. In this study, we sought to determine whether differences in treatment efficacy were related to microbiome diversity and composition as well as the abundance of specific genera. Machine learning algorithms were used to construct predictive models for urine microbiota-based treatment of OAB.

METHODS : Urine samples were obtained from 64 adult female OAB patients for 16S rRNA gene sequencing. Patients' overactive bladder symptom scores (OABSS) were collected before and after mirabegron treatment and patients were divided into effective and ineffective groups. The relationship between the relative abundance of certain genera and OABSS were analyzed. Three machine learning algorithms, including random forest (RF), supporting vector machine (SVM) and eXtreme gradient boosting (XGBoost) were utilized to predict the therapeutic effect of mirabegron based on the relative abundance of certain genera in OAB patients' urine microbiome.

RESULTS : The species composition of the two groups differed. For one, the relative abundance of Lactobacillus was significantly higher in the effective group than in the ineffective group. In addition, the relative abundance of Gardnerella and Prevotella in the effective group was significantly lower than in the ineffective group. Alpha-diversity and beta-diversity differed significantly between the two groups. LEfSe analysis revealed that Lactobacillus abundance increased while Prevotella and Gardnerella abundance decreased in the effective group. The Lactobacillus abundance ROC curve had high predictive accuracy. The OABSS after treatment was negatively correlated with the abundance of Lactobacillus, whereas the relationship between OABSS and Prevotella and Gardnerella showed the opposite trend. In addition, RF, SVM and XGBoost models demonstrated high predictive ability to assess the effect of mirabegron in OAB patients in the test cohort.

CONCLUSIONS : The results of this study indicate that urinary microbiota might influence the efficacy of mirabegron, and that Lactobacillus might be a potential marker for evaluating the therapeutic efficacy of mirabegron in OAB patients.

Zhou Zhipeng, Qiu Yifeng, Li Kun, Sun Qi, Xie Ming, Huang Pengcheng, Yu Yao, Wang Benlin, Xue Jingwen, Zhu Zhangrui, Feng Zhengyuan, Zhao Jie, Wu Peng

2022

Lactobacillus, biomarker, female urinary microbiome, mirabegron, overactive bladder

General General

Integration of Artificial Intelligence and CRISPR/Cas9 System for Vaccine Design.

In Cancer informatics

The CRISPR/Cas9 system offers a new approach to genome editing and cancer treatment. This approach is able to detect drug targets and genomic analysis of cancer. The use of artificial intelligence (AI) capacity to edit genomes through CRISPR/Cas9 enables modification of gene mutations, molecular simulation. AI approaches include knowledge discovery approaches, antigen and epitope prediction approaches, and agent based-model approaches. These methods in combination with CRISPR/Cas9 can be used in vaccine design.

Maserat Elham

2022

CRISPR/Cas9, artificial intelligence, knowledge discovery, prediction, vaccine

General General

A Homogeneous Ensemble of Robust Pre-defined Neural Network Enables Automated Annotation of Human Embryo Morphokinetics.

In Journal of reproduction & infertility

BACKGROUND : The purpose of the current study was to reduce the risk of human bias in assessing embryos by automatically annotating embryonic development based on their morphological changes at specified time-points with convolutional neural network (CNN) and artificial intelligence (AI).

METHODS : Time-lapse videos of embryo development were manually annotated by the embryologist and extracted for use as a supervised dataset, where the data were split into 14 unique classifications based on morphological differences. A compilation of homogeneous pre-trained CNN models obtained via TensorFlow Hub was tested with various hyperparameters on a controlled environment using transfer learning to create a new model. Subsequently, the performances of the AI models in correctly annotating embryo morphologies within the 14 designated classifications were compared with a collection of AI models with different built-in configurations so as to derive a model with the highest accuracy.

RESULTS : Eventually, an AI model with a specific configuration and an accuracy score of 67.68% was obtained, capable of predicting the embryo developmental stages (t1, t2, t3, t4, t5, t6, t7, t8, t9+, tCompaction, tM, tSB, tB, tEB).

CONCLUSION : Currently, the technology and research of artificial intelligence and machine learning in the medical field have significantly and continuingly progressed in an effort to develop computer-assisted technology which could potentially increase the efficiency and accuracy of medical personnel's performance. Nonetheless, building AI models with larger data is required to properly increase AI model reliability.

Danardono Gunawan B, Erwin Alva, Purnama James, Handayani Nining, Polim Arie A, Boediono Arief, Sini Ivan

2022

Artificial intelligence, Automation, Computer-assisted image processing, Embryonic development, In vitro fertilization, Machine learning, Neural networks

Radiology Radiology

Identifying hepatocellular carcinoma patients with survival benefits from surgery combined with chemotherapy: based on machine learning model.

In World journal of surgical oncology

BACKGROUND : Hepatocellular carcinoma (HCC) is still fatal even after surgical resection. The purpose of this study was to analyze the prognostic factors of 5-year survival rate and to establish a model to identify HCC patients with gain of surgery combined with chemotherapy.

METHODS : All patients with HCC after surgery from January 2010 to December 2015 were selected from the Surveillance, Epidemiology, and End Results (SEER) database. Univariate and multivariate logistic analysis were used to analyze the prognostic factors of patients, and the risk prediction model of 5-year survival rate of HCC patients was established by classical decision tree method. Propensity score matching was used to eliminate the confounding factors of whether to receive chemotherapy in high-risk group or low-risk group.

RESULTS : One-thousand six-hundred twenty-five eligible HCC patients were included in the study. Marital status, α-fetoprotein (AFP), vascular infiltration, tumor size, number of lesions, and grade were independent prognostic factors affecting the 5-year survival rate of HCC patients. The area under the curve of the 5-year survival risk prediction model constructed from the above variables was 0.76, and the classification accuracy, precision, recall, and F1 scores were 0.752, 0.83, 0.842, and 0.836, respectively. High-risk patients classified according to the prediction model had better 5-year survival rate after chemotherapy, while there was no difference in 5-year survival rate between patients receiving chemotherapy and patients not receiving chemotherapy in the low-risk group.

CONCLUSIONS : The 5-year survival risk prediction model constructed in this study provides accurate survival prediction information. The high-risk patients determined according to the prediction model may benefit from the 5-year survival rate after combined chemotherapy.

Hu Jie, Gong Ni, Li Dan, Deng Youyuan, Chen Jiawei, Luo Dingan, Zhou Wei, Xu Ke

2022-Dec-01

Chemotherapy, Hepatocellular carcinoma, Machine learning, Prognosis, SEER

General General

Next-generation proteomics of serum extracellular vesicles combined with single-cell RNA sequencing identifies MACROH2A1 associated with refractory COVID-19.

In Inflammation and regeneration

BACKGROUND : The coronavirus disease 2019 (COVID-19) pandemic is widespread; however, accurate predictors of refractory cases have not yet been established. Circulating extracellular vesicles, involved in many pathological processes, are ideal resources for biomarker exploration.

METHODS : To identify potential serum biomarkers and examine the proteins associated with the pathogenesis of refractory COVID-19, we conducted high-coverage proteomics on serum extracellular vesicles collected from 12 patients with COVID-19 at different disease severity levels and 4 healthy controls. Furthermore, single-cell RNA sequencing of peripheral blood mononuclear cells collected from 10 patients with COVID-19 and 5 healthy controls was performed.

RESULTS : Among the 3046 extracellular vesicle proteins that were identified, expression of MACROH2A1 was significantly elevated in refractory cases compared to non-refractory cases; moreover, its expression was increased according to disease severity. In single-cell RNA sequencing of peripheral blood mononuclear cells, the expression of MACROH2A1 was localized to monocytes and elevated in critical cases. Consistently, single-nucleus RNA sequencing of lung tissues revealed that MACROH2A1 was highly expressed in monocytes and macrophages and was significantly elevated in fatal COVID-19. Moreover, molecular network analysis showed that pathways such as "estrogen signaling pathway," "p160 steroid receptor coactivator (SRC) signaling pathway," and "transcriptional regulation by STAT" were enriched in the transcriptome of monocytes in the peripheral blood mononuclear cells and lungs, and they were also commonly enriched in extracellular vesicle proteomics.

CONCLUSIONS : Our findings highlight that MACROH2A1 in extracellular vesicles is a potential biomarker of refractory COVID-19 and may reflect the pathogenesis of COVID-19 in monocytes.

Kawasaki Takahiro, Takeda Yoshito, Edahiro Ryuya, Shirai Yuya, Nogami-Itoh Mari, Matsuki Takanori, Kida Hiroshi, Enomoto Takatoshi, Hara Reina, Noda Yoshimi, Adachi Yuichi, Niitsu Takayuki, Amiya Saori, Yamaguchi Yuta, Murakami Teruaki, Kato Yasuhiro, Morita Takayoshi, Yoshimura Hanako, Yamamoto Makoto, Nakatsubo Daisuke, Miyake Kotaro, Shiroyama Takayuki, Hirata Haruhiko, Adachi Jun, Okada Yukinori, Kumanogoh Atsushi

2022-Nov-30

COVID-19, Exosome, Liquid biopsy, MACROH2A1, Multi-omics, SARS-CoV-2

General General

Predicting Immune Escape with Pretrained Protein Language Model Embeddings

bioRxiv Preprint

Assessing the severity of new pathogenic variants requires an understanding of which mutations enable escape of the human immune response. Even single point mutations to an antigen can cause immune escape and infection by disrupting antibody binding. Recent work has modeled the effect of single point mutations on proteins by leveraging the information contained in large-scale, pretrained protein language models (PLMs). PLMs are often applied in a zero-shot setting, where the effect of each mutation is predicted based on the output of the language model with no additional training. However, this approach cannot appropriately model immune escape, which involves the interaction of two proteins--antibody and antigen--instead of one protein and requires making different predictions for the same antigenic mutation in response to different antibodies. Here, we explore several methods for predicting immune escape by building models on top of embeddings from PLMs. We evaluate our methods on a SARS-CoV-2 deep mutational scanning dataset and show that our embedding-based methods significantly outperform zero-shot methods, which have almost no predictive power. We also highlight insights gained into how best to use embeddings from PLMs to predict escape. Despite these promising results, simple statistical and machine learning baseline models that do not use pretraining perform comparably, showing that computationally expensive pretraining approaches may not be beneficial for escape prediction. Furthermore, all models perform relatively poorly, indicating that future work is necessary to improve escape prediction with or without pretrained embeddings.

Swanson, K.; Chang, H.; Zou, J.

2022-12-02

General General

Retracted: Application of Internet of Things Artificial Intelligence and Knowledge Innovation System in Table Tennis Teaching and Training.

In Applied bionics and biomechanics

[This retracts the article DOI: 10.1155/2022/7625626.].

And Biomechanics Applied Bionics

2022

Surgery Surgery

Landscape of sialylation patterns identify biomarkers for diagnosis and prediction of response to anti-TNF therapy in crohn's disease.

In Frontiers in genetics ; h5-index 62.0

Crohn's disease (CD), a subtype of inflammatory bowel disease (IBD), causes chronic gastrointestinal tract inflammation. Thirty percent of patients do not respond to anti-tumor necrosis factor (TNF) therapy. Sialylation is involved in the pathogenesis of IBD. We aimed to identify potential biomarkers for diagnosing CD and predicting anti-TNF medication outcomes in CD. Three potential biomarkers (SERPINB2, TFPI2, and SLC9B2) were screened using bioinformatics analysis and machine learning based on sialylation-related genes. Moreover, the combined model of SERPINB2, TFPI2, and SLC9B2 showed excellent diagnostic value in both the training and validation cohorts. Importantly, a Sial-score was constructed based on the expression of SERPINB2, TFPI2, and SLC9B2. The Sial-low group showed a lower level of immune infiltration than the Sial-high group. Anti-TNF therapy was effective for 94.4% of patients in the Sial-low group but only 15.8% in the Sial-high group. The Sial-score had an outstanding ability to predict and distinguish between responders and non-responders. Our comprehensive analysis indicates that SERPINB2, TFPI2, and SLC9B2 play essential roles in pathogenesis and anti-TNF therapy resistance in CD. Furthermore, it may provide novel concepts for customizing treatment for individual patients with CD.

Ye Chenglin, Zhu Sizhe, Gao Yuan, Huang Yabing

2022

anti-TNF therapy, bioinformatics analysis, crohn’s disease, immune infiltration, sialylation

General General

Radiomorphological signs and clinical severity of SARS-CoV-2 lineage B.1.1.7.

In BJR open

OBJECTIVE : We aimed to assess the differences in the severity and chest-CT radiomorphological signs of SARS-CoV-2 B.1.1.7 and non-B.1.1.7 variants.

METHODS : We collected clinical data of consecutive patients with laboratory-confirmed COVID-19 and chest-CT imaging who were admitted to the Emergency Department between September 1- November 13, 2020 (non-B.1.1.7 cases) and March 1-March 18, 2021 (B.1.1.7 cases). We also examined the differences in the severity and radiomorphological features associated with COVID-19 pneumonia. Total pneumonia burden (%), mean attenuation of ground-glass opacities and consolidation were quantified using deep-learning research software.

RESULTS : The final population comprised 500 B.1.1.7 and 500 non-B.1.1.7 cases. Patients with B.1.1.7 infection were younger (58.5 ± 15.6 vs 64.8 ± 17.3; p < .001) and had less comorbidities. Total pneumonia burden was higher in the B.1.1.7 patient group (16.1% [interquartile range (IQR):6.0-34.2%] vs 6.6% [IQR:1.2-18.3%]; p < .001). In the age-specific analysis, in patients <60 years B.1.1.7 pneumonia had increased consolidation burden (0.1% [IQR:0.0-0.7%] vs 0.1% [IQR:0.0-0.2%]; p < .001), and severe COVID-19 was more prevalent (11.5% vs  4.9%; p = .032). Mortality rate was similar in all age groups.

CONCLUSION : Despite B.1.1.7 patients were younger and had fewer comorbidities, they experienced more severe disease than non-B.1.1.7 patients, however, the risk of death was the same between the two groups.

ADVANCES IN KNOWLEDGE : Our study provides data on deep-learning based quantitative lung lesion burden and clinical outcomes of patients infected by B.1.1.7 VOC. Our findings might serve as a model for later investigations, as new variants are emerging across the globe.

Simon Judit, Grodecki Kajetan, Cadet Sebastian, Killekar Aditya, Slomka Piotr, Zara Samuel James, Zsarnóczay Emese, Nardocci Chiara, Nagy Norbert, Kristóf Katalin, Vásárhelyi Barna, Müller Veronika, Merkely Béla, Dey Damini, Maurovich-Horvat Pál

2022

General General

Predicting Hospice Transitions in Dementia Caregiving Dyads: An Exploratory Machine Learning Approach.

In Innovation in aging

BACKGROUND AND OBJECTIVES : Hospice programs assist people with serious illness and their caregivers with aging in place, avoiding unnecessary hospitalizations, and remaining at home through the end-of-life. While evidence is emerging of the myriad of factors influencing end-of-life care transitions among persons living with dementia, current research is primarily cross- sectional and does not account for the effect that changes over time have on hospice care uptake, access, and equity within dyads.

RESEARCH DESIGN AND METHODS : Secondary data analysis linking the National Health and Aging Trends Study to the National Study of Caregiving investigating important social determinants of health and quality-of-life factors of persons living with dementia and their primary caregivers (n = 117) on hospice utilization over 3 years (2015-2018). We employ cutting-edge machine learning approaches (correlation matrix analysis, principal component analysis, random forest [RF], and information gain ratio [IGR]).

RESULTS : IGR indicators of hospice use include persons living with dementia having diabetes, a regular physician, a good memory rating, not relying on food stamps, not having chewing or swallowing problems, and whether health prevents them from enjoying life (accuracy = 0.685; sensitivity = 0.824; specificity = 0.537; area under the curve (AUC) = 0.743). RF indicates primary caregivers' age, and the person living with dementia's income, census division, number of days help provided by caregiver per month, and whether health prevents them from enjoying life predicts hospice use (accuracy = 0.624; sensitivity = 0.713; specificity = 0.557; AUC = 0.703).

DISCUSSION AND IMPLICATIONS : Our exploratory models create a starting point for the future development of precision health approaches that may be integrated into learning health systems that prompt providers with actionable information about who may benefit from discussions around serious illness goals-for-care. Future work is necessary to investigate those not considered in this study-that is, persons living with dementia who do not use hospice care so additional insights can be gathered around barriers to care.

Sullivan Suzanne S, Bo Wei, Li Chin-Shang, Xu Wenyao, Chang Yu-Ping

2022

Dementia, NHATS, Precision health, Serious illness planning, Social determinants of health

Dermatology Dermatology

Dermoscopy and skin imaging light sources: a comparison and review of spectral power distribution and color consistency.

In Journal of biomedical optics

SIGNIFICANCE : Dermoscopes incorporate light, polarizers, and optical magnification into a handheld tool that is commonly used by dermatologists to evaluate skin findings. Diagnostic accuracy is improved when dermoscopes are used, and some major artificial intelligence (AI) projects have been accomplished using dermocopic images. Color rendering consistency and fidelity are crucial for clinical diagnostics, AI, and image processing applications.

AIM : With many devices available on the market, our objective was to measure the emission spectra of various dermoscopes, compare them with other light sources, and illustrate variations in reflected colors from images of a reference sample.

APPROACH : A spectrometer measured the spectral power distribution (SPD) produced by four dermoscope models and three alternate light sources, illustrating differences in the emission spectra. Most dermoscopes use light-emitting diodes (LEDs), which are inconsistent when compared with one another. An LED was compared with halogen, xenon-arc, and daylight sources. Images of a micro ColorChecker were acquired from several sources, and three specific colors were selected to compare in CIELAB color space. Color consistency and color fidelity measured by color rendering index (CRI) and TM-30-18 graphical vectors show variation in saturation and chroma fidelity.

RESULTS : A marked degree of variation was observed in both the emission and reflected light coming from different dermoscopes and compared with other sources. The same chromophores appeared differently depending on the light source used.

CONCLUSIONS : A lack of uniform illumination resulted in inconsistent image color and likely impacted metamerism and visibility of skin chromophores in real-world settings. Artificial light in skin examinations, especially LEDs, may present challenges for the visual separation of specific colors. Attention to LEDs SPD may be important, especially as the field increases dependency on machine/computer vision.

