In The Science of the total environment

Liu Junjie, Wang Benya, Oldham Carolyn E, Hipsey Matthew R

2020-Mar-19

Constructed wetland, Hydrodynamic model, Hypoxia, Machine learning, Photosynthesis, Urban drainage

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

Huang Keke, Li Shuo, Dai Penglin, Wang Zhen, Yu Zhaofei

2020-Mar-14

Complex network, Compressive sensing, Deep learning, Network structure reconstruction, Stacked denoising autoencoder

In Journal of environmental management

Oliveira Sandra, Zêzere José Luís

2020-Mar-26

Biophysical factors, Local communities, Portugal, Risk mitigation, Sociodemographic variables, Wildfire incidence

In Computers in biology and medicine

BACKGROUND AND OBJECTIVES : The image registration methods for deformable soft tissues utilize nonlinear transformations to align a pair of images precisely. In some situations, when there is huge gray scale difference or large deformation between the images to be registered, the deformation field tends to fold at some local voxels, which will result in the breakdown of the one-to-one mapping between images and the reduction of invertibility of the deformation field. In order to address this issue, a novel registration approach based on unsupervised learning is presented for deformable soft tissue image registration.

METHODS : A novel unsupervised learning based registration approach, which consists of a registration network, a velocity field integration module and a grid sampling module, is presented for deformable soft tissue image registration. The main contributions are: (1) A novel encoder-decoder network is presented for the evaluation of stationary velocity field. (2) A Jacobian determinant based penalty term (Jacobian loss) is developed to reduce the folding voxels and to improve the invertibility of the deformation field.

RESULTS AND CONCLUSIONS : The experimental results show that a new pair of images can be accurately registered using the trained registration model. In comparison with the conventional state-of-the-art method, SyN, the invertibility of the deformation field, accuracy and speed are all improved. Compared with the deep learning based method, VoxelMorph, the proposed method improves the invertibility of the deformation field.

Zhang Shuo, Liu Peter Xiaoping, Zheng Minhua, Shi Wen

2020-Mar-20

Deformable soft tissue image registration, Encoder–decoder network, Invertibility, Jacobian loss, Unsupervised learning

In Computers in biology and medicine

PURPOSE : To evaluate the impact of different supervision regimens on the training of artificial intelligence (AI) in the classification of chest radiographs as normal or abnormal in a moderately sized cohort of individuals more likely to be outpatients.

MATERIALS AND METHODS : In a retrospective study, 7000 consecutive two-view chest radiographs obtained from 2012 to 2015 were labeled as normal or abnormal based on clinical reports. A convolutional neural network (CNN) was trained on this dataset and then evaluated with an unseen subset of 500 radiographs. Five different training approaches were tested: (1) weak supervision and four hybrid approaches combining weak supervision and extra supervision with annotation in (2) an unbalanced set of normal and abnormal cases, (3) a set of only abnormal cases, (4) a set of only normal cases, and (5) a balanced set of normal and abnormal cases. Standard binary classification metrics were assessed.

RESULTS : The weakly supervised model achieved an accuracy of 82%, but yielded 75 false negative cases, at a sensitivity of 70.0% and a negative predictive value (NPV) of 75.5%. Extra supervision increased NPV at the expense of the false positive rate and overall accuracy. Extra supervision with training using a balance of abnormal and normal radiographs resulted in the greatest increase in NPV (87.2%), improved sensitivity (92.8%), and reduced the number of false negatives by more than fourfold (18 compared to 75 cases).

CONCLUSION : Extra supervision using a balance of annotated normal and abnormal cases applied to a weakly supervised model can minimize the number of false negative cases when classifying two-view chest radiographs. Further refinement of such hybrid training approaches for AI is warranted to refine models for practical clinical applications.

Ellis Ryan, Ellestad Erik, Elicker Brett, Hope Michael D, Tosun Duygu

2020-Mar-17

Attention mining, Chest radiographs, Extra supervision, Hybrid supervision, Outpatient, Two-view radiographs, Weak supervision

In Clinical microbiology and infection : the official publication of the European Society of Clinical Microbiology and Infectious Diseases

BACKGROUND : The matrix assisted laser desorption/ionization and time-of-flight mass spectrometry (MALDI-TOF MS) technology has revolutionized the field of microbiology by facilitating precise and rapid species identification. Recently, machine learning techniques have been leveraged to maximally exploit the information contained in MALDI-TOF M with the ultimate goal to refine species identification and streamline antimicrobial resistance determination.

OBJECTIVES : To systematically review and evaluate studies employing machine learning for the analysis of MALDI-TOF mass spectra.

DATA SOURCES : Using PubMed/Medline, Scopus, and Web of Science, we searched the existing literature for machine learning supported applications of MALDI-TOF mass spectra for microbial species and antimicrobial susceptibility identification.

STUDY ELIGIBILITY CRITERIA : Original research studies using machine learning to exploit MALDI-TOF mass spectra for microbial species and antimicrobial susceptibility identification were included. Studies focusing on single proteins and peptides, case studies, and review articles were excluded.

METHODS : A systematic review according to the PRISMA guidelines was performed and a quality assessment of the machine learning models conducted.

RESULTS : From the 36 studies that met our inclusion criteria, 27 employed machine learning for species identification and 9 for antimicrobial susceptibility testing. Support Vector Machines, Genetic Algorithms, Artificial Neural Networks, and Quick Classifiers were the most frequently used machine learning algorithms. The quality of the studies ranged between poor and very good. While, the majority of the studies reported how to interpret the predictors (88.89%) and suggested possible clinical applications of the developed algorithm (100%), only four studies (11.11%) validated machine learning algorithms on external datasets.

CONCLUSIONS : A growing number of studies utilizes machine learning to optimize the analysis of MALDI-TOF mass spectra. This review, however, demonstrates that there are certain shortcomings of current machine learning supported approaches that have to be addressed to make them widely available and incorporated them in the clinical routine.

Cv Weis, Cr Jutzeler, K Borgwardt

2020-Mar-23

MALDI-TOF MS, antimicrobial resistance, antimicrobial susceptibility testing, antimicrobial treatment, machine learning, microbial identification

In Genome biology ; h5-index 114.0

Trieu Tuan, Martinez-Fundichely Alexander, Khurana Ekta

2020-Mar-26

3D genome, BCL2, Cancer, Deep learning, MYC, Non-coding mutation

In Annals of nuclear medicine

OBJECTIVE : The aim of the study was to investigate the outcomes and prognostic factors of high-dose ¹³¹I-metaiodobenzylguanidine (¹³¹I-MIBG) therapy in patients with refractory or relapsed neuroblastoma (NBL) in Japan.

METHODS : We retrospectively analyzed 20 patients with refractory or relapsed high-risk NBL who underwent ¹³¹I-MIBG therapy with an administration dose ranging from 444 to 666 MBq/kg at Kanazawa University Hospital, Japan, between September 2008 and September 2013. We focused on measurements regarding their initial responses, prognostic factors, survivals, and toxicities following ¹³¹I-MIBG therapy using our hospital data and questionnaires from the hospitals that these patients were initially referred from. Furthermore, we performed Kaplan-Meier survival analysis to evaluate event-free survival (EFS) and overall survival (OS).

RESULTS : In 19 patients with complete follow-up data, the median age at first ¹³¹I-MIBG treatment was 7.9 years (range 2.5-17.7 years). Following ¹³¹I-MIBG therapy, 17 of the 19 patients underwent stem-cell transplantations, and their treatment response was either complete (CR) or partial (PR) in three and two cases, respectively. The EFS and OS rates at 1 year following ¹³¹I-MIBG therapy were 42% and 58%, respectively, and those at 5 years following ¹³¹I-MIBG therapy were 16% and 42%, respectively. Using the two-sample log-rank test, the OS time following ¹³¹I-MIBG therapy was significantly longer for < 3-year time interval between the initial diagnosis and ¹³¹I-MIBG therapy (p = 0.017), Curie score < 16 just before ¹³¹I-MIBG therapy (p = 0.002), without pain (p = 0.002), without both vanillylmandelic acid (VMA) and homovanillic acid (HVA) elevation (p = 0.037) at ¹³¹I-MIBG therapy, and with CR or PR following ¹³¹I-MIBG therapy (p = 0.015). Although severe hematological toxicities were identified in all 19 patients, severe nonhematological toxicity was not recorded in any patient, except for one patient with grade 3 anorexia and nausea.

CONCLUSIONS : High-dose ¹³¹I-MIBG therapy in patients with refractory or relapsed high-risk NBL can provide a favorable prognosis without severe nonhematological toxicities. Better prognosis may be anticipated in patients with the initial good response, no pain at ¹³¹I-MIBG therapy, no VMA and HVA elevation at ¹³¹I-MIBG therapy, low Curie score (< 16) just before ¹³¹I-MIBG therapy, and short time interval (< 3 years) between the initial diagnosis and ¹³¹I-MIBG therapy.

Kayano Daiki, Wakabayashi Hiroshi, Nakajima Kenichi, Kuroda Rie, Watanabe Satoru, Inaki Anri, Toratani Ayane, Akatani Norihito, Yamase Takafumi, Kunita Yuji, Hiromasa Tomo, Takata Aki, Mori Hiroshi, Saito Shintaro, Araki Raita, Taki Junichi, Kinuya Seigo

2020-Mar-26

131I-metaiodobenzylguanidine, Internal radiation therapy, Radionuclide therapy, Refractory neuroblastoma, Relapsed neuroblastoma

In Journal of autism and developmental disorders ; h5-index 76.0

Cantin-Garside Kristine D, Kong Zhenyu, White Susan W, Antezana Ligia, Kim Sunwook, Nussbaum Maury A

2020-Mar-26

Activity recognition, Autism, Machine learning, Wearable sensors

In European journal of nuclear medicine and molecular imaging ; h5-index 66.0

PURPOSE : Attenuation correction using CT transmission scanning increases the accuracy of single-photon emission computed tomography (SPECT) and enables quantitative analysis. Current existing SPECT-only systems normally do not support transmission scanning and therefore scans on these systems are susceptible to attenuation artifacts. Moreover, the use of CT scans also increases radiation dose to patients and significant artifacts can occur due to the misregistration between the SPECT and CT scans as a result of patient motion. The purpose of this study is to develop an approach to estimate attenuation maps directly from SPECT emission data using deep learning methods.

METHODS : Both photopeak window and scatter window SPECT images were used as inputs to better utilize the underlying attenuation information embedded in the emission data. The CT-based attenuation maps were used as labels with which cardiac SPECT/CT images of 65 patients were included for training and testing. We implemented and evaluated deep fully convolutional neural networks using both standard training and training using an adversarial strategy.

RESULTS : The synthetic attenuation maps were qualitatively and quantitatively consistent with the CT-based attenuation map. The globally normalized mean absolute error (NMAE) between the synthetic and CT-based attenuation maps were 3.60% ± 0.85% among the 25 testing subjects. The SPECT reconstructed images corrected using the CT-based attenuation map and synthetic attenuation map are highly consistent. The NMAE between the reconstructed SPECT images that were corrected using the synthetic and CT-based attenuation maps was 0.26% ± 0.15%, whereas the localized absolute percentage error was 1.33% ± 3.80% in the left ventricle (LV) myocardium and 1.07% ± 2.58% in the LV blood pool.

CONCLUSION : We developed a deep convolutional neural network to estimate attenuation maps for SPECT directly from the emission data. The proposed method is capable of generating highly reliable attenuation maps to facilitate attenuation correction for SPECT-only scanners for myocardial perfusion imaging.

Shi Luyao, Onofrey John A, Liu Hui, Liu Yi-Hwa, Liu Chi

2020-Mar-26

Deep learning, Myocardial perfusion imaging, SPECT, Synthetic attenuation map

In The international journal of neuropsychopharmacology

Mujica-Parodi Lilianne R, Strey Helmut H

2020-Mar-27

** control systems, RDoC, circuit, fMRI, generative models, machine learning, neuroimaging, neuroscience, psychiatry, system identification**

In American journal of epidemiology ; h5-index 65.0

Goin Dana E, Rudolph Kara E, Gomez Anu Manchikanti, Ahern Jennifer

2020-Mar-27

causal mediation analysis, firearm violence, pregnancy complications, preterm birth

In ACS pharmacology & translational science

Latysheva Natasha S, Babu M Madan

2019-Apr-12

In NPJ digital medicine

Perez-Pozuelo Ignacio, Zhai Bing, Palotti Joao, Mall Raghvendra, Aupetit Michaël, Garcia-Gomez Juan M, Taheri Shahrad, Guan Yu, Fernandez-Luque Luis

2020

Biomedical engineering, Diagnostic markers, Predictive markers, Preventive medicine, Sleep

In NPJ digital medicine

Sendak Mark P, Gao Michael, Brajer Nathan, Balu Suresh

2020

Health policy, Health services, Translational research

In NPJ digital medicine

Yip Michelle Y T, Lim Gilbert, Lim Zhan Wei, Nguyen Quang D, Chong Crystal C Y, Yu Marco, Bellemo Valentina, Xie Yuchen, Lee Xin Qi, Hamzah Haslina, Ho Jinyi, Tan Tien-En, Sabanayagam Charumathi, Grzybowski Andrzej, Tan Gavin S W, Hsu Wynne, Lee Mong Li, Wong Tien Yin, Ting Daniel S W

2020

Population screening, Translational research

In BMC bioinformatics

BACKGROUND : The notion of heme as a regulator of many physiological processes via transient binding to proteins is one that is recently being acknowledged. The broad spectrum of the effects of heme makes it important to identify further heme-regulated proteins to understand physiological and pathological processes. Moreover, several proteins were shown to be functionally regulated by interaction with heme, yet, for some of them the heme-binding site(s) remain unknown. The presented application HeMoQuest enables identification and qualitative evaluation of such heme-binding motifs from protein sequences.

RESULTS : We present HeMoQuest, an online interface (http://bit.ly/hemoquest) to algorithms that provide the user with two distinct qualitative benefits. First, our implementation rapidly detects transient heme binding to nonapeptide motifs from protein sequences provided as input. Additionally, the potential of each predicted motif to bind heme is qualitatively gauged by assigning binding affinities predicted by an ensemble learning implementation, trained on experimentally determined binding affinity data. Extensive testing of our implementation on both existing and new manually curated datasets reveal that our method produces an unprecedented level of accuracy (92%) in identifying those residues assigned "heme binding" in all of the datasets used. Next, the machine learning implementation for the prediction and qualitative assignment of binding affinities to the predicted motifs achieved 71% accuracy on our data.

CONCLUSIONS : Heme plays a crucial role as a regulatory molecule exerting functional consequences via transient binding to surfaces of target proteins. HeMoQuest is designed to address this imperative need for a computational approach that enables rapid detection of heme-binding motifs from protein datasets. While most existing implementations attempt to predict sites of permanent heme binding, this application is to the best of our knowledge, the first of its kind to address the significance of predicting transient heme binding to proteins.

Paul George Ajay Abisheck, Lacerda Mauricio, Syllwasschy Benjamin Franz, Hopp Marie-Thérèse, Wißbrock Amelie, Imhof Diana

2020-Mar-27

Heme, Heme-binding site prediction, Heme-regulated protein, Machine learning, Transient heme binding, Web application

In Journal of medical imaging (Bellingham, Wash.)

Wang Xiaoyong, Teng Pangyu, Ontiveros Ashley, Goldin Jonathan G, Brown Matthew S

2020-Mar

clinical trials, computed tomography, convolutional neural network, image labeling

In BioMed research international ; h5-index 102.0

Background : Next-generation sequencing enables massively parallel processing, allowing lower cost than the other sequencing technologies. In the subsequent analysis with the NGS data, one of the major concerns is the reliability of variant calls. Although researchers can utilize raw quality scores of variant calling, they are forced to start the further analysis without any preevaluation of the quality scores.

Method : We presented a machine learning approach for estimating quality scores of variant calls derived from BWA+GATK. We analyzed correlations between the quality score and these annotations, specifying informative annotations which were used as features to predict variant quality scores. To test the predictive models, we simulated 24 paired-end Illumina sequencing reads with 30x coverage base. Also, twenty-four human genome sequencing reads resulting from Illumina paired-end sequencing with at least 30x coverage were secured from the Sequence Read Archive.

Results : Using BWA+GATK, VCFs were derived from simulated and real sequencing reads. We observed that the prediction models learned by RFR outperformed other algorithms in both simulated and real data. The quality scores of variant calls were highly predictable from informative features of GATK Annotation Modules in the simulated human genome VCF data (R2: 96.7%, 94.4%, and 89.8% for RFR, MLR, and NNR, respectively). The robustness of the proposed data-driven models was consistently maintained in the real human genome VCF data (R2: 97.8% and 96.5% for RFR and MLR, respectively).

Cosgun Erdal, Oh Min

2020

In NPJ vaccines

Babji Sudhir, Manickavasagam Punithavathy, Chen Yin-Huai, Jeyavelu Nithya, Jose Nisha Vincy, Praharaj Ira, Syed Chanduni, Kaliappan Saravanakumar Puthupalayam, John Jacob, Giri Sidhartha, Venugopal Srinivasan, Kampmann Beate, Parker Edward P K, Iturriza-Gómara Miren, Kang Gagandeep, Grassly Nicholas C, Uhlig Holm H

2020

Live attenuated vaccines, Paediatric research

In NPJ aging and mechanisms of disease

Frenzel Alexander, Binder Hans, Walter Nadja, Wirkner Kerstin, Loeffler Markus, Loeffler-Wirth Henry

2020

Ageing, Health care

In Royal Society open science

Joglekar Sagar, Quercia Daniele, Redi Miriam, Aiello Luca Maria, Kauer Tobias, Sastry Nishanth

2020-Jan

deep learning, explainable models, generative models, urban beauty, urban design

In Royal Society open science

Kaler Jasmeet, Mitsch Jurgen, Vázquez-Diosdado Jorge A, Bollard Nicola, Dottorini Tania, Ellis Keith A

2020-Jan

behaviour, lameness, machine learning, precision livestock farming, sensor, signal processing

In Oncology letters

Cheng Jia’Nan, Ding Xiaofang, Xu Shouxia, Zhu Bo, Jia Qingzhu

2020-Apr

TP53MutPIK3CAWild, biomarker, immune checkpoint inhibitors, triple-negative breast cancer

In Current treatment options in infectious diseases

Purpose of Review : Artificial intelligence (AI) offers huge potential in infection prevention and control (IPC). We explore its potential IPC benefits in epidemiology, laboratory infection diagnosis, and hand hygiene.

Recent Findings : AI has the potential to detect transmission events during outbreaks or predict high-risk patients, enabling development of tailored IPC interventions. AI offers opportunities to enhance diagnostics with objective pattern recognition, standardize the diagnosis of infections with IPC implications, and facilitate the dissemination of IPC expertise. AI hand hygiene applications can deliver behavior change, though it requires further evaluation in different clinical settings. However, staff can become dependent on automatic reminders, and performance returns to baseline if feedback is removed.

Summary : Advantages for IPC include speed, consistency, and capability of handling infinitely large datasets. However, many challenges remain; improving the availability of high-quality representative datasets and consideration of biases within preexisting databases are important challenges for future developments. AI in itself will not improve IPC; this requires culture and behavior change. Most studies to date assess performance retrospectively so there is a need for prospective evaluation in the real-life, often chaotic, clinical setting. Close collaboration with IPC experts to interpret outputs and ensure clinical relevance is essential.

Fitzpatrick Fidelma, Doherty Aaron, Lacey Gerard

2020-Mar-19

Artificial intelligence, Epidemiology, Hand hygiene, Infection diagnosis, Infection prevention and control, Machine learning

In AI & society

Arogyaswamy Bernard

2020-Mar-19

Big tech, Centralized power, Cognition, Ethical criteria, Social impacts, User activism

In Modern pathology : an official journal of the United States and Canadian Academy of Pathology, Inc

Choi Gyuheon, Kim Young-Gon, Cho Haeyon, Kim Namkug, Lee Hyunna, Moon Kyung Chul, Go Heounjeong

2020-Mar-26

In JCO clinical cancer informatics

PURPOSE : Machine Learning Package for Cancer Diagnosis (MLCD) is the result of a National Institutes of Health/National Cancer Institute (NIH/NCI)-sponsored project for developing a unified software package from state-of-the-art breast cancer biopsy diagnosis and machine learning algorithms that can improve the quality of both clinical practice and ongoing research.

METHODS : Whole-slide images of 240 well-characterized breast biopsy cases, initially assembled under R01 CA140560, were used for developing the algorithms and training the machine learning models. This software package is based on the methodology developed and published under our recent NIH/NCI-sponsored research grant (R01 CA172343) for finding regions of interest (ROIs) in whole-slide breast biopsy images, for segmenting ROIs into histopathologic tissue types and for using this segmentation in classifiers that can suggest final diagnoses.

RESULT : The package provides an ROI detector for whole-slide images and modules for semantic segmentation into tissue classes and diagnostic classification into 4 classes (benign, atypia, ductal carcinoma in situ, invasive cancer) of the ROIs. It is available through the GitHub repository under the Massachusetts Institute of Technology license and will later be distributed with the Pathology Image Informatics Platform system. A Web page provides instructions for use.

CONCLUSION : Our tools have the potential to provide help to other cancer researchers and, ultimately, to practicing physicians and will motivate future research in this field. This article describes the methodology behind the software development and gives sample outputs to guide those interested in using this package.

Wu Wenjun, Li Beibin, Mercan Ezgi, Mehta Sachin, Bartlett Jamen, Weaver Donald L, Elmore Joann G, Shapiro Linda G

2020-Mar

In Scientific reports ; h5-index 158.0

Chen Yueh-Peng, Yeh Chun-I, Lee Tsung-Chi, Huang Jian-Jia, Pei Yu-Cheng

2020-Mar-26

In Scientific reports ; h5-index 158.0

Jamal Salma, Khubaib Mohd, Gangwar Rishabh, Grover Sonam, Grover Abhinav, Hasnain Seyed E

2020-Mar-26

In Nutrients ; h5-index 86.0

Xu Ran, Blanchard Bruce E, McCaffrey Jeanne M, Woolley Stephen, Corso Lauren M L, Duffy Valerie B

2020-Mar-25

cardiometabolic health, diet, diet quality, food preference, metabolic syndrome, principal component analysis, ridge regression analysis, sweets, vegetables, young adult

In Journal of the Chinese Medical Association : JCMA

BACKGROUND : Prostate cancer (PCa) is the most common malignancy seen in men and the second leading cause of cancer-related death in males. The incidence and mortality associated with PCa has been rapidly increasing in China recently.

METHODS : Multiple diagnostic models of human PCa were developed based on Taylor database by combining the artificial neural networks (ANNs) to enhance the ability of PCa diagnosis. Genetic algorithm (GA) is used to select feature genes as numerical encoded parameters that reflect cancer, metastatic or normal samples. Back propagation (BP) neural network and learning vector quantization (LVQ) neural network were used to build different Cancer/Normal, Primary/Metastatic and Gleason Grade diagnostic models.

RESULTS : The performance of these modeling approaches was evaluated by predictive accuracy (ACC) and area under the ROC curve (AUC). By observing the statistically significant parameters of the three training sets, our Cancer/Normal, Primary/Metastatic and Gleason Grade models' with ACC and AUC can be drawn (97.33%, 0.9832), (99.17%, 0.9952), and (90.48%, 0.8742), respectively.

CONCLUSION : These results indicated that our diagnostic models of human PCa based on Taylor database combining the feature gene expression profiling data and artificial intelligence algorithms might act as a powerful tool for diagnosing PCa. Gleason Grade diagnostic models were used as novel prognostic diagnosis models for biochemical recurrence-free survival and overall survival, which might be helpful in the prognostic diagnosis of PCa in patients.

Jiang Fu-Neng, Dai Li-Jun, Wu Yong-Ding, Yang Sheng-Bang, Liang Yu-Xiang, Zhang Xin, Zou Cui-Yun, He Ren-Qiang, Xu Xiao-Ming, Zhong Wei-De

2020-Mar-11

In Physics in medicine and biology

Fu Yabo, Lei Yang, Wang Tonghe, Curran Walter J, Liu Tian, Yang Xiaofeng

2020-Mar-27

deep learning, medical image registration, review

In IEEE transactions on neural networks and learning systems

Wu Zonghan, Pan Shirui, Chen Fengwen, Long Guodong, Zhang Chengqi, Yu Philip S

2020-Mar-24

In IEEE transactions on ultrasonics, ferroelectrics, and frequency control

Wildeboer R R, Van Sloun R J G, Mannaerts C K, Moraes P H, Salomon G, Chammas M C, Wijkstra H, Mischi M

2020-Mar-24

In IEEE transactions on medical imaging ; h5-index 74.0

Pan Yongsheng, Liu Mingxia, Lian Chunfeng, Xia Yong, Shen Dinggang

2020-Mar-24

In IEEE transactions on pattern analysis and machine intelligence ; h5-index 127.0

Wang Zhihao, Chen Jian, Hoi Steven C H

2020-Mar-23

In NeuroImage. Clinical

BACKGROUND : Those with autism spectrum disorder (ASD) and/or attention-deficit-hyperactivity disorder (ADHD) exhibit symptoms of hyperactivity and inattention, causing significant hardships for families and society. A potential mechanism involved in these conditions is atypical executive function (EF). Inconsistent findings highlight that EF features may be shared or distinct across ADHD and ASD. With ADHD and ASD each also being heterogeneous, we hypothesized that there may be nested subgroups across disorders with shared or unique underlying mechanisms.

METHODS : Participants (N = 130) included adolescents aged 7-16 with ASD (n = 64) and ADHD (n = 66). Typically developing (TD) participants (n = 28) were included for a comparative secondary sub-group analysis. Parents completed the K-SADS and youth completed an extended battery of executive and other cognitive measures. A two stage hybrid machine learning tool called functional random forest (FRF) was applied as a classification approach and then subsequently to subgroup identification. We input 43 EF variables to the classification step, a supervised random forest procedure in which the features estimated either hyperactive or inattentive ADHD symptoms per model. The FRF then produced proximity matrices and identified optimal subgroups via the infomap algorithm (a type of community detection derived from graph theory). Resting state functional connectivity MRI (rs-fMRI) was used to evaluate the neurobiological validity of the resulting subgroups.

RESULTS : Both hyperactive (Mean absolute error (MAE) = 0.72, Null model MAE = 0.8826, (t(58) = -4.9, p < .001) and inattentive (MAE = 0.7, Null model MAE = 0.85, t(58) = -4.4, p < .001) symptoms were predicted better than chance by the EF features selected. Subgroup identification was robust (Hyperactive: Q = 0.2356, p < .001; Inattentive: Q = 0.2350, p < .001). Two subgroups representing severe and mild symptomology were identified for each symptom domain. Neuroimaging data revealed that the subgroups and TD participants significantly differed within and between multiple functional brain networks, but no consistent "severity" patterns of over or under connectivity were observed between subgroups and TD.

CONCLUSION : The FRF estimated hyperactive/inattentive symptoms and identified 2 distinct subgroups per model, revealing distinct neurocognitive profiles of Severe and Mild EF performance per model. Differences in functional connectivity between subgroups did not appear to follow a severity pattern based on symptom expression, suggesting a more complex mechanistic interaction that cannot be attributed to symptom presentation alone.

Cordova Michaela, Shada Kiryl, Demeter Damion V, Doyle Olivia, Miranda-Dominguez Oscar, Perrone Anders, Schifsky Emma, Graham Alice, Fombonne Eric, Langhorst Beth, Nigg Joel, Fair Damien A, Feczko Eric

2020-Mar-16

ADHD, ASD, Executive function, Machine learning, rs-fMRI

In JMIR medical informatics ; h5-index 23.0

BACKGROUND : A timely decision in the initial stages for patients with an acute illness is important. However, only a few studies have determined the prognosis of patients based on insufficient laboratory data during the initial stages of treatment.

OBJECTIVE : This study aimed to develop and validate time adaptive prediction models to predict the severity of illness in the emergency department (ED) using highly sparse laboratory test data (test order status and test results) and a machine learning approach.

METHODS : This retrospective study used ED data from a tertiary academic hospital in Seoul, Korea. Two different models were developed based on laboratory test data: order status only (OSO) and order status and results (OSR) models. A binary composite adverse outcome was used, including mortality or hospitalization in the intensive care unit. Both models were evaluated using various performance criteria, including the area under the receiver operating characteristic curve (AUC) and balanced accuracy (BA). Clinical usefulness was examined by determining the positive likelihood ratio (PLR) and negative likelihood ratio (NLR).

RESULTS : Of 9491 eligible patients in the ED (mean age, 55.2 years, SD 17.7 years; 4839/9491, 51.0% women), the model development cohort and validation cohort included 6645 and 2846 patients, respectively. The OSR model generally exhibited better performance (AUC=0.88, BA=0.81) than the OSO model (AUC=0.80, BA=0.74). The OSR model was more informative than the OSO model to predict patients at low or high risk of adverse outcomes (P<.001 for differences in both PLR and NLR).

CONCLUSIONS : Early-stage adverse outcomes for febrile patients could be predicted using machine learning models of highly sparse data including test order status and laboratory test results. This prediction tool could help medical professionals who are simultaneously treating the same patient share information, lead dynamic communication, and consequently prevent medical errors.

Lee Sungjoo, Hong Sungjun, Cha Won Chul, Kim Kyunga

2020-Mar-26

adverse outcome, emergency department, imbalanced data, machine learning, order status, sparse laboratory data, time adaptive model

In JMIR mHealth and uHealth

BACKGROUND : Hand hygiene is a crucial and cost-effective method to prevent health care-associated infections, and in 2009, the World Health Organization (WHO) issued guidelines to encourage and standardize hand hygiene procedures. However, a common challenge in health care settings is low adherence, leading to low handwashing quality. Recent advances in machine learning and wearable sensing have made it possible to accurately measure handwashing quality for the purposes of training, feedback, or accreditation.

OBJECTIVE : We measured the accuracy of a sensor armband (Myo armband) in detecting the steps and duration of the WHO procedures for handwashing and handrubbing.

METHODS : We recruited 20 participants (10 females; mean age 26.5 years, SD 3.3). In a semistructured environment, we collected armband data (acceleration, gyroscope, orientation, and surface electromyography data) and video data from each participant during 15 handrub and 15 handwash sessions. We evaluated the detection accuracy for different armband placements, sensor configurations, user-dependent vs user-independent models, and the use of bootstrapping.

RESULTS : Using a single armband, the accuracy was 96% (SD 0.01) for the user-dependent model and 82% (SD 0.08) for the user-independent model. This increased when using two armbands to 97% (SD 0.01) and 91% (SD 0.04), respectively. Performance increased when the armband was placed on the forearm (user dependent: 97%, SD 0.01; and user independent: 91%, SD 0.04) and decreased when placed on the arm (user dependent: 96%, SD 0.01; and user independent: 80%, SD 0.06). In terms of bootstrapping, user-dependent models can achieve more than 80% accuracy after six training sessions and 90% with 16 sessions. Finally, we found that the combination of accelerometer and gyroscope minimizes power consumption and cost while maximizing performance.

CONCLUSIONS : A sensor armband can be used to measure hand hygiene quality relatively accurately, in terms of both handwashing and handrubbing. The performance is acceptable using a single armband worn in the upper arm but can substantially improve by placing the armband on the forearm or by using two armbands.

Wang Chaofan, Sarsenbayeva Zhanna, Chen Xiuge, Dingler Tilman, Goncalves Jorge, Kostakos Vassilis

2020-Mar-26

hand hygiene, machine learning, wearable devices

In Clinical microbiology and infection : the official publication of the European Society of Clinical Microbiology and Infectious Diseases

BACKGROUND : Microbiologists are valued for their time-honed skills in image analysis including identification of pathogens and inflammatory context in Gram stains, ova and parasite preparations, blood smears, and histopathological slides. They also must classify colonial growth on a variety of agar plates for triage and workup. Recent advances in image analysis, in particular application of artificial intelligence (AI), have the potential to automate these processes and support more timely and accurate diagnoses.

OBJECTIVES : To review current artificial intelligence-based image analysis as applied to clinical microbiology and discuss future trends in the field.

SOURCES : Material sourced for this review included peer-reviewed literature annotated in the PubMed or Google Scholar databases and preprint articles from bioRxiv. Articles describing use of AI for analysis of images used in infectious disease diagnostics were reviewed.

CONTENT : We describe application of machine learning towards analysis of different types of microbiological image data. Specifically, we outline progress in smear and plate interpretation and potential for AI diagnostic applications in the clinical microbiology laboratory.

IMPLICATIONS : Combined with automation, we predict that AI algorithms will be used in the future to pre-screen and pre-classify image data, thereby increasing productivity and enabling more accurate diagnoses through collaboration between the AI and microbiologist. Once developed, image-based AI analysis is inexpensive and amenable to local and remote diagnostic use.

Smith Kenneth P, Kirby James E

2020-Mar-22

In Brain research

PURPOSE : Previous studies showed voxel-based volumetry as a helpful tool in detecting pathologic brain atrophy. Aim of this study was to investigate whether the inclusion of CSF volume improves the imaging based diagnostic accuracy by using combined automated voxel- and region-based volumetry.

METHODS : In total, 120 individuals (30 healthy elderly, 30 frontotemporal dementia (FTD), 30 Alzheimer's dementia (AD) and 30 Lewy body dementia (LBD) patients) were analyzed with voxel-based morphometry and compared to a reference group of 360 healthy elderly controls. Abnormal GM and CSF volumes were visualized via z-scores. Volumetric results were finally evaluated by ROC analyses.

RESULTS : Based on the volume of abnormal GM and CSF voxels high accuracy was shown in separating dementia from normal ageing (AUC 0.93 and 0.91, respectively) within 5 different brain regions per hemisphere (frontal, medial temporal, temporal, parietal, occipital). Accuracy for separating FTD and AD was higher based on CSF volume (FTD: AUC 0.80 vs. 0.75 in frontal regions; AD: AUC 0.78 vs. 0.68 in parietal regions based on CSF and GM respectively).

CONCLUSIONS : Differentiation of dementia patients from normal ageing persons shows high accuracy when based on automatic volumetry alone. Using volumes of abnormal CSF performed better than volumes of abnormal GM, especially in AD and FTD patients.

Egger Karl, Rau Alexander, Yang Shan, Klöppel Stefan, Abdulkadir Ahmed, Kellner Elias, Frings Lars, Hellwig Sabine, Urbach Horst

2020-Mar-22

Alzheimeŕs disease, Dementia, Lewy body dementia, frontotemporal dementia, machine learning, volumetry

In Journal of biomechanics

Hernandez Vincent, Kulić Dana, Venture Gentiane

2020-Feb-26

Adversarial autoencoder, Deep learning, Ground reaction force, Human activity recognition, Machine learning

In JCO clinical cancer informatics

PURPOSE : For patients with early-stage breast cancer, predicting the risk of metastatic relapse is of crucial importance. Existing predictive models rely on agnostic survival analysis statistical tools (eg, Cox regression). Here we define and evaluate the predictive ability of a mechanistic model for time to distant metastatic relapse.

METHODS : The data we used for our model consisted of 642 patients with 21 clinicopathologic variables. A mechanistic model was developed on the basis of two intrinsic mechanisms of metastatic progression: growth (parameter α) and dissemination (parameter μ). Population statistical distributions of the parameters were inferred using mixed-effects modeling. A random survival forest analysis was used to select a minimal set of five covariates with the best predictive power. These were further considered to individually predict the model parameters by using a backward selection approach. Predictive performances were compared with classic Cox regression and machine learning algorithms.

RESULTS : The mechanistic model was able to accurately fit the data. Covariate analysis revealed statistically significant association of Ki67 expression with α (P = .001) and EGFR expression with μ (P = .009). The model achieved a c-index of 0.65 (95% CI, 0.60 to 0.71) in cross-validation and had predictive performance similar to that of random survival forest (95% CI, 0.66 to 0.69) and Cox regression (95% CI, 0.62 to 0.67) as well as machine learning classification algorithms.

CONCLUSION : By providing informative estimates of the invisible metastatic burden at the time of diagnosis and forward simulations of metastatic growth, the proposed model could be used as a personalized prediction tool for routine management of patients with breast cancer.

Nicolò Chiara, Périer Cynthia, Prague Melanie, Bellera Carine, MacGrogan Gaëtan, Saut Olivier, Benzekry Sébastien

2020-Mar

In Telemedicine journal and e-health : the official journal of the American Telemedicine Association

Figueroa Caroline A, DeMasi Orianna, Hernandez-Ramos Rosa, Aguilera Adrian

2020-Mar-26

cognitive behavioral therapy, digital literacy, engagement, short messaging service, telehealth

In Digestive endoscopy : official journal of the Japan Gastroenterological Endoscopy Society

Louis Ho Shing Lau, Sung Joseph Jy

2020-Mar-26

In Journal of magnetic resonance imaging : JMRI

BACKGROUND : Twenty-five percent of rectal adenocarcinoma patients achieve pathologic complete response (pCR) to neoadjuvant chemoradiation and could avoid proctectomy. However, pretreatment clinical or imaging markers are lacking in predicting response to chemoradiation. Radiomic texture features from MRI have recently been associated with therapeutic response in other cancers.

PURPOSE : To construct a radiomics texture model based on pretreatment MRI for identifying patients who will achieve pCR to neoadjuvant chemoradiation in rectal cancer, including validation across multiple scanners and sites.

STUDY TYPE : Retrospective.

SUBJECTS : In all, 104 rectal cancer patients staged with MRI prior to long-course chemoradiation followed by proctectomy; curated from three institutions.

FIELD STRENGTH/SEQUENCE : 1.5T-3.0T, axial higher resolution T₂ -weighted turbo spin echo sequence.

ASSESSMENT : Pathologic response was graded on postsurgical specimens. In total, 764 radiomic features were extracted from single-slice sections of rectal tumors on processed pretreatment T₂ -weighted MRI.

STATISTICAL TESTS : Three feature selection schemes were compared for identifying radiomic texture descriptors associated with pCR via a discovery cohort (one site, N = 60, cross-validation). The top-selected radiomic texture features were used to train and validate a random forest classifier model for pretreatment identification of pCR (two external sites, N = 44). Model performance was evaluated via area under the curve (AUC), accuracy, sensitivity, and specificity.

RESULTS : Laws kernel responses and gradient organization features were most associated with pCR (P ≤ 0.01); as well as being commonly identified across all feature selection schemes. The radiomics model yielded a discovery AUC of 0.699 ± 0.076 and a hold-out validation AUC of 0.712 with 70.5% accuracy (70.0% sensitivity, 70.6% specificity) in identifying pCR. Radiomic texture features were resilient to variations in magnetic field strength as well as being consistent between two different expert annotations. Univariate analysis revealed no significant associations of baseline clinicopathologic or MRI findings with pCR (P = 0.07-0.96).

DATA CONCLUSION : Radiomic texture features from pretreatment MRIs may enable early identification of potential pCR to neoadjuvant chemoradiation, as well as generalize across sites.

LEVEL OF EVIDENCE : 3 TECHNICAL EFFICACY STAGE: 2.

Antunes Jacob T, Ofshteyn Asya, Bera Kaustav, Wang Erik Y, Brady Justin T, Willis Joseph E, Friedman Kenneth A, Marderstein Eric L, Kalady Matthew F, Stein Sharon L, Purysko Andrei S, Paspulati Rajmohan, Gollamudi Jayakrishna, Madabhushi Anant, Viswanath Satish E

2020-Mar-26

machine learning, pathologic complete response, radiomics, rectal cancer

In Journal of applied clinical medical physics ; h5-index 28.0

PURPOSE : The purpose of this study was to address the dosimetric accuracy of synthetic computed tomography (sCT) images of patients with brain tumor generated using a modified generative adversarial network (GAN) method, for their use in magnetic resonance imaging (MRI)-only treatment planning for proton therapy.

METHODS : Dose volume histogram (DVH) analysis was performed on CT and sCT images of patients with brain tumor for plans generated for intensity-modulated proton therapy (IMPT). All plans were robustly optimized using a commercially available treatment planning system (RayStation, from RaySearch Laboratories) and standard robust parameters reported in the literature. The IMPT plan was then used to compute the dose on CT and sCT images for dosimetric comparison, using RayStation analytical (pencil beam) dose algorithm. We used a second, independent Monte Carlo dose calculation engine to recompute the dose on both CT and sCT images to ensure a proper analysis of the dosimetric accuracy of the sCT images.

RESULTS : The results extracted from RayStation showed excellent agreement for most DVH metrics computed on the CT and sCT for the nominal case, with a mean absolute difference below 0.5% (0.3 Gy) of the prescription dose for the clinical target volume (CTV) and below 2% (1.2 Gy) for the organs at risk (OARs) considered. This demonstrates a high dosimetric accuracy for the generated sCT images, especially in the target volume. The metrics obtained from the Monte Carlo doses mostly agreed with the values extracted from RayStation for the nominal and worst-case scenarios (mean difference below 3%).

CONCLUSIONS : This work demonstrated the feasibility of using sCT generated with a GAN-based deep learning method for MRI-only treatment planning of patients with brain tumor in intensity-modulated proton therapy.

Kazemifar Samaneh, Barragán Montero Ana M, Souris Kevin, Rivas Sara T, Timmerman Robert, Park Yang K, Jiang Steve, Geets Xavier, Sterpin Edmond, Owrangi Amir

2020-Mar-26

GAN structure, artificial intelligence, brain MRI, deep learning, proton therapy, synthetic CT

In Clinical and translational science

Ota Nagomi, Tachibana Keisuke, Kusakabe Tetsuya, Sanada Shoji, Kondoh Masuo

2020-Mar-26

In Journal of medical toxicology : official journal of the American College of Medical Toxicology

Chary Michael A, Manini Alex F, Boyer Edward W, Burns Michele

2020-Mar-25

Artificial intelligence, Big data, Knowledge representation, Machine learning

In International archives of occupational and environmental health

PURPOSE : There is increasing interest in the use of heart rate variability (HRV) as an objective measurement of mental stress in the surgical setting. To identify areas of improvement, the aim of our study was to review current use of HRV measurements in the surgical setting, evaluate the different methods used for the analysis of HRV, and to assess whether HRV is being measured correctly.

METHODS : A systematic review was performed according to the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA). 17 studies regarding HRV as a measurement of mental stress in the surgical setting were included and analysed.

RESULTS : 24% of the studies performed long-term measurements (24 h and longer) to assess the long-term effects of and recovery from mental stress. In 24% of the studies, artefact correction took place.

CONCLUSIONS : HRV showed to be a good objective assessment method of stress induced in the workplace environment: it was able to pinpoint stressors during operations, determine which operating techniques induced most stress for surgeons, and indicate differences in stress levels between performing and assisting surgery. For future research, this review recommends using singular guidelines to standardize research, and performing artefact correction. This will improve further evaluation of the long-term effects of mental stress and its recovery.

The Anne-Fleur, Reijmerink Iris, van der Laan Maarten, Cnossen Fokie

2020-Mar-25

Heart rate variability, Mental stress, Occupational stress, Surgery

In Emerging microbes & infections ; h5-index 36.0

Miao Dong, Dai Ke, Zhao Guo-Ping, Li Xin-Lou, Shi Wen-Qiang, Zhang Jiu Song, Yang Yang, Liu Wei, Fang Li-Qun

2020-Mar-26

Haemaphysalis longicornis, Severe fever with thrombocytopenia syndrome, distribution, machine learning, modeling, risk assessment, world

In JAMA ophthalmology ; h5-index 58.0

Importance : Evaluating corneal morphologic characteristics with corneal tomographic scans before refractive surgery is necessary to exclude patients with at-risk corneas and keratoconus. In previous studies, researchers performed screening with machine learning methods based on specific corneal parameters. To date, a deep learning algorithm has not been used in combination with corneal tomographic scans.