Hanlon Katharine L, Wei Grace, Correa-Selm Lilia, Grichnik James M

2022-Aug

color rendering, color science, dermoscopy, light-emitting diodes, skin imaging, spectral power distribution

General General

Assuring safe artificial intelligence in critical ambulance service response: study protocol.

In British paramedic journal

INTRODUCTION : Early recognition of out-of-hospital cardiac arrest (OHCA) by ambulance service call centre operators is important so that cardiopulmonary resuscitation can be delivered immediately, but around 25% of OHCAs are not picked up by call centre operators. An artificial intelligence (AI) system has been developed to support call centre operators in the detection of OHCA. The study aims to (1) explore ambulance service stakeholder perceptions on the safety of OHCA AI decision support in call centres, and (2) develop a clinical safety case for the OHCA AI decision-support system.

METHODS AND ANALYSIS : The study will be undertaken within the Welsh Ambulance Service. The study is part research and part service evaluation. The research utilises a qualitative study design based on thematic analysis of interview data. The service evaluation consists of the development of a clinical safety case based on document analysis, analysis of the AI model and its development process and informal interviews with the technology developer.

CONCLUSIONS : AI presents many opportunities for ambulance services, but safety assurance requirements need to be understood. The ASSIST project will continue to explore and build the body of knowledge in this area.

Sujan Mark, Thimbleby Harold, Habli Ibrahim, Cleve Andreas, Maaløe Lars, Rees Nigel

2022-Jun-01

artificial intelligence, emergency medical services, out-of-hospital cardiac arrest, safety

General General

A multi-frame network model for predicting seizure based on sEEG and iEEG data.

In Frontiers in computational neuroscience

INTRODUCTION : Analysis and prediction of seizures by processing the EEG signals could assist doctors in accurate diagnosis and improve the quality of the patient's life with epilepsy. Nowadays, seizure prediction models based on deep learning have become one of the most popular topics in seizure studies, and many models have been presented. However, the prediction results are strongly related to the various complicated pre-processing strategies of models, and cannot be directly applied to raw data in real-time applications. Moreover, due to the inherent deficiencies in single-frame models and the non-stationary nature of EEG signals, the generalization ability of the existing model frameworks is generally poor.

METHODS : Therefore, we proposed an end-to-end seizure prediction model in this paper, where we designed a multi-frame network for automatic feature extraction and classification. Instance and sequence-based frames are proposed in our approach, which can help us simultaneously extract features of different modes for further classification. Moreover, complicated pre-processing steps are not included in our model, and the novel frames can be directly applied to the raw data. It should be noted that the approaches proposed in the paper can be easily used as the general model which has been validated and compared with existing model frames.

RESULTS : The experimental results showed that the multi-frame network proposed in this paper was superior to the existing model frame in accuracy, sensitivity, specificity, F1-score, and AUC in the classification performance of EEG signals.

DISCUSSION : Our results provided a new research idea for this field. Researchers can further integrate the idea of the multi-frame network into the state-of-the-art single-frame seizure prediction models and then achieve better results.

Lu Liangfu, Zhang Feng, Wu Yubo, Ma Songnan, Zhang Xin, Ni Guangjian

2022

EEG, deep learning, feature extraction, multi-frame network, pre-ictal, seizure prediction

Cardiology Cardiology

Machine learning outperforms traditional logistic regression and offers new possibilities for cardiovascular risk prediction: A study involving 143,043 Chinese patients with hypertension.

In Frontiers in cardiovascular medicine

INTRODUCTION : Identifying people at risk of cardiovascular diseases (CVD) is a cornerstone of preventive cardiology. We developed machine learning (ML) algorithms and investigated their performance in predicting patients' current CVD risk (coronary heart disease and stroke in this study).

MATERIALS AND METHODS : We compared traditional logistic regression (LR) with five ML algorithms LR with Elastic-Net, Random Forest (RF), XGBoost (XGB), Support Vector Machine, Deep Learning, and an Ensemble model averaging predictions from RF, XGB, and Deep Learning for CVD risk prediction using pre-existing patient-level data from a multi-center, cross-sectional study (the Microalbuminuria Screening in Hypertensive Patients Project initiated by the China International Exchange and Promotive Association for Medical and Healthcare) that enrolled 143,043 patients with hypertension from 600 tertiary, secondary, or community hospitals. Each of the five ML algorithms incorporated 18 variables, such as demographics, examinations, comorbidities, and treatment regimens, and were trained and evaluated using 5-fold cross-validation. Predictive accuracy was assessed by the area under the receiver operating curve (AUROC).

RESULTS : Patients' mean age was 62 ± 12 years and 57% were men. Advanced ML algorithms outperformed the traditional LR model. Particularly, the Ensemble model had superior discrimination with an AUROC of 0.760 than LR (AUC = 0.737) and other tested models.

CONCLUSION : We establishes an Ensemble model that shows better performance in predicting patients' current CVD risk using routine information compared to the traditional LR model. ML can help physicians design follow-up plans with more accurate results, offering new possibilities for short-term risk prediction and early detection. Further, ML models can be trained with longitudinal data and used to predict long-term CVD risks, thereby informing CVD prevention.

Xi Yang, Wang Hongyi, Sun Ningling

2022

CVD, hypertension, machine learning, risk prediction, traditional logistic regression

General General

SegVeg: Segmenting RGB Images into Green and Senescent Vegetation by Combining Deep and Shallow Methods.

In Plant phenomics (Washington, D.C.)

Pixel segmentation of high-resolution RGB images into chlorophyll-active or nonactive vegetation classes is a first step often required before estimating key traits of interest. We have developed the SegVeg approach for semantic segmentation of RGB images into three classes (background, green, and senescent vegetation). This is achieved in two steps: A U-net model is first trained on a very large dataset to separate whole vegetation from background. The green and senescent vegetation pixels are then separated using SVM, a shallow machine learning technique, trained over a selection of pixels extracted from images. The performances of the SegVeg approach is then compared to a 3-class U-net model trained using weak supervision over RGB images segmented with SegVeg as groundtruth masks. Results show that the SegVeg approach allows to segment accurately the three classes. However, some confusion is observed mainly between the background and senescent vegetation, particularly over the dark and bright regions of the images. The U-net model achieves similar performances, with slight degradation over the green vegetation: the SVM pixel-based approach provides more precise delineation of the green and senescent patches as compared to the convolutional nature of U-net. The use of the components of several color spaces allows to better classify the vegetation pixels into green and senescent. Finally, the models are used to predict the fraction of three classes over whole images or regularly spaced grid-pixels. Results show that green fraction is very well estimated (R 2 = 0.94) by the SegVeg model, while the senescent and background fractions show slightly degraded performances (R 2 = 0.70 and 0.73, respectively) with a mean 95% confidence error interval of 2.7% and 2.1% for the senescent vegetation and background, versus 1% for green vegetation. We have made SegVeg publicly available as a ready-to-use script and model, along with the entire annotated grid-pixels dataset. We thus hope to render segmentation accessible to a broad audience by requiring neither manual annotation nor knowledge or, at least, offering a pretrained model for more specific use.

Serouart Mario, Madec Simon, David Etienne, Velumani Kaaviya, Lopez Lozano Raul, Weiss Marie, Baret Frédéric

2022

Ophthalmology Ophthalmology

Pterygium Screening and Lesion Area Segmentation Based on Deep Learning.

In Journal of healthcare engineering

A two-category model and a segmentation model of pterygium were proposed to assist ophthalmologists in establishing the diagnosis of ophthalmic diseases. A total of 367 normal anterior segment images and 367 pterygium anterior segment images were collected at the Affiliated Eye Hospital of Nanjing Medical University. AlexNet, VGG16, ResNet18, and ResNet50 models were used to train the two-category pterygium models. A total of 150 normal and 150 pterygium anterior segment images were used to test the models, and the results were compared. The main evaluation indicators, including sensitivity, specificity, area under the curve, kappa value, and receiver operator characteristic curves of the four models, were compared. Simultaneously, 367 pterygium anterior segment images were used to train two improved pterygium segmentation models based on PSPNet. A total of 150 pterygium images were used to test the models, and the results were compared with those of the other four segmentation models. The main evaluation indicators included mean intersection over union (MIOU), IOU, mean average precision (MPA), and PA. Among the two-category models of pterygium, the best diagnostic result was obtained using the VGG16 model. The diagnostic accuracy, kappa value, diagnostic sensitivity of pterygium, diagnostic specificity of pterygium, and F1-score were 99%, 98%, 98.67%, 99.33%, and 99%, respectively. Among the pterygium segmentation models, the double phase-fusion PSPNet model had the best results, with MIOU, IOU, MPA, and PA of 86.57%, 78.1%, 92.3%, and 86.96%, respectively. This study designed a pterygium two-category model and a pterygium segmentation model for the images of the normal anterior and pterygium anterior segments, which could help patients self-screen easily and assist ophthalmologists in establishing the diagnosis of ophthalmic diseases and marking the actual scope of surgery.

Zhu Shaojun, Fang Xinwen, Qian Yong, He Kai, Wu Maonian, Zheng Bo, Song Junyang

2022

Surgery Surgery

Artificial intelligence and machine learning on diagnosis and classification of hip fracture: systematic review.

In Journal of orthopaedic surgery and research

BACKGROUND : In the emergency room, clinicians spend a lot of time and are exposed to mental stress. In addition, fracture classification is important for determining the surgical method and restoring the patient's mobility. Recently, with the help of computers using artificial intelligence (AI) or machine learning (ML), diagnosis and classification of hip fractures can be performed easily and quickly. The purpose of this systematic review is to search for studies that diagnose and classify for hip fracture using AI or ML, organize the results of each study, analyze the usefulness of this technology and its future use value.

METHODS : PubMed Central, OVID Medline, Cochrane Collaboration Library, Web of Science, EMBASE, and AHRQ databases were searched to identify relevant studies published up to June 2022 with English language restriction. The following search terms were used [All Fields] AND (", "[MeSH Terms] OR (""[All Fields] AND "bone"[All Fields]) OR "bone fractures"[All Fields] OR "fracture"[All Fields]). The following information was extracted from the included articles: authors, publication year, study period, type of image, type of fracture, number of patient or used images, fracture classification, reference diagnosis of fracture diagnosis and classification, and augments of each studies. In addition, AI name, CNN architecture type, ROI or important region labeling, data input proportion in training/validation/test, and diagnosis accuracy/AUC, classification accuracy/AUC of each studies were also extracted.

RESULTS : In 14 finally included studies, the accuracy of diagnosis for hip fracture by AI was 79.3-98%, and the accuracy of fracture diagnosis in AI aided humans was 90.5-97.1. The accuracy of human fracture diagnosis was 77.5-93.5. AUC of fracture diagnosis by AI was 0.905-0.99. The accuracy of fracture classification by AI was 86-98.5 and AUC was 0.873-1.0. The forest plot represented that the mean AI diagnosis accuracy was 0.92, the mean AI diagnosis AUC was 0.969, the mean AI classification accuracy was 0.914, and the mean AI classification AUC was 0.933. Among the included studies, the architecture based on the GoogLeNet architectural model or the DenseNet architectural model was the most common with three each. Among the data input proportions, the study with the lowest training rate was 57%, and the study with the highest training rate was 95%. In 14 studies, 5 studies used Grad-CAM for highlight important regions.

CONCLUSION : We expected that our study may be helpful in making judgments about the use of AI in the diagnosis and classification of hip fractures. It is clear that AI is a tool that can help medical staff reduce the time and effort required for hip fracture diagnosis with high accuracy. Further studies are needed to determine what effect this causes in actual clinical situations.

Cha Yonghan, Kim Jung-Taek, Park Chan-Ho, Kim Jin-Woo, Lee Sang Yeob, Yoo Jun-Il

2022-Dec-01

Artificial intelligence, Classification, Diagnosis, Hip fracture, Machine learning

General General

Automatic ML-based vestibular gait classification: examining the effects of IMU placement and gait task selection.

In Journal of neuroengineering and rehabilitation ; h5-index 53.0

BACKGROUND : Vestibular deficits can impair an individual's ability to maintain postural and/or gaze stability. Characterizing gait abnormalities among individuals affected by vestibular deficits could help identify patients at high risk of falling and inform rehabilitation programs. Commonly used gait assessment tools rely on simple measures such as timing and visual observations of path deviations by clinicians. These simple measures may not capture subtle changes in gait kinematics. Therefore, we investigated the use of wearable inertial measurement units (IMUs) and machine learning (ML) approaches to automatically discriminate between gait patterns of individuals with vestibular deficits and age-matched controls. The goal of this study was to examine the effects of IMU placement and gait task selection on the performance of automatic vestibular gait classifiers.

METHODS : Thirty study participants (15 with vestibular deficits and 15 age-matched controls) participated in a single-session gait study during which they performed seven gait tasks while donning a full-body set of IMUs. Classification performance was reported in terms of area under the receiver operating characteristic curve (AUROC) scores for Random Forest models trained on data from each IMU placement for each gait task.

RESULTS : Several models were able to classify vestibular gait better than random (AUROC > 0.5), but their performance varied according to IMU placement and gait task selection. Results indicated that a single IMU placed on the left arm when walking with eyes closed resulted in the highest AUROC score for a single IMU (AUROC = 0.88 [0.84, 0.89]). Feature permutation results indicated that participants with vestibular deficits reduced their arm swing compared to age-matched controls while they walked with eyes closed.

CONCLUSIONS : These findings highlighted differences in upper extremity kinematics during walking with eyes closed that were characteristic of vestibular deficits and showed evidence of the discriminative ability of IMU-based automated screening for vestibular deficits. Further research should explore the mechanisms driving arm swing differences in the vestibular population.

Jabri Safa, Carender Wendy, Wiens Jenna, Sienko Kathleen H

2022-Dec-01

Balance, Classification, Gait, Machine learning, Vestibular disorders, Wearable sensors

Cardiology Cardiology

Integration of proteomic and metabolomic characterization in atrial fibrillation-induced heart failure.

In BMC genomics ; h5-index 78.0

BACKGROUND : The exact mechanism of atrial fibrillation (AF)-induced heart failure (HF) remains unclear. Proteomics and metabolomics were integrated to in this study, as to describe AF patients' dysregulated proteins and metabolites, comparing patients without HF to patients with HF.

METHODS : Plasma samples of 20 AF patients without HF and another 20 with HF were analyzed by multi-omics platforms. Proteomics was performed with data independent acquisition-based liquid chromatography-tandem mass spectrometry (LC-MS/MS), as metabolomics was performed with LC-MS/MS platform. Proteomic and metabolomic results were analyzed separately and integrated using univariate statistical methods, multivariate statistical methods or machine learning model.

RESULTS : We found 35 up-regulated and 15 down-regulated differentially expressed proteins (DEPs) in AF patients with HF compared to AF patients without HF. Moreover, 121 up-regulated and 14 down-regulated differentially expressed metabolites (DEMs) were discovered in HF patients compared to AF patients without HF. An integrated analysis of proteomics and metabolomics revealed several significantly enriched pathways, including Glycolysis or Gluconeogenesis, Tyrosine metabolism and Pentose phosphate pathway. A total of 10 DEPs and DEMs selected as potential biomarkers provided excellent predictive performance, with an AUC of 0.94. In addition, subgroup analysis of HF classification was performed based on metabolomics, which yielded 9 DEMs that can distinguish between AF and HF for HF classification.

CONCLUSIONS : This study provides novel insights to understanding the mechanisms of AF-induced HF progression and identifying novel biomarkers for prognosis of AF with HF by using metabolomics and proteomics analyses.

Zhang Haiyu, Wang Lu, Yin Dechun, Zhou Qi, Lv Lin, Dong Zengxiang, Shi Yuanqi

2022-Dec-01

Atrial fibrillation, Biomarkers, Heart failure, Metabolomics, Proteomics

General General

ENTAIL: yEt aNoTher amyloid fIbrils cLassifier.

In BMC bioinformatics

BACKGROUND : This research aims to increase our knowledge of amyloidoses. These disorders cause incorrect protein folding, affecting protein functionality (on structure). Fibrillar deposits are the basis of some wellknown diseases, such as Alzheimer, Creutzfeldt-Jakob diseases and type II diabetes. For many of these amyloid proteins, the relative precursors are known. Discovering new protein precursors involved in forming amyloid fibril deposits would improve understanding the pathological processes of amyloidoses.

RESULTS : A new classifier, called ENTAIL, was developed using over than 4000 molecular descriptors. ENTAIL was based on the Naive Bayes Classifier with Unbounded Support and Gaussian Kernel Type, with an accuracy on the test set of 81.80%, SN of 100%, SP of 63.63% and an MCC of 0.683 on a balanced dataset.

CONCLUSIONS : The analysis carried out has demonstrated how, despite the various configurations of the tests, performances are superior in terms of performance on a balanced dataset.

Auriemma Citarella Alessia, Di Biasi Luigi, De Marco Fabiola, Tortora Genoveffa

2022-Dec-01

Amyloidoses, Fibrils machine learning, Protein classification

General General

Supervised Machine Learning Approach to COVID-19 Detection Based on Clinical Data.

In Medical journal of the Islamic Republic of Iran

Background: The new coronavirus has been spreading since the beginning of 2020, and many efforts have been made to develop vaccines to help patients recover. It is now clear that the world needs a rapid solution to curb the spread of COVID-19 worldwide with non-clinical approaches such as artificial intelligence techniques. These approaches can be effective in reducing the burden on the health care system to provide the best possible way to diagnose the COVID-19 epidemic. This study was conducted to use Machine Learning (ML) algorithms for the early detection of COVID-19 in patients. Methods: This retrospective study used data from hospitals affiliated with Shiraz University of Medical Sciences in Iran. This dataset was collected in the period March to October 2020 andcontained 10055 cases with 63 features. We selected and compared six algorithms: C4.5, support vector machine (SVM), Naive Bayes, logistic Regression (LR), Random Forest, and K-Nearest Neighbor algorithm using Rapid Miner software. The performance of algorithms was measured using evaluation metrics, such as precision, recall, accuracy, and f-measure. Results: The results of the study show that among the various used classification methods in the diagnosis of coronavirus, SVM (93.41% accuracy) and C4.5 (91.87% accuracy) achieved the highest performance. According to the C4.5 decision tree, "contact with a person who has COVID-19" was considered the most important diagnostic criterion based on the Gini index. Conclusion: We found that ML approaches enable a reasonable level of accuracy in the diagnosis of COVID-19.

Yazdani Azita, Zahmatkeshan Maryam, Ravangard Ramin, Sharifian Roxana, Shirdeli Mohammad

2022

Artificial Intelligence, COVID-19, Classification, Data mining, Machine Learning

General General

Integrating high-throughput phenotyping, GWAS and prediction models reveals the genetic architecture of plant height in maize.

In Molecular plant

Plant height (PH) is an essential trait in maize (Zea mays L.) which is tightly associated with planting density, biomass, lodging resistance and grain yield in the field. Dissecting the dynamics of maize plant architecture will be beneficial for ideotype-based maize breeding and prediction, as the genetic basis controlling PH in maize remains largely unknown. Here, we developed an automated high-throughput phenotyping platform (HTP) to systematically and noninvasively quantify 77 image-based traits (i-traits) and 20 field traits (f-traits) for 228 maize inbred lines across all developmental stages. Time-resolved i-traits with novel digital phenotypes and complex correlations with agronomic traits were characterized to reveal the dynamics of maize growth. An i-trait-based genome-wide association study (GWAS) identified 4945 trait-associated SNPs, 2603 genetic loci, and 1974 corresponding candidate genes. Interestingly, we found that rapid growth of maize plants mainly occurs at two developmental stages, Stage 2 (S2) to S3 and S5 to S6, accounting for the final PH indicators. By integrating the plant height-association network with the transcriptome profiles of specific internodes, we revealed 13 hub genes that might play vital roles during the rapid growth. The candidate genes and novel i-traits identified at multiple growth stages might be used as potential indicators for final PH in maize. The function of one candidate gene, ZmVATE, was validated to regulate plant height-related traits in maize by using genetic mutation. Furthermore, we used machine learning to build prediction models for final plant height based on i-traits, and predictive performance was assessed in validation across developmental stages. Moderate, strong, and very strong correlations between prediction and experimental datasets were achieved from early S4 (tenth-leaf) stage. Overall, our study provided a valuable tool for dissecting the spatiotemporal formation of specific internodes and the genetic architecture of PH, as well as resources and prediction models that are useful for molecular design breeding and predicting maize varieties with ideal plant architectures.

Wang Weixuan, Guo Weijun, Le Liang, Yu Jia, Wu Yue, Li Dongwei, Wang Yifan, Wang Huan, Lu Xiaoduo, Qiao Hong, Gu Xiaofeng, Tian Jian, Zhang Chunyi, Pu Li

2022-Nov-28

GWAS, machine learning, maize, phenomics, plant height, prediction

Radiology Radiology

Prediction of Decompensation and Death in Advanced Chronic Liver Disease Using Deep Learning Analysis of Gadoxetic Acid-Enhanced MRI.

In Korean journal of radiology

OBJECTIVE : This study aimed to evaluate the usefulness of quantitative indices obtained from deep learning analysis of gadoxetic acid-enhanced hepatobiliary phase (HBP) MRI and their longitudinal changes in predicting decompensation and death in patients with advanced chronic liver disease (ACLD).

MATERIALS AND METHODS : We included patients who underwent baseline and 1-year follow-up MRI from a prospective cohort that underwent gadoxetic acid-enhanced MRI for hepatocellular carcinoma surveillance between November 2011 and August 2012 at a tertiary medical center. Baseline liver condition was categorized as non-ACLD, compensated ACLD, and decompensated ACLD. The liver-to-spleen signal intensity ratio (LS-SIR) and liver-to-spleen volume ratio (LS-VR) were automatically measured on the HBP images using a deep learning algorithm, and their percentage changes at the 1-year follow-up (ΔLS-SIR and ΔLS-VR) were calculated. The associations of the MRI indices with hepatic decompensation and a composite endpoint of liver-related death or transplantation were evaluated using a competing risk analysis with multivariable Fine and Gray regression models, including baseline parameters alone and both baseline and follow-up parameters.

RESULTS : Our study included 280 patients (153 male; mean age ± standard deviation, 57 ± 7.95 years) with non-ACLD, compensated ACLD, and decompensated ACLD in 32, 186, and 62 patients, respectively. Patients were followed for 11-117 months (median, 104 months). In patients with compensated ACLD, baseline LS-SIR (sub-distribution hazard ratio [sHR], 0.81; p = 0.034) and LS-VR (sHR, 0.71; p = 0.01) were independently associated with hepatic decompensation. The ΔLS-VR (sHR, 0.54; p = 0.002) was predictive of hepatic decompensation after adjusting for baseline variables. ΔLS-VR was an independent predictor of liver-related death or transplantation in patients with compensated ACLD (sHR, 0.46; p = 0.026) and decompensated ACLD (sHR, 0.61; p = 0.023).

CONCLUSION : MRI indices automatically derived from the deep learning analysis of gadoxetic acid-enhanced HBP MRI can be used as prognostic markers in patients with ACLD.

Heo Subin, Lee Seung Soo, Kim So Yeon, Lim Young-Suk, Park Hyo Jung, Yoon Jee Seok, Suk Heung-Il, Sung Yu Sub, Park Bumwoo, Lee Ji Sung

2022-Dec

Cirrhosis, Deep learning, Gadolinium methoxybenzyl DTPA, Magnetic resonance imaging

Radiology Radiology

Application of deep learning-based diagnostic systems in screening asymptomatic COVID-19 patients among oversea returnees.

In Journal of infection in developing countries

INTRODUCTION : Our study aimed to investigate the performance of deep learning (DL)-based diagnostic systems in alerting against COVID-19, especially among asymptomatic individuals coming from overseas, and to analyze the features of identified asymptomatic patients in detail.

METHODOLOGY : DL diagnostic systems were deployed to assist in the screening of COVID-19, including the pneumonia system and pulmonary nodules system. 1,917 overseas returnees who underwent CT examination and rRT-PCR tests were enrolled. DL pneumonia system promptly alerted clinicians to suspected COVID-19 after CT examinations while the performance was evaluated with rRT-PCR results as the reference. The radiological features of asymptomatic COVID-19 cases were described according to the Nomenclature of the Fleischner Society.

RESULTS : Fifty-three cases were confirmed as COVID-19 patients by rRT-PCR tests, including 5 asymptomatic cases. DL pneumonia system correctly alerted 50 cases as suspected COVID-19 with a sensitivity of 0.9434 and specificity of 0.9592 (within 2 minutes per case); while the pulmonary nodules system alerted 2 of the 3 missed asymptomatic cases. Additionally, five asymptomatic patients presented different characteristics such as elevated creatine kinase level and prolonged prothrombin time, as well as atypical radiological features.

CONCLUSIONS : DL diagnostic systems are promising complementary approaches for prompt screening of imported COVID-19 patients, even the imported asymptomatic cases. Unique clinical and radiological characteristics of asymptomatic cases might be of great value in screening as well.

ADVANCES IN KNOWLEDGE : DL-based systems are practical, efficient, and reliable to assist radiologists in screening COVID-19 patients. Differential features of asymptomatic patients might be useful to clinicians in the frontline to differentiate asymptomatic cases.

Dong Dawei, Luo Zujin, Zheng Yue, Liang Ying, Zhao Pengfei, Feng Linlin, Wang Dawei, Cao Ying, Zhao Zhenhao, Ma Yingmin

2022-Nov-29

COVID-19, Deep learning, asymptomatic cases, diagnostic systems, performance evaluation

Public Health Public Health

Spatial statistical machine learning models to assess the relationship between development vulnerabilities and educational factors in children in Queensland, Australia.

In BMC public health ; h5-index 82.0

BACKGROUND : The health and development of children during their first year of full time school is known to impact their social, emotional, and academic capabilities throughout and beyond early education. Physical health, motor development, social and emotional well-being, learning styles, language and communication, cognitive skills, and general knowledge are all considered to be important aspects of a child's health and development. It is important for many organisations and governmental agencies to continually improve their understanding of the factors which determine or influence development vulnerabilities among children. This article studies the relationships between development vulnerabilities and educational factors among children in Queensland, Australia.

METHODS : Spatial statistical machine learning models are reviewed and compared in the context of a study of geographic variation in the association between development vulnerabilities and attendance at preschool among children in Queensland, Australia. A new spatial random forest (SRF) model is suggested that can explain more of the spatial variation in data than other approaches.

RESULTS : In the case study, spatial models were shown to provide a better fit compared to models that ignored the spatial variation in the data. The SRF model was shown to be the only model which can explain all of the spatial variation in each of the development vulnerabilities considered in the case study. The spatial analysis revealed that the attendance at preschool factor has a strong influence on the physical health domain vulnerability and emotional maturity vulnerability among children in their first year of school.

CONCLUSION : This study confirmed that it is important to take into account the spatial nature of data when fitting statistical machine learning models. A new spatial random forest model was introduced and was shown to explain more of the spatial variation and provide a better model fit in the case study of development vulnerabilities among children in Queensland. At small-area population level, increased attendance at preschool was strongly associated with reduced physical and emotional development vulnerabilities among children in their first year of school.

Draidi Areed Wala, Price Aiden, Arnett Kathryn, Mengersen Kerrie

2022-Nov-30

Deveplomental vulnerabilities, Spatial random forest, Statistical machine learning methods

Radiology Radiology

Automated Measurement of Native T1 and Extracellular Volume Fraction in Cardiac Magnetic Resonance Imaging Using a Commercially Available Deep Learning Algorithm.

In Korean journal of radiology

OBJECTIVE : T1 mapping provides valuable information regarding cardiomyopathies. Manual drawing is time consuming and prone to subjective errors. Therefore, this study aimed to test a DL algorithm for the automated measurement of native T1 and extracellular volume (ECV) fractions in cardiac magnetic resonance (CMR) imaging with a temporally separated dataset.

MATERIALS AND METHODS : CMR images obtained for 95 participants (mean age ± standard deviation, 54.5 ± 15.2 years), including 36 left ventricular hypertrophy (12 hypertrophic cardiomyopathy, 12 Fabry disease, and 12 amyloidosis), 32 dilated cardiomyopathy, and 27 healthy volunteers, were included. A commercial deep learning (DL) algorithm based on 2D U-net (Myomics-T1 software, version 1.0.0) was used for the automated analysis of T1 maps. Four radiologists, as study readers, performed manual analysis. The reference standard was the consensus result of the manual analysis by two additional expert readers. The segmentation performance of the DL algorithm and the correlation and agreement between the automated measurement and the reference standard were assessed. Interobserver agreement among the four radiologists was analyzed.

RESULTS : DL successfully segmented the myocardium in 99.3% of slices in the native T1 map and 89.8% of slices in the post-T1 map with Dice similarity coefficients of 0.86 ± 0.05 and 0.74 ± 0.17, respectively. Native T1 and ECV showed strong correlation and agreement between DL and the reference: for T1, r = 0.967 (95% confidence interval [CI], 0.951-0.978) and bias of 9.5 msec (95% limits of agreement [LOA], -23.6-42.6 msec); for ECV, r = 0.987 (95% CI, 0.980-0.991) and bias of 0.7% (95% LOA, -2.8%-4.2%) on per-subject basis. Agreements between DL and each of the four radiologists were excellent (intraclass correlation coefficient [ICC] of 0.98-0.99 for both native T1 and ECV), comparable to the pairwise agreement between the radiologists (ICC of 0.97-1.00 and 0.99-1.00 for native T1 and ECV, respectively).

CONCLUSION : The DL algorithm allowed automated T1 and ECV measurements comparable to those of radiologists.

Chang Suyon, Han Kyunghwa, Lee Suji, Yang Young Joong, Kim Pan Ki, Choi Byoung Wook, Suh Young Joo

2022-Dec

Deep learning, Extracellular volume fraction, Heart, Magnetic resonance imaging, T1 mapping

General General

Multigroup prediction in lung cancer patients and comparative controls using signature of volatile organic compounds in breath samples.

In PloS one ; h5-index 176.0

Early detection of lung cancer is a crucial factor for increasing its survival rates among the detected patients. The presence of carbonyl volatile organic compounds (VOCs) in exhaled breath can play a vital role in early detection of lung cancer. Identifying these VOC markers in breath samples through innovative statistical and machine learning techniques is an important task in lung cancer research. Therefore, we proposed an experimental approach for generation of VOC molecular concentration data using unique silicon microreactor technology and further identification and characterization of key relevant VOCs important for lung cancer detection through statistical and machine learning algorithms. We reported several informative VOCs and tested their effectiveness in multi-group classification of patients. Our analytical results indicated that seven key VOCs, including C4H8O2, C13H22O, C11H22O, C2H4O2, C7H14O, C6H12O, and C5H8O, are sufficient to detect the lung cancer patients with higher mean classification accuracy (92%) and lower standard error (0.03) compared to other combinations. In other words, the molecular concentrations of these VOCs in exhaled breath samples were able to discriminate the patients with lung cancer (n = 156) from the healthy smoker and nonsmoker controls (n = 193) and patients with benign pulmonary nodules (n = 65). The quantification of carbonyl VOC profiles from breath samples and identification of crucial VOCs through our experimental approach paves the way forward for non-invasive lung cancer detection. Further, our experimental and analytical approach of VOC quantitative analysis in breath samples may be extended to other diseases, including COVID-19 detection.

Rai Shesh N, Das Samarendra, Pan Jianmin, Mishra Dwijesh C, Fu Xiao-An

2022

Public Health Public Health

Spatial statistical machine learning models to assess the relationship between development vulnerabilities and educational factors in children in Queensland, Australia.

In BMC public health ; h5-index 82.0

BACKGROUND : The health and development of children during their first year of full time school is known to impact their social, emotional, and academic capabilities throughout and beyond early education. Physical health, motor development, social and emotional well-being, learning styles, language and communication, cognitive skills, and general knowledge are all considered to be important aspects of a child's health and development. It is important for many organisations and governmental agencies to continually improve their understanding of the factors which determine or influence development vulnerabilities among children. This article studies the relationships between development vulnerabilities and educational factors among children in Queensland, Australia.

METHODS : Spatial statistical machine learning models are reviewed and compared in the context of a study of geographic variation in the association between development vulnerabilities and attendance at preschool among children in Queensland, Australia. A new spatial random forest (SRF) model is suggested that can explain more of the spatial variation in data than other approaches.

RESULTS : In the case study, spatial models were shown to provide a better fit compared to models that ignored the spatial variation in the data. The SRF model was shown to be the only model which can explain all of the spatial variation in each of the development vulnerabilities considered in the case study. The spatial analysis revealed that the attendance at preschool factor has a strong influence on the physical health domain vulnerability and emotional maturity vulnerability among children in their first year of school.

CONCLUSION : This study confirmed that it is important to take into account the spatial nature of data when fitting statistical machine learning models. A new spatial random forest model was introduced and was shown to explain more of the spatial variation and provide a better model fit in the case study of development vulnerabilities among children in Queensland. At small-area population level, increased attendance at preschool was strongly associated with reduced physical and emotional development vulnerabilities among children in their first year of school.

Draidi Areed Wala, Price Aiden, Arnett Kathryn, Mengersen Kerrie

2022-Nov-30

Deveplomental vulnerabilities, Spatial random forest, Statistical machine learning methods

Ophthalmology Ophthalmology

Global-local multi-stage temporal convolutional network for cataract surgery phase recognition.

In Biomedical engineering online

BACKGROUND : Surgical video phase recognition is an essential technique in computer-assisted surgical systems for monitoring surgical procedures, which can assist surgeons in standardizing procedures and enhancing postsurgical assessment and indexing. However, the high similarity between the phases and temporal variations of cataract videos still poses the greatest challenge for video phase recognition.

METHODS : In this paper, we introduce a global-local multi-stage temporal convolutional network (GL-MSTCN) to explore the subtle differences between high similarity surgical phases and mitigate the temporal variations of surgical videos. The presented work consists of a triple-stream network (i.e., pupil stream, instrument stream, and video frame stream) and a multi-stage temporal convolutional network. The triple-stream network first detects the pupil and surgical instruments regions in the frame separately and then obtains the fine-grained semantic features of the video frames. The proposed multi-stage temporal convolutional network improves the surgical phase recognition performance by capturing longer time series features through dilated convolutional layers with varying receptive fields.

RESULTS : Our method is thoroughly validated on the CSVideo dataset with 32 cataract surgery videos and the public Cataract101 dataset with 101 cataract surgery videos, outperforming state-of-the-art approaches with 95.8% and 96.5% accuracy, respectively.

CONCLUSIONS : The experimental results show that the use of global and local feature information can effectively enhance the model to explore fine-grained features and mitigate temporal and spatial variations, thus improving the surgical phase recognition performance of the proposed GL-MSTCN.

Fang Lixin, Mou Lei, Gu Yuanyuan, Hu Yan, Chen Bang, Chen Xu, Wang Yang, Liu Jiang, Zhao Yitian

2022-Nov-30

Cataract surgery videos, Deep learning, Surgical phase recognition, Temporal convolutional networks

Pathology Pathology

Scalable transcriptomics analysis with Dask: applications in data science and machine learning.

In BMC bioinformatics

BACKGROUND : Gene expression studies are an important tool in biological and biomedical research. The signal carried in expression profiles helps derive signatures for the prediction, diagnosis and prognosis of different diseases. Data science and specifically machine learning have many applications in gene expression analysis. However, as the dimensionality of genomics datasets grows, scalable solutions become necessary.

METHODS : In this paper we review the main steps and bottlenecks in machine learning pipelines, as well as the main concepts behind scalable data science including those of concurrent and parallel programming. We discuss the benefits of the Dask framework and how it can be integrated with the Python scientific environment to perform data analysis in computational biology and bioinformatics.

RESULTS : This review illustrates the role of Dask for boosting data science applications in different case studies. Detailed documentation and code on these procedures is made available at https://github.com/martaccmoreno/gexp-ml-dask .

CONCLUSION : By showing when and how Dask can be used in transcriptomics analysis, this review will serve as an entry point to help genomic data scientists develop more scalable data analysis procedures.