Objective : To examine the use of a deep learning model in the screening of candidates for refractive surgery.

Design, Setting, and Participants : A diagnostic, cross-sectional study was conducted at the Zhongshan Ophthalmic Center, Guangzhou, China, with examination dates extending from July 18, 2016, to March 29, 2019. The investigation was performed from July 2, 2018, to June 28, 2019. Participants included 1385 patients; 6465 corneal tomographic images were used to generate the artificial intelligence (AI) model. The Pentacam HR system was used for data collection.

Interventions : The deidentified images were analyzed by ophthalmologists and the AI model.

Main Outcomes and Measures : The performance of the AI classification system.

Results : A classification system centered on the AI model Pentacam InceptionResNetV2 Screening System (PIRSS) was developed for screening potential candidates for refractive surgery. The model achieved an overall detection accuracy of 94.7% (95% CI, 93.3%-95.8%) on the validation data set. Moreover, on the independent test data set, the PIRSS model achieved an overall detection accuracy of 95% (95% CI, 88.8%-97.8%), which was comparable with that of senior ophthalmologists who are refractive surgeons (92.8%; 95% CI, 91.2%-94.4%) (P = .72). In distinguishing corneas with contraindications for refractive surgery, the PIRSS model performed better than the classifiers (95% vs 81%; P < .001) in the Pentacam HR system on an Asian patient database.

Conclusions and Relevance : PIRSS appears to be useful in classifying images to provide corneal information and preliminarily identify at-risk corneas. PIRSS may provide guidance to refractive surgeons in screening candidates for refractive surgery as well as for generalized clinical application for Asian patients, but its use needs to be confirmed in other populations.

Xie Yi, Zhao Lanqin, Yang Xiaonan, Wu Xiaohang, Yang Yahan, Huang Xiaoman, Liu Fang, Xu Jiping, Lin Limian, Lin Haiqin, Feng Qiting, Lin Haotian, Liu Quan

2020-Mar-26

In Microscopy (Oxford, England)

Ishii Shin, Lee Sehyung, Urakubo Hidetoshi, Kume Hideaki, Kasai Haruo

2020-Mar-26

Bayesian estimation, deep learning, image processing, image segmentation, image super-resolution, maximum likelihood estimation

In Sleep

STUDY OBJECTIVES : Multisensor wearable consumer devices allowing collection of multiple data sources, such as heart rate and motion, for the evaluation of sleep in the home environment, are increasingly ubiquitous. However, the validity of such devices for sleep assessment has not been directly compared to alternatives such as wrist actigraphy or PSG.

METHODS : Eight participants each completed four nights in a sleep laboratory, equipped with polysomnography (PSG) and several wearable devices. RPSGT-scored PSG served as ground truth for sleep-wake state. Wearable devices providing sleep-wake classification data were compared to PSG at both an epoch-by-epoch and night level. Data from multisensor wearables (Apple Watch and Oura Ring) were compared to data available from ECG and a tri-axial wrist actigraph to evaluate quality and utility of heart rate and motion data. Machine learning methods were used to train and test sleep-wake classifiers, using data from consumer wearables. Quality of classifications derived from devices were compared.

RESULTS : For epoch-by-epoch sleep-wake performance, research devices ranged in d' between 1.771 and 1.874, with sensitivity between 0.912 and 0.982, and specificity between 0.366 and 0.647. Data from multisensor wearables were strongly correlated at an epoch-by-epoch level with reference data sources. Classifiers developed from the multisensor wearable data ranged in d' between 1.827 and 2.347, with sensitivity between 0.883 and 0.977, and specificity between 0.407 and 0.821.

CONCLUSIONS : Data from multisensor consumer wearables is strongly correlated with reference devices at the epoch level and can be used to develop epoch-by-epoch models of sleep-wake rivaling existing research devices.

Roberts Daniel M, Schade Margeaux M, Mathew Gina M, Gartenberg Daniel, Buxton Orfeu M

2020-Mar-26

Actigraphy, Artificial Intelligence, Big Data, Machine Learning, Polysomnography, Smartphone, Wearable

In General psychiatry

Wu Tsung-Chin, Zhou Zhirou, Wang Hongyue, Wang Bokai, Lin Tuo, Feng Changyong, Tu Xin M

2020

mental health

In General psychiatry

**

2020

In Applied network science

Heidari Farzaneh, Papagelis Manos

2020

Dynamic graph embedding, Dynamic random walks, Evolving networks, Network representation learning

In Data in brief

Zago Mattia, Gil Pérez Manuel, Martínez Pérez Gregorio

2020-Jun

Data, Domain Generation Algorithm (DGA), Machine learning, Natural Language Processing (NLP), Network security

In Internet interventions

Schuster Raphael, Schreyer Manuela Larissa, Kaiser Tim, Berger Thomas, Klein Jan Philipp, Moritz Steffen, Laireiter Anton-Rupert, Trutschnig Wolfgang

2020-Apr

In Statistical analysis and data mining

Park Soyoung, Carriquiry Alicia

2020-Apr

SURF, forensic science, image comparison, machine learning, maximum clique

In Cancer management and research

Objective : The disease complexity of metastatic non-small-cell lung cancer (mNSCLC) makes it difficult for physicians to make clinical decisions efficiently and accurately. The Watson for Oncology (WFO) system of artificial intelligence might help physicians by providing fast and precise treatment regimens. This study measured the concordance of the medical treatment regimens of the WFO system and actual clinical regimens, with the aim of determining the suitability of WFO recommendations for Chinese patients with mNSCLC.

Methods : Retrospective data of mNSCLC patients were input to the WFO, which generated a treatment regimen (WFO regimen). The actual regimen was made by physicians in a medical team for patients (medical-team regimen). The factors influencing the consistency of the two treatment options were analyzed by univariate and multivariate analyses.

Results : The concordance rate was 85.16% between the WFO and medical-team regimens for mNSCLC patients. Logistic regression showed that the concordance differed significantly for various pathological types and gene mutations in two treatment regimens. Patients with adenocarcinoma had a lower rate of "recommended" regimen than those with squamous cell carcinoma. There was a statistically significant difference in EGFR-mutant patients for "not recommended" regimens with inconsistency rate of 18.75%. In conclusion, the WFO regimen has 85.16% consistency rate with medical-team regimen in our treatment center. The different pathological type and different gene mutation markedly influenced the agreement rate of the two treatment regimens.

Conclusion : WFO recommendations have high applicability to mNSCLC patients in our hospital. This study demonstrates that the valuable WFO system may assist the doctors better to determine the accurate and effective treatment regimens for mNSCLC patients in the Chinese medical setting.

You Hai-Sheng, Gao Chun-Xia, Wang Hai-Bin, Luo Sai-Sai, Chen Si-Ying, Dong Ya-Lin, Lyu Jun, Tian Tao

2020

Watson for Oncology, artificial intelligence, concordance, metastatic non-small-cell lung cancer, treatment recommendations

In The journal of physical chemistry. A

McCarthy Michael C, Lee Kin Long Kelvin

2020-Mar-26

In The VLDB journal : very large data bases : a publication of the VLDB Endowment

Ratner Alexander, Bach Stephen H, Ehrenberg Henry, Fries Jason, Wu Sen, Ré Christopher

2020

Machine learning, Training data, Weak supervision

In PloS one ; h5-index 176.0

Wu Hao, Wang Qiaomei, Yu Kunjian, Hu Xiaotao, Ran Maoxia

2020

In PloS one ; h5-index 176.0

López-García Guillermo, Jerez José M, Franco Leonardo, Veredas Francisco J

2020

In Scientific reports ; h5-index 158.0

Sheng Jinhua, Shao Meiling, Zhang Qiao, Zhou Rougang, Wang Luyun, Xin Yu

2020-Mar-25

In Scientific reports ; h5-index 158.0

Zhu Hengshu, Sun Ying, Zhao Wenjia, Zhuang Fuzhen, Wang Baoshan, Xiong Hui

2020-Mar-25

In Nature communications ; h5-index 260.0

Golestani Negar, Moghaddam Mahta

2020-Mar-25

In Metabolites

Mitchell Joshua M, Flight Robert M, Moseley Hunter N B

2020-Mar-24

Random Forest, SMIRFE, lipid category, lipidomics, machine learning, metabolomics

In Psychiatry investigation

OBJECTIVE : Suicidal ideation (SI) precedes actual suicidal event. Thus, it is important for the prevention of suicide to screen the individuals with SI. This study aimed to identify the factors associated with SI and to build prediction models in Korean adults using machine learning methods.

METHODS : The 2010-2013 dataset of the Korea National Health and Nutritional Examination Survey was used as the training dataset (n=16,437), and the subset collected in 2015 was used as the testing dataset (n=3,788). Various machine learning algorithms were applied and compared to the conventional logistic regression (LR)-based model.

RESULTS : Common risk factors for SI included stress awareness, experience of continuous depressive mood, EQ-5D score, depressive disorder, household income, educational status, alcohol abuse, and unmet medical service needs. The prediction performances of the machine learning models, as measured by the area under receiver-operating curve, ranged from 0.794 to 0.877, some of which were better than that of the conventional LR model (0.867). The Bayesian network, LogitBoost with LR, and ANN models outperformed the conventional LR model.

CONCLUSION : A machine learning-based approach could provide better SI prediction performance compared to a conventional LR-based model. These may help primary care physicians to identify patients at risk of SI and will facilitate the early prevention of suicide.

Oh Bumjo, Yun Je-Yeon, Yeo Eun Chong, Kim Dong-Hoi, Kim Jin, Cho Bum-Joo

2020-Mar-27

Artificial intelligence, Machine learning, Risk factor, Suicidal ideation

In Genes & genetic systems

Kaminuma Eli, Baba Yukino, Mochizuki Masahiro, Matsumoto Hirotaka, Ozaki Haruka, Okayama Toshitsugu, Kato Takuya, Oki Shinya, Fujisawa Takatomo, Nakamura Yasukazu, Arita Masanori, Ogasawara Osamu, Kashima Hisashi, Takagi Toshihisa

2020-Mar-26

chromatin features prediction, deep learning, machine learning competition, sequence read archive

In BMJ (Clinical research ed.)

OBJECTIVE : To systematically examine the design, reporting standards, risk of bias, and claims of studies comparing the performance of diagnostic deep learning algorithms for medical imaging with that of expert clinicians.

DESIGN : Systematic review.

DATA SOURCES : Medline, Embase, Cochrane Central Register of Controlled Trials, and the World Health Organization trial registry from 2010 to June 2019.

ELIGIBILITY CRITERIA FOR SELECTING STUDIES : Randomised trial registrations and non-randomised studies comparing the performance of a deep learning algorithm in medical imaging with a contemporary group of one or more expert clinicians. Medical imaging has seen a growing interest in deep learning research. The main distinguishing feature of convolutional neural networks (CNNs) in deep learning is that when CNNs are fed with raw data, they develop their own representations needed for pattern recognition. The algorithm learns for itself the features of an image that are important for classification rather than being told by humans which features to use. The selected studies aimed to use medical imaging for predicting absolute risk of existing disease or classification into diagnostic groups (eg, disease or non-disease). For example, raw chest radiographs tagged with a label such as pneumothorax or no pneumothorax and the CNN learning which pixel patterns suggest pneumothorax.

REVIEW METHODS : Adherence to reporting standards was assessed by using CONSORT (consolidated standards of reporting trials) for randomised studies and TRIPOD (transparent reporting of a multivariable prediction model for individual prognosis or diagnosis) for non-randomised studies. Risk of bias was assessed by using the Cochrane risk of bias tool for randomised studies and PROBAST (prediction model risk of bias assessment tool) for non-randomised studies.

RESULTS : Only 10 records were found for deep learning randomised clinical trials, two of which have been published (with low risk of bias, except for lack of blinding, and high adherence to reporting standards) and eight are ongoing. Of 81 non-randomised clinical trials identified, only nine were prospective and just six were tested in a real world clinical setting. The median number of experts in the comparator group was only four (interquartile range 2-9). Full access to all datasets and code was severely limited (unavailable in 95% and 93% of studies, respectively). The overall risk of bias was high in 58 of 81 studies and adherence to reporting standards was suboptimal (<50% adherence for 12 of 29 TRIPOD items). 61 of 81 studies stated in their abstract that performance of artificial intelligence was at least comparable to (or better than) that of clinicians. Only 31 of 81 studies (38%) stated that further prospective studies or trials were required.

CONCLUSIONS : Few prospective deep learning studies and randomised trials exist in medical imaging. Most non-randomised trials are not prospective, are at high risk of bias, and deviate from existing reporting standards. Data and code availability are lacking in most studies, and human comparator groups are often small. Future studies should diminish risk of bias, enhance real world clinical relevance, improve reporting and transparency, and appropriately temper conclusions.

STUDY REGISTRATION : PROSPERO CRD42019123605.

Nagendran Myura, Chen Yang, Lovejoy Christopher A, Gordon Anthony C, Komorowski Matthieu, Harvey Hugh, Topol Eric J, Ioannidis John P A, Collins Gary S, Maruthappu Mahiben

2020-Mar-25

ArXiv Preprint

Nathan Kallus, Xiaojie Mao

2020-03-27

ArXiv Preprint

Jianpeng Zhang, Yutong Xie, Yi Li, Chunhua Shen, Yong Xia

2020-03-27

In Infectious diseases of poverty ; h5-index 31.0

BACKGROUND : Coronavirus can cross the species barrier and infect humans with a severe respiratory syndrome. SARS-CoV-2 with potential origin of bat is still circulating in China. In this study, a prediction model is proposed to evaluate the infection risk of non-human-origin coronavirus for early warning.

METHODS : The spike protein sequences of 2666 coronaviruses were collected from 2019 Novel Coronavirus Resource (2019nCoVR) Database of China National Genomics Data Center on Jan 29, 2020. A total of 507 human-origin viruses were regarded as positive samples, whereas 2159 non-human-origin viruses were regarded as negative. To capture the key information of the spike protein, three feature encoding algorithms (amino acid composition, AAC; parallel correlation-based pseudo-amino-acid composition, PC-PseAAC and G-gap dipeptide composition, GGAP) were used to train 41 random forest models. The optimal feature with the best performance was identified by the multidimensional scaling method, which was used to explore the pattern of human coronavirus.

RESULTS : The 10-fold cross-validation results showed that well performance was achieved with the use of the GGAP (g = 3) feature. The predictive model achieved the maximum ACC of 98.18% coupled with the Matthews correlation coefficient (MCC) of 0.9638. Seven clusters for human coronaviruses (229E, NL63, OC43, HKU1, MERS-CoV, SARS-CoV, and SARS-CoV-2) were found. The cluster for SARS-CoV-2 was very close to that for SARS-CoV, which suggests that both of viruses have the same human receptor (angiotensin converting enzyme II). The big gap in the distance curve suggests that the origin of SARS-CoV-2 is not clear and further surveillance in the field should be made continuously. The smooth distance curve for SARS-CoV suggests that its close relatives still exist in nature and public health is challenged as usual.

CONCLUSIONS : The optimal feature (GGAP, g = 3) performed well in terms of predicting infection risk and could be used to explore the evolutionary dynamic in a simple, fast and large-scale manner. The study may be beneficial for the surveillance of the genome mutation of coronavirus in the field.

Qiang Xiao-Li, Xu Peng, Fang Gang, Liu Wen-Bin, Kou Zheng

2020-Mar-25

Coronavirus, Cross-species infection, Machine learning, Spike protein

bioRxiv Preprint

Lopez-Rincon, A.; Tonda, A.; Mendoza-Maldonado, L.; Claassen, E.; Garssen, J.; Kraneveld, A. D.

2020-03-27

ArXiv Preprint

Huiqiang Zhong, Cunxiang Yin, Xiaohui Wu, Jinchang Luo, JiaWei He

2020-03-27

In PloS one ; h5-index 176.0

Marzban Eman N, Eldeib Ayman M, Yassine Inas A, Kadah Yasser M

2020

In Physics in medicine and biology

Samala Ravi K, Chan Heang-Ping, Hadjiiski Lubomir M, Helvie Mark A, Richter Caleb

2020-Mar-24

artificial intelligence, breast cancer, deep convolutional neural network, generalization error, mammography

In The Science of the total environment

Abimbola Olufemi P, Mittelstet Aaron R, Messer Tiffany L, Berry Elaine D, Bartelt-Hunt Shannon L, Hansen Samuel P

2020-Mar-12

Animal density estimation, E. coli prediction, Feature selection, Grazing pattern, Machine learning

In The Science of the total environment

Huang Jinying, Zhu Yun, Kelly James T, Jang Carey, Wang Shuxiao, Xing Jia, Chiang Pen-Chi, Fan Shaojia, Zhao Xuetao, Yu Lian

2020-Mar-06

Air pollution control strategies, Cost-benefit analysis, Genetic algorithm, Multi-pollutant optimization, Ozone, PM(2.5)

In Radiology ; h5-index 91.0

Larson David B, Magnus David C, Lungren Matthew P, Shah Nigam H, Langlotz Curtis P

2020-Mar-24

In Journal of personality assessment

Schönbrodt Felix D, Hagemeyer Birk, Brandstätter Veronika, Czikmantori Thomas, Gröpel Peter, Hennecke Marie, Israel Laura S F, Janson Kevin T, Kemper Nina, Köllner Martin G, Kopp Philipp M, Mojzisch Andreas, Müller-Hotop Raphael, Prüfer Johanna, Quirin Markus, Scheidemann Bettina, Schiestel Lena, Schulz-Hardt Stefan, Sust Larissa N N, Zygar-Hoffmann Caroline, Schultheiss Oliver C

2020-Mar-24

ArXiv Preprint

Lu Wang, Dong-xue Liang, Xiao-lei Yin, Jing Qiu, Zhi-yun Yang, Jun-hui Xing, Jian-zeng Dong, Zhao-yuan Ma

2020-03-26

In The British journal of radiology

Schiaffino Simone, Cozzi Andrea, Sardanelli Francesco

2020-Mar-24

ArXiv Preprint

Lu Wang, Dong-xue Liang, Xiao-lei Yin, Jing Qiu, Zhi-yun Yang, Jun-hui Xing, Jian-zeng Dong, Zhao-yuan Ma

2020-03-26

In Clinical gastroenterology and hepatology : the official clinical practice journal of the American Gastroenterological Association

BACKGROUND & AIMS : Non-invasive and accurate methods are needed to identify patients with clinically significant portal hypertension (CSPH). We investigated the ability of deep convolutional neural network (CNN) analysis of computed tomography (CT) or magnetic resonance (MR) to identify patients with CSPH.

METHODS : We collected liver and spleen image from patients who underwent contrast-enhanced CT or MR analysis within 14 days of transjugular catheterization for hepatic venous pressure gradient measurement. The CT cohort comprised participants with cirrhosis in the CHESS1701 study, performed at 4 university hospitals in China from August 2016 through September 2017. The MR cohort comprised participants with cirrhosis in the CHESS1802 study, performed at 8 university hospitals in China and 1 in Turkey from December 2018 through April 2019. Patients with CSPH were identified as those with a hepatic venous pressure gradient ≥10 mmHg. In total, we analyzed 10014 liver images and 899 spleen images collected from 679 participants who underwent CT analysis, and 45554 liver and spleen images from 271 participants who underwent MR analysis. For each cohort, participants were shuffled and then randomly and equiprobably sampled for 6 times into training, validation, and test datasets (ratio of 3:1:1). Therefore, a total of 6 deep CNN models for each cohort were developed for identification of CSPH.

RESULTS : The CT-based CNN analysis identified patients with CSPH with the area under receiver operating characteristic curve (AUC) value of 0.998 in the training set (95% CI, 0.996-1.000), an AUC of 0.912 in the validation set (95% CI, 0.854-0.971), and an AUC of 0.933 (95% CI, 0.883-0.984) in the test datasets. The MR-based CNN analysis identified patients with CSPH with an AUC of 1.000 in the training set (95% CI, 0.999-1.000), and AUC of 0.924 in the validation set (95% CI, 0.833-1.000), and an AUC of 0.940 in the test dataset (95% CI, 0.880-0.999). When the model development procedures were repeated 6 times, and AUCs for all CNN analyses were 0.888 or greater, with no significant differences between rounds (P>.05).

CONCLUSIONS : We developed a deep CNN to analyze CT or MR images of liver and spleen from patients with cirrhosis that identifies patients with CSPH with an AUC value of 0.9. This provides a non-invasive and rapid method for detection of CSPH (ClincialTrials.gov number, NCT03138915; NCT03766880).

Liu Yanna, Ning Zhenyuan, Örmeci Necati, An Weimin, Yu Qian, Han Kangfu, Huang Yifei, Liu Dengxiang, Liu Fuquan, Li Zhiwei, Ding Huiguo, Luo Hongwu, Zuo Changzeng, Liu Changchun, Wang Jitao, Zhang Chunqing, Ji Jiansong, Wang Wenhui, Wang Zhiwei, Wang Weidong, Yuan Min, Li Lei, Zhao Zhongwei, Wang Guangchuan, Li Mingxing, Liu Qingbo, Lei Junqiang, Liu Chuan, Tang Tianyu, Akçalar Seray, Çelebioğlu Emrecan, Üstüner Evren, Bilgiç Sadık, Ellik Zeynep, Asiller Özgün Ömer, Liu Zaiyi, Teng Gaojun, Chen Yaolong, Hou Jinlin, Li Xun, He Xiaoshun, Dong Jiahong, Tian Jie, Liang Ping, Ju Shenghong, Zhang Yu, Qi Xiaolong

2020-Mar-20

AI, HVPG, deep learning, diagnostic

In Academic radiology

RATIONALE AND OBJECTIVES : Recently, advanced magnetic resonance imaging has been widely adopted to investigate altered structure and functional activities in patients with diffuse axonal injury (DAI), this patient presumed to be caused by shearing forces and results in significant neurological effects. However, little is known regarding cerebral temporal dynamics and its predictive ability in the clinical dysfunction of DAI.