Moreno Marta, Vilaça Ricardo, Ferreira Pedro G

2022-Nov-30

Data analysis, Gene expression, Machine learning, Scalable data science, Transcriptomics

oncology Oncology

Prediction of radiosensitivity and radiocurability using a novel supervised artificial neural network.

In BMC cancer

BACKGROUND : Radiotherapy has been widely used to treat various cancers, but its efficacy depends on the individual involved. Traditional gene-based machine-learning models have been widely used to predict radiosensitivity. However, there is still a lack of emerging powerful models, artificial neural networks (ANN), in the practice of gene-based radiosensitivity prediction. In addition, ANN may overfit and learn biologically irrelevant features.

METHODS : We developed a novel ANN with Selective Connection based on Gene Patterns (namely ANN-SCGP) to predict radiosensitivity and radiocurability. We creatively used gene patterns (gene similarity or gene interaction information) to control the "on-off" of the first layer of weights, enabling the low-dimensional features to learn the gene pattern information. ANN-SCGP was trained and tested in 82 cell lines and 1,101 patients from the 11 pan-cancer cohorts.

RESULTS : For survival fraction at 2 Gy, the root mean squared errors (RMSE) of prediction in ANN-SCGP was the smallest among all algorithms (mean RMSE: 0.1587-0.1654). For radiocurability, ANN-SCGP achieved the first and second largest C-index in the 12/20 and 4/20 tests, respectively. The low dimensional output of ANN-SCGP reproduced the patterns of gene similarity. Moreover, the pan-cancer analysis indicated that immune signals and DNA damage responses were associated with radiocurability.

CONCLUSIONS : As a model including gene pattern information, ANN-SCGP had superior prediction abilities than traditional models. Our work provided novel insights into radiosensitivity and radiocurability.

Zeng Zihang, Luo Maoling, Li Yangyi, Li Jiali, Huang Zhengrong, Zeng Yuxin, Yuan Yu, Wang Mengqin, Liu Yuying, Gong Yan, Xie Conghua

2022-Dec-01

Computational Biology, High-Throughput Sequencing, Multi-Omics, Neural Network Models, Radiosensitivity

General General

Validity and reliability of a mobile digital imaging analysis trained by a 4-compartment model.

In Journal of human nutrition and dietetics : the official journal of the British Dietetic Association

BACKGROUND : Digital imaging analysis (DIA) estimates collected from mobile applications are a novel technique that can collect body composition estimates remotely without the inherent restrictions of other research-grade devices. However, the accuracy of the artificial intelligence used in DIA are reliant on the accuracy of the developmental methods. Few DIA applications are trained by multi-compartment models, but this developmental strategy may be most accurate. Thus, the aim of this study was to assess the precision and agreement of a DIA application with developmental software trained by a 4-compartment (4C) model using an actual 4C model as the criterion method.

METHODOLOGY : For this cross-sectional study, body composition estimations were collected from 102 participants (F:63, M:39) using the methods necessary for a rapid 4C model and a DIA application using two different smartphones.

RESULTS : Intraclass correlation coefficients (0.96-0.99; all p<0.001) and root mean square coefficients of variation (0.5%-3.0%) showed good reliability for body fat %, fat mass, and fat-free mass. There were no significant mean differences between the 4C model or the DIA estimates for the total sample, by sex, and for non-Hispanic White (n:61) and Black/African-American (n:32) participants (all p>0.050). DIA estimates demonstrated equivalence with the 4-compartment model for all variables, but revealed proportional biases that underestimated body fat % (both β = -0.25; p<0.001) and fat mass (both β = -0.07; p<0.010) at higher degrees of each variable.

CONCLUSIONS : DIA applications trained by a 4C model are reliable and produce body composition estimates equivalent with an actual 4C model. This article is protected by copyright. All rights reserved.

Graybeal Austin J, Brandner Caleb F, Tinsley Grant M

2022-Nov-30

artificial intelligence, body composition assessment, digital anthropometry, mobile health, obesity, smartphone

General General

DLA-H: A Deep Learning Accelerator for Histopathologic Image Classification.

In Journal of digital imaging

It is more than a decade since machine learning and especially its leading subtype deep learning have become one of the most interesting topics in almost all areas of science and industry. In numerous contexts, at least one of the applications of deep learning is utilized or is going to be utilized. Using deep learning for image classification is now very popular and widely used in various use cases. Many types of research in medical sciences have been focused on the advantages of deep learning for image classification problems. Some recent researches show more than 90% accuracy for breast tissue classification which is a breakthrough. A huge number of computations in deep neural networks are considered a big challenge both from software and hardware point of view. From the architectural perspective, this big amount of computing operations will result in high power consumption and computation runtime. This led to the emersion of deep learning accelerators which are designed mainly for improving performance and energy efficiency. Data reuse and localization are two great opportunities for achieving energy-efficient computations with lower runtime. Data flows are mainly designed based on these important parameters. In this paper, DLA-H and BJS, a deep learning accelerator, and its data flow for histopathologic image classification are proposed. The simulation results with the MAESTRO tool showed 756 cycles for total runtime and [Formula: see text] GFLOPS roofline throughput that is an extreme performance improvement in comparison to current general-purpose deep learning accelerators and data flows.

Bolhasani Hamidreza, Jassbi Somayyeh Jafarali, Sharifi Arash

2022-Nov-30

Classification, Convolutional neural networks, Data flow, Deep learning, Deep neural networks, Hardware accelerator, Histopathologic images

General General

Dendrocentric learning for synthetic intelligence.

In Nature ; h5-index 368.0

Artificial intelligence now advances by performing twice as many floating-point multiplications every two months, but the semiconductor industry tiles twice as many multipliers on a chip every two years. Moreover, the returns from tiling these multipliers ever more densely now diminish because signals must travel relatively farther and farther. Although travel can be shortened by stacking tiled multipliers in a three-dimensional chip, such a solution acutely reduces the available surface area for dissipating heat. Here I propose to transcend this three-dimensional thermal constraint by moving away from learning with synapses to learning with dendrites. Synaptic inputs are not weighted precisely but rather ordered meticulously along a short stretch of dendrite, termed dendrocentric learning. With the help of a computational model of a dendrite and a conceptual model of a ferroelectric device that emulates it, I illustrate how dendrocentric learning artificial intelligence-or synthetic intelligence for short-could run not with megawatts in the cloud but rather with watts on a smartphone.

Boahen Kwabena

2022-Dec

General General

Decoding the cognitive states of attention and distraction in a real-life setting using EEG.

In Scientific reports ; h5-index 158.0

Lapses in attention can have serious consequences in situations such as driving a car, hence there is considerable interest in tracking it using neural measures. However, as most of these studies have been done in highly controlled and artificial laboratory settings, we want to explore whether it is also possible to determine attention and distraction using electroencephalogram (EEG) data collected in a natural setting using machine/deep learning. 24 participants volunteered for the study. Data were collected from pairs of participants simultaneously while they engaged in Tibetan Monastic debate, a practice that is interesting because it is a real-life situation that generates substantial variability in attention states. We found that attention was on average associated with increased left frontal alpha, increased left parietal theta, and decreased central delta compared to distraction. In an attempt to predict attention and distraction, we found that a Long Short Term Memory model classified attention and distraction with maximum accuracy of 95.86% and 95.4% corresponding to delta and theta waves respectively. This study demonstrates that EEG data collected in a real-life setting can be used to predict attention states in participants with good accuracy, opening doors for developing Brain-Computer Interfaces that track attention in real-time using data extracted in daily life settings, rendering them much more usable.

Kaushik Pallavi, Moye Amir, Vugt Marieke van, Roy Partha Pratim

2022-Nov-30

General General

A multi-scale feature extraction fusion model for human activity recognition.

In Scientific reports ; h5-index 158.0

Human Activity Recognition (HAR) is an important research area in human-computer interaction and pervasive computing. In recent years, many deep learning (DL) methods have been widely used for HAR, and due to their powerful automatic feature extraction capabilities, they achieve better recognition performance than traditional methods and are applicable to more general scenarios. However, the problem is that DL methods increase the computational cost of the system and take up more system resources while achieving higher recognition accuracy, which is more challenging for its operation in small memory terminal devices such as smartphones. So, we need to reduce the model size as much as possible while taking into account the recognition accuracy. To address this problem, we propose a multi-scale feature extraction fusion model combining Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU). The model uses different convolutional kernel sizes combined with GRU to accomplish the automatic extraction of different local features and long-term dependencies of the original data to obtain a richer feature representation. In addition, the proposed model uses separable convolution instead of classical convolution to meet the requirement of reducing model parameters while improving recognition accuracy. The accuracy of the proposed model is 97.18%, 96.71%, and 96.28% on the WISDM, UCI-HAR, and PAMAP2 datasets respectively. The experimental results show that the proposed model not only obtains higher recognition accuracy but also costs lower computational resources compared with other methods.

Zhang Chuanlin, Cao Kai, Lu Limeng, Deng Tao

2022-Nov-30

General General

Reduced order modeling for flow and transport problems with Barlow Twins self-supervised learning.

In Scientific reports ; h5-index 158.0

We propose a unified data-driven reduced order model (ROM) that bridges the performance gap between linear and nonlinear manifold approaches. Deep learning ROM (DL-ROM) using deep-convolutional autoencoders (DC-AE) has been shown to capture nonlinear solution manifolds but fails to perform adequately when linear subspace approaches such as proper orthogonal decomposition (POD) would be optimal. Besides, most DL-ROM models rely on convolutional layers, which might limit its application to only a structured mesh. The proposed framework in this study relies on the combination of an autoencoder (AE) and Barlow Twins (BT) self-supervised learning, where BT maximizes the information content of the embedding with the latent space through a joint embedding architecture. Through a series of benchmark problems of natural convection in porous media, BT-AE performs better than the previous DL-ROM framework by providing comparable results to POD-based approaches for problems where the solution lies within a linear subspace as well as DL-ROM autoencoder-based techniques where the solution lies on a nonlinear manifold; consequently, bridges the gap between linear and nonlinear reduced manifolds. We illustrate that a proficient construction of the latent space is key to achieving these results, enabling us to map these latent spaces using regression models. The proposed framework achieves a relative error of 2% on average and 12% in the worst-case scenario (i.e., the training data is small, but the parameter space is large.). We also show that our framework provides a speed-up of [Formula: see text] times, in the best case, and [Formula: see text] times on average compared to a finite element solver. Furthermore, this BT-AE framework can operate on unstructured meshes, which provides flexibility in its application to standard numerical solvers, on-site measurements, experimental data, or a combination of these sources.

Kadeethum Teeratorn, Ballarin Francesco, O’Malley Daniel, Choi Youngsoo, Bouklas Nikolaos, Yoon Hongkyu

2022-Nov-30

Radiology Radiology

Use of Artificial Intelligence for Reducing Unnecessary Recalls at Screening Mammography: A Simulation Study.

In Korean journal of radiology

OBJECTIVE : To conduct a simulation study to determine whether artificial intelligence (AI)-aided mammography reading can reduce unnecessary recalls while maintaining cancer detection ability in women recalled after mammography screening.

MATERIALS AND METHODS : A retrospective reader study was performed by screening mammographies of 793 women (mean age ± standard deviation, 50 ± 9 years) recalled to obtain supplemental mammographic views regarding screening mammography-detected abnormalities between January 2016 and December 2019 at two screening centers. Initial screening mammography examinations were interpreted by three dedicated breast radiologists sequentially, case by case, with and without AI aid, in a single session. The area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and recall rate for breast cancer diagnosis were obtained and compared between the two reading modes.

RESULTS : Fifty-four mammograms with cancer (35 invasive cancers and 19 ductal carcinomas in situ) and 739 mammograms with benign or negative findings were included. The reader-averaged AUC improved after AI aid, from 0.79 (95% confidence interval [CI], 0.74-0.85) to 0.89 (95% CI, 0.85-0.94) (p < 0.001). The reader-averaged specificities before and after AI aid were 41.9% (95% CI, 39.3%-44.5%) and 53.9% (95% CI, 50.9%-56.9%), respectively (p < 0.001). The reader-averaged sensitivity was not statistically different between AI-unaided and AI-aided readings: 89.5% (95% CI, 83.1%-95.9%) vs. 92.6% (95% CI, 86.2%-99.0%) (p = 0.053), although the sensitivities of the least experienced radiologists before and after AI aid were 79.6% (43 of 54 [95% CI, 66.5%-89.4%]) and 90.7% (49 of 54 [95% CI, 79.7%-96.9%]), respectively (p = 0.031). With AI aid, the reader-averaged recall rate decreased by from 60.4% (95% CI, 57.8%-62.9%) to 49.5% (95% CI, 46.5%-52.4%) (p < 0.001).

CONCLUSION : AI-aided reading reduced the number of recalls and improved the diagnostic performance in our simulation using women initially recalled for supplemental mammographic views after mammography screening.

Kim Yeon Soo, Jang Myoung-Jin, Lee Su Hyun, Kim Soo-Yeon, Ha Su Min, Kwon Bo Ra, Moon Woo Kyung, Chang Jung Min

2022-Dec

Artificial intelligence, Breast cancer, Mammography, Screening

General General

Highly Adsorptive Au-TiO2 Nanocomposites for the SERS Face Mask Allow the Machine-Learning-Based Quantitative Assay of SARS-CoV-2 in Artificial Breath Aerosols.

In ACS applied materials & interfaces ; h5-index 147.0

Human respiratory aerosols contain diverse potential biomarkers for early disease diagnosis. Here, we report the direct and label-free detection of SARS-CoV-2 in respiratory aerosols using a highly adsorptive Au-TiO2 nanocomposite SERS face mask and an ablation-assisted autoencoder. The Au-TiO2 SERS face mask continuously preconcentrates and efficiently captures the oronasal aerosols, which substantially enhances the SERS signal intensities by 47% compared to simple Au nanoislands. The ultrasensitive Au-TiO2 nanocomposites also demonstrate the successful detection of SARS-CoV-2 spike proteins in artificial respiratory aerosols at a 100 pM concentration level. The deep learning-based autoencoder, followed by the partial ablation of nondiscriminant SERS features of spike proteins, allows a quantitative assay of the 101-104 pfu/mL SARS-CoV-2 lysates (comparable to 19-29 PCR cyclic threshold from COVID-19 patients) in aerosols with an accuracy of over 98%. The Au-TiO2 SERS face mask provides a platform for breath biopsy for the detection of various biomarkers in respiratory aerosols.

Hwang Charles S H, Lee Sangyeon, Lee Sejin, Kim Hanjin, Kang Taejoon, Lee Doheon, Jeong Ki-Hun

2022-Nov-30

SARS-CoV-2, breath biopsy, machine-learning, nanocomposite, plasmonics, surface-enhanced Raman spectroscopy

General General

Analyzing the State of Computer Science Research with the DBLP Discovery Dataset

ArXiv Preprint

The number of scientific publications continues to rise exponentially, especially in Computer Science (CS). However, current solutions to analyze those publications restrict access behind a paywall, offer no features for visual analysis, limit access to their data, only focus on niches or sub-fields, and/or are not flexible and modular enough to be transferred to other datasets. In this thesis, we conduct a scientometric analysis to uncover the implicit patterns hidden in CS metadata and to determine the state of CS research. Specifically, we investigate trends of the quantity, impact, and topics for authors, venues, document types (conferences vs. journals), and fields of study (compared to, e.g., medicine). To achieve this we introduce the CS-Insights system, an interactive web application to analyze CS publications with various dashboards, filters, and visualizations. The data underlying this system is the DBLP Discovery Dataset (D3), which contains metadata from 5 million CS publications. Both D3 and CS-Insights are open-access, and CS-Insights can be easily adapted to other datasets in the future. The most interesting findings of our scientometric analysis include that i) there has been a stark increase in publications, authors, and venues in the last two decades, ii) many authors only recently joined the field, iii) the most cited authors and venues focus on computer vision and pattern recognition, while the most productive prefer engineering-related topics, iv) the preference of researchers to publish in conferences over journals dwindles, v) on average, journal articles receive twice as many citations compared to conference papers, but the contrast is much smaller for the most cited conferences and journals, and vi) journals also get more citations in all other investigated fields of study, while only CS and engineering publish more in conferences than journals.

Lennart Küll

2022-12-01

General General

Cheminformatics analysis of chemicals that increase estrogen and progesterone synthesis for a breast cancer hazard assessment.

In Scientific reports ; h5-index 158.0

Factors that increase estrogen or progesterone (P4) action are well-established as increasing breast cancer risk, and many first-line treatments to prevent breast cancer recurrence work by blocking estrogen synthesis or action. In previous work, using data from an in vitro steroidogenesis assay developed for the U.S. Environmental Protection Agency (EPA) ToxCast program, we identified 182 chemicals that increased estradiol (E2up) and 185 that increased progesterone (P4up) in human H295R adrenocortical carcinoma cells, an OECD validated assay for steroidogenesis. Chemicals known to induce mammary effects in vivo were very likely to increase E2 or P4 synthesis, further supporting the importance of these pathways for breast cancer. To identify additional chemical exposures that may increase breast cancer risk through E2 or P4 steroidogenesis, we developed a cheminformatics approach to identify structural features associated with these activities and to predict other E2 or P4 steroidogens from their chemical structures. First, we used molecular descriptors and physicochemical properties to cluster the 2,012 chemicals screened in the steroidogenesis assay using a self-organizing map (SOM). Structural features such as triazine, phenol, or more broadly benzene ramified with halide, amine or alcohol, are enriched for E2 or P4up chemicals. Among E2up chemicals, phenol and benzenone are found as significant substructures, along with nitrogen-containing biphenyls. For P4up chemicals, phenol and complex aromatic systems ramified with oxygen-based groups such as flavone or phenolphthalein are significant substructures. Chemicals that are active for both E2up and P4up are enriched with substructures such as dihydroxy phosphanedithione or are small chemicals that contain one benzene ramified with chlorine, alcohol, methyl or primary amine. These results are confirmed with a chemotype ToxPrint analysis. Then, we used machine learning and artificial intelligence algorithms to develop and validate predictive classification QSAR models for E2up and P4up chemicals. These models gave reasonable external prediction performances (balanced accuracy ~ 0.8 and Matthews Coefficient Correlation ~ 0.5) on an external validation. The QSAR models were enriched by adding a confidence score that considers the chemical applicability domain and a ToxPrint assessment of the chemical. This profiling and these models may be useful to direct future testing and risk assessments for chemicals related to breast cancer and other hormonally-mediated outcomes.