MATERIALS AND METHODS : In this study, static and dynamic fractional amplitude of low-frequency fluctuation (fALFF), an improved approach to detect the intensity of intrinsic neural activities, and their temporal variability were applied to examine the alteration between DAI patients (n = 24) and healthy controls (n = 26) at the voxel level. Then, the altered functional index was used to explore the clinical relationship and predict dysfunction in DAI patients.

RESULTS : We discovered that, compared to healthy controls, DAI patients showed commonly altered regions of static fALFF, and its variability was mainly located in the left cerebellum posterior lobe. Furthermore, decreased static fALFF values over the left cerebellum posterior lobe and bilateral medial frontal gyrus showed significant correlations with disease duration and Mini-Mental State Examination scores. More important, the increased temporal variability of dynamic fALFF in the left caudate could predict the severity of the Glasgow Coma Scale score in DAI patients.

CONCLUSION : Overall, these results suggested selective abnormalities in intrinsic neural activities with reduced intensity and increased variability, and this novel predictive marker may be developed as a useful indicator for future connectomics or artificial intelligence analyses.

Zhou Fuqing, Zhan Jie, Gong Tao, Xu Wenhua, Kuang Hongmei, Li Jian, Wang Yinhua, Gong Honghan

2020-Mar-20

Diffuse axonal injury, Fractional amplitude of low-frequency fluctuation, Temporal variability

In Early human development

Grech Victor, Scerri Mariella

2020-Mar-20

In The Canadian journal of cardiology

BACKGROUND : The ability to predict readmission accurately after hospitalization for acute myocardial infarction (AMI) is limited in current statistical models. Machine-learning (ML) methods have shown improved predictive ability in various clinical contexts, but their utility in predicting readmission after hospitalization for AMI is unknown.

METHODS : Using detailed clinical information collected from patients hospitalized with AMI, we evaluated 6 ML algorithms (logistic regression, naïve Bayes, support vector machines, random forest, gradient boosting, and deep neural networks) to predict readmission within 30 days and 1 year of discharge. A nested cross-validation approach was used to develop and test models. We used C-statistics to compare discriminatory capacity, whereas the Brier score was used to indicate overall model performance. Model calibration was assessed using calibration plots.

RESULTS : The 30-day readmission rate was 16.3%, whereas the 1-year readmission rate was 45.1%. For 30-day readmission, the discriminative ability for the ML models was modest (C-statistic 0.641; 95% confidence interval (CI), 0.621-0.662 for gradient boosting) and did not outperform previously reported methods. For 1-year readmission, different ML models showed moderate performance, with C-statistics around 0.72. Despite modest discriminatory capabilities, the observed readmission rates were markedly higher in the tenth decile of predicted risk compared with the first decile of predicted risk for both 30-day and 1-year readmission.

CONCLUSIONS : Despite including detailed clinical information and evaluating various ML methods, these models did not have better discriminatory ability to predict readmission outcomes compared with previously reported methods.

Gupta Shagun, Ko Dennis T, Azizi Paymon, Bouadjenek Mohamed Reda, Koh Maria, Chong Alice, Austin Peter C, Sanner Scott

2019-Oct-25

In Critical care (London, England)

Gutierrez Guillermo

2020-Mar-24

In Cancers

Metz Marie-Christin, Molina-Romero Miguel, Lipkova Jana, Gempt Jens, Liesche-Starnecker Friederike, Eichinger Paul, Grundl Lioba, Menze Bjoern, Combs Stephanie E, Zimmer Claus, Wiestler Benedikt

2020-Mar-19

DTI, FA, deep learning, glioblastoma, recurrence prediction.

In Voprosy kurortologii, fizioterapii, i lechebnoi fizicheskoi kultury

INTRODUCTION : Bronchial asthma (BA) is a relevant social and medical problem in our country and around the world. Currently, phenotypes of the disease are distinguished. One of the original decisions in phenotypes distinguishing is the use of cluster analysis. However, the concept of BA phenotypes at the health resort period of rehabilitation has not yet been formed.

AIM : To determine the BA phenotypes upon admission of patients to a health resort medical rehabilitation (HRMR) using cluster analysis and to offer personalized rehabilitation programs.

MATERIAL AND METHODS : 518 patients with asthma who underwent HRMR on the southern coast of Crimea were examined. Each patient received clinical, functional and laboratory examination. HRMR included correction of long-term treatment according to the severity of asthma, climate therapy, respiratory therapy, educational programs, and physiotherapeutic procedures. We applied cluster analysis in order to identify BA phenotypes. Description statistics methods were used for phenotype-cluster characterization, comparative analysis - for determination of reliable phenotypic characteristics and relation of the effectiveness of HRMR and phenotypes.

RESULTS : A model of three phenotype-clusters was developed. The first cluster included patients with BA of moderate severity, uncontrolled course, frequent exacerbations, history of atopy, a tendency to obesity, moderately reduced external respiration function, fixed airway obstruction, high adherence to long-term therapy with medium doses of inhaled glucocorticoids (ICS) combined with long-acting β-2 agonists (LABA). Cluster 2 included patients with mild asthma, controlled or partially controlled course of the disease, with rare short exacerbations, late onset, preserved external respiration function and exercise tolerance, but low adherence to long-term therapy with medium and low doses of ICS. Cluster 3 included patients with moderate to severe BA, uncontrolled course, with early onset, frequent and prolonged exacerbations, severe symptoms, significantly reduced external respiration function with fixed obstruction, decreased exercise tolerance, but low adherence to long-term therapy (4th stage) with high doses of ICS in combination with LABA and long-acting anticholinergics. A close relationship was found between phenotypes-clusters and the achieved effects: a significant increase in the control of BA and a high efficiency of rehabilitation in patients of the 1st and especially 3rd clusters and low in the 2nd cluster. The optimal rehabilitation programs for each of the selected cluster phenotypes were determined.

CONCLUSION : The cluster model developed with the help of artificial intelligence has demonstrated high prognostic value in the determination of the effectiveness and change of control over the course of asthma as a result of HRMR. Personalized HRMR programs are suggested.

Ivashchenko A S, Dudchenko L Sh, Kaladze N N, Mizin V I

2020

bronchial asthma, cluster analysis, health resort medical rehabilitation, phenotypes

In Advances in clinical and experimental medicine : official organ Wroclaw Medical University

Machoy Monika Elżbieta, Szyszka-Sommerfeld Liliana, Vegh Andras, Gedrange Tomasz, Woźniak Krzysztof

2020-Mar-24

CDSS, artificial intelligence, clinical decision support systems, dentistry, machine learning

In Bioinformatics (Oxford, England)

MOTIVATION : Protein Structural Annotations are essential abstractions to deal with the prediction of Protein Structures. Many increasingly sophisticated Protein Structural Annotations have been devised in the last few decades. However the need for annotations that are easy to compute, process and predict has not diminished. This is especially true for protein structures that are hardest to predict such as novel folds.

RESULTS : We propose Brewery, a suite of ab initio predictors of 1D Protein Structural Annotations. Brewery uses multiple sources of evolutionary information to achieve state-of-the-art predictions of Secondary Structure, Structural Motifs, Relative Solvent Accessibility and Contact Density.

AVAILABILITY : The web server, standalone program, Docker image and training sets of Brewery are available at http://distilldeep.ucd.ie/brewery/.

Torrisi Mirko, Pollastri Gianluca

2020-Mar-24

In International journal of molecular sciences ; h5-index 102.0

Ancuceanu Robert, Hovanet Marilena Viorica, Anghel Adriana Iuliana, Furtunescu Florentina, Neagu Monica, Constantin Carolina, Dinu Mihaela

2020-Mar-19

DILI, DILIrank, QSAR, drug hepatotoxicity, in silico, nested cross-validation, virtual screening

In Bioinformatics (Oxford, England)

MOTIVATION : Biological pathway is important curated knowledge of biological processes. Thus, cancer subtype classification based on pathways will be very useful to understand differences in biological mechanisms among cancer subtypes. However, pathways include only a fraction of the entire gene set, only 1/3 of human genes in KEGG, and pathways are fragmented. For this reason, there are few computational methods to use pathways for cancer subtype classification.

RESULTS : We present an explainable deep learning model with attention mechanism and network propagation for cancer subtype classification. Each pathway is modeled by a graph convolutional network. then, a multi-attention based ensemble model combines several hundreds of pathways in an explainable manner. Lastly, network propagation on pathway-gene network explains why gene expression profiles in subtypes are different. In experiments with five TCGA cancer data sets, our method achieved very good classification accuracies and, additionally, identified subtype-specific pathways and biological functions.

SUPPLEMENTARY INFORMATION : Supplementary data are available at Bioinformatics online.

Lee Sangseon, Lim Sangsoo, Lee Taeheon, Sung Inyoung, Kim Sun

2020-Mar-24

In Endocrinology and metabolism (Seoul, Korea)

Hong Namki, Park Heajeong, Rhee Yumie

2020-Mar

Adrenal, Artificial intelligence, Deep learning, Diabetes, Endocrinology, Machine learning, Metabolism, Osteoporosis, Pituitary, Thyroid

In NMR in biomedicine ; h5-index 41.0

Jung Woojin, Bollmann Steffen, Lee Jongho

2020-Mar-23

background field correction, deep learning, dipole inversion, quantitative susceptibility mapping, unwrapping

In Journal of digital imaging

Zeiser Felipe André, da Costa Cristiano André, Zonta Tiago, Marques Nuno M C, Roehe Adriana Vial, Moreno Marcelo, da Rosa Righi Rodrigo

2020-Mar-23

Breast cancer, Computer-aided detection, Deep learning, Fully convolutional network, Segmentation, U-Net

In Psychological research

Spatola Nicolas, Normand Alice

2020-Mar-21

Cognitive control, Human–machine interaction, Logical reasoning, Social comparison

In APL bioengineering

Yu Chi-Hua, Buehler Markus J

2020-Mar

In Science advances

Kiesow Hannah, Dunbar Robin I M, Kable Joseph W, Kalenscher Tobias, Vogeley Kai, Schilbach Leonhard, Marquand Andre F, Wiecki Thomas V, Bzdok Danilo

2020-Mar

In Journal of medical imaging (Bellingham, Wash.)

Mattonen Sarah A, Gude Dev, Echegaray Sebastian, Bakr Shaimaa, Rubin Daniel L, Napel Sandy

2020-Jul

feature extraction, machine learning, medical image analysis, processing pipeline, radiomics

In Journal of medical imaging (Bellingham, Wash.)

Whiteley William, Luk Wing K, Gregor Jens

2020-May

deep learning, image reconstruction, medical imaging, neural network, positron emission tomography

In PeerJ

Background : This study assesses the feasibility of using machine learning methods such as Random Forests (RF), Artificial Neural Networks (ANN), Support Vector Regression (SVR) and Self-Organizing Feature Maps (SOM) to identify and determine factors associated with hypertensive patients' adherence levels. Hypertension is the medical term for systolic and diastolic blood pressure higher than 140/90 mmHg. A conventional medication adherence scale was used to identify patients' adherence to their prescribed medication. Using machine learning applications to predict precise numeric adherence scores in hypertensive patients has not yet been reported in the literature.

Methods : Data from 160 hypertensive patients from a tertiary hospital in Kuala Lumpur, Malaysia, were used in this study. Variables were ranked based on their significance to adherence levels using the RF variable importance method. The backward elimination method was then performed using RF to obtain the variables significantly associated with the patients' adherence levels. RF, SVR and ANN models were developed to predict adherence using the identified significant variables. Visualizations of the relationships between hypertensive patients' adherence levels and variables were generated using SOM.

Result : Machine learning models constructed using the selected variables reported RMSE values of 1.42 for ANN, 1.53 for RF, and 1.55 for SVR. The accuracy of the dichotomised scores, calculated based on a percentage of correctly identified adherence values, was used as an additional model performance measure, resulting in accuracies of 65% (ANN), 78% (RF) and 79% (SVR), respectively. The Wilcoxon signed ranked test reported that there was no significant difference between the predictions of the machine learning models and the actual scores. The significant variables identified from the RF variable importance method were educational level, marital status, General Overuse, monthly income, and Specific Concern.

Conclusion : This study suggests an effective alternative to conventional methods in identifying the key variables to understand hypertensive patients' adherence levels. This can be used as a tool to educate patients on the importance of medication in managing hypertension.

Aziz Firdaus, Malek Sorayya, Mhd Ali Adliah, Wong Mee Sieng, Mosleh Mogeeb, Milow Pozi

2020

Adherence level, Artificial neural network, Hypertension, Random forest, Self-organizing Map (SOM), Support Vector Regression, Variable importance

In International journal of environmental research and public health ; h5-index 73.0

Li Sijia, Wang Yilin, Xue Jia, Zhao Nan, Zhu Tingshao

2020-Mar-19

cognition, emotion, mental health, public health emergencies, word frequency analysis

In Biomedical optics express

Jiang Zhe, Huang Zhiyu, Qiu Bin, Meng Xiangxi, You Yunfei, Liu Xi, Liu Gangjun, Zhou Chuangqing, Yang Kun, Maier Andreas, Ren Qiushi, Lu Yanye

2020-Mar-01

In Biomedical optics express

Halicek Martin, Dormer James D, Little James V, Chen Amy Y, Fei Baowei

2020-Mar-01

In Biomedical optics express

Zhan Qi, Wang Wenjin, de Haan Gerard

2020-Mar-01

In Biomedical optics express

Unger Jakob, Hebisch Christoph, Phipps Jennifer E, Lagarto João L, Kim Hanna, Darrow Morgan A, Bold Richard J, Marcu Laura

2020-Mar-01

In Biomedical optics express

Dardikman-Yoffe Gili, Roitshtain Darina, Mirsky Simcha K, Turko Nir A, Habaza Mor, Shaked Natan T

2020-Feb-01

In Biomedical optics express

Liu Wenquan, Zhang Rui, Ling Yu, Tang Hongping, She Rongbin, Wei Guanglu, Gong Xiaojing, Lu Yuanfu

2020-Feb-01

In Digital health

Objective : To understand the therapeutic processes associated with the helpfulness of an online relational agent intervention, Manage Your Life Online (MYLO).

Methods : Fifteen participants experiencing a mental health related problem used Manage Your Life Online for 2 weeks. At follow-up, the participants each identified two helpful and two unhelpful questions posed by Manage Your Life Online within a single intervention session. Qualitative interviews were conducted and analyzed using thematic and content analysis to gain insight into the process of therapy with Manage Your Life Online.

Results : MYLO appeared acceptable to participants with a range of presenting problems. Questions enabling free expression, increased awareness, and new insights were key to a helpful intervention. The findings were consistent with the core processes of therapeutic change, according to Perceptual Control Theory, a unifying theory of psychological distress. Questions that elicited intense emotions, were repetitive, confusing, or inappropriate were identified as unhelpful and were associated with disengagement or loss of faith in Manage Your Life Online.

Conclusions : The findings provide insight into the likely core therapy processes experienced as helpful or hindering and outlines further ways to optimize acceptability of Manage Your Life Online.

Gaffney Hannah, Mansell Warren, Tai Sara

Mental health, artificial intelligence, computer-assisted, conversational agent, psychotherapeutic processes, psychotherapy, relational agent, therapy

In Archives of public health = Archives belges de sante publique

Background : This article describes the design of an intervention study that focuses on whether and to what degree culturally competent social robots can improve health and well-being related outcomes among older adults residing long-term care homes. The trial forms the final stage of the international, multidisciplinary CARESSES project aimed at designing, developing and evaluating culturally competent robots that can assist older people according to the culture of the individual they are supporting. The importance of cultural competence has been demonstrated in previous nursing literature to be key towards improving health outcomes among patients.

Method : This study employed a mixed-method, single-blind, parallel-group controlled before-and-after experimental trial design that took place in England and Japan. It aimed to recruit 45 residents of long-term care homes aged ≥65 years, possess sufficient cognitive and physical health and who self-identify with the English, Indian or Japanese culture (n = 15 each). Participants were allocated to either the experimental group, control group 1 or control group 2 (all n = 15). Those allocated to the experimental group or control group 1 received a Pepper robot programmed with the CARESSES culturally competent artificial intelligence (experimental group) or a limited version of this software (control group 1) for 18 h across 2 weeks. Participants in control group 2 did not receive a robot and continued to receive care as usual. Participants could also nominate their informal carer(s) to participate. Quantitative data collection occurred at baseline, after 1 week of use, and after 2 weeks of use with the latter time-point also including qualitative semi-structured interviews that explored their experience and perceptions further. Quantitative outcomes of interest included perceptions of robotic cultural competence, health-related quality of life, loneliness, user satisfaction, attitudes towards robots and caregiver burden.

Discussion : This trial adds to the current preliminary and limited pool of evidence regarding the benefits of socially assistive robots for older adults which to date indicates considerable potential for improving outcomes. It is the first to assess whether and to what extent cultural competence carries importance in generating improvements to well-being.

Trial registration : Name of the registry: ClinicalTrials.govTrial registration number: NCT03756194.Date of registration: 28 November 2018. URL of trial registry record.

Papadopoulos Chris, Hill Tetiana, Battistuzzi Linda, Castro Nina, Nigath Abiha, Randhawa Gurch, Merton Len, Kanoria Sanjeev, Kamide Hiroko, Chong Nak-Young, Hewson David, Davidson Rosemary, Sgorbissa Antonio

2020

Artificial intelligence, CARESSES, Cultural competence, Culturally competent robots, Social robotics, Study protocol

In Health information science and systems

Pasha Akram, Latha P H

2020-Dec

Binary particle swarm optimization, Bio-inspired computing, Classification, Data mining, Dimensionality reduction, Feature selection, Genetic algorithm, Machine learning

In Studies in mycology

Haridas S, Albert R, Binder M, Bloem J, LaButti K, Salamov A, Andreopoulos B, Baker S E, Barry K, Bills G, Bluhm B H, Cannon C, Castanera R, Culley D E, Daum C, Ezra D, González J B, Henrissat B, Kuo A, Liang C, Lipzen A, Lutzoni F, Magnuson J, Mondo S J, Nolan M, Ohm R A, Pangilinan J, Park H-J, Ramírez L, Alfaro M, Sun H, Tritt A, Yoshinaga Y, Zwiers L-H, Turgeon B G, Goodwin S B, Spatafora J W, Crous P W, Grigoriev I V

2020-Jun

Aulographales Crous, Spatafora, Haridas & Grigoriev, Coniosporiaceae Crous, Spatafora, Haridas & Grigoriev, Coniosporiales Crous, Spatafora, Haridas & Grigoriev, Eremomycetales Crous, Spatafora, Haridas & Grigoriev, Fungal evolution, Genome-based prediction, Lineolataceae Crous, Spatafora, Haridas & Grigoriev, Lineolatales Crous, Spatafora, Haridas & Grigoriev, Machine-learning, New taxa, Rhizodiscinaceae Crous, Spatafora, Haridas & Grigoriev

In International journal of environmental research and public health ; h5-index 73.0

Goulier Laura, Paas Bastian, Ehrnsperger Laura, Klemm Otto

2020-Mar-19

ANN, acoustic, ammonia, deep learning, nitrogen oxides, ozone, particulate matter, prediction, sound, traffic

In International journal of environmental research and public health ; h5-index 73.0

Li Sijia, Wang Yilin, Xue Jia, Zhao Nan, Zhu Tingshao

2020-Mar-19

cognition, emotion, mental health, public health emergencies, word frequency analysis

ArXiv Preprint

Joseph Bullock, Alexandra, Luccioni, Katherine Hoffmann Pham, Cynthia Sin Nga Lam, Miguel Luengo-Oroz

2020-03-25

In Nuclear medicine and molecular imaging

Wong Teck Huat, Shagera Qaid Ahmed, Ryoo Hyun Gee, Ha Seunggyun, Lee Dong Soo

2020-Feb

Acetazolamide SPECT, Brain perfusion, Carotid artery stenosis, Deep learning, Moyamoya disease, Vascular reserve

In Plant methods

Background : High throughput non-destructive phenotyping is emerging as a significant approach for phenotyping germplasm and breeding populations for the identification of superior donors, elite lines, and QTLs. Detection and counting of spikes, the grain bearing organs of wheat, is critical for phenomics of a large set of germplasm and breeding lines in controlled and field conditions. It is also required for precision agriculture where the application of nitrogen, water, and other inputs at this critical stage is necessary. Further, counting of spikes is an important measure to determine yield. Digital image analysis and machine learning techniques play an essential role in non-destructive plant phenotyping analysis.

Results : In this study, an approach based on computer vision, particularly object detection, to recognize and count the number of spikes of the wheat plant from the digital images is proposed. For spike identification, a novel deep-learning network, SpikeSegNet, has been developed by combining two proposed feature networks: Local Patch extraction Network (LPNet) and Global Mask refinement Network (GMRNet). In LPNet, the contextual and spatial features are learned at the local patch level. The output of LPNet is a segmented mask image, which is further refined at the global level using GMRNet. Visual (RGB) images of 200 wheat plants were captured using LemnaTec imaging system installed at Nanaji Deshmukh Plant Phenomics Centre, ICAR-IARI, New Delhi. The precision, accuracy, and robustness (F₁ score) of the proposed approach for spike segmentation are found to be 99.93%, 99.91%, and 99.91%, respectively. For counting the number of spikes, "analyse particles"-function of imageJ was applied on the output image of the proposed SpikeSegNet model. For spike counting, the average precision, accuracy, and robustness are 99%, 95%, and 97%, respectively. SpikeSegNet approach is tested for robustness with illuminated image dataset, and no significant difference is observed in the segmentation performance.