Borrel Alexandre, Rudel Ruthann A

2022-Nov-30

General General

Multi-day dataset of forearm and wrist electromyogram for hand gesture recognition and biometrics.

In Scientific data

Surface electromyography (sEMG) signals have been used for advanced prosthetics control, hand-gesture recognition (HGR), and more recently as a novel biometric trait. For these sEMG-based applications, the translation from laboratory research setting to real-life scenarios suffers from two major limitations: (1) a small subject pool, and (2) single-session data recordings, both of which prevents acceptable generalization ability. In this longitudinal database, forearm and wrist sEMG data were collected from 43 participants over three different days with long separation (Days 1, 8, and 29) while they performed static hand/wrist gestures. The objective of this dataset is to provide a comprehensive dataset for the development of robust machine learning algorithms of sEMG, for both HGR and biometric applications. We demonstrated the high quality of the current dataset by comparing with the Ninapro dataset. And we presented its usability for both HGR and biometric applications. Among other applications, the dataset can also be used for developing electrode-shift invariant generalized models, which can further bolster the development of wristband and forearm-bracelet sensors.

Pradhan Ashirbad, He Jiayuan, Jiang Ning

2022-Nov-30

General General

Prediction of antifreeze proteins using machine learning.

In Scientific reports ; h5-index 158.0

Living organisms including fishes, microbes, and animals can live in extremely cold weather. To stay alive in cold environments, these species generate antifreeze proteins (AFPs), also referred to as ice-binding proteins. Moreover, AFPs are extensively utilized in many important fields including medical, agricultural, industrial, and biotechnological. Several predictors were constructed to identify AFPs. However, due to the sequence and structural heterogeneity of AFPs, correct identification is still a challenging task. It is highly desirable to develop a more promising predictor. In this research, a novel computational method, named AFP-LXGB has been proposed for prediction of AFPs more precisely. The information is explored by Dipeptide Composition (DPC), Grouped Amino Acid Composition (GAAC), Position Specific Scoring Matrix-Segmentation-Autocorrelation Transformation (Sg-PSSM-ACT), and Pseudo Position Specific Scoring Matrix Tri-Slicing (PseTS-PSSM). Keeping the benefits of ensemble learning, these feature sets are concatenated into different combinations. The best feature set is selected by Extremely Randomized Tree-Recursive Feature Elimination (ERT-RFE). The models are trained by Light eXtreme Gradient Boosting (LXGB), Random Forest (RF), and Extremely Randomized Tree (ERT). Among classifiers, LXGB has obtained the best prediction results. The novel method (AFP-LXGB) improved the accuracies by 3.70% and 4.09% than the best methods. These results verified that AFP-LXGB can predict AFPs more accurately and can participate in a significant role in medical, agricultural, industrial, and biotechnological fields.

Khan Adnan, Uddin Jamal, Ali Farman, Ahmad Ashfaq, Alghushairy Omar, Banjar Ameen, Daud Ali

2022-Nov-30

Public Health Public Health

Analysis of the first genetic engineering attribution challenge.

In Nature communications ; h5-index 260.0

The ability to identify the designer of engineered biological sequences-termed genetic engineering attribution (GEA)-would help ensure due credit for biotechnological innovation, while holding designers accountable to the communities they affect. Here, we present the results of the first Genetic Engineering Attribution Challenge, a public data-science competition to advance GEA techniques. Top-scoring teams dramatically outperformed previous models at identifying the true lab-of-origin of engineered plasmid sequences, including an increase in top-1 and top-10 accuracy of 10 percentage points. A simple ensemble of prizewinning models further increased performance. New metrics, designed to assess a model's ability to confidently exclude candidate labs, also showed major improvements, especially for the ensemble. Most winning teams adopted CNN-based machine-learning approaches; however, one team achieved very high accuracy with an extremely fast neural-network-free approach. Future work, including future competitions, should further explore a wide diversity of approaches for bringing GEA technology into practical use.

Crook Oliver M, Warmbrod Kelsey Lane, Lipstein Greg, Chung Christine, Bakerlee Christopher W, McKelvey T Greg, Holland Shelly R, Swett Jacob L, Esvelt Kevin M, Alley Ethan C, Bradshaw William J

2022-Nov-30

General General

The E3 ubiquitin ligase WWP2 regulates pro-fibrogenic monocyte infiltration and activity in heart fibrosis.

In Nature communications ; h5-index 260.0

Non-ischemic cardiomyopathy (NICM) can cause left ventricular dysfunction through interstitial fibrosis, which corresponds to the failure of cardiac tissue remodeling. Recent evidence implicates monocytes/macrophages in the etiopathology of cardiac fibrosis, but giving their heterogeneity and the antagonizing roles of macrophage subtypes in fibrosis, targeting these cells has been challenging. Here we focus on WWP2, an E3 ubiquitin ligase that acts as a positive genetic regulator of human and murine cardiac fibrosis, and show that myeloid specific deletion of WWP2 reduces cardiac fibrosis in hypertension-induced NICM. By using single cell RNA sequencing analysis of immune cells in the same model, we establish the functional heterogeneity of macrophages and define an early pro-fibrogenic phase of NICM that is driven by Ccl5-expressing Ly6chigh monocytes. Among cardiac macrophage subtypes, WWP2 dysfunction primarily affects Ly6chigh monocytes via modulating Ccl5, and consequentially macrophage infiltration and activation, which contributes to reduced myofibroblast trans-differentiation. WWP2 interacts with transcription factor IRF7, promoting its non-degradative mono-ubiquitination, nuclear translocation and transcriptional activity, leading to upregulation of Ccl5 at transcriptional level. We identify a pro-fibrogenic macrophage subtype in non-ischemic cardiomyopathy, and demonstrate that WWP2 is a key regulator of IRF7-mediated Ccl5/Ly6chigh monocyte axis in heart fibrosis.

Chen Huimei, Chew Gabriel, Devapragash Nithya, Loh Jui Zhi, Huang Kevin Y, Guo Jing, Liu Shiyang, Tan Elisabeth Li Sa, Chen Shuang, Tee Nicole Gui Zhen, Mia Masum M, Singh Manvendra K, Zhang Aihua, Behmoaras Jacques, Petretto Enrico

2022-Nov-30

General General

Machine Learning Methods for Predicting Patient-Level Emergency Department Workload.

In The Journal of emergency medicine

BACKGROUND : Work Relative Value Units (wRVUs) are a component of many compensation models, and a proxy for the effort required to care for a patient. Accurate prediction of wRVUs generated per patient at triage could facilitate real-time load balancing between physicians and provide many practical operational and clinical benefits.

OBJECTIVE : We examined whether deep-learning approaches could predict the wRVUs generated by a patient's visit using data commonly available at triage.

METHODS : Adult patients presenting to an urban, academic emergency department from July 1, 2016-March 1, 2020 were included. Deidentified triage information included structured data (age, sex, vital signs, Emergency Severity Index score, language, race, standardized chief complaint) and unstructured data (free-text chief complaint) with wRVUs as outcome. Five models were examined: average wRVUs per chief complaint, linear regression, neural network and gradient-boosted tree on structured data, and neural network on unstructured textual data. Models were evaluated using mean absolute error.

RESULTS : We analyzed 204,064 visits between July 1, 2016 and March 1, 2020. The median wRVUs were 3.80 (interquartile range 2.56-4.21), with significant effects of age, gender, and race. Models demonstrated lower error as complexity increased. Predictions using averages from chief complaints alone demonstrated a mean error of 2.17 predicted wRVUs per visit (95% confidence interval [CI] 2.07-2.27), the linear regression model: 1.00 wRVUs (95% CI 0.97-1.04), gradient-boosted tree: 0.85 wRVUs (95% CI 0.84-0.86), neural network with structured data: 0.86 wRVUs (95% CI 0.85-0.87), and neural network with unstructured data: 0.78 wRVUs (95% CI 0.76-0.80).

CONCLUSIONS : Chief complaints are a poor predictor of the effort needed to evaluate a patient; however, deep-learning techniques show promise. These algorithms have the potential to provide many practical applications, including balancing workloads and compensation between emergency physicians, quantify crowding and mobilizing resources, and reducing bias in the triage process.

Joseph Joshua W, Leventhal Evan L, Grossestreuer Anne V, Chen Paul C, White Benjamin A, Nathanson Larry A, Elhadad Noémie, Sanchez Leon D

2022-Nov-27

clinical decision support, machine learning, operations management, quality assurance

Pathology Pathology

Artificial Intelligence in the Diagnosis of Invasive Mold Infection: Development of an Automated Histologic Identification System to Distinguish Between Aspergillus and Mucorales.

In Medical mycology journal

BACKGROUND : Histopathological identification is usually required since the sensitivity of fungal culture is not sufficient for accurate diagnosis. On the other hand, pathological diagnosis, especially of molds, often is not accurate, even when performed by an experienced pathologist. This is particularly true in the differentiation between mucormycosis and aspergillosis, which have different drugs of choice and medical management. The diseases can easily become severe in a short period of time in accordance with the severity of the underlying disease or predisposing factors. Therefore, correct diagnosis is extremely important and should be entrusted to the pathologist.

AIM : To develop an artificial intelligence (AI)-based automated histological diagnostic system for mold infection to support the diagnosis by general pathologists, especially for distinguishing between Aspergillus and Mucorales.

METHOD : We used two indicators for the diagnostic system; namely, the angle of independent hyphae and tortuosity of each hypha.

RESULTS AND CONCLUSION : We collected 147 and 67 image samples respectively from standard cases of aspergillosis and mucormycosis. All the images were successfully analyzed by automatic recognition of the two indicators. The independent areas divided by the threshold curve generated by two-dimensional plots of the data clearly include the test data obtained from the cases of Aspergillus and Mucorales. The present study demonstrates the usefulness of our newly developed AI-based diagnostic system. Further investigation is required for its practical use.

Tochigi Naobumi, Sadamoto Sota, Oura Shinji, Kurose Yasuko, Miyazaki Yoshitsugu, Shibuya Kazutoshi

2022

AI method, Aspergillus, Mucorales, Python, invasive mold infection

General General

Errata: Automatic Detection of Left Ventricular Dilatation and Hypertrophy from Electrocardiograms Using Deep Learning.

In International heart journal

Several errors (shown with underlines) in the following list appeared in the article entitled "Automatic Detection of Left Ventricular Dilatation and Hypertrophy from Electrocardiograms Using Deep Learning" by Takahiro Kokubo, Satoshi Kodera, Shinnosuke Sawano, Susumu Katsushika, Mitsuhiko Nakamoto, Hirotoshi Takeuchi, Nisei Kimura, Hiroki Shinohara, Ryo Matsuoka, Koki Nakanishi, Tomoko Nakao, Yasutomi Higashikuni, Norifumi Takeda, Katsuhito Fujiu, Masao Daimon, Hiroshi Akazawa, Hiroyuki Morita, Yutaka Matsuyama, and Issei Komuro (Vol. 63, 939-947, 2022).

**

2022

Public Health Public Health

Artificial intelligence and health inequities in primary care: a systematic scoping review and framework.

In Family medicine and community health

OBJECTIVE : Artificial intelligence (AI) will have a significant impact on healthcare over the coming decade. At the same time, health inequity remains one of the biggest challenges. Primary care is both a driver and a mitigator of health inequities and with AI gaining traction in primary care, there is a need for a holistic understanding of how AI affect health inequities, through the act of providing care and through potential system effects. This paper presents a systematic scoping review of the ways AI implementation in primary care may impact health inequity.

DESIGN : Following a systematic scoping review approach, we searched for literature related to AI, health inequity, and implementation challenges of AI in primary care. In addition, articles from primary exploratory searches were added, and through reference screening.The results were thematically summarised and used to produce both a narrative and conceptual model for the mechanisms by which social determinants of health and AI in primary care could interact to either improve or worsen health inequities.Two public advisors were involved in the review process.

ELIGIBILITY CRITERIA : Peer-reviewed publications and grey literature in English and Scandinavian languages.

INFORMATION SOURCES : PubMed, SCOPUS and JSTOR.

RESULTS : A total of 1529 publications were identified, of which 86 met the inclusion criteria. The findings were summarised under six different domains, covering both positive and negative effects: (1) access, (2) trust, (3) dehumanisation, (4) agency for self-care, (5) algorithmic bias and (6) external effects. The five first domains cover aspects of the interface between the patient and the primary care system, while the last domain covers care system-wide and societal effects of AI in primary care. A graphical model has been produced to illustrate this. Community involvement throughout the whole process of designing and implementing of AI in primary care was a common suggestion to mitigate the potential negative effects of AI.

CONCLUSION : AI has the potential to affect health inequities through a multitude of ways, both directly in the patient consultation and through transformative system effects. This review summarises these effects from a system tive and provides a base for future research into responsible implementation.

d’Elia Alexander, Gabbay Mark, Rodgers Sarah, Kierans Ciara, Jones Elisa, Durrani Irum, Thomas Adele, Frith Lucy

2022-Nov

General Practice, Health Equity, Healthcare Disparities

Pathology Pathology

Interpretable deep learning translation of GWAS and multi-omics findings to identify pathobiology and drug repurposing in Alzheimer's disease.

In Cell reports ; h5-index 119.0

Translating human genetic findings (genome-wide association studies [GWAS]) to pathobiology and therapeutic discovery remains a major challenge for Alzheimer's disease (AD). We present a network topology-based deep learning framework to identify disease-associated genes (NETTAG). We leverage non-coding GWAS loci effects on quantitative trait loci, enhancers and CpG islands, promoter regions, open chromatin, and promoter flanking regions under the protein-protein interactome. Via NETTAG, we identified 156 AD-risk genes enriched in druggable targets. Combining network-based prediction and retrospective case-control observations with 10 million individuals, we identified that usage of four drugs (ibuprofen, gemfibrozil, cholecalciferol, and ceftriaxone) is associated with reduced likelihood of AD incidence. Gemfibrozil (an approved lipid regulator) is significantly associated with 43% reduced risk of AD compared with simvastatin using an active-comparator design (95% confidence interval 0.51-0.63, p < 0.0001). In summary, NETTAG offers a deep learning methodology that utilizes GWAS and multi-genomic findings to identify pathobiology and drug repurposing in AD.

Xu Jielin, Mao Chengsheng, Hou Yuan, Luo Yuan, Binder Jessica L, Zhou Yadi, Bekris Lynn M, Shin Jiyoung, Hu Ming, Wang Fei, Eng Charis, Oprea Tudor I, Flanagan Margaret E, Pieper Andrew A, Cummings Jeffrey, Leverenz James B, Cheng Feixiong

2022-Nov-29

AD, Alzheimer’s disease, CP: Neuroscience, EHR, GWAS, deep learning, drug repurposing, drug target, electronic health record, gemfibrozil, genome-wide association studies, multi-omics, pathobiology, protein-protein Interactome

General General

Antibiotic discovery in the artificial intelligence era.

In Annals of the New York Academy of Sciences

As the global burden of antibiotic resistance continues to grow, creative approaches to antibiotic discovery are needed to accelerate the development of novel medicines. A rapidly progressing computational revolution-artificial intelligence-offers an optimistic path forward due to its ability to alleviate bottlenecks in the antibiotic discovery pipeline. In this review, we discuss how advancements in artificial intelligence are reinvigorating the adoption of past antibiotic discovery models-namely natural product exploration and small molecule screening. We then explore the application of contemporary machine learning approaches to emerging areas of antibiotic discovery, including antibacterial systems biology, drug combination development, antimicrobial peptide discovery, and mechanism of action prediction. Lastly, we propose a call to action for open access of high-quality screening datasets and interdisciplinary collaboration to accelerate the rate at which machine learning models can be trained and new antibiotic drugs can be developed.

Lluka Telmah, Stokes Jonathan M

2022-Nov-29

antibiotics, drug discovery, machine learning

General General

Emerging 0D, 1D, 2D, and 3D nanostructures for efficient point-of-care biosensing.

In Biosensors & bioelectronics: X

The recent COVID-19 infection outbreak has raised the demand for rapid, highly sensitive POC biosensing technology for intelligent health and wellness. In this direction, efforts are being made to explore high-performance nano-systems for developing novel sensing technologies capable of functioning at point-of-care (POC) applications for quick diagnosis, data acquisition, and disease management. A combination of nanostructures [i.e., 0D (nanoparticles & quantum dots), 1D (nanorods, nanofibers, nanopillars, & nanowires), 2D (nanosheets, nanoplates, nanopores) & 3D nanomaterials (nanocomposites and complex hierarchical structures)], biosensing prototype, and micro-electronics makes biosensing suitable for early diagnosis, detection & prevention of life-threatening diseases. However, a knowledge gap associated with the potential of 0D, 1D, 2D, and 3D nanostructures for the design and development of efficient POC sensing is yet to be explored carefully and critically. With this focus, this review highlights the latest engineered 0D, 1D, 2D, and 3D nanomaterials for developing next-generation miniaturized, portable POC biosensors development to achieve high sensitivity with potential integration with the internet of medical things (IoMT, for miniaturization and data collection, security, and sharing), artificial intelligence (AI, for desired analytics), etc. for better diagnosis and disease management at the personalized level.