Conclusion : In this study, a new approach called as SpikeSegNet has been proposed based on combined digital image analysis and deep learning techniques. A dedicated deep learning approach has been developed to identify and count spikes in the wheat plants. The performance of the approach demonstrates that SpikeSegNet is an effective and robust approach for spike detection and counting. As detection and counting of wheat spikes are closely related to the crop yield, and the proposed approach is also non-destructive, it is a significant step forward in the area of non-destructive and high-throughput phenotyping of wheat.

Misra Tanuj, Arora Alka, Marwaha Sudeep, Chinnusamy Viswanathan, Rao Atmakuri Ramakrishna, Jain Rajni, Sahoo Rabi Narayan, Ray Mrinmoy, Kumar Sudhir, Raju Dhandapani, Jha Ranjeet Ranjan, Nigam Aditya, Goel Swati

2020

Deep learning, Encoder-decoder deep network, Image analysis, Non-destructive plant phenotyping, Wheat spikes identification and count

In Journal of thoracic imaging

PURPOSE : Pneumonia is a common clinical diagnosis for which chest radiographs are often an important part of the diagnostic workup. Deep learning has the potential to expedite and improve the clinical interpretation of chest radiographs. While earlier approaches have emphasized the feasibility of "binary classification" to accomplish this task, alternative strategies may be possible. We explore the feasibility of a "semantic segmentation" deep learning approach to highlight the potential foci of pneumonia on frontal chest radiographs.

MATERIALS AND METHODS : In this retrospective study, we trained a U-net convolutional neural network (CNN) to predict pixel-wise probability maps for pneumonia using a public data set provided by the Radiological Society of North America (RSNA) comprised of 22,000 radiographs and radiologist-defined bounding boxes. We reserved 3684 radiographs as an independent validation data set and assessed overall performance for localization using Dice overlap and classification performance using the area under the receiver-operator characteristic curve.

RESULTS : For classification/detection of pneumonia, area under the receiver-operator characteristic curve on frontal radiographs was 0.854 with a sensitivity of 82.8% and specificity of 72.6%. Using this strategy of neural network training, probability maps localized pneumonia to lung parenchyma for essentially all validation cases. For segmentation of pneumonia for positive cases, predicted probability maps had a mean Dice score (±SD) of 0.603±0.204, and 60.0% of these had a Dice score >0.5.

CONCLUSIONS : A "semantic segmentation" deep learning approach can provide a probabilistic map to assist in the diagnosis of pneumonia. In combination with the patient's history, clinical findings and other imaging, this strategy may help expedite and improve diagnosis.

Hurt Brian, Yen Andrew, Kligerman Seth, Hsiao Albert

2020-Mar-20

In Journal of thoracic imaging

Sharma Puneet, Suehling Michael, Flohr Thomas, Comaniciu Dorin

2020-Mar-20

In Critical care medicine ; h5-index 87.0

OBJECTIVES : As the performance of a conventional track and trigger system in a rapid response system has been unsatisfactory, we developed and implemented an artificial intelligence for predicting in-hospital cardiac arrest, denoted the deep learning-based early warning system. The purpose of this study was to compare the performance of an artificial intelligence-based early warning system with that of conventional methods in a real hospital situation.

DESIGN : Retrospective cohort study.

SETTING : This study was conducted at a hospital in which deep learning-based early warning system was implemented.

PATIENTS : We reviewed the records of adult patients who were admitted to the general ward of our hospital from April 2018 to March 2019.

INTERVENTIONS : The study population included 8,039 adult patients. A total 83 events of deterioration occurred during the study period. The outcome was events of deterioration, defined as cardiac arrest and unexpected ICU admission. We defined a true alarm as an alarm occurring within 0.5-24 hours before a deteriorating event.

MEASUREMENTS AND MAIN RESULTS : We used the area under the receiver operating characteristic curve, area under the precision-recall curve, number needed to examine, and mean alarm count per day as comparative measures. The deep learning-based early warning system (area under the receiver operating characteristic curve, 0.865; area under the precision-recall curve, 0.066) outperformed the modified early warning score (area under the receiver operating characteristic curve, 0.682; area under the precision-recall curve, 0.010) and reduced the number needed to examine and mean alarm count per day by 69.2% and 59.6%, respectively. At the same specificity, deep learning-based early warning system had up to 257% higher sensitivity than conventional methods.

CONCLUSIONS : The developed artificial intelligence based on deep-learning, deep learning-based early warning system, accurately predicted deterioration of patients in a general ward and outperformed conventional methods. This study showed the potential and effectiveness of artificial intelligence in an rapid response system, which can be applied together with electronic health records. This will be a useful method to identify patients with deterioration and help with precise decision-making in daily practice.

Cho Kyung-Jae, Kwon Oyeon, Kwon Joon-Myoung, Lee Yeha, Park Hyunho, Jeon Ki-Hyun, Kim Kyung-Hee, Park Jinsik, Oh Byung-Hee

2020-Apr

In Current opinion in nephrology and hypertension

PURPOSE OF REVIEW : Successful integration of artificial intelligence into extant clinical workflows is contingent upon a number of factors including clinician comprehension and interpretation of computer vision. This article discusses how image analysis and machine learning have enabled comprehensive characterization of kidney morphology for development of automated diagnostic and prognostic renal pathology applications.

RECENT FINDINGS : The primordial digital pathology informatics work employed classical image analysis and machine learning to prognosticate renal disease. Although this classical approach demonstrated tremendous potential, subsequent advancements in hardware technology rendered artificial neural networks '(ANNs) the method of choice for machine vision in computational pathology'. Offering rapid and reproducible detection, characterization and classification of kidney morphology, ANNs have facilitated the development of diagnostic and prognostic applications. In addition, modern machine learning with ANNs has revealed novel biomarkers in kidney disease, demonstrating the potential for machine vision to elucidate novel pathologic mechanisms beyond extant clinical knowledge.

SUMMARY : Despite the revolutionary developments potentiated by modern machine learning, several challenges remain, including data quality control and curation, image annotation and ontology, integration of multimodal data and interpretation of machine vision or 'opening the black box'. Resolution of these challenges will not only revolutionize diagnostic pathology but also pave the way for precision medicine and integration of artificial intelligence in the process of care.

Santo Briana A, Rosenberg Avi Z, Sarder Pinaki

2020-Mar-19

In Computers, informatics, nursing : CIN

Hu Ya-Han, Lee Yi-Lien, Kang Ming-Feng, Lee Pei-Ju

2020-Mar-19

In Current opinion in ophthalmology

PURPOSE OF REVIEW : The aim of this article is to review and discuss the history, current state, and future implications of promising biomedical offerings in the field of retina.

RECENT FINDINGS : The technologies discussed are some of the more recent promising biomedical developments within the field of retina. There is a US Food and Drug Administration-approved gene therapy product and artificial intelligence device for retina, with many other offerings in the pipeline.

SUMMARY : Signaling pathway therapies, genetic therapies, mitochondrial therapies, and artificial intelligence have shaped retina care as we know it and are poised to further impact the future of retina care. Retina specialists have the privilege and responsibility of shaping this future for the visual health of current and future generations.

Wood Edward H, Korot Edward, Storey Philip P, Muscat Stephanie, Williams George A, Drenser Kimberly A

2020-Mar-19

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

Koenecke Allison, Nam Andrew, Lake Emily, Nudell Joe, Quartey Minnie, Mengesha Zion, Toups Connor, Rickford John R, Jurafsky Dan, Goel Sharad

2020-Mar-23

fair machine learning, natural language processing, speech-to-text

In BMJ open

AIMS : We conducted a systematic review assessing the reporting quality of studies validating models based on machine learning (ML) for clinical diagnosis, with a specific focus on the reporting of information concerning the participants on which the diagnostic task was evaluated on.

METHOD : Medline Core Clinical Journals were searched for studies published between July 2015 and July 2018. Two reviewers independently screened the retrieved articles, a third reviewer resolved any discrepancies. An extraction list was developed from the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis guideline. Two reviewers independently extracted the data from the eligible articles. Third and fourth reviewers checked, verified the extracted data as well as resolved any discrepancies between the reviewers.

RESULTS : The search results yielded 161 papers, of which 28 conformed to the eligibility criteria. Detail of data source was reported in 24 of the 28 papers. For all of the papers, the set of patients on which the ML-based diagnostic system was evaluated was partitioned from a larger dataset, and the method for deriving such set was always reported. Information on the diagnostic/non-diagnostic classification was reported well (23/28). The least reported items were the use of reporting guideline (0/28), distribution of disease severity (8/28 patient flow diagram (10/28) and distribution of alternative diagnosis (10/28). A large proportion of studies (23/28) had a delay between the conduct of the reference standard and ML tests, while one study did not and four studies were unclear. For 15 studies, it was unclear whether the evaluation group corresponded to the setting in which the ML test will be applied to.

CONCLUSION : All studies in this review failed to use reporting guidelines, and a large proportion of them lacked adequate detail on participants, making it difficult to replicate, assess and interpret study findings.

PROSPERO REGISTRATION NUMBER : CRD42018099167.

Yusuf Mohamed, Atal Ignacio, Li Jacques, Smith Philip, Ravaud Philippe, Fergie Martin, Callaghan Michael, Selfe James

2020-Mar-23

clinical prediction, machine learning, medical diagnosis, reporting quality

In Proceedings of SPIE--the International Society for Optical Engineering

Guha Indranil, Nadeem Syed Ahmed, You Chenyu, Zhang Xiaoliu, Levy Steven M, Wang Ge, Torner James C, Saha Punam K

2020-Feb

GAN-CIRCLE, deep learning, high-resolution reconstruction, microstructure, osteoporosis, trabecular bone

In British journal of sports medicine ; h5-index 104.0

Tanisawa Kumpei, Wang Guan, Seto Jane, Verdouka Ioanna, Twycross-Lewis Richard, Karanikolou Antonia, Tanaka Masashi, Borjesson Mats, Di Luigi Luigi, Dohi Michiko, Wolfarth Bernd, Swart Jeroen, Bilzon James Lee John, Badtieva Victoriya, Papadopoulou Theodora, Casasco Maurizio, Geistlinger Michael, Bachl Norbert, Pigozzi Fabio, Pitsiladis Yannis

2020-Mar-22

genes, genetic testing, genetics

In Progress in cardiovascular diseases

Xu Bo, Kocyigit Duygu, Griffin Brian P, Cheng Feixiong

2020-Mar-19

Artificial intelligence, Cardiac computed tomography, Cardiac magnetic resonance, Deep learning, Echocardiography, Machine learning, Nuclear cardiac imaging

In Journal of clinical epidemiology ; h5-index 60.0

OBJECTIVE : We aimed to explore the added value of common machine learning (ML) algorithms for prediction of outcome for moderate and severe traumatic brain injury.

STUDY DESIGN AND SETTING : We performed logistic (LR), lasso, and ridge regression with key baseline predictors in the IMPACT-II database (15 studies, n=11,022). ML algorithms included support vector machines, random forests, gradient boosting machines, and artificial neural networks, and were trained using the same predictors. To assess generalizability of predictions, we performed internal, internal-external, and external validation on the recent CENTER-TBI study (patients with GCS<13, n = 1,554). Both calibration (calibration slope/intercept) and discrimination (AUC) was quantified.

RESULTS : In the IMPACT-II database, 3,332/11,022(30%) died and 5,233(48%) had unfavorable outcome (Glasgow Outcome Scale below 4). In the CENTER-TBI study, 348/1,554(29%) died and 651(54%) had unfavorable outcome. Discrimination and calibration varied widely between the studies, and less so between the studied algorithms. The mean AUC was 0.82 for mortality and 0.77 for unfavorable outcome in CENTER-TBI.

CONCLUSION : ML algorithms may not outperform traditional regression approaches in a low-dimensional setting for outcome prediction after moderate or severe TBI. Similar to regression-based prediction models, ML algorithms should be rigorously validated to ensure applicability to new populations.

Gravesteijn Benjamin Y, Nieboer Daan, Ercole Ari, Lingsma Hester F, Nelson David, van Calster Ben, Steyerberg Ewout W

2020-Mar-19

Cohort study, Data science, Machine learning, Prediction, Prognosis, Traumatic brain injury

In Biological psychiatry ; h5-index 105.0

Habes Mohamad, Grothe Michel J, Tunc Birkan, McMillan Corey, Wolk David A, Davatzikos Christos

2020-Jan-31

Alzheimer’s disease, Brain aging, Clustering, Frontotemporal dementia, Heterogeneity, Lewy body dementias, MRI, Machine learning, Neuroimaging, PET

In Early human development

Scerri Mariella, Grech Victor

2020-Mar-20

ArXiv Preprint

Maxim Vashkevich, Alexander Petrovsky, Yuliya Rushkevich

2020-03-24

In Journal of the International Neuropsychological Society : JINS

OBJECTIVE : To determine how well machine learning algorithms can classify mild cognitive impairment (MCI) subtypes and Alzheimer's disease (AD) using features obtained from the digital Clock Drawing Test (dCDT).

METHODS : dCDT protocols were administered to 163 patients diagnosed with AD(n = 59), amnestic MCI (aMCI; n = 26), combined mixed/dysexecutive MCI (mixed/dys MCI; n = 43), and patients without MCI (non-MCI; n = 35) using standard clock drawing command and copy procedures, that is, draw the face of the clock, put in all of the numbers, and set the hands for "10 after 11." A digital pen and custom software recorded patient's drawings. Three hundred and fifty features were evaluated for maximum information/minimum redundancy. The best subset of features was used to train classification models to determine diagnostic accuracy.

RESULTS : Neural network employing information theoretic feature selection approaches achieved the best 2-group classification results with 10-fold cross validation accuracies at or above 83%, that is, AD versus non-MCI = 91.42%; AD versus aMCI = 91.49%; AD versus mixed/dys MCI = 84.05%; aMCI versus mixed/dys MCI = 84.11%; aMCI versus non-MCI = 83.44%; and mixed/dys MCI versus non-MCI = 85.42%. A follow-up two-group non-MCI versus all MCI patients analysis yielded comparable results (83.69%). Two-group classification analyses were achieved with 25-125 dCDT features depending on group classification. Three- and four-group analyses yielded lower but still promising levels of classification accuracy.

CONCLUSION : Early identification of emergent neurodegenerative illness is criterial for better disease management. Applying machine learning to standard neuropsychological tests promises to be an effective first line screening method for classification of non-MCI and MCI subtypes.

Binaco Russell, Calzaretto Nicholas, Epifano Jacob, McGuire Sean, Umer Muhammad, Emrani Sheina, Wasserman Victor, Libon David J, Polikar Robi

2020-Mar-23

Clock drawing, Cognitive assessment, Machine learning, Mild cognitive impairment, The Digital Clock Drawing Test

ArXiv Preprint

Jevgenij Gamper, Navid Alemi Koohbanani, Simon Graham, Mostafa Jahanifar, Syed Ali Khurram, Ayesha Azam, Katherine Hewitt, Nasir Rajpoot

2020-03-24

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

Song Minryung R, Lee Sang Wan

2020-Mar-10

Habit, Pearce-Hall model, Prediction error, Salience, Striatum, Temporal-difference learning model

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

Baldeon Calisto Maria, Lai-Yuen Susana K

2020-Mar-10

Deep learning, Hyperparameter optimization, Medical image segmentation, Multiobjective optimization, Neural architecture search

In Environment international

BACKGROUND : In the screening phase of systematic review, researchers use detailed inclusion/exclusion criteria to decide whether each article in a set of candidate articles is relevant to the research question under consideration. A typical review may require screening thousands or tens of thousands of articles in and can utilize hundreds of person-hours of labor.

METHODS : Here we introduce SWIFT-Active Screener, a web-based, collaborative systematic review software application, designed to reduce the overall screening burden required during this resource-intensive phase of the review process. To prioritize articles for review, SWIFT-Active Screener uses active learning, a type of machine learning that incorporates user feedback during screening. Meanwhile, a negative binomial model is employed to estimate the number of relevant articles remaining in the unscreened document list. Using a simulation involving 26 diverse systematic review datasets that were previously screened by reviewers, we evaluated both the document prioritization and recall estimation methods.

RESULTS : On average, 95% of the relevant articles were identified after screening only 40% of the total reference list. In the 5 document sets with 5,000 or more references, 95% recall was achieved after screening only 34% of the available references, on average. Furthermore, the recall estimator we have proposed provides a useful, conservative estimate of the percentage of relevant documents identified during the screening process.

CONCLUSION : SWIFT-Active Screener can result in significant time savings compared to traditional screening and the savings are increased for larger project sizes. Moreover, the integration of explicit recall estimation during screening solves an important challenge faced by all machine learning systems for document screening: when to stop screening a prioritized reference list. The software is currently available in the form of a multi-user, collaborative, online web application.

Howard Brian E, Phillips Jason, Tandon Arpit, Maharana Adyasha, Elmore Rebecca, Mav Deepak, Sedykh Alex, Thayer Kristina, Merrick B Alex, Walker Vickie, Rooney Andrew, Shah Ruchir R

2020-Mar-20

Active learning, Document screening, Evidence mapping, Machine learning, Recall estimation, Systematic review

In PloS one ; h5-index 176.0

Soliman Hatem

2020

In PloS one ; h5-index 176.0

Zhou Mengshi, Xu Rong, Kaelber David C, Gurney Mark E

2020

In Journal of the American Heart Association ; h5-index 70.0

Kwon Joon-Myoung, Lee Soo Youn, Jeon Ki-Hyun, Lee Yeha, Kim Kyung-Hee, Park Jinsik, Oh Byung-Hee, Lee Myong-Mook

2020-Apr-07

aortic valve stenosis, deep learning, electrocardiography

ArXiv Preprint

Kengo Tajiri, Yasuhiro Ikeda, Yuusuke Nakano, Keishiro Watanabe

2020-03-24

In Nature protocols

Kohoutová Lada, Heo Juyeon, Cha Sungmin, Lee Sungwoo, Moon Taesup, Wager Tor D, Woo Choong-Wan

2020-Mar-18

In European journal of clinical nutrition ; h5-index 46.0

Harty Patrick S, Sieglinger Breck, Heymsfield Steven B, Shepherd John A, Bruner David, Stratton Matthew T, Tinsley Grant M

2020-Mar-16

In IEEE transactions on cybernetics

Zhang Kuangen, Fu Chenglong, Luo Jianwen, Xiao Wentao, Zhang Wen, Liu Haiyuan, Zhu Jiale, Lu Zeyu, Rong Yiming, de Silva Clarence W

2020-Mar-19

In IEEE transactions on cybernetics

Nguyen Thanh Thi, Nguyen Ngoc Duy, Nahavandi Saeid

2020-Mar-20

In IEEE transactions on neural networks and learning systems

Li Caoyuan, Xie Hong-Bo, Fan Xuhui, Xu Richard Yi Da, Van Huffel Sabine, Mengersen Kerrie

2020-Mar-23

In IEEE transactions on neural networks and learning systems

Gong Zhiqiang, Zhong Ping, Hu Weidong

2020-Mar-19

In IEEE/ACM transactions on computational biology and bioinformatics

Chen Junyi, Hou Junhui, Wong Ka-Chun

2020-Mar-20

In IEEE transactions on ultrasonics, ferroelectrics, and frequency control

Wiacek Alycen, Gonzalez Eduardo, Bell Muyinatu A Lediju

2020-Mar-23

In Journal of chemical information and modeling

Yang Ziyi, Dong Jie, Yang Zhijiang, Lu Aiping, Hou Tingjun, Cao Dongsheng

2020-Mar-23

In Environmental science & technology ; h5-index 132.0

Romeiko Xiaobo Xue, Lee Eun Kyung, Sorunmu Yetunde, Zhang Xuesong

2020-Mar-23

In Clinical linguistics & phonetics ; h5-index 19.0

Speights Atkins Marisha, Bailey Dallin J, Boyce Suzanne E

2020-Mar-23

Database, adult speech, child speech, speech disorders, speech production

ArXiv Preprint

Iroro Orife

2020-03-24

In JMIR medical informatics ; h5-index 23.0

BACKGROUND : Metabolic syndrome is a cluster of disorders that significantly influence the development and deterioration of numerous diseases. FibroScan is an ultrasound device that was recently shown to predict metabolic syndrome with moderate accuracy. However, previous research regarding prediction of metabolic syndrome in subjects examined with FibroScan has been mainly based on conventional statistical models. Alternatively, machine learning, whereby a computer algorithm learns from prior experience, has better predictive performance over conventional statistical modeling.

OBJECTIVE : We aimed to evaluate the accuracy of different decision tree machine learning algorithms to predict the state of metabolic syndrome in self-paid health examination subjects who were examined with FibroScan.

METHODS : Multivariate logistic regression was conducted for every known risk factor of metabolic syndrome. Principal components analysis was used to visualize the distribution of metabolic syndrome patients. We further applied various statistical machine learning techniques to visualize and investigate the pattern and relationship between metabolic syndrome and several risk variables.

RESULTS : Obesity, serum glutamic-oxalocetic transaminase, serum glutamic pyruvic transaminase, controlled attenuation parameter score, and glycated hemoglobin emerged as significant risk factors in multivariate logistic regression. The area under the receiver operating characteristic curve values for classification and regression trees and for the random forest were 0.831 and 0.904, respectively.

CONCLUSIONS : Machine learning technology facilitates the identification of metabolic syndrome in self-paid health examination subjects with high accuracy.

Yu Cheng-Sheng, Lin Yu-Jiun, Lin Chang-Hsien, Wang Sen-Te, Lin Shiyng-Yu, Lin Sanders H, Wu Jenny L, Chang Shy-Shin

2020-Mar-23

controlled attenuation parameter technology, decision tree, machine learning, metabolic syndrome

In Journal of medical Internet research ; h5-index 88.0

BACKGROUND : Scalable and accurate health outcome prediction using electronic health record (EHR) data has gained much attention in research recently. Previous machine learning models mostly ignore relations between different types of clinical data (ie, laboratory components, International Classification of Diseases codes, and medications).

OBJECTIVE : This study aimed to model such relations and build predictive models using the EHR data from intensive care units. We developed innovative neural network models and compared them with the widely used logistic regression model and other state-of-the-art neural network models to predict the patient's mortality using their longitudinal EHR data.

METHODS : We built a set of neural network models that we collectively called as long short-term memory (LSTM) outcome prediction using comprehensive feature relations or in short, CLOUT. Our CLOUT models use a correlational neural network model to identify a latent space representation between different types of discrete clinical features during a patient's encounter and integrate the latent representation into an LSTM-based predictive model framework. In addition, we designed an ablation experiment to identify risk factors from our CLOUT models. Using physicians' input as the gold standard, we compared the risk factors identified by both CLOUT and logistic regression models.

RESULTS : Experiments on the Medical Information Mart for Intensive Care-III dataset (selected patient population: 7537) show that CLOUT (area under the receiver operating characteristic curve=0.89) has surpassed logistic regression (0.82) and other baseline NN models (<0.86). In addition, physicians' agreement with the CLOUT-derived risk factor rankings was statistically significantly higher than the agreement with the logistic regression model.

CONCLUSIONS : Our results support the applicability of CLOUT for real-world clinical use in identifying patients at high risk of mortality.

Rongali Subendhu, Rose Adam J, McManus David D, Bajracharya Adarsha S, Kapoor Alok, Granillo Edgard, Yu Hong

2020-Mar-23

ablation, neural networks, patient mortality, predictive modeling

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

Vasanthi S Mary, Jayasree T

2020-Mar-23

Finger movements, artificial neural network, discrete wavelet transform, pattern recognition, time-domain features

In Ergonomics

Asadi Hamed, Zhou Guoyang, Lee Jae Joong, Aggarwal Vaneet, Yu Denny

2020-Mar-22

Computer Vision, Facial Expressions, High Force Exertions, Machine Learning

In Journal of the International AIDS Society ; h5-index 45.0

INTRODUCTION : Real-time electronic adherence monitoring (EAM) systems could inform on-going risk assessment for HIV viraemia and be used to personalize viral load testing schedules. We evaluated the potential of real-time EAM (transferred via cellular signal) and standard EAM (downloaded via USB cable) in rural Uganda to inform individually differentiated viral load testing strategies by applying machine learning approaches.

METHODS : We evaluated an observational cohort of persons living with HIV and treated with antiretroviral therapy (ART) who were monitored longitudinally with standard EAM from 2005 to 2011 and real-time EAM from 2011 to 2015. Super learner, an ensemble machine learning method, was used to develop a tool for targeting viral load testing to detect viraemia (>1000 copies/ml) based on clinical (CD4 count, ART regimen), viral load and demographic data, together with EAM-based adherence. Using sample-splitting (cross-validation), we evaluated area under the receiver operating characteristic curve (cvAUC), potential for EAM data to selectively defer viral load tests while minimizing delays in viraemia detection, and performance compared to WHO-recommended testing schedules.

RESULTS : In total, 443 persons (1801 person-years) and 485 persons (930 person-years) contributed to standard and real-time EAM analyses respectively. In the 2011 to 2015 dataset, addition of real-time EAM (cvAUC: 0.88; 95% CI: 0.83, 0.93) significantly improved prediction compared to clinical/demographic data alone (cvAUC: 0.78; 95% CI: 0.72, 0.86; p = 0.03). In the 2005 to 2011 dataset, addition of standard EAM (cvAUC: 0.77; 95% CI: 0.72, 0.81) did not significantly improve prediction compared to clinical/demographic data alone (cvAUC: 0.70; 95% CI: 0.64, 0.76; p = 0.08). A hypothetical testing strategy using real-time EAM to guide deferral of viral load tests would have reduced the number of tests by 32% while detecting 87% of viraemia cases without delay. By comparison, the WHO-recommended testing schedule would have reduced the number of tests by 69%, but resulted in delayed detection of viraemia a mean of 74 days for 84% of individuals with viraemia. Similar rules derived from standard EAM also resulted in potential testing frequency reductions.

CONCLUSIONS : Our machine learning approach demonstrates potential for combining EAM data with other clinical measures to develop a selective testing rule that reduces number of viral load tests ordered, while still identifying those at highest risk for viraemia.

Benitez Alejandra E, Musinguzi Nicholas, Bangsberg David R, Bwana Mwebesa B, Muzoora Conrad, Hunt Peter W, Martin Jeffrey N, Haberer Jessica E, Petersen Maya L

2020-Mar

adherence, machine learning, real-time adherence monitoring, viraemia, viral load monitoring, virologic failure

In Medical physics ; h5-index 59.0

PURPOSE : Accurate identification of the prostatic urethra and bladder can help determine dosing and evaluate urinary toxicity during intensity-modulated radiation therapy (IMRT) planning in patients with localized prostate cancer. However, it is challenging to locate the prostatic urethra in planning CT (pCT). In the present study, we developed a multi-atlas-based auto-segmentation method for prostatic urethra identification using deformable image registration accuracy prediction with machine learning (ML) and assessed its feasibility.

METHODS : We examined 120 patients with prostate cancer treated with IMRT. All patients underwent temporary urinary catheter placement for identification and contouring of the prostatic urethra in pCT images (ground truth). Our method comprises the following three steps: (1) select four atlas datasets from the atlas datasets using the deformable image registration (DIR) accuracy prediction model, (2) deform them by structure-based DIR, (3) and propagate urethra contour using displacement vector field calculated by the DIR. In (1), for identifying suitable datasets, we used the trained support vector machine regression (SVR) model and five feature descriptors (e.g., prostate volume) to increase DIR accuracy. This method was trained/validated using 100 patients and performance was evaluated within an independent test set of 20 patients. Five-fold cross-validation was used to optimize the hype parameters of the DIR accuracy prediction model. We assessed the accuracy of our method by comparing it with those of two others: Acosta's method-based patient selection (previous study method, by Acosta et al.), and the Waterman's method (defines the prostatic urethra based on the center of the prostate, by Waterman et al.). We used the centerlines distance (CLD) between the ground truth and the predicted prostatic urethra as the evaluation index.

RESULTS : The CLD in the entire prostatic urethra was 2.09 ± 0.89 mm (our proposed method), 2.77 ± 0.99 mm (Acosta et al., p = 0.022), and 3.47 ± 1.19 mm (Waterman et al., p< 0.001); our proposed method showed the highest accuracy. In segmented CLD, CLD in the top 1/3 segment was highly improved from that of Waterman et.al. and was slightly improved from that of Acosta et.al., with results of 2.49 ± 1.78 mm (our proposed method), 2.95 ± 1.75 mm (Acosta et al., p = 0.42), and 5.76 ± 3.09 mm (Waterman et al., p < 0.001).

CONCLUSIONS : We developed a DIR accuracy prediction model-based multi-atlas-based auto-segmentation method for prostatic urethra identification. Our method identified prostatic urethra with mean error of 2.09 mm, likely due to combined effects of SVR model employment in patient selection, modified atlas dataset characteristics and DIR algorithm. Our method has potential utility in prostate cancer IMRT and can replace use of temporary indwelling urinary catheters.

Takagi Hisamichi, Kadoya Noriyuki, Kajikawa Tomohiro, Tanaka Shohei, Takayama Yoshiki, Chiba Takahito, Ito Kengo, Dobashi Suguru, Takeda Ken, Jingu Keiichi

2020-Mar-22

auto-segmentation, deformable image registration, machine learning, prostate cancer, radiotherapy

In Journal of animal science

Aiken Vera Cardoso Ferreira, Fernandes Arthur Francisco Araújo, Passafaro Tiago Luciano, Acedo Juliano Sabella, Dias Fábio Guerra, Dórea João Ricardo Rebouças, Rosa Guilherme Jordão de Magalhães

2020-Mar-23

Brazil, beef, forecasting, large scale data, machine learning

In PeerJ

Martín-Perea David M, Courtenay Lloyd A, Domingo M Soledad, Morales Jorge

2020

Archaeological site, Archaeostratigraphy, Batallones Butte sites, Machine Learning, Palaeontological site, Palaeostratigraphy, Spatial data

In F1000Research

King Christopher R, Abraham Joanna, Kannampallil Thomas G, Fritz Bradley A, Ben Abdallah Arbi, Chen Yixin, Henrichs Bernadette, Politi Mary, Torres Brian A, Mickle Angela, Budelier Thaddeus P, McKinnon Sherry, Gregory Stephen, Kheterpal Sachin, Wildes Troy, Avidan Michael S

2019

Anesthesiology, Artificial Intelligence, Decision Support, Forecasting Algorithms, Machine Learning, Randomized Controlled Trial, Telemedicine

In F1000Research

Martinez Viedma Maria Del Pilar, Kose Nurgun, Parham Leda, Balmaseda Angel, Kuan Guillermina, Lorenzana Ivette, Harris Eva, Crowe James E, Pickett Brett E

2019

B-cell epitopes, Zika virus, bioinformatics, mosquito-borne viruses, peptide arrays, serodiagnostic

In La Radiologia medica

PURPOSE : To test the technical reproducibility of acquisition and scanners of CT image-based radiomics model for early recurrent hepatocellular carcinoma (HCC).

METHODS : We included primary HCC patient undergone curative therapies, using early recurrence as endpoint. Four datasets were constructed: 109 images from hospital #1 for training (set 1: 1-mm image slice thickness), 47 images from hospital #1 for internal validation (sets 2 and 3: 1-mm and 10-mm image slice thicknesses, respectively), and 47 images from hospital #2 for external validation (set 4: vastly different from training dataset). A radiomics model was constructed. Radiomics technical reproducibility was measured by overfitting and calibration deviation in external validation dataset. The influence of slice thickness on reproducibility was evaluated in two internal validation datasets.

RESULTS : Compared with set 1, the model in set 2 indicated favorable prediction efficiency (the area under the curve 0.79 vs. 0.80, P = 0.47) and good calibration (unreliability statistic U: P = 0.33). However, in set 4, significant overfitting (0.63 vs. 0.80, P < 0.01) and calibration deviation (U: P < 0.01) were observed. Similar poor performance was also observed in set 3 (0.56 vs. 0.80, P = 0.02; U: P < 0.01).

CONCLUSIONS : CT-based radiomics has poor reproducibility between centers. Image heterogeneity, such as slice thickness, can be a significant influencing factor.

Hu Hang-Tong, Shan Quan-Yuan, Chen Shu-Ling, Li Bin, Feng Shi-Ting, Xu Er-Jiao, Li Xin, Long Jian-Yan, Xie Xiao-Yan, Lu Ming-de, Kuang Ming, Shen Jing-Xian, Wang Wei

2020-Mar-21

Hepatocellular carcinoma, Radiomics, Reproducibility, Tomography

In Medical & biological engineering & computing ; h5-index 32.0

Arora Ridhi, Rai Prateek Kumar, Raman Balasubramanian

2020-Mar-21

Breast lesion, Computer-aided diagnosis, Feature extraction, Image processing, Medical imaging

In Multiple sclerosis and related disorders

BACKGROUND : Multiple sclerosis is a progressive disease responsible for gait disabilities and cognitive impairment, which affect functional performance. Robot-assisted gait training is an emerging training method to facilitate body-weight-supported treadmill training in many neurologic diseases. Through this study, we aimed to determine the efficacy of robot-assisted gait training in patients with multiple sclerosis.

METHODS : We performed a systematic review and meta-analysis of randomized controlled trials evaluating the effect of robot-assisted gait training for multiple sclerosis. We searched PubMed, EMBASE, the Cochrane Library, and ClinicalTrials.gov registry for articles published before May 2019. The primary outcome was walking performance (gait parameters, balance, and ambulation capability). The secondary outcomes were changes in perceived fatigue, severity of spasticity, global mobility, physical and mental quality of life, severity of pain, activities of daily living, and treatment acceptance.

RESULTS : We identified 10 studies (9 different trials) that included patients with multiple sclerosis undergoing robot-assisted gait training or conventional walk training. The meta-analysis showed comparable effectiveness between robot-assisted gait training and conventional walking therapy in walking performance, quality of life, pain, or activities of daily living. The robot-assisted gait training was even statistically superior to conventional walking therapy in improving perceived fatigue (pooled SMD: 0.34, 95% CI: 0.02-0.67), spasticity (pooled SMD: 0.70, 95% CI: 0.08-1.33, I² = 53%), and global mobility (borderline) after the intervention.

CONCLUSION : Our results provide the most up-to-date evidence regarding the robot-assisted gait training on multiple sclerosis. In addition to the safety and good tolerance, its efficacy on multiple sclerosis is comparable to that of conventional walking training and is even superior in improving fatigue and spasticity.

Yeh Shu-Wei, Lin Li-Fong, Tam Ka-Wai, Tsai Ching-Piao, Hong Chien-Hsiung, Kuan Yi-Chun

2020-Mar-03

Fatigue, Multiple sclerosis, Quality of life, Robot-assisted gait training, Walking performance

In International journal of medical informatics ; h5-index 49.0

BACKGROUND : To explore attitudes about artificial intelligence (AI) among staff who utilized AI-based clinical decision support (CDS).

METHODS : A survey was designed to assess staff attitudes about AI-based CDS tools. The survey was anonymously and voluntarily completed by clinical staff in three primary care outpatient clinics before and after implementation of an AI-based CDS system aimed to improve glycemic control in patients with diabetes as part of a quality improvement project. The CDS identified patients at risk for poor glycemic control and generated intervention recommendations intended to reduce patients' risk.

RESULTS : Staff completed 45 surveys pre-intervention and 38 post-intervention. Following implementation, staff felt that care was better coordinated (11 favorable responses, 14 unfavorable responses pre-intervention; 21 favorable responses, 3 unfavorable responses post-intervention; p < 0.01). However, only 14 % of users would recommend the AI-based CDS. Staff feedback revealed that the most favorable aspect of the CDS was that it promoted team dialog about patient needs (N = 14, 52 %), and the least favorable aspect was inadequacy of the interventions recommended by the CDS.

CONCLUSIONS : AI-based CDS tools that are perceived negatively by staff may reduce staff excitement about AI technology, and hands-on experience with AI may lead to more realistic expectations about the technology's capabilities. In our setting, although AI-based CDS prompted an interdisciplinary discussion about the needs of patients at high risk for poor glycemic control, the interventions recommended by the CDS were often perceived to be poorly tailored, inappropriate, or not useful. Developers should carefully consider tasks that are best performed by AI and those best performed by the patient's care team.

Romero-Brufau Santiago, Wyatt Kirk D, Boyum Patricia, Mickelson Mindy, Moore Matthew, Cognetta-Rieke Cheristi

2019-Dec-30

Artificial, Clinical, Decision support systems, Diabetes mellitus, Intelligence

In Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy

Weng Shizhuang, Tang Peipei, Yuan Hecai, Guo Bingqing, Yu Shuan, Huang Linsheng, Xu Chao

2020-Mar-06

Deep learning network, High-quality rice, Hyperspectral imaging, Multi-feature fusion

In JACC. Cardiovascular imaging

OBJECTIVES : The authors applied unsupervised machine-learning techniques for integrating echocardiographic features of left ventricular (LV) structure and function into a patient similarity network that predicted major adverse cardiac events (MACE) in an individual patient.

BACKGROUND : Patient similarity analysis is an evolving paradigm for precision medicine in which patients are clustered or classified based on their similarities in several clinical features.

METHODS : A retrospective cohort of 866 patients was used to develop a network architecture using 9 echocardiographic features of LV structure and function. The data for 468 patients from 2 prospective cohort registries were then added to test the model's generalizability.

RESULTS : The map of cross-sectional data in the retrospective cohort resulted in a looped patient network that persisted even after the addition of data from the prospective cohort registries. After subdividing the loop into 4 regions, patients in each region showed unique differences in LV function, with Kaplan-Meier curves demonstrating significant differences in MACE-related rehospitalization and death (both p < 0.001). Addition of network information to clinical risk predictors resulted in significant improvements in net reclassification, integrated discrimination, and median risk scores for predicting MACE (p < 0.05 for all). Furthermore, the network predicted the cardiac disease cycle in each of the 96 patients who had second echocardiographic evaluations. An improvement or remaining in low-risk regions was associated with lower MACE-related rehospitalization rates than worsening or remaining in high-risk regions (3% vs. 37%; p < 0.001).

CONCLUSIONS : Patient similarity analysis integrates multiple features of cardiac function to develop a phenotypic network in which patients can be mapped to specific locations associated with specific disease stage and clinical outcomes. The use of patient similarity analysis may have relevance for automated staging of cardiac disease severity, personalized prediction of prognosis, and monitoring progression or response to therapies.

Tokodi Márton, Shrestha Sirish, Bianco Christopher, Kagiyama Nobuyuki, Casaclang-Verzosa Grace, Narula Jagat, Sengupta Partho P

2020-Mar-13

echocardiography, patient similarity, topological data analysis

ArXiv Preprint

David Higgins, Vince I. Madai

2020-03-23

In Early human development

Grech Victor

2020-Mar-18

ArXiv Preprint

Tobias Ross, Annika Reinke, Peter M. Full, Martin Wagner, Hannes Kenngott, Martin Apitz, Hellena Hempe, Diana Mindroc Filimon, Patrick Scholz, Thuy Nuong Tran, Pierangela Bruno, Pablo Arbeláez, Gui-Bin Bian, Sebastian Bodenstedt, Jon Lindström Bolmgren, Laura Bravo-Sánchez, Hua-Bin Chen, Cristina González, Dong Guo, Pål Halvorsen, Pheng-Ann Heng, Enes Hosgor, Zeng-Guang Hou, Fabian Isensee, Debesh Jha, Tingting Jiang, Yueming Jin, Kadir Kirtac, Sabrina Kletz, Stefan Leger, Zhixuan Li, Klaus H. Maier-Hein, Zhen-Liang Ni, Michael A. Riegler, Klaus Schoeffmann, Ruohua Shi, Stefanie Speidel, Michael Stenzel, Isabell Twick, Gutai Wang, Jiacheng Wang, Liansheng Wang, Lu Wang, Yujie Zhang, Yan-Jie Zhou, Lei Zhu, Manuel Wiesenfarth, Annette Kopp-Schneider, Beat P. Müller-Stich, Lena Maier-Hein

2020-03-23

In Early human development

Grech Victor

2020-Mar-18

ArXiv Preprint

Antoine Boutet, Carole Frindel, Sébastien Gambs, Théo Jourdan, Claude Rosin Ngueveu

2020-03-23

In Journal of safety research

INTRODUCTION : This study addressed a gap in the literature - the potential of using autonomous vehicles (AV) to enhance children's mobility. Prior studies documented the perceived benefits and concerns about this prospect, but did not examine the features in AV and support mechanisms that are desired by potential users.

METHOD : An on-line survey was used to collect public opinions within the United States. In the survey, willingness to use AVs for this use case was asked twice to assess if participants changed their mind after being asked about concerns related to this prospect and importance of car features. A combination of statistical and machine-learning methods were used to profile individuals with high versus low post-willingness and to identify variables that differentiated the two groups.

RESULTS : Results indicated that respondents who were lower on their post-willingness to use AVs to transport children were more concerned about how AVs would protect children, how someone could harm the children inside, and whether there would be someone at the destination. In addition, they were less in favor of technology, older in age, and rated car features such as having a designated adult waiting at destination, a camera, and a microphone as relatively required (as opposed to optional). These results highlight potential users' needs and requirements as they think about AVs in the context of parent-children mobility practices. Practical Applications: Relevant stakeholders should develop deployment and implementation plans while taking into account ridership contexts and vulnerable road users who can benefit from enhanced mobility.

Lee Yi-Ching, Hand Somer H, Lilly Hsien

2020-Feb

Autonomous vehicle, Children’s mobility, Ridership context, Safety, Vulnerable road users

ArXiv Preprint

Yikuan Li, Shishir Rao, Abdelaali Hassaine, Rema Ramakrishnan, Yajie Zhu, Dexter Canoy, Gholamreza Salimi-Khorshidi, Thomas Lukasiewicz, Kazem Rahimi

2020-03-23

In British journal of clinical pharmacology ; h5-index 58.0

AIMS : To identify, characterize, and compare all FDA and EMA approvals that included real-world data on efficacy from expanded access programs METHODS: Cross-sectional study of FDA (1955-2018) and EMA (1995-2018) regulatory approval documentation. We automated searching for terms related to expanded access in 22,506 documents using machine learning techniques. We included all approvals where expanded access terms appeared in the regulatory documentation. Our main outcome was the inclusion of expanded access data as evidence of clinical efficacy. Characterization was based on approval date, disease area, orphan designation and whether the evidence was supportive or pivotal.

RESULTS : Expanded access terms appeared in 693 out of 22,506 (3.1%) documents, which referenced 187 approvals. For 39 approvals, data from expanded access programs were used to inform on clinical efficacy. The yearly number of approvals with EA data increased from 1.25 for 1993-2013 to 4.6 from 2014-2018. In 13 cases, these programs formed the main evidence for approval. Of these, patients in expanded access programs formed over half (median 71%, IQR: 34-100) of the total patient population available for efficacy evaluation. All but one (12/13) approvals were granted orphan designation. In 8/13, there were differences between regulators in approval status and valuation of evidence. Strikingly, 4 treatments were granted approval based solely on efficacy from expanded access.