Byakodi Manisha, Shrikrishna Narlawar Sagar, Sharma Riya, Bhansali Shekhar, Mishra Yogendra, Kaushik Ajeet, Gandhi Sonu

2022-Nov-25

0D to 3D nanomaterials, Biosensors, Efficient diagnostics, Personalized health management, Point-of-care testing, Wearable

General General

Deep Kernel Learning for Mortality Prediction in the Face of Temporal Shift

ArXiv Preprint

Neural models, with their ability to provide novel representations, have shown promising results in prediction tasks in healthcare. However, patient demographics, medical technology, and quality of care change over time. This often leads to drop in the performance of neural models for prospective patients, especially in terms of their calibration. The deep kernel learning (DKL) framework may be robust to such changes as it combines neural models with Gaussian processes, which are aware of prediction uncertainty. Our hypothesis is that out-of-distribution test points will result in probabilities closer to the global mean and hence prevent overconfident predictions. This in turn, we hypothesise, will result in better calibration on prospective data. This paper investigates DKL's behaviour when facing a temporal shift, which was naturally introduced when an information system that feeds a cohort database was changed. We compare DKL's performance to that of a neural baseline based on recurrent neural networks. We show that DKL indeed produced superior calibrated predictions. We also confirm that the DKL's predictions were indeed less sharp. In addition, DKL's discrimination ability was even improved: its AUC was 0.746 (+- 0.014 std), compared to 0.739 (+- 0.028 std) for the baseline. The paper demonstrated the importance of including uncertainty in neural computing, especially for their prospective use.

Miguel Rios, Ameen Abu-Hanna

2022-12-01

General General

Adaptive Memory and In Materia Reinforcement Learning Enabled by Flexoelectric-like Response from Ultrathin HfO2.

In ACS applied materials & interfaces ; h5-index 147.0

Reinforcement learning (RL) is a mathematical framework of neural learning by trial and error that revolutionized the field of artificial intelligence. However, until now, RL has been implemented in algorithms with the compatibly of traditional complementary metal-oxide-semiconductor-based von Neumann digital platforms, which thus limits performance in terms of latency, fault tolerance, and robustness. Here, we demonstrate that nanocolumnar (∼12 nm) HfO2 structures can be used as building blocks to conduct the RL within the material by combining its stress-adjustable charge transport and memory functions. Specifically, HfO2 nanostructures grown by the sputtering method exhibit self-assembled vertical nanocolumnar structures that generate voltage depending on the impact of stress under self-biased conditions. The observed results are attributed to the flexoelectric-like response of HfO2. Further, multilevel current (>10-3 A) modulation with touch and controlled suspension (∼10-12 A) with a short electric pulse (100 ms) were demonstrated, yielding a proof-of-concept memory with an on/off ratio greater than 109. Utilizing multipattern dynamic memory and tactile sensing, RL was implemented to successfully solve a maze game using an array of 6 × 4. This work could pave the way to do RL within materials for a variety of applications such as memory storage, neuromorphic sensors, smart robots, and human-machine interaction systems.

Kumar Mohit, Seo Hyungtak

2022-Nov-30

adaptive memory, flexoelectric effect, in materia, reinforcement learning, ultrathin HfO2

General General

Using Self-Organizing Maps to find spatial relationships between wildlife-vehicle crashes and land use classes.

In Anais da Academia Brasileira de Ciencias

The construction and expansion of roads cause significant impacts on the environment. The main potential impacts to biotic environment are vegetation suppression, reduction of the amount and composition of animal distribution due to forest fragmentation and increasing risks of animal (domestic and wildlife) vehicle collisions. The objective of this work was to establish a relationship between the different spatial patterns in wildlife-vehicle crash, by using spatial analysis and machine learning tools. Self-Organizing Maps (SOM), an artificial neural network (ANN), was selected to reorganize the multi-dimensional data according to the similarity between them. The results of the spatial pattern analysis were important to perceive that the point data pattern varies from an animal type to another. The events occur spatially clustered and are not uniformly distributed along the highway. SOM was able to analyze the relationship between multiple variables, linear and non-linear, such as ecological data, and established distinct spatial patterns per each animal type. In the studied area, most of the wildlife was run over very close to forest area and water bodies, and not so close to sugarcane fields, forestry and built environment. A considerable part of the wildlife-vehicle collisions occurred in areas with diverse landscape.

Tsuda Larissa S, Carneiro Cleyton C, Quintanilha José Alberto

2022

Radiology Radiology

Application of deep learning-based diagnostic systems in screening asymptomatic COVID-19 patients among oversea returnees.

In Journal of infection in developing countries

INTRODUCTION : Our study aimed to investigate the performance of deep learning (DL)-based diagnostic systems in alerting against COVID-19, especially among asymptomatic individuals coming from overseas, and to analyze the features of identified asymptomatic patients in detail.

METHODOLOGY : DL diagnostic systems were deployed to assist in the screening of COVID-19, including the pneumonia system and pulmonary nodules system. 1,917 overseas returnees who underwent CT examination and rRT-PCR tests were enrolled. DL pneumonia system promptly alerted clinicians to suspected COVID-19 after CT examinations while the performance was evaluated with rRT-PCR results as the reference. The radiological features of asymptomatic COVID-19 cases were described according to the Nomenclature of the Fleischner Society.

RESULTS : Fifty-three cases were confirmed as COVID-19 patients by rRT-PCR tests, including 5 asymptomatic cases. DL pneumonia system correctly alerted 50 cases as suspected COVID-19 with a sensitivity of 0.9434 and specificity of 0.9592 (within 2 minutes per case); while the pulmonary nodules system alerted 2 of the 3 missed asymptomatic cases. Additionally, five asymptomatic patients presented different characteristics such as elevated creatine kinase level and prolonged prothrombin time, as well as atypical radiological features.

CONCLUSIONS : DL diagnostic systems are promising complementary approaches for prompt screening of imported COVID-19 patients, even the imported asymptomatic cases. Unique clinical and radiological characteristics of asymptomatic cases might be of great value in screening as well.

ADVANCES IN KNOWLEDGE : DL-based systems are practical, efficient, and reliable to assist radiologists in screening COVID-19 patients. Differential features of asymptomatic patients might be useful to clinicians in the frontline to differentiate asymptomatic cases.

Dong Dawei, Luo Zujin, Zheng Yue, Liang Ying, Zhao Pengfei, Feng Linlin, Wang Dawei, Cao Ying, Zhao Zhenhao, Ma Yingmin

2022-Nov-29

COVID-19, Deep learning, asymptomatic cases, diagnostic systems, performance evaluation

General General

Concentrated poverty, ambient air pollution, and child cognitive development.

In Science advances

Why does growing up in a poor neighborhood impede cognitive development? Although a large volume of evidence indicates that neighborhood poverty negatively affects child outcomes, little is known about the mechanisms that might explain these effects. In this study, we outline and test a theoretical model of neighborhood effects on cognitive development that highlights the mediating role of early life exposure to neurotoxic air pollution. To evaluate this model, we analyze data from a national sample of American infants matched with information on their exposure to more than 50 different pollutants known or suspected to harm the central nervous system. Integrating methods of causal inference with supervised machine learning, we find that living in a high-poverty neighborhood increases exposure to many different air toxics during infancy, that it reduces cognitive abilities measured later at age 4 by about one-tenth of a standard deviation, and that about one-third of this effect can be attributed to disparities in air quality.

Wodtke Geoffrey T, Ard Kerry, Bullock Clair, White Kailey, Priem Betsy

2022-Dec-02

General General

A Survey on Deep Learning Technique for Video Segmentation.

In IEEE transactions on pattern analysis and machine intelligence ; h5-index 127.0

Video segmentation-partitioning video frames into multiple segments or objects-plays a critical role in a broad range of practical applications, from enhancing visual effects in movie, to understanding scenes in autonomous driving, to creating virtual background in video conferencing. Recently, with the renaissance of connectionism in computer vision, there has been an influx of deep learning based approaches for video segmentation that have delivered compelling performance. In this survey, we comprehensively review two basic lines of research - generic object segmentation (of unknown categories) in videos, and video semantic segmentation - by introducing their respective task settings, background concepts, perceived need, development history, and main challenges. We also offer a detailed overview of representative literature on both methods and datasets. We further benchmark the reviewed methods on several well-known datasets. Finally, we point out open issues in this field, and suggest opportunities for further research. We also provide a public website to continuously track developments in this fast advancing field: https://github.com/tfzhou/VS-Survey.

Zhou Tianfei, Porikli Fatih, Crandall David J, Gool Luc Van, Wang Wenguan

2022-Nov-30

General General

Rectification-based Knowledge Retention for Task Incremental Learning.

In IEEE transactions on pattern analysis and machine intelligence ; h5-index 127.0

In the task incremental learning problem, deep learning models suffer from catastrophic forgetting of previously seen classes/tasks as they are trained on new classes/tasks. This problem becomes even harder when some of the test classes do not belong to the training class set, i.e., the task incremental generalized zero-shot learning problem. We propose a novel approach to address the task incremental learning problem for both the non zero-shot and zero-shot settings. Our proposed approach, called Rectification-based Knowledge Retention (RKR), applies weight rectifications and affine transformations for adapting the model to any task. During testing, our approach can use the task label information (task-aware) to quickly adapt the network to that task. We also extend our approach to make it task-agnostic so that it can work even when the task label information is not available during testing. Specifically, given a continuum of test data, our approach predicts the task and quickly adapts the network to the predicted task. We experimentally show that our proposed approach achieves state-of-the-art results on several benchmark datasets for both non zero-shot and zero-shot task incremental learning.

Mazumder Pratik, Singh Pravendra, Rai Piyush, Namboodiri Vinay P

2022-Nov-30

General General

MouseGAN++: Unsupervised Disentanglement and Contrastive Representation for Multiple MRI Modalities Synthesis and Structural Segmentation of Mouse Brain.

In IEEE transactions on medical imaging ; h5-index 74.0

Segmenting the fine structure of the mouse brain on magnetic resonance (MR) images is critical for delineating morphological regions, analyzing brain function, and understanding their relationships. Compared to a single MRI modality, multimodal MRI data provide complementary tissue features that can be exploited by deep learning models, resulting in better segmentation results. However, multimodal mouse brain MRI data is often lacking, making automatic segmentation of mouse brain fine structure a very challenging task. To address this issue, it is necessary to fuse multimodal MRI data to produce distinguished contrasts in different brain structures. Hence, we propose a novel disentangled and contrastive GAN-based framework, named MouseGAN++, to synthesize multiple MR modalities from single ones in a structure-preserving manner, thus improving the segmentation performance by imputing missing modalities and multi-modality fusion. Our results demonstrate that the translation performance of our method outperforms the state-of-the-art methods. Using the subsequently learned modality-invariant information as well as the modality-translated images, MouseGAN++ can segment fine brain structures with averaged dice coefficients of 90.0% (T2w) and 87.9% (T1w), respectively, achieving around +10% performance improvement compared to the state-of-the-art algorithms. Our results demonstrate that MouseGAN++, as a simultaneous image synthesis and segmentation method, can be used to fuse cross-modality information in an unpaired manner and yield more robust performance in the absence of multimodal data. We release our method as a mouse brain structural segmentation tool for free academic usage at https://github.com/yu02019.

Yu Ziqi, Han Xiaoyang, Zhang Shengjie, Feng Jianfeng, Peng Tingying, Zhang Xiao-Yong

2022-Nov-30

General General

DREAM-Net: Deep Residual Error iterAtive Minimization Network for Sparse-View CT Reconstruction.

In IEEE journal of biomedical and health informatics

Sparse-view Computed Tomography (CT) has the ability to reduce radiation dose and shorten the scan time, while the severe streak artifacts will compromise anatomical information. How to reconstruct high-quality images from sparsely sampled projections is a challenging ill-posed problem. In this context, we propose the unrolled Deep Residual Error iterAtive Minimization Network (DREAM-Net) based on a novel iterative reconstruction framework to synergize the merits of deep learning and iterative reconstruction. DREAM-Net performs constraints using deep neural networks in the projection domain, residual space, and image domain simultaneously, which is different from the routine practice in deep iterative reconstruction frameworks. First, a projection inpainting module completes the missing views to fully explore the latent relationship between projection data and reconstructed images. Then, the residual awareness module attempts to estimate the accurate residual image after transforming the projection error into the image space. Finally, the image refinement module learns a non-standard regularizer to further fine-tune the intermediate image. There is no need to empirically adjust the weights of different terms in DREAM-Net because the hyper-parameters are embedded implicitly in network modules. Qualitative and quantitative results have demonstrated the promising performance of DREAM-Net in artifact removal and structural fidelity.

Zhang Yikun, Hu Dianlin, Hao Shilei, Liu Jin, Quan Guotao, Zhang Yi, Ji Xu, Chen Yang

2022-Nov-30

General General

Low-Rank Graph Completion-Based Incomplete Multiview Clustering.

In IEEE transactions on neural networks and learning systems

In order to reduce the negative effect of missing data on clustering, incomplete multiview clustering (IMVC) has become an important research content in machine learning. At present, graph-based methods are widely used in IMVC, but these methods still have some defects. First, some of the methods overlook potential relationships across views. Second, most of the methods depend on local structure information and ignore the global structure information. Third, most of the methods cannot use both global structure information and potential information across views to adaptively recover the incomplete relationship structure. To address the above issues, we propose a unified optimization framework to learn reasonable affinity relationships, called low-rank graph completion-based IMVC (LRGR_IMVC). 1) Our method introduces adaptive graph embedding to effectively explore the potential relationship among views; 2) we append a low-rank constraint to adequately exploit the global structure information among views; and 3) this method unites related information within views, potential information across views, and global structure information to adaptively recover the incomplete graph structure and obtain complete affinity relationships. Experimental results on several commonly used datasets show that the proposed method achieves better clustering performance significantly than some of the most advanced methods.

Cui Jinrong, Fu Yulu, Huang Cheng, Wen Jie

2022-Nov-30

General General

Multigroup prediction in lung cancer patients and comparative controls using signature of volatile organic compounds in breath samples.

In PloS one ; h5-index 176.0

Early detection of lung cancer is a crucial factor for increasing its survival rates among the detected patients. The presence of carbonyl volatile organic compounds (VOCs) in exhaled breath can play a vital role in early detection of lung cancer. Identifying these VOC markers in breath samples through innovative statistical and machine learning techniques is an important task in lung cancer research. Therefore, we proposed an experimental approach for generation of VOC molecular concentration data using unique silicon microreactor technology and further identification and characterization of key relevant VOCs important for lung cancer detection through statistical and machine learning algorithms. We reported several informative VOCs and tested their effectiveness in multi-group classification of patients. Our analytical results indicated that seven key VOCs, including C4H8O2, C13H22O, C11H22O, C2H4O2, C7H14O, C6H12O, and C5H8O, are sufficient to detect the lung cancer patients with higher mean classification accuracy (92%) and lower standard error (0.03) compared to other combinations. In other words, the molecular concentrations of these VOCs in exhaled breath samples were able to discriminate the patients with lung cancer (n = 156) from the healthy smoker and nonsmoker controls (n = 193) and patients with benign pulmonary nodules (n = 65). The quantification of carbonyl VOC profiles from breath samples and identification of crucial VOCs through our experimental approach paves the way forward for non-invasive lung cancer detection. Further, our experimental and analytical approach of VOC quantitative analysis in breath samples may be extended to other diseases, including COVID-19 detection.

Rai Shesh N, Das Samarendra, Pan Jianmin, Mishra Dwijesh C, Fu Xiao-An

2022

Ophthalmology Ophthalmology

Retinal age gap as a predictive biomarker of stroke risk.

In BMC medicine ; h5-index 89.0

BACKGROUND : The aim of this study is to investigate the association of retinal age gap with the risk of incident stroke and its predictive value for incident stroke.

METHODS : A total of 80,169 fundus images from 46,969 participants in the UK Biobank cohort met the image quality standard. A deep learning model was constructed based on 19,200 fundus images of 11,052 disease-free participants at baseline for age prediction. Retinal age gap (retinal age predicted based on the fundus image minus chronological age) was generated for the remaining 35,917 participants. Stroke events were determined by data linkage to hospital records on admissions and diagnoses, and national death registers, whichever occurred earliest. Cox proportional hazards regression models were used to estimate the effect of retinal age gap on risk of stroke. Logistic regression models were used to estimate the predictive value of retinal age and well-established risk factors in 10-year stroke risk.

RESULTS : A total of 35,304 participants without history of stroke at baseline were included. During a median follow-up of 5.83 years, 282 (0.80%) participants had stroke events. In the fully adjusted model, each one-year increase in the retinal age gap was associated with a 4% increase in the risk of stroke (hazard ratio [HR] = 1.04, 95% confidence interval [CI]: 1.00-1.08, P = 0.029). Compared to participants with retinal age gap in the first quintile, participants with retinal age gap in the fifth quintile had significantly higher risks of stroke events (HR = 2.37, 95% CI: 1.37-4.10, P = 0.002). The predictive capability of retinal age alone was comparable to the well-established risk factor-based model (AUC=0.676 vs AUC=0.661, p=0.511).

CONCLUSIONS : We found that retinal age gap was significantly associated with incident stroke, implying the potential of retinal age gap as a predictive biomarker of stroke risk.

Zhu Zhuoting, Hu Wenyi, Chen Ruiye, Xiong Ruilin, Wang Wei, Shang Xianwen, Chen Yifan, Kiburg Katerina, Shi Danli, He Shuang, Huang Yu, Zhang Xueli, Tang Shulin, Zeng Jieshan, Yu Honghua, Yang Xiaohong, He Mingguang

2022-Nov-30

Biomarker, Prediction, Retinal age, Stroke

General General

Automatic detection of Covid-19 from chest X-ray and lung computed tomography images using deep neural networks and transfer learning.

In Applied soft computing

The world has been undergoing the most ever unprecedented circumstances caused by the coronavirus pandemic, which is having a devastating global effect in different aspects of life. Since there are not effective antiviral treatments for Covid-19 yet, it is crucial to early detect and monitor the progression of the disease, thereby helping to reduce mortality. While different measures are being used to combat the virus, medical imaging techniques have been examined to support doctors in diagnosing the disease. In this paper, we present a practical solution for the detection of Covid-19 from chest X-ray (CXR) and lung computed tomography (LCT) images, exploiting cutting-edge Machine Learning techniques. As the main classification engine, we make use of EfficientNet and MixNet, two recently developed families of deep neural networks. Furthermore, to make the training more effective and efficient, we apply three transfer learning algorithms. The ultimate aim is to build a reliable expert system to detect Covid-19 from different sources of images, making it be a multi-purpose AI diagnosing system. We validated our proposed approach using four real-world datasets. The first two are CXR datasets consist of 15,000 and 17,905 images, respectively. The other two are LCT datasets with 2,482 and 411,528 images, respectively. The five-fold cross-validation methodology was used to evaluate the approach, where the dataset is split into five parts, and accordingly the evaluation is conducted in five rounds. By each evaluation, four parts are combined to form the training data, and the remaining one is used for testing. We obtained an encouraging prediction performance for all the considered datasets. In all the configurations, the obtained accuracy is always larger than 95.0%. Compared to various existing studies, our approach yields a substantial performance gain. Moreover, such an improvement is statistically significant.

Duong Linh T, Nguyen Phuong T, Iovino Ludovico, Flammini Michele

2022-Nov-24

AI Diagnosis systems, COVID-19, Chest X-ray image, Expert systems, Lung CT images

Pathology Pathology

Embracing Annotation Efficient Learning (AEL) for Digital Pathology and Natural Images

ArXiv Preprint

Jitendra Malik once said, "Supervision is the opium of the AI researcher". Most deep learning techniques heavily rely on extreme amounts of human labels to work effectively. In today's world, the rate of data creation greatly surpasses the rate of data annotation. Full reliance on human annotations is just a temporary means to solve current closed problems in AI. In reality, only a tiny fraction of data is annotated. Annotation Efficient Learning (AEL) is a study of algorithms to train models effectively with fewer annotations. To thrive in AEL environments, we need deep learning techniques that rely less on manual annotations (e.g., image, bounding-box, and per-pixel labels), but learn useful information from unlabeled data. In this thesis, we explore five different techniques for handling AEL.

Eu Wern Teh

2022-12-01

General General

Using passive sensor data to probe associations of social structure with changes in personality: A synthesis of network analysis and machine learning.

In PloS one ; h5-index 176.0

Social network analysis (SNA) is an increasingly popular and effective tool for modeling psychological phenomena. Through application to the personality literature, social networks, in conjunction with passive, non-invasive sensing technologies, have begun to offer powerful insight into personality state variability. Resultant constructions of social networks can be utilized alongside machine learning-based frameworks to uniquely model personality states. Accordingly, this work leverages data from a previously published study to combine passively collected wearable sensor information on face-to-face, workplace social interactions with ecological momentary assessments of personality state. Data from 54 individuals across six weeks was used to explore the relative importance of 26 unique structural and nodal social network features in predicting individual changes in each of the Big Five (5F) personality states. Changes in personality state were operationalized by calculating the weekly root mean square of successive differences (RMSSD) in 5F state scores measured daily via self-report. Using only SNA-derived features from wearable sensor data, boosted tree-based machine learning models explained, on average, approximately 28-30% of the variance in individual personality state change. Model introspection implicated egocentric features as the most influential predictors across 5F-specific models, with network efficiency, constraint, and effective size measures among the most important. Feature importance profiles for each 5F model partially echoed previous empirical findings. Results support future efforts focusing on egocentric components of SNA and suggest particular investment in exploring efficiency measures to model personality fluctuations within the workplace setting.

Lekkas Damien, Gyorda Joseph A, Moen Erika L, Jacobson Nicholas C

2022

General General

Extracting film thickness and optical constants from spectrophotometric data by evolutionary optimization.

In PloS one ; h5-index 176.0

In this paper, we propose a simple and elegant method to extract the thickness and the optical constants of various films from the reflectance and transmittance spectra in the wavelength range of 350 - 1000 nm. The underlying inverse problem is posed here as an optimization problem. To find unique solutions to this problem, we adopt an evolutionary optimization approach that drives a population of candidate solutions towards the global optimum. An ensemble of Tauc-Lorentz Oscillators (TLOs) and an ensemble of Gaussian Oscillators (GOs), are leveraged to compute the reflectance and transmittance spectra for different candidate thickness values and refractive index profiles. This model-based optimization is solved using two efficient evolutionary algorithms (EAs), namely genetic algorithm (GA) and covariance matrix adaptation evolution strategy (CMAES), such that the resulting spectra simultaneously fit all the given data points in the admissible wavelength range. Numerical results validate the effectiveness of the proposed approach in estimating the optical parameters of interest.

Dutta Rajdeep, Tian Siyu Isaac Parker, Liu Zhe, Lakshminarayanan Madhavkrishnan, Venkataraj Selvaraj, Cheng Yuanhang, Bash Daniil, Chellappan Vijila, Buonassisi Tonio, Jayavelu Senthilnath

2022

General General

Toward a Mobility-Preserving Coarse-Grained Model: A Data-Driven Approach.

In Journal of chemical theory and computation

Coarse-grained molecular dynamics (MD) simulation is a promising alternative to all-atom MD simulation for the fast calculation of system properties, which is imperative in designing materials with a specific target property. There have been several coarse-graining strategies developed over the past few years that provide accurate structural properties of the system. However, these coarse-grained models share a major drawback in that they introduce an artificial acceleration in molecular mobility. In this paper, we report a data-driven approach to generate coarse-grained models that preserve the all-atom molecular mobility. We designed a machine learning model in the form of an artificial neural network, which directly predicts the simulation-ready mobility-preserving coarse-grained potential as an output given the all-atom force field (FF) parameters as inputs. As a proof of principle, we took 2,3,4-trimethylpentane as a model system and described the development of machine learning models in detail. We quantify the artificial acceleration in molecular mobility by defining the acceleration factor as the ratio of the coarse-grained and the all-atom diffusion coefficient. The predicted coarse-grained potential generated by the best machine learning model can bring down the acceleration factor to a value of ∼2, which could be otherwise as large as 7 for a typical value of 3 × 10-9 m2 s-1 for the all-atom diffusion coefficient. We believe our method will be of interest in the community as a route to generating coarse-grained potentials with accurate dynamics.

Bag Saientan, Meinel Melissa K, Müller-Plathe Florian

2022-Nov-30

General General

Artificial Intelligence in Intensive Care Medicine: Bibliometric Analysis.

In Journal of medical Internet research ; h5-index 88.0

BACKGROUND : Interest in critical care-related artificial intelligence (AI) research is growing rapidly. However, the literature is still lacking in comprehensive bibliometric studies that measure and analyze scientific publications globally.

OBJECTIVE : The objective of this study was to assess the global research trends in AI in intensive care medicine based on publication outputs, citations, coauthorships between nations, and co-occurrences of author keywords.

METHODS : A total of 3619 documents published until March 2022 were retrieved from the Scopus database. After selecting the document type as articles, the titles and abstracts were checked for eligibility. In the final bibliometric study using VOSviewer, 1198 papers were included. The growth rate of publications, preferred journals, leading research countries, international collaborations, and top institutions were computed.

RESULTS : The number of publications increased steeply between 2018 and 2022, accounting for 72.53% (869/1198) of all the included papers. The United States and China contributed to approximately 55.17% (661/1198) of the total publications. Of the 15 most productive institutions, 9 were among the top 100 universities worldwide. Detecting clinical deterioration, monitoring, predicting disease progression, mortality, prognosis, and classifying disease phenotypes or subtypes were some of the research hot spots for AI in patients who are critically ill. Neural networks, decision support systems, machine learning, and deep learning were all commonly used AI technologies.

CONCLUSIONS : This study highlights popular areas in AI research aimed at improving health care in intensive care units, offers a comprehensive look at the research trend in AI application in the intensive care unit, and provides an insight into potential collaboration and prospects for future research. The 30 articles that received the most citations were listed in detail. For AI-based clinical research to be sufficiently convincing for routine critical care practice, collaborative research efforts are needed to increase the maturity and robustness of AI-driven models.

Tang Ri, Zhang Shuyi, Ding Chenling, Zhu Mingli, Gao Yuan

2022-Nov-30

artificial intelligence, bibliometric analysis, intensive care medicine, machine learning, sepsis

Public Health Public Health

The Passive Monitoring of Depression and Anxiety Among Workers Using Digital Biomarkers Based on Their Physical Activity and Working Conditions: 2-Week Longitudinal Study.

In JMIR formative research

BACKGROUND : Digital data on physical activity are useful for self-monitoring and preventing depression and anxiety. Although previous studies have reported machine or deep learning models that use physical activity for passive monitoring of depression and anxiety, there are no models for workers. The working population has different physical activity patterns from other populations, which is based on commuting, holiday patterns, physical demands, occupations, and industries. These working conditions are useful in optimizing the model used in predicting depression and anxiety. Further, recurrent neural networks increase predictive accuracy by using previous inputs on physical activity, depression, and anxiety.

OBJECTIVE : This study evaluated the performance of a deep learning model optimized for predicting depression and anxiety in workers. Psychological distress was considered a depression and anxiety indicator.

METHODS : A 2-week longitudinal study was conducted with workers in urban areas in Japan. Absent workers were excluded. In a daily survey, psychological distress was measured using a self-reported questionnaire. As features, activity time by intensity was determined using the Google Fit application. Additionally, we measured age, gender, occupations, employment status, work shift types, working hours, and whether the response date was a working or nonworking day. A deep learning model, using long short-term memory, was developed and validated to predict psychological distress the next day, using features of the previous day. Further, a 5-fold cross-validation method was used to evaluate the performance of the aforementioned model. As the primary indicator of performance, classification accuracy for the severity of the psychological distress (light, subthreshold, and severe) was considered.

RESULTS : A total of 1661 days of supervised data were obtained from 236 workers, who were aged between 20 and 69 years. The overall classification accuracy for psychological distress was 76.3% (SD 0.04%). The classification accuracy for severe-, subthreshold-, and light-level psychological distress was 51.1% (SD 0.05%), 60.6% (SD 0.05%), and 81.6% (SD 0.04%), respectively. The model predicted a light-level psychological distress the next day after the participants had been involved in 3 peaks of activity (in the morning, noon, and evening) on the previous day. Lower activity levels were predicted as subthreshold- and severe-level psychological distress. Different predictive results were observed on the basis of occupations and whether the previous day was a working or nonworking day.

CONCLUSIONS : The developed deep learning model showed a similar performance as in previous studies and, in particular, high accuracy for light-level psychological distress. Working conditions and long short-term memory were useful in maintaining the model performance for monitoring depression and anxiety, using digitally recorded physical activity in workers. The developed model can be implemented in mobile apps and may further be practically used by workers to self-monitor and maintain their mental health state.

Watanabe Kazuhiro, Tsutsumi Akizumi

2022-Nov-30

anxiety, depression, digital biomarkers, mental health, mobile health, physical activity, psychological distress

Public Health Public Health

Maximum Accuracy Machine Learning Statistical Analysis-A Novel Approach.

In Cancer treatment and research

Logistic regression is a statistical tool of paramount significance in the field of epidemiology1 and ranks as one of the most frequently published multivariable analyses for designs involving a single binary dependent variable and one or more independent variables in the fields of public health2,3 and medical4 research.

Ugarte Shannon, Yarnold Paul, Ray Paul, Knopf Kevin, Hoque Shamia, Taylor Matthew, Bennett Charles L

2022

General General

A preliminary attempt to use radiomic features in the diagnosis of extra-articular long head biceps tendinitis.

In Magma (New York, N.Y.)

BACKGROUND : This study aims to present a radiomic application in diagnosing the long head of biceps (LHB) tendinitis. Moreover, we evaluated whether machine learning-derived radiomic features recognize LHB tendinitis.

PATIENTS AND METHODS : A total of 170 patients were reviewed. All LHB tendinitis patients were diagnosed under arthroscopy. Radiomic features were extracted from preoperative magnetic resonance imaging (MRI), and the input dataset was divided into a training set and a test set. For feature selection, the t test and least absolute shrinkage and selection operator (LASSO) methods were used, and random forest (RF) and support vector machine (SVM) were used as machine learning classifiers. The sensitivity, specificity, accuracy, and area under the curve (AUC) of each model's receiver operating characteristic (ROC) curves were calculated to evaluate model performance.

RESULTS : In total, 851 radiomic features were extracted, with 109 radiomic features extracted using a t test and 20 radiomic features extracted using the LASSO method. The random forest classifier shows the highest sensitivity, specificity, accuracy, and AUC (0.52, 0.92, 0.73, and 0.72).

CONCLUSION : The classifier contract by 20 radiomic features demonstrated a good ability to predict extra-articular LHB tendinitis.However because of poor segmentation reliability, the value of Radiomic in LHB tendinitis still needs to be further explored.

Yin Lifeng, Kong Yanggang, Guo Mingkang, Zhang Xingyu, Yan Wenlong, Zhang Hua

2022-Nov-30

Long head of biceps tendon, MRI, Machine learning, Radiomic, Tendinitis

Radiology Radiology

Primary bone tumor detection and classification in full-field bone radiographs via YOLO deep learning model.

In European radiology ; h5-index 62.0

OBJECTIVES : Automatic bone lesions detection and classifications present a critical challenge and are essential to support radiologists in making an accurate diagnosis of bone lesions. In this paper, we aimed to develop a novel deep learning model called You Only Look Once (YOLO) to handle detecting and classifying bone lesions on full-field radiographs with limited manual intervention.

METHODS : In this retrospective study, we used 1085 bone tumor radiographs and 345 normal bone radiographs from two centers between January 2009 and December 2020 to train and test our YOLO deep learning (DL) model. The trained model detected bone lesions and then classified these radiographs into normal, benign, intermediate, or malignant types. The intersection over union (IoU) was used to assess the model's performance in the detection task. Confusion matrices and Cohen's kappa scores were used for evaluating classification performance. Two radiologists compared diagnostic performance with the trained model using the external validation set.

RESULTS : In the detection task, the model achieved accuracies of 86.36% and 85.37% in the internal and external validation sets, respectively. In the DL model, radiologist 1 and radiologist 2 achieved Cohen's kappa scores of 0.8187, 0.7927, and 0.9077 for four-way classification in the external validation set, respectively. The YOLO DL model illustrated a significantly higher accuracy for intermediate bone tumor classification than radiologist 1 (95.73% vs 88.08%, p = 0.004).

CONCLUSIONS : The developed YOLO DL model could be used to assist radiologists at all stages of bone lesion detection and classification in full-field bone radiographs.

KEY POINTS : • YOLO DL model can automatically detect bone neoplasms from full-field radiographs in one shot and then simultaneously classify radiographs into normal, benign, intermediate, or malignant. • The dataset used in this retrospective study includes normal bone radiographs. • YOLO can detect even some challenging cases with small volumes.

Li Jie, Li Sudong, Li Xiaoli, Miao Sheng, Dong Cheng, Gao Chuanping, Liu Xuejun, Hao Dapeng, Xu Wenjian, Huang Mingqian, Cui Jiufa

2022-Nov-30

Bone neoplasms, Deep learning, Radiologists, Retrospective studies

Radiology Radiology

Brain Microstructural Changes in Patients with Amnestic mild Cognitive Impairment : Detected by Neurite Orientation Dispersion and Density Imaging (NODDI) Combined with Machine Learning.

In Clinical neuroradiology

PURPOSE : This study investigated brain microstructural changes in patients with amnestic mild cognitive impairment (aMCI) by retrospectively analyzing neurite orientation dispersion and density imaging (NODDI) data with machine learning algorithms.

METHODS : A total of 26 aMCI patients and 24 healthy controls (HC) underwent NODDI magnetic resonance imaging (MRI) examinations. The NODDI parameters including neurite density index (NDI), orientation dispersion index (ODI), and volume fraction of isotropic water molecules (Viso) were estimated. Machine learning algorithms such as K‑nearest neighbor (KNN), logistic regression (LR), random forest (RF), and support vector machine (SVM) were used to evaluate the diagnostic efficacy of NODDI parameters in predicting aMCI. The differences in the NODDI parameter values between the aMCI and HC groups were analyzed using the independent sample t‑test, False discovery rate (FDR) correction was used for multiple testing. After adjusting for age, sex, and educational years, partial correlation analysis was used to evaluate the relationship between NODDI parameters and clinical cognitive status of aMCI patients.

RESULTS : The NDI, ODI, and Viso values of white matter (WM) and gray matter (GM) structure templates combined with the KNN, LR, RF and SVM machine learning algorithms accomplished the discrimination between aMCI and HC groups. The NDI and ODI values decreased (p value range, < 0.001-0.042) and Viso values increased (p value range, < 0.001-0.043) in the aMCI group compared to the HCs. The NDI, ODI, and Viso values of the WM and GM structure templates with significant differences were significantly correlated with mini-mental state examination (MMSE) and Montreal cognitive assessment (MoCA) scores.

CONCLUSION : NODDI combined with machine learning algorithms is a promising strategy for early diagnosis of aMCI. Moreover, NODDI parameters correlated with the clinical cognitive status of aMCI patients.

Fu Xiuwei, Wang Xiaonan, Zhang Yu, Li Tongtong, Tan Zixuan, Chen Yuanyuan, Zhang Xianchang, Ni Hongyan

2022-Nov-30

Classification algorithm, Cognitive impairment, Diffusion weighted imaging, Neurite density, Orientation dispersion

General General

Detecting Screen Presence with Activity-Oriented RGB Camera in Egocentric Videos.

In Proceedings of the ... IEEE International Conference on Pervasive Computing and Communications Workshops : PerCom ... IEEE International Conference on Pervasive Computing and Communications. Workshops

Screen time is associated with several health risk behaviors including mindless eating, sedentary behavior, and decreased academic performance. Screen time behavior is traditionally assessed with self-report measures, which are known to be burdensome, inaccurate, and imprecise. Recent methods to automatically detect screen time are geared more towards detecting television screens from wearable cameras that record high-resolution video. Activity-oriented wearable cameras (i.e., cameras oriented towards the wearer with a fisheye lens) have recently been designed and shown to reduce privacy concerns, yet pose a greater challenge in capturing screens due to their orientation and fewer pixels on target. Methods that detect screens from low-power, low-resolution wearable camera video are needed given the increased adoption of such devices in longitudinal studies. We propose a method that leverages deep learning algorithms and lower-resolution images from an activity-oriented camera to detect screen presence from multiple types of screens with high variability of pixel on target (e.g., near and far TV, smartphones, laptops, and tablets). We test our system in a real-world study comprising 10 individuals, 80 hours of data, and 1.2 million low-resolution RGB frames. Our results outperform existing state-of-the-art video screen detection methods yielding an F1-score of 81%. This paper demonstrates the potential for detecting screen-watching behavior in longitudinal studies using activity-oriented cameras, paving the way for a nuanced understanding of screen time's relationship with health risk behaviors.