CONCLUSIONS : Sponsors and regulators increasingly include real-world data from expanded access programs in the efficacy profile of a treatment. The indications of the approved treatments are characterized by orphan designation and high unmet medical need.

Polak Tobias B, van Rosmalen Joost, Uyl-de Groot Carin A

2020-Mar-22

Drug Regulation, Effectiveness, Evidence-Based Medicine, Health Policy

In Scientific reports ; h5-index 158.0

Mourad Moustafa, Moubayed Sami, Dezube Aaron, Mourad Youssef, Park Kyle, Torreblanca-Zanca Albertina, Torrecilla José S, Cancilla John C, Wang Jiwu

2020-Mar-20

In Development (Cambridge, England)

Kimmel Jacob C, Hwang Ara B, Scaramozza Annarita, Marshall Wallace F, Brack Andrew S

2020-Mar-20

Aging, Muscle stem cell, Single cell RNA-seq, State transition, Stem cell activation, Timelapse imaging

In Clinical cancer research : an official journal of the American Association for Cancer Research

PURPOSE : Using standard-of-care CT images obtained from patients with a diagnosis of non-small cell lung cancer (NSCLC), we defined radiomics signatures predicting the sensitivity of tumors to nivolumab, docetaxel, and gefitinib.

EXPERIMENTAL DESIGN : Data were collected prospectively and analyzed retrospectively across multicenter clinical trials [nivolumab, n = 92, CheckMate017 (NCT01642004), CheckMate063 (NCT01721759); docetaxel, n = 50, CheckMate017; gefitinib, n = 46, (NCT00588445)]. Patients were randomized to training or validation cohorts using either a 4:1 ratio (nivolumab: 72T:20V) or a 2:1 ratio (docetaxel: 32T:18V; gefitinib: 31T:15V) to ensure an adequate sample size in the validation set. Radiomics signatures were derived from quantitative analysis of early tumor changes from baseline to first on-treatment assessment. For each patient, 1,160 radiomics features were extracted from the largest measurable lung lesion. Tumors were classified as treatment sensitive or insensitive; reference standard was median progression-free survival (NCT01642004, NCT01721759) or surgery (NCT00588445). Machine learning was implemented to select up to four features to develop a radiomics signature in the training datasets and applied to each patient in the validation datasets to classify treatment sensitivity.

RESULTS : The radiomics signatures predicted treatment sensitivity in the validation dataset of each study group with AUC (95 confidence interval): nivolumab, 0.77 (0.55-1.00); docetaxel, 0.67 (0.37-0.96); and gefitinib, 0.82 (0.53-0.97). Using serial radiographic measurements, the magnitude of exponential increase in signature features deciphering tumor volume, invasion of tumor boundaries, or tumor spatial heterogeneity was associated with shorter overall survival.

CONCLUSIONS : Radiomics signatures predicted tumor sensitivity to treatment in patients with NSCLC, offering an approach that could enhance clinical decision-making to continue systemic therapies and forecast overall survival.

Dercle Laurent, Fronheiser Matthew, Lu Lin, Du Shuyan, Hayes Wendy, Leung David K, Roy Amit, Wilkerson Julia, Guo Pingzhen, Fojo Antonio T, Schwartz Lawrence H, Zhao Binsheng

2020-Mar-20

In Ophthalmology ; h5-index 90.0

PURPOSE : Aggressive posterior retinopathy of prematurity (AP-ROP) is a vision-threatening disease with a significant rate of progression to retinal detachment. The purpose of this study was to characterize AP-ROP quantitatively by demographics, rate of disease progression, and a deep learning-based vascular severity score.

DESIGN : Retrospective analysis.

PARTICIPANTS : The Imaging and Informatics in ROP cohort from 8 North American centers, consisting of 947 patients and 5945 clinical eye examinations with fundus images, was used. Pretreatment eyes were categorized by disease severity: none, mild, type 2 or pre-plus, treatment-requiring (TR) without AP-ROP, TR with AP-ROP. Analyses compared TR with AP-ROP and TR without AP-ROP to investigate differences between AP-ROP and other TR disease.

METHODS : A reference standard diagnosis was generated for each eye examination using previously published methods combining 3 independent image-based gradings and 1 ophthalmoscopic grading. All fundus images were analyzed using a previously published deep learning system and were assigned a score from 1 through 9.

MAIN OUTCOME MEASURES : Birth weight, gestational age, postmenstrual age, and vascular severity score.

RESULTS : Infants who demonstrated AP-ROP were more premature by birth weight (617 g vs. 679 g; P = 0.01) and gestational age (24.3 weeks vs. 25.0 weeks; P < 0.01) and reached peak severity at an earlier postmenstrual age (34.7 weeks vs. 36.9 weeks; P < 0.001) compared with infants with TR without AP-ROP. The mean vascular severity score was greatest in TR with AP-ROP infants compared with TR without AP-ROP infants (8.79 vs. 7.19; P < 0.001). Analyzing the severity score over time, the rate of progression was fastest in infants with AP-ROP (P < 0.002 at 30-32 weeks).

CONCLUSIONS : Premature infants in North America with AP-ROP are born younger and demonstrate disease earlier than infants with less severe ROP. Disease severity is quantifiable with a deep learning-based score, which correlates with clinically identified categories of disease, including AP-ROP. The rate of progression to peak disease is greatest in eyes that demonstrate AP-ROP compared with other treatment-requiring eyes. Analysis of quantitative characteristics of AP-ROP may help improve diagnosis and treatment of an aggressive, vision-threatening form of ROP.

Bellsmith Kellyn N, Brown James, Kim Sang Jin, Goldstein Isaac H, Coyner Aaron, Ostmo Susan, Gupta Kishan, Chan R V Paul, Kalpathy-Cramer Jayashree, Chiang Michael F, Campbell J Peter

2020-Feb-07

In Ophthalmology ; h5-index 90.0

PURPOSE : To develop and validate a deep learning model for the automatic segmentation of geographic atrophy (GA) using color fundus images (CFIs) and its application to study the growth rate of GA.

DESIGN : Prospective, multicenter, natural history study with up to 15 years of follow-up.

PARTICIPANTS : Four hundred nine CFIs of 238 eyes with GA from the Rotterdam Study (RS) and Blue Mountain Eye Study (BMES) for model development, and 3589 CFIs of 376 eyes from the Age-Related Eye Disease Study (AREDS) for analysis of GA growth rate.

METHODS : A deep learning model based on an ensemble of encoder-decoder architectures was implemented and optimized for the segmentation of GA in CFIs. Four experienced graders delineated, in consensus, GA in CFIs from the RS and BMES. These manual delineations were used to evaluate the segmentation model using 5-fold cross-validation. The model was applied further to CFIs from the AREDS to study the growth rate of GA. Linear regression analysis was used to study associations between structural biomarkers at baseline and the GA growth rate. A general estimate of the progression of GA area over time was made by combining growth rates of all eyes with GA from the AREDS set.

MAIN OUTCOME MEASURES : Automatically segmented GA and GA growth rate.

RESULTS : The model obtained an average Dice coefficient of 0.72±0.26 on the BMES and RS set while comparing the automatically segmented GA area with the graders' manual delineations. An intraclass correlation coefficient of 0.83 was reached between the automatically estimated GA area and the graders' consensus measures. Nine automatically calculated structural biomarkers (area, filled area, convex area, convex solidity, eccentricity, roundness, foveal involvement, perimeter, and circularity) were significantly associated with growth rate. Combining all growth rates indicated that GA area grows quadratically up to an area of approximately 12 mm², after which growth rate stabilizes or decreases.

CONCLUSIONS : The deep learning model allowed for fully automatic and robust segmentation of GA on CFIs. These segmentations can be used to extract structural characteristics of GA that predict its growth rate.

Liefers Bart, Colijn Johanna M, González-Gonzalo Cristina, Verzijden Timo, Wang Jie Jin, Joachim Nichole, Mitchell Paul, Hoyng Carel B, van Ginneken Bram, Klaver Caroline C W, Sánchez Clara I

2020-Feb-15

In The Journal of surgical research

BACKGROUND : Reduced surgical site infection (SSI) rates have been reported with use of closed incision negative pressure therapy (ciNPT) in high-risk patients.

METHODS : A deep learning-based, risk-based prediction model was developed from a large national database of 72,435 patients who received infrainguinal vascular surgeries involving upper thigh/groin incisions. Patient demographics, histories, laboratory values, and other variables were inputs to the multilayered, adaptive model. The model was then retrospectively applied to a prospectively tracked single hospital data set of 370 similar patients undergoing vascular surgery, with ciNPT or control dressings applied over the closed incision at the surgeon's discretion. Objective predictive risk scores were generated for each patient and used to categorize patients as "high" or "low" predicted risk for SSI.

RESULTS : Actual institutional cohort SSI rates were 10/148 (6.8%) and 28/134 (20.9%) for high-risk ciNPT versus control, respectively (P < 0.001), and 3/31 (9.7%) and 5/57 (8.8%) for low-risk ciNPT versus control, respectively (P = 0.99). Application of the model to the institutional cohort suggested that 205/370 (55.4%) patients were matched with their appropriate intervention over closed surgical incision (high risk with ciNPT or low risk with control), and 165/370 (44.6%) were inappropriately matched. With the model applied to the cohort, the predicted SSI rate with perfect utilization would be 27/370 (7.3%), versus 12.4% actual rate, with estimated cost savings of $231-$458 per patient.

CONCLUSIONS : Compared with a subjective practice strategy, an objective risk-based strategy using prediction software may be associated with superior results in optimizing SSI rates and costs after vascular surgery.

Chang Bora, Sun Zhifei, Peiris Prabath, Huang Erich S, Benrashid Ehsan, Dillavou Ellen D

2020-Mar-17

Closed incision negative pressure therapy, High risk vascular patients, Infrainguinal vascular surgery, Prediction model, Surgical site infection

In ISA transactions

Tightiz Lilia, Nasab Morteza Azimi, Yang Hyosik, Addeh Abdoljalil

2020-Mar-14

ANFIS, Association rules, BWOA, DGAM, Power transformer

In BMC bioinformatics

BACKGROUND : The ability to confidently predict health outcomes from gene expression would catalyze a revolution in molecular diagnostics. Yet, the goal of developing actionable, robust, and reproducible predictive signatures of phenotypes such as clinical outcome has not been attained in almost any disease area. Here, we report a comprehensive analysis spanning prediction tasks from ulcerative colitis, atopic dermatitis, diabetes, to many cancer subtypes for a total of 24 binary and multiclass prediction problems and 26 survival analysis tasks. We systematically investigate the influence of gene subsets, normalization methods and prediction algorithms. Crucially, we also explore the novel use of deep representation learning methods on large transcriptomics compendia, such as GTEx and TCGA, to boost the performance of state-of-the-art methods. The resources and findings in this work should serve as both an up-to-date reference on attainable performance, and as a benchmarking resource for further research.

RESULTS : Approaches that combine large numbers of genes outperformed single gene methods consistently and with a significant margin, but neither unsupervised nor semi-supervised representation learning techniques yielded consistent improvements in out-of-sample performance across datasets. Our findings suggest that using l₂-regularized regression methods applied to centered log-ratio transformed transcript abundances provide the best predictive analyses overall.

CONCLUSIONS : Transcriptomics-based phenotype prediction benefits from proper normalization techniques and state-of-the-art regularized regression approaches. In our view, breakthrough performance is likely contingent on factors which are independent of normalization and general modeling techniques; these factors might include reduction of systematic errors in sequencing data, incorporation of other data types such as single-cell sequencing and proteomics, and improved use of prior knowledge.

Smith Aaron M, Walsh Jonathan R, Long John, Davis Craig B, Henstock Peter, Hodge Martin R, Maciejewski Mateusz, Mu Xinmeng Jasmine, Ra Stephen, Zhao Shanrong, Ziemek Daniel, Fisher Charles K

2020-Mar-20

Deep learning, Machine learning, Molecular diagnostics, Normalization methods, Phenotype prediction, RNA-seq, Representation learning, Transcriptomics

In International journal of environmental research and public health ; h5-index 73.0

Joda Tim, Bornstein Michael M, Jung Ronald E, Ferrari Marco, Waltimo Tuomas, Zitzmann Nicola U

2020-Mar-18

artificial intelligence (AI), augmented and virtual reality (AR/VR), digital transformation, machine learning (ML), patient-centered outcomes, personalized dental medicine, rapid prototyping, tele-health

ArXiv Preprint

Feng Shi, Liming Xia, Fei Shan, Dijia Wu, Ying Wei, Huan Yuan, Huiting Jiang, Yaozong Gao, He Sui, Dinggang Shen

2020-03-22

In The Science of the total environment

Feio Maria João, Serra Sónia R Q, Mortágua Andreia, Bouchez Agnès, Rimet Frédéric, Vasselon Valentin, Almeida Salomé F P

2020-Mar-12

Bioassessment, HYDRA, Machine learning, Metabarcoding, OTUs, Rivers

In Environmental research ; h5-index 67.0

Pourghasemi Hamid Reza, Gayen Amiya, Lasaponara Rosa, Tiefenbacher John P

2020-Feb-29

Boosted regression trees, Forest-fire susceptibility map, Generalized linear model, Learning-vector quantization, Mixture discriminant analysis

In Computer methods and programs in biomedicine

BACKGROUND : Metabolic engineering aims at contriving microbes as biocatalysts for enhanced and cost-effective production of countless secondary metabolites. These secondary metabolites can be treated as the resources of industrial chemicals, pharmaceuticals and fuels. Plants are also crucial targets for metabolic engineers to produce necessary secondary metabolites. Metabolic engineering of both microorganism and plants also contributes towards drug discovery. In order to implement advanced metabolic engineering techniques efficiently, metabolic engineers should have detailed knowledge about cell physiology and metabolism. Principle behind methodologies: Genome-scale mathematical models of integrated metabolic, signal transduction, gene regulatory and protein-protein interaction networks along with experimental validation can provide such knowledge in this context. Incorporation of omics data into these models is crucial in the case of drug discovery. Inverse metabolic engineering and metabolic control analysis (MCA) can help in developing such models. Artificial intelligence methodology can also be applied for efficient and accurate metabolic engineering.

CONCLUSION : In this review, we discuss, at the beginning, the perspectives of metabolic engineering and its application on microorganism and plant leading to drug discovery. At the end, we elaborate why inverse metabolic engineering and MCA are closely related to modern metabolic engineering. In addition, some crucial steps ensuring efficient and optimal metabolic engineering strategies have been discussed. Moreover, we explore the use of genomics data for the activation of silent metabolic clusters and how it can be integrated with metabolic engineering. Finally, we exhibit a few applications of artificial intelligence to metabolic engineering.

Dasgupta Abhijit, Chowdhury Nirmalya, De Rajat K

2020-Mar-18

Artificial intelligence,, CRISPR-Cas9, Drug discovery, Genomics, Inverse metabolic engineering, MCA, Secondary metabolites, TALENs, ZFNs

In NeuroImage. Clinical

Pirondini Elvira, Goldshuv-Ezra Nurit, Zinger Nofya, Britz Juliane, Soroker Nachum, Deouell Leon Y, Ville Dimitri Van De

2020-Mar-05

Computer-enhanced measurement, EEG analysis, EEG topography features, Machine learning, Outcome measurement, Rehabilitation, Resting-state EEG biomarkers, Stroke, Unilateral spatial neglect

In Ultrasonics sonochemistry

Xu Tianqi, Cui Zhiwei, Li Dapeng, Cao Fangyuan, Xu Jichen, Zong Yujin, Wang Supin, Bouakaz Ayache, Wan Mingxi, Zhang Siyuan

2020-Mar-09

Boiling-point, Cavitation activity, Flowing phase-shift nanodroplets, Focused ultrasound

In CNS neuroscience & therapeutics

BACKGROUND : Up to 90% of patients with Parkinson's disease (PD) eventually develop the speech and voice disorder referred to as hypokinetic dysarthria (HD). However, the brain morphological changes associated with HD have not been investigated. Moreover, no reliable model for predicting the severity of HD based on neuroimaging has yet been developed.

METHODS : A total of 134 PD patients were included in this study and divided into a training set and a test set. All participants underwent a structural magnetic resonance imaging (MRI) scan and neuropsychological evaluation. Individual cortical thickness, subcortical structure, and white matter volume were extracted, and their association with HD severity was analyzed. After feature selection, a machine-learning model was established using a support vector machine in the training set. The severity of HD was then predicted in the test set.

RESULTS : Atrophy of the right precentral cortex and the right fusiform gyrus was significantly associated with HD. No association was found between HD and volume of white matter or subcortical structures. Favorable and optimal performance of machine learning on HD severity prediction was achieved using feature selection, giving a correlation coefficient (r) of .7516 and a coefficient of determination (R² ) of .5649 (P < .001).

CONCLUSION : The brain morphological changes were associated with HD. Excellent prediction of the severity of HD was achieved using machine learning based on neuroimaging.

Chen Yingchuan, Zhu Guanyu, Liu Defeng, Liu Yuye, Yuan Tianshuo, Zhang Xin, Jiang Yin, Du Tingting, Zhang Jianguo

2020-Mar-20

“Parkinsons disease”, brain morphology, hypokinetic dysarthria, machine learning, structural magnetic resonance imaging

In PM & R : the journal of injury, function, and rehabilitation

BACKGROUND : A lack of studies with large sample sizes of patients with rotator cuff tears is a barrier to performing clinical and genomic research.

OBJECTIVE : To develop and validate an electronic medical record (EMR)-based algorithm to identify individuals with and without rotator cuff tear.

DESIGN : We used a de-identified version of the EMR of more than 2 million subjects. A screening algorithm was applied to classify subjects into likely rotator cuff tear and likely normal rotator cuff groups. From these subjects, 500 likely rotator cuff tear and 500 likely normal rotator cuff were randomly chosen for algorithm development. Chart review of all 1000 subjects confirmed the true phenotype of rotator cuff tear or normal rotator cuff based on magnetic resonance imaging and operative report. An algorithm was then developed based on logistic regression and validation of the algorithm was performed.

RESULTS : The variables significantly predicting rotator cuff tear included the number of times a Current Procedural Terminology code related to rotator cuff procedures was used (OR = 3.3; 95% CI: 1.6-6.8 for ≥3 vs 0), the number of times a term related to rotator cuff lesions occurred in radiology reports (OR = 2.2; 95% CI: 1.2-4.1 for ≥1 vs 0), and the number of times a term related to rotator cuff lesions occurred in physician notes (OR = 4.5; 95% CI: 2.2-9.1 for 1 or 2 times vs 0). This phenotyping algorithm had a specificity of 0.89 (95% CI: 0.79-0.95) for rotator cuff tear, AUC of 0.842, and diagnostic likelihood ratios, DLR+ and DLR- of 5.94 (95%CI: 3.07-11.48) and 0.363 (95%CI: 0.291-0.453).

CONCLUSION : Our informatics algorithm enables identification of cohorts of individuals with and without rotator cuff tear from an EMR-based dataset with moderate accuracy. This article is protected by copyright. All rights reserved.

Gao Chan, Fan Run, Ayers Gregory D, Giri Ayush, Harris Kindred, Atreya Ravi, Teixeira Pedro L, Jain Nitin B

2020-Mar-20

algorithm, electronic medical record, logistic regression, machine learning, phenotyping, rotator cuff tear

In Pediatric cardiology

Salavitabar Arash, Armstrong Aimee K

2020-Mar-20

3D rotational angiography, 3D visualization, Computational fluid dynamics, Mixed reality, Pediatric interventional cardiology, Personalized interventions

In Pediatric cardiology

Duignan Sophie, Walsh Kevin P, McMahon Colin J

2020-Mar-20

Cardiac, Catheterization, Decision-making, Human factors

In Scientific reports ; h5-index 158.0

Kayasandik Cihan Bilge, Ru Wenjuan, Labate Demetrio

2020-Mar-20

In Early human development

Grech Victor

2020-Mar-16

In Clinical nutrition (Edinburgh, Scotland)

BACKGROUND & AIMS : Sarcopenia, or age-related muscle loss, is an enormous health problem in an aging world because of its many clinical and societal adverse effects. The uncovering of healthy dietary patterns is an important strategy to prevent or delay sarcopenia. We used K-means clustering to identify subgroups of men and women based on nutritional and health-related factors and investigated risk factors for low muscle mass in the subgroups and in the study population as a whole.

METHODS : We analyzed a total 10,863 participants over 40 years of age who participated in the Korea National Health and Nutrition Survey from 2008 to 2011. Dual energy X-ray absorptiometry was used to determine the appendicular lean mass (ALM) of the participants. Participants with low ALM adjusted BMI (ALM/BMI) were then identified using the criteria of the Foundation for the National Institutes of Health sarcopenia project. K-means clustering and multivariate logistic regression were used to analyze associations between nutritional and health-related variables and low ALM/BMI in the population as a whole and in the individual clusters.

RESULTS : A total of 712 (15.8%) men and 869 (13.7%) women had low ALM/BMI. Five clusters were identified in men and women, respectively. Two clusters of men and one cluster of women exhibited an increased risk of low ALM/BMI. Old age, low total energy intake, low levels of physical activity, and a high number of chronic diseases were consistent risk factors for low ALM/BMI in all Korean men and women. Low protein was a common risk factor for low ALM/BMI in men. After dividing all subjects by the K-means clustering algorithm, two risk factors (high fat intake and smoking) and four factors (low intakes of carbohydrate, protein and fat, and high alcohol consumption) were additionally proposed in Korean men and women, respectively.

CONCLUSIONS : Age, low total energy intake, low level of physical activity, and an increased number of chronic diseases were consistent risk factors for low ALM/BMI in men and women. Cluster-specific risk factors were also noted in men and women.

Kwon Yu-Jin, Kim Hyoung Sik, Jung Dong-Hyuk, Kim Jong-Koo

2020-Mar-06

Aging, Nutrition, Sarcopenia, Unsupervised machine learning

In Journal of the American College of Cardiology ; h5-index 167.0

BACKGROUND : Better risk stratification strategies are needed to enhance clinical care and trial design in heart failure with preserved ejection fraction (HFpEF).

OBJECTIVES : The purpose of this study was to assess the value of a targeted plasma multi-marker approach to enhance our phenotypic characterization and risk prediction in HFpEF.

METHODS : In this study, the authors measured 49 plasma biomarkers from TOPCAT (Treatment of Preserved Cardiac Function Heart Failure With an Aldosterone Antagonist) trial participants (n = 379) using a Multiplex assay. The relationship between biomarkers and the risk of all-cause death or heart failure-related hospital admission (DHFA) was assessed. A tree-based pipeline optimizer platform was used to generate a multimarker predictive model for DHFA. We validated the model in an independent cohort of HFpEF patients enrolled in the PHFS (Penn Heart Failure Study) (n = 156).

RESULTS : Two large, tightly related dominant biomarker clusters were found, which included biomarkers of fibrosis/tissue remodeling, inflammation, renal injury/dysfunction, and liver fibrosis. Other clusters were composed of neurohormonal regulators of mineral metabolism, intermediary metabolism, and biomarkers of myocardial injury. Multiple biomarkers predicted incident DHFA, including 2 biomarkers related to mineral metabolism/calcification (fibroblast growth factor-23 and OPG [osteoprotegerin]), 3 inflammatory biomarkers (tumor necrosis factor-alpha, sTNFRI [soluble tumor necrosis factor-receptor I], and interleukin-6), YKL-40 (related to liver injury and inflammation), 2 biomarkers related to intermediary metabolism and adipocyte biology (fatty acid binding protein-4 and growth differentiation factor-15), angiopoietin-2 (related to angiogenesis), matrix metalloproteinase-7 (related to extracellular matrix turnover), ST-2, and N-terminal pro-B-type natriuretic peptide. A machine-learning-derived model using a combination of biomarkers was strongly predictive of the risk of DHFA (standardized hazard ratio: 2.85; 95% confidence interval: 2.03 to 4.02; p < 0.0001) and markedly improved the risk prediction when added to the MAGGIC (Meta-Analysis Global Group in Chronic Heart Failure Risk Score) risk score. In an independent cohort (PHFS), the model strongly predicted the risk of DHFA (standardized hazard ratio: 2.74; 95% confidence interval: 1.93 to 3.90; p < 0.0001), which was also independent of the MAGGIC risk score.

CONCLUSIONS : Various novel circulating biomarkers in key pathophysiological domains are predictive of outcomes in HFpEF, and a multimarker approach coupled with machine-learning represents a promising strategy for enhancing risk stratification in HFpEF.

Chirinos Julio A, Orlenko Alena, Zhao Lei, Basso Michael D, Cvijic Mary Ellen, Li Zhuyin, Spires Thomas E, Yarde Melissa, Wang Zhaoqing, Seiffert Dietmar A, Prenner Stuart, Zamani Payman, Bhattacharya Priyanka, Kumar Anupam, Margulies Kenneth B, Car Bruce D, Gordon David A, Moore Jason H, Cappola Thomas P

2020-Mar-24

HFpEF, Penn Heart Failure Study, TOPCAT trial, biomarkers, fibrosis, inflammation, kidney, liver

In BMC ophthalmology

BACKGROUND : Classification of optical coherence tomography (OCT) images can be achieved with high accuracy using classical convolution neural networks (CNN), a commonly used deep learning network for computer-aided diagnosis. Classical CNN has often been criticized for suppressing positional relations in a pooling layer. Therefore, because capsule networks can learn positional information from images, we attempted application of a capsule network to OCT images to overcome that shortcoming. This study is our attempt to improve classification accuracy by replacing CNN with a capsule network.

METHODS : From an OCT dataset, we produced a training dataset of 83,484 images and a test dataset of 1000 images. For training, the dataset comprises 37,205 images with choroidal neovascularization (CNV), 11,348 with diabetic macular edema (DME), 8616 with drusen, and 26,315 normal images. The test dataset has 250 images from each category. The proposed model was constructed based on a capsule network for improving classification accuracy. It was trained using the training dataset. Subsequently, the test dataset was used to evaluate the trained model.

RESULTS : Classification of OCT images using our method achieved accuracy of 99.6%, which is 3.2 percentage points higher than that of other methods described in the literature.

CONCLUSION : The proposed method achieved classification accuracy results equivalent to those reported for other methods for CNV, DME, drusen, and normal images.

Tsuji Takumasa, Hirose Yuta, Fujimori Kohei, Hirose Takuya, Oyama Asuka, Saikawa Yusuke, Mimura Tatsuya, Shiraishi Kenshiro, Kobayashi Takenori, Mizota Atsushi, Kotoku Jun’ichi

2020-Mar-19

Capsule network, Choroidal neovascularization, Deep learning, Diabetic macular edema, Drusen, Optical coherence tomography

In Chinese clinical oncology

Iwamoto Takayuki, Kajiwara Yukiko, Zhu Yidan, Iha Shigemichi

2020-Mar-13

Biomarker, breast cancer, chemotherapy, gene expression

In ACS applied materials & interfaces ; h5-index 147.0

Halter Mattia, Bégon-Lours Laura, Bragaglia Valeria, Sousa Marilyne, Offrein Bert, Abel Stefan, Luisier Mathieu, Fompeyrine Jean

2020-Mar-20

In Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB)

PURPOSE : In this study we trained a deep neural network model for female pelvis organ segmentation using data from several sites without any personal data sharing. The goal was to assess its prediction power compared with the model trained in a centralized manner.

METHODS : Varian Learning Portal (VLP) is a distributed machine learning (ML) infrastructure enabling privacy-preserving research across hospitals from different regions or countries, within the framework of a trusted consortium. Such a framework is relevant in the case when there is a high level of trust among the participating sites, but there are legal restrictions which do not allow the actual data sharing between them. We trained an organ segmentation model for the female pelvic region using the synchronous data distributed framework provided by the VLP.

RESULTS : The prediction performance of the model trained using the federated framework offered by VLP was on the same level as the performance of the model trained in a centralized manner where all training data was pulled together in one centre.

CONCLUSIONS : VLP infrastructure can be used for GPU-based training of a deep neural network for organ segmentation for the female pelvic region. This organ segmentation instance is particularly difficult due to the high variation in the organs' shape and size. Being able to train the model using data from several clinics can help, for instance, by exposing the model to a larger range of data variations. VLP framework enables such a distributed training approach without sharing protected health information.

Czeizler Elena, Wiessler Wolfgang, Koester Thorben, Hakala Mikko, Basiri Shahab, Jordan Petr, Kuusela Esa

2020-Mar-17

Convolutional Neural Network, Distributed Training, Federated Data Sources, Female Pelvis Organ Segmentation, Varian Learning Portal

In The Science of the total environment

Qian Yuehui, Xing Weiran, Guan Xuefeng, Yang Tingting, Wu Huayi

2020-Mar-12

Cellular automata, Land use, Neighborhood effects, Spatial heterogeneity, Spatiotemporal features

In NeuroImage. Clinical

Frässle Stefan, Marquand Andre F, Schmaal Lianne, Dinga Richard, Veltman Dick J, van der Wee Nic J A, van Tol Marie-José, Schöbi Dario, Penninx Brenda W J H, Stephan Klaas E

2020-Feb-17

In Journal of chemical theory and computation

Berg Andrej, Franke Leon, Scheffner Martin, Peter Christine

2020-Mar-20

In Journal of the American Medical Informatics Association : JAMIA

OBJECTIVES : Sharing patient data across institutions to train generalizable deep learning models is challenging due to regulatory and technical hurdles. Distributed learning, where model weights are shared instead of patient data, presents an attractive alternative. Cyclical weight transfer (CWT) has recently been demonstrated as an effective distributed learning method for medical imaging with homogeneous data across institutions. In this study, we optimize CWT to overcome performance losses from variability in training sample sizes and label distributions across institutions.

MATERIALS AND METHODS : Optimizations included proportional local training iterations, cyclical learning rate, locally weighted minibatch sampling, and cyclically weighted loss. We evaluated our optimizations on simulated distributed diabetic retinopathy detection and chest radiograph classification.

RESULTS : Proportional local training iteration mitigated performance losses from sample size variability, achieving 98.6% of the accuracy attained by centrally hosting in the diabetic retinopathy dataset split with highest sample size variance across institutions. Locally weighted minibatch sampling and cyclically weighted loss both mitigated performance losses from label distribution variability, achieving 98.6% and 99.1%, respectively, of the accuracy attained by centrally hosting in the diabetic retinopathy dataset split with highest label distribution variability across institutions.

DISCUSSION : Our optimizations to CWT improve its capability of handling data variability across institutions. Compared to CWT without optimizations, CWT with optimizations achieved performance significantly closer to performance from centrally hosting.

CONCLUSION : Our work is the first to identify and address challenges of sample size and label distribution variability in simulated distributed deep learning for medical imaging. Future work is needed to address other sources of real-world data variability.

Balachandar Niranjan, Chang Ken, Kalpathy-Cramer Jayashree, Rubin Daniel L

2020-Mar-20

deep learning, distributed learning, federated learning, medical imaging, transfer learning

In Journal of thoracic imaging

Monti Caterina B, Codari Marina, van Assen Marly, De Cecco Carlo N, Vliegenthart Rozemarijn

2020-Mar-17

In Clinical orthopaedics and related research ; h5-index 71.0

BACKGROUND : PATHFx is a clinical decision-support tool based on machine learning capable of estimating the likelihood of survival after surgery for patients with skeletal metastases. The applicability of any machine-learning tool depends not only on successful external validation in unique patient populations but also on remaining relevant as more effective systemic treatments are introduced. With advancements in the treatment of metastatic disease, it is our responsibility to patients to ensure clinical support tools remain contemporary and accurate.

QUESTION/PURPOSES : Therefore, we sought to (1) generate updated PATHFx models using recent data from patients treated at one large, urban tertiary referral center and (2) externally validate the models using two contemporary patient populations treated either surgically or nonsurgically with external-beam radiotherapy alone for symptomatic skeletal metastases for symptomatic lesions.

METHODS : After obtaining institutional review board approval, we collected data on 208 patients undergoing surgical treatment for pathologic fractures at Memorial Sloan Kettering Cancer Center between 2015 and 2018. These data were combined with the original PATHFx training set (n = 189) to create the final training set (n = 397). We then created six Bayesian belief networks designed to estimate the likelihood of 1-month, 3-month, 6-month, 12-month, 18-month, and 24-month survival after treatment. Bayesian belief analysis is a statistical method that allows data-driven learning to arise from conditional probabilities by exploring relationships between variables to estimate the likelihood of an outcome using observed data. For external validation, we extracted the records of patients treated between 2016 and 2018 from the International Bone Metastasis Registry and records of patients treated nonoperatively with external-beam radiation therapy for symptomatic skeletal metastases from 2012 to 2016 using the Military Health System Data Repository (radiotherapy-only group). From each record, we collected the date of treatment, laboratory values at the time of treatment initiation, demographic data, details of diagnosis, and the date of death. All records reported sufficient follow-up to establish survival (yes/no) at 24-months after treatment. For external validation, we applied the data from each record to the new PATHFx models. We assessed calibration (calibration plots), accuracy (Brier score), discriminatory ability (area under the receiver operating characteristic curve [AUC]).

RESULTS : The updated PATHFx version 3.0 models successfully classified survival at each time interval in both external validation sets and demonstrated appropriate discriminatory ability and model calibration. The Bayesian models were reasonably calibrated to the Memorial Sloan Kettering Cancer Center training set. External validation with 197 records from the International Bone Metastasis Registry and 192 records from the Military Health System Data Repository for analysis found Brier scores that were all less than 0.20, with upper bounds of the 95% confidence intervals all less than 0.25, both for the radiotherapy-only and International Bone Metastasis Registry groups. Additionally, AUC estimates were all greater than 0.70, with lower bounds of the 95% CI all greater than 0.68, except for the 1-month radiotherapy-only group. To complete external validation, decision curve analysis demonstrated clinical utility. This means it was better to use the PATHFx models when compared to the default assumption that all or no patients would survive at all time periods except for the 1-month models. We believe the favorable Brier scores (< 0.20) as well as DCA indicate these models are suitable for clinical use.

CONCLUSIONS : We successfully updated PATHFx using contemporary data from patients undergoing either surgical or nonsurgical treatment for symptomatic skeletal metastases. These models have been incorporated for clinical use on PATHFx version 3.0 (https://www.pathfx.org). Clinically, external validation suggests it is better to use PATHFx version 3.0 for all time periods except when deciding whether to give radiotherapy to patients with the life expectancy of less than 1 month. This is partly because most patients survived 1-month after treatment. With the advancement of medical technology in treatment and diagnosis for patients with metastatic bone disease, part of our fiduciary responsibility is to the main current clinical support tools.

LEVEL OF EVIDENCE : Level III, therapeutic study.

Anderson Ashley B, Wedin Rikard, Fabbri Nicola, Boland Patrick, Healey John, Forsberg Jonathan A

2020-Apr

In Journal of chemical information and modeling

Imrie Fergus, Bradley Anthony R, van der Schaar Mihaela, Deane Charlotte M

2020-Mar-20

In Heliyon

Junejo Imran N, Ahmed Naveed

2020-Mar

Computer Vision, Computer science, Deep learning, Image processing, Pedestrian attribute recognition

In Heliyon

Almasre Miada A, Al-Nuaim Hana

2020-Mar

Arabic sign language, Classification, Computer science, Dynamic gesture recognition models, Machine learning

In International journal of environmental research and public health ; h5-index 73.0

Vu Giang Thu, Tran Bach Xuan, McIntyre Roger S, Pham Hai Quang, Phan Hai Thanh, Ha Giang Hai, Gwee Kenneth K, Latkin Carl A, Ho Roger C M, Ho Cyrus S H

2020-Mar-17

LDA, artificial intelligence, bibliometric, diabetes, machine learning

In NPJ digital medicine

Engelhard Matthew M, Oliver Jason A, McClernon F Joseph

2020

Cardiovascular diseases, Psychiatric disorders, Risk factors

In NPJ digital medicine

Kalra Shivam, Tizhoosh H R, Shah Sultaan, Choi Charles, Damaskinos Savvas, Safarpoor Amir, Shafiei Sobhan, Babaie Morteza, Diamandis Phedias, Campbell Clinton J V, Pantanowitz Liron

2020

Cancer imaging, Data mining, Machine learning

In NPJ digital medicine

Stafford I S, Kellermann M, Mossotto E, Beattie R M, MacArthur B D, Ennis S

2020

Autoimmune diseases, Machine learning, Predictive medicine

In NPJ digital medicine

Epstein David H, Tyburski Matthew, Kowalczyk William J, Burgess-Hull Albert J, Phillips Karran A, Curtis Brenda L, Preston Kenzie L

2020

Disease-free survival, Risk factors

In Frontiers in cardiovascular medicine

Chen Chen, Qin Chen, Qiu Huaqi, Tarroni Giacomo, Duan Jinming, Bai Wenjia, Rueckert Daniel

2020

CT, MRI, artificial intelligence, cardiac image analysis, cardiac image segmentation, deep learning, neural networks, ultrasound

In Frontiers in bioengineering and biotechnology

Zago Matteo, Luzzago Matteo, Marangoni Tommaso, De Cecco Mariolino, Tarabini Marco, Galli Manuela

2020

artificial intelligence, computer vision, gait analysis, markerless motion capture, movement measurement

In Frontiers in bioengineering and biotechnology

Côté-Allard Ulysse, Campbell Evan, Phinyomark Angkoon, Laviolette François, Gosselin Benoit, Scheme Erik

2020

CNN, ConvNet, EMG, Grad-CAM, MAPPER, deep learning, feature extraction, gesture recognition

In NPJ genomic medicine

Zheng Hong, Momeni Alexandre, Cedoz Pierre-Louis, Vogel Hannes, Gevaert Olivier

2020

CNS cancer, Cancer, Cancer imaging, Computational biology and bioinformatics

In Light, science & applications

Deng Mo, Li Shuai, Goy Alexandre, Kang Iksung, Barbastathis George

2020

Applied optics, Imaging and sensing

In Theranostics

Zeng Yifeng, Xu Shiqi, Chapman William C, Li Shuying, Alipour Zahra, Abdelal Heba, Chatterjee Deyali, Mutch Matthew, Zhu Quing

2020

colorectal cancer, deep learning, optical biopsy, optical coherence tomography (OCT)

In Plants (Basel, Switzerland)

Sonobe Rei, Hirono Yuhei, Oi Ayako

2020-Mar-17

deep belief nets, extreme learning machine, first derivative spectra, random forest, shade-grown tea, support vector machine

In Frontiers in neurology

Yang Xue-Juan, Liu Lu, Xu Zi-Liang, Zhang Ya-Jie, Liu Da-Peng, Fishers Marc, Zhang Lan, Sun Jin-Bo, Liu Peng, Zeng Xiao, Wang Lin-Peng, Qin Wei

2020

acupuncture, gray matter, machine learning, migraine, prediction

In Frontiers in computational neuroscience

Howard Newton, Chouikhi Naima, Adeel Ahsan, Dial Katelyn, Howard Adam, Hussain Amir

2020

BrainOS, architecture design, artificial intelligence, automatic machine learning, human brain, hyperparameters

In Frontiers in neuroscience ; h5-index 72.0

Shin Jaeyoung, Im Chang-Hwan

2020

bootstrap aggregating, brain-computer interface, ensemble learning, near-infrared spectroscopy, pattern classification

In Frontiers in neuroscience ; h5-index 72.0

Li Xiang, Zhao Zhigang, Song Dawei, Zhang Yazhou, Pan Jingshan, Wu Lu, Huo Jidong, Niu Chunyang, Wang Di

2020

EEG, deep learning, emotion recognition, latent factor decoding, variational autoencoder

In Global health action ; h5-index 41.0

Mackey Tim K, Cuomo Raphael E

2020

Anti-Corruption, Transparency and Accountability, Medicines procurement, access to medicines, corruption, e-procurement, global health, technology, transparency

In Neurorehabilitation and neural repair ; h5-index 48.0

Tozlu Ceren, Edwards Dylan, Boes Aaron, Labar Douglas, Tsagaris K Zoe, Silverstein Joshua, Pepper Lane Heather, Sabuncu Mert R, Liu Charles, Kuceyeski Amy

2020-Mar-20

Fugl-Meyer Assessment, chronic stroke, machine learning, predictive models, white matter disconnectivity

In Korean journal of radiology

Park Hyo Jung, Park Bumwoo, Lee Seung Soo

2020-Apr

Artificial intelligence, Computer-assisted, Deep learning, Liver, Radiomics

In Journal of digital imaging

Maaref Ahmad, Romero Francisco Perdigon, Montagnon Emmanuel, Cerny Milena, Nguyen Bich, Vandenbroucke Franck, Soucy Geneviève, Turcotte Simon, Tang An, Kadoury Samuel

2020-Mar-19

CT scans, Chemotherapy, Colorectal liver metastases, Deep convolutional neural network, FOLFOX-based regimen, Prediction response

In European radiology ; h5-index 62.0

OBJECTIVES : To assess the diagnostic accuracy of machine learning (ML) in predicting isocitrate dehydrogenase (IDH) mutations in patients with glioma and to identify potential covariates that could influence the diagnostic performance of ML.

METHODS : A systematic search of PubMed, Web of Science, and the Cochrane library up to 1 August 2019 was conducted to collect all the articles investigating the diagnostic performance of ML for prediction of IDH mutation in glioma. The search strategy combined synonyms for 'machine learning', 'glioma', and 'IDH'. Pooled sensitivity, specificity, and their 95% confidence intervals (CIs) were calculated, and the area under the receiver operating characteristic curve (AUC) was obtained.

RESULTS : Nine original articles assessing a total of 996 patients with glioma were included. Among these studies, five divided the participants into training and validation sets, while the remaining four studies only had a training set. The AUC of ML for predicting IDH mutation in the training and validation sets was 93% (95% CI 91-95%) and 89% (95% CI 86-92%), respectively. The pooled sensitivity and specificity were, respectively, 87% (95% CI 82-91%) and 88% (95% CI 83-92%) in the training set and 87% (95% CI 76-93%) and 90% (95% CI 72-97%) in the validation set. In subgroup analyses in the training set, the combined use of clinical and imaging features with ML yielded higher sensitivity (90% vs. 83%) and specificity (90% vs. 82%) than the use of imaging features alone. In addition, ML performed better for high-grade gliomas than for low-grade gliomas, and ML that used conventional MRI sequences demonstrated higher specificity for predicting IDH mutation than ML using conventional and advanced MRI sequences.

CONCLUSIONS : ML demonstrated an excellent diagnostic performance in predicting IDH mutation of glioma. Clinical information, MRI sequences, and glioma grade were the main factors influencing diagnostic specificity.

KEY POINTS : • Machine learning demonstrated an excellent diagnostic performance for prediction of IDH mutation in glioma (the pooled sensitivity and specificity were 88% and 87%, respectively). • Machine learning that used conventional MRI sequences demonstrated higher specificity in predicting IDH mutation than that based on conventional and advanced MRI sequences (89% vs. 85%). • Integration of clinical and imaging features in machine learning yielded a higher sensitivity (90% vs. 83%) and specificity (90% vs. 82%) than that achieved by using imaging features alone.

Zhao Jing, Huang Yingqian, Song Yukun, Xie Dingxiang, Hu Manshi, Qiu Haishan, Chu Jianping

2020-Mar-19

Glioma, Isocitrate dehydrogenase (IDH), MRI, Machine learning

In Histochemistry and cell biology

Pernal