Adate Amit, Shahi Soroush, Alharbi Rawan, Sen Sougata, Gao Yang, Katsaggelos Aggelos K, Alshurafa Nabil

2022-Mar

Egocentric Videos, Fisheye Lens, Object Detection, Wearable Camera

Pathology Pathology

Identified in blood diet-related methylation changes stratify liver biopsies of NAFLD patients according to fibrosis grade.

In Clinical epigenetics

BACKGROUND : High caloric diet and lack of physical activity are considered main causes of NAFLD, and a change in the diet is still the only effective treatment of this disease. However, molecular mechanism of the effectiveness of diet change in treatment of NAFLD is poorly understood. We aimed to assess the involvement of epigenetic mechanisms of gene expression regulation in treatment of NAFLD. Eighteen participants with medium- to high-grade steatosis were recruited and trained to follow the Mediterranean diet modified to include fibre supplements. At three timepoints (baseline, after 30 and 60 days), we evaluated adherence to the diet and measured a number of physiological parameters such as anthropometry, blood and stool biochemistry, liver steatosis and stiffness. We also collected whole blood samples for genome-wide methylation profiling and histone acetylation assessment.

RESULTS : The diet change resulted in a decrease in liver steatosis along with statistically significant, but a minor change in BMI and weight of our study participants. The epigenetic profiling of blood cells identified significant genome-wide changes of methylation and acetylation with the former not involving regions directly regulating gene expression. Most importantly, we were able to show that identified blood methylation changes occur also in liver cells of NAFLD patients and the machine learning-based classifier that we build on those methylation changes was able to predict the stage of liver fibrosis with ROC AUC = 0.9834.

CONCLUSION : Methylomes of blood cells from NAFLD patients display a number of changes that are most likely a consequence of unhealthy diet, and the diet change appears to reverse those epigenetic changes. Moreover, the methylation status at CpG sites undergoing diet-related methylation change in blood cells stratifies liver biopsies from NAFLD patients according to fibrosis grade.

Sokolowska Katarzyna Ewa, Maciejewska-Markiewicz Dominika, Bińkowski Jan, Palma Joanna, Taryma-Leśniak Olga, Kozlowska-Petriczko Katarzyna, Borowski Konrad, Baśkiewicz-Hałasa Magdalena, Hawryłkowicz Viktoria, Załęcka Patrycja, Ufnal Marcin, Strapagiel Dominik, Jarczak Justyna, Skonieczna-Żydecka Karolina, Ryterska Karina, Machaliński Bogusław, Wojdacz Tomasz Kazimierz, Stachowska Ewa

2022-Nov-30

Acetylation, DNA methylation, Epigenetics, Fibre, Liver, Mediterranean diet, Non-alcoholic fatty liver disease, Nutrition

General General

Contextual counters and multimodal Deep Learning for activity-level traffic classification of mobile communication apps during COVID-19 pandemic.

In Computer networks

The COVID-19 pandemic has reshaped Internet traffic due to the huge modifications imposed to lifestyle of people resorting more and more to collaboration and communication apps to accomplish daily tasks. Accordingly, these dramatic changes call for novel traffic management solutions to adequately countermeasure such unexpected and massive changes in traffic characteristics. In this paper, we focus on communication and collaboration apps whose traffic experienced a sudden growth during the last two years. Specifically, we consider nine apps whose traffic we collect, reliably label, and publicly release as a new dataset (MIRAGE-COVID-CCMA-2022) to the scientific community. First, we investigate the capability of state-of-art single-modal and multimodal Deep Learning-based classifiers in telling the specific app, the activity performed by the user, or both. While we highlight that state-of-art solutions reports a more-than-satisfactory performance in addressing app classification (96%-98% F-measure), evident shortcomings stem out when tackling activity classification (56%-65% F-measure) when using approaches that leverage the transport-layer payload and/or per-packet information attainable from the initial part of the biflows. In line with these limitations, we design a novel set of inputs (namely Context Inputs) providing clues about the nature of a biflow by observing the biflows coexisting simultaneously. Based on these considerations, we propose Mimetic-All a novel early traffic classification multimodal solution that leverages Context Inputs as an additional modality, achieving ≥ 82 % F-measure in activity classification. Also, capitalizing the multimodal nature of Mimetic-All, we evaluate different combinations of the inputs. Interestingly, experimental results witness that Mimetic-ConSeq-a variant that uses the Context Inputs but does not rely on payload information (thus gaining greater robustness to more opaque encryption sub-layers possibly going to be adopted in the future)-experiences only ≈ 1 % F-measure drop in performance w.r.t. Mimetic-All and results in a shorter training time.

Guarino Idio, Aceto Giuseppe, Ciuonzo Domenico, Montieri Antonio, Persico Valerio, Pescapè Antonio

2022-Dec-24

COVID-19, Collaboration apps, Communication apps, Contextual counters, Deep Learning, Encrypted traffic, Multimodal techniques, Traffic classification

Pathology Pathology

Reliable Joint Segmentation of Retinal Edema Lesions in OCT Images

ArXiv Preprint

Focusing on the complicated pathological features, such as blurred boundaries, severe scale differences between symptoms, background noise interference, etc., in the task of retinal edema lesions joint segmentation from OCT images and enabling the segmentation results more reliable. In this paper, we propose a novel reliable multi-scale wavelet-enhanced transformer network, which can provide accurate segmentation results with reliability assessment. Specifically, aiming at improving the model's ability to learn the complex pathological features of retinal edema lesions in OCT images, we develop a novel segmentation backbone that integrates a wavelet-enhanced feature extractor network and a multi-scale transformer module of our newly designed. Meanwhile, to make the segmentation results more reliable, a novel uncertainty segmentation head based on the subjective logical evidential theory is introduced to generate the final segmentation results with a corresponding overall uncertainty evaluation score map. We conduct comprehensive experiments on the public database of AI-Challenge 2018 for retinal edema lesions segmentation, and the results show that our proposed method achieves better segmentation accuracy with a high degree of reliability as compared to other state-of-the-art segmentation approaches. The code will be released on: https://github.com/LooKing9218/ReliableRESeg.

Meng Wang, Kai Yu, Chun-Mei Feng, Ke Zou, Yanyu Xu, Qingquan Meng, Rick Siow Mong Goh, Yong Liu, Xinxing Xu, Huazhu Fu

2022-12-01

General General

Impacts of Image Obfuscation on Fine-grained Activity Recognition in Egocentric Video.

In Proceedings of the ... IEEE International Conference on Pervasive Computing and Communications Workshops : PerCom ... IEEE International Conference on Pervasive Computing and Communications. Workshops

Automated detection and validation of fine-grained human activities from egocentric vision has gained increased attention in recent years due to the rich information afforded by RGB images. However, it is not easy to discern how much rich information is necessary to detect the activity of interest reliably. Localization of hands and objects in the image has proven helpful to distinguishing between hand-related fine-grained activities. This paper describes the design of a hand-object-based mask obfuscation method (HOBM) and assesses its effect on automated recognition of fine-grained human activities. HOBM masks all pixels other than the hand and object in-hand, improving the protection of personal user information (PUI). We test a deep learning model trained with and without obfuscation using a public egocentric activity dataset with 86 class labels and achieve almost similar classification accuracies (2% decrease with obfuscation). Our findings show that it is possible to protect PUI at smaller image utility costs (loss of accuracy).

Shahi Soroush, Alharbi Rawan, Gao Yang, Sen Sougata, Katsaggelos Aggelos K, Hester Josiah, Alshurafa Nabil

2022-Mar

Deep Learning, Human Activity Recognition, Image Obfuscation, Wearable Camera

General General

Machine Learning Modeling and Insights into the Structural Characteristics of Drug-Induced Neurotoxicity.

In Journal of chemical information and modeling

Neurotoxicity can be resulted from many diverse clinical drugs, which has been a cause of concern to human populations across the world. The detection of drug-induced neurotoxicity (DINeurot) potential with biological experimental methods always required a lot of budget and time. In addition, few studies have addressed the structural characteristics of neurotoxic chemicals. In this study, we focused on the computational modeling for drug-induced neurotoxicity with machine learning methods and the insights into the structural characteristics of neurotoxic chemicals. Based on the clinical drug data with neurotoxicity effects, we developed 35 different classifiers by combining five different machine learning methods and seven fingerprint packages. The best-performing model achieved good results on both 5-fold cross-validation (balanced accuracy of 76.51%, AUC value of 0.83, and MCC value of 0.52) and external validation (balanced accuracy of 83.63%, AUC value of 0.87, and MCC value of 0.67). The model can be freely accessed on the web server DINeuroTpredictor (http://dineurot.sapredictor.cn/). We also analyzed the distribution of several key molecular properties between neurotoxic and non-neurotoxic structures. The results indicated that several physicochemical properties were significantly different between the neurotoxic and non-neurotoxic compounds, including molecular polar surface area (MPSA), AlogP, the number of hydrogen bond acceptors (nHAcc) and donors (nHDon), the number of rotatable bonds (nRotB), and the number of aromatic rings (nAR). In addition, 18 structural alerts responsible for chemical neurotoxicity were identified. The structural alerts have been integrated with our web server SApredictor (http://www.sapredictor.cn). The results of this study could provide useful information for the understanding of the structural characteristics and computational prediction for chemical neurotoxicity.

Zhao Xia, Sun Yuhao, Zhang Ruiqiu, Chen Zhaoyang, Hua Yuqing, Zhang Pei, Guo Huizhu, Cui Xueyan, Huang Xin, Li Xiao

2022-Nov-30

Ophthalmology Ophthalmology

Global Disparities in Retinopathy of Prematurity: A Literature Review.

In Seminars in ophthalmology

PURPOSE : To provide an overview of the impact of retinopathy of prematurity (ROP), and the challenges in the screening, diagnosis, and treatment of ROP worldwide.

METHODS : A comprehensive search was conducted using the PubMed database from January 2011 to October 2021 using the following keywords: retinopathy of prematurity, laser, and anti-vascular endothelial growth factor (VEGF). Data on patient characteristics, ROP treatment type, and recurrence rates were collected. The countries included in these studies were classified based on 2021-2022 World Bank definitions of high, upper-middle, lower-middle, and low-income groups. Moreover, a search for surgical outcomes for ROP and screening algorithms and artificial intelligence for ROP was conducted.

RESULTS : Thirty-nine studies met the inclusion criteria. ROP treatment and outcomes showed a trend towards intravitreal anti-VEGF injections as the initial treatment for ROP globally and the treatment of recurrent ROP in high-income countries. However, laser remains the treatment of choice for ROP recurrence in middle-income countries. Surgical outcomes for ROP stage 4A, 4B and 5 are similar worldwide. The incidence of ROP and ROP-related visual impairment continue to increase globally. Although telemedicine and artificial intelligence offer potential solutions to ROP screening in resource-limited areas, the current models require further optimization to reflect the global diversity of ROP patients.

CONCLUSION : ROP screening and treatment paradigms vary widely based on country income group due to disparities in resources, limited access to care, and lack of universal guidelines.

Ahmed Ishrat, Hoyek Sandra, Patel Nimesh A

2022-Nov-30

Artificial intelligence, Retinopathy of prematurity, disparities, screening, treatment

General General

Profiling students via clustering in a flipped clinical skills course using learning analytics.

In Medical teacher

Flipped classrooms have become popular as a student-centered approach in medical education because they allow students to improve higher-order thinking skills and problem-solving applications during in-class activities. However, students are expected to study videos and other class materials before class begins. Learning analytics and unsupervised machine learning algorithms (clustering) can be used to examine the pre-class activities of these students to identify inadequate student preparation before the in-class stage and make appropriate interventions. Furthermore, the students' profiles, which provide their interaction strategies towards online materials, can be used to design appropriate interventions. This study investigates student profiles in a flipped classroom. The learning management system interactions of 375 medical students are collected and preprocessed. The k-means clustering algorithms examined in this study show a two-cluster structure: 'high interaction' and 'low-interaction.' These results can be used to help identify low-engaged students and give appropriate feedback.

Bayazit Alper, Ilgaz Hale, Gönüllü İpek, Erden Şengül

2022-Nov-30

Clustering, clinical skills, flipped classrooms, learning analytics

General General

Dementia Detection from Brain Activity During Sleep.

In Sleep

STUDY OBJECTIVES : Dementia is a growing cause of disability and loss of independence in the elderly, yet remains largely under-diagnosed. Early detection and classification of dementia can help close this diagnostic gap and improve management of disease progression. Altered oscillations in brain activity during sleep is an early feature of neurodegenerative diseases and be used to identify those on the verge of cognitive decline.

METHODS : Our observational cross-sectional study used a clinical dataset of 10,784 polysomnography from 8,044 participants. Sleep macro-and micro-structural features were extracted from the electroencephalogram (EEG). Micro-structural features were engineered from spectral band powers, EEG coherence, spindle, and slow oscillations. Participants were classified as dementia (DEM), mild cognitive impairment (MCI), or cognitively normal (CN) based on clinical diagnosis, Montreal Cognitive Assessment (MoCA), Mini-Mental State Exam (MMSE) scores, Clinical Dementia Rating (CDR), and prescribed medications. We trained logistic regression, support vector machine, and random forest models to classify patients into DEM, MCI, and CN groups.

RESULTS : For discriminating DEM vs. CN, the best model achieved an area under receiver operating characteristic curve (AUROC) of 0.78 and area under precision-recall curve (AUPRC) of 0.22. For discriminating MCI vs. CN, the best model achieved an AUROC of 0.73 and AUPRC of 0.18. For discriminating DEM or MCI vs. CN, the best model achieved an AUROC of 0.76 and AUPRC of 0.32.

CONCLUSIONS : Our dementia classification algorithms show promise for incorporating dementia screening techniques using routine sleep EEG. The findings strengthen the concept of sleep as a window into neurodegenerative diseases.

Ye Elissa M, Sun Haoqi, Krishnamurthy Parimala V, Adra Noor, Ganglberger Wolfgang, Thomas Robert J, Lam Alice D, Westover M Brandon

2022-Nov-30

Biomarker, Dementia, EEG, Machine Learning, Sleep

General General

Weighted entropy deep features on hybrid RNN with LSTM for glucose level and diabetes prediction.

In Computer methods in biomechanics and biomedical engineering

Glucose level regulation with essential advice regarding diabetes must be provided to the patients to maintain their diet for diabetes treatment. Therefore, the academic community has focused on implementing novel glucose prediction techniques for decision support systems. Recent computational techniques for diagnosing diabetes have certain limitations, and also they are not evaluated under various datasets obtained from the different people of various countries. This generates inefficiency in the prediction systems to apply it in real-time applications. This paper plans to suggest a hybrid deep learning model for diabetes prediction and glucose level classification. Two benchmark datasets are used in the data collection process for experimenting. Initially, the deep selected features were extracted by the Convolutional Neural Network (CNN). Further, weighted entropy deep features are extracted, where the tuning of weight is taken place by the Modified Escaping Energy-based Harris Hawks Optimization. These features are processed in the glucose level classification using the modified Fuzzy classifier for classifying the high-level and low-level glucose. Further, glucose prediction is done by the Hybrid Recurrent Neural Network (RNN), and Long Short Term Memory (LSTM) termed R-LSTM with parameter optimization. From the experimental result, In the dataset 2 analyses on SMAPE, the MEE-HHO-R-LSTM is 12.5%, 87.5%, 50%, 12.5%, and 2.5% better than SVM, LSTM, DNN, RNN, and RNN-LSTM, at the learning percentage of 75%. The analytical results enforce that the suggested methods attain enhanced prediction performance concerning the evaluation metrics compared to conventional prediction models.

Naveena Somasundaram, Bharathi Ayyasamy

2022-Nov-30

Glucose level and diabetes prediction, convolutional neural network, modified escaping energy-based harris hawks optimization, modified fuzzy classifier, recurrent-long short term memory, weighted entropy deep features

General General

Spatial arrangement of dynamic surface species from solid-state NMR and machine learning-accelerated MD simulations.

In Chemical communications (Cambridge, England) ; h5-index 131.0

The surface arrangement of motional organic functionalities is explored by experimental dipolar coupling measurements and the prediction of motionally-averaged coupling constant from molecular dynamics simulations. The use of machine learning potentials was key to reaching the timescale required. The distance between dynamic surface species are important in cooperative heterogeneous catalysis.

Kobayashi Takeshi, Liu Da-Jiang, Perras Frédéric A

2022-Nov-30

General General

Highly Adsorptive Au-TiO2 Nanocomposites for the SERS Face Mask Allow the Machine-Learning-Based Quantitative Assay of SARS-CoV-2 in Artificial Breath Aerosols.

In ACS applied materials & interfaces ; h5-index 147.0

Human respiratory aerosols contain diverse potential biomarkers for early disease diagnosis. Here, we report the direct and label-free detection of SARS-CoV-2 in respiratory aerosols using a highly adsorptive Au-TiO2 nanocomposite SERS face mask and an ablation-assisted autoencoder. The Au-TiO2 SERS face mask continuously preconcentrates and efficiently captures the oronasal aerosols, which substantially enhances the SERS signal intensities by 47% compared to simple Au nanoislands. The ultrasensitive Au-TiO2 nanocomposites also demonstrate the successful detection of SARS-CoV-2 spike proteins in artificial respiratory aerosols at a 100 pM concentration level. The deep learning-based autoencoder, followed by the partial ablation of nondiscriminant SERS features of spike proteins, allows a quantitative assay of the 101-104 pfu/mL SARS-CoV-2 lysates (comparable to 19-29 PCR cyclic threshold from COVID-19 patients) in aerosols with an accuracy of over 98%. The Au-TiO2 SERS face mask provides a platform for breath biopsy for the detection of various biomarkers in respiratory aerosols.

Hwang Charles S H, Lee Sangyeon, Lee Sejin, Kim Hanjin, Kang Taejoon, Lee Doheon, Jeong Ki-Hun

2022-Nov-30

SARS-CoV-2, breath biopsy, machine-learning, nanocomposite, plasmonics, surface-enhanced Raman spectroscopy

Radiology Radiology

Application of Digital Imaging and Artificial Intelligence to Pathology of the Placenta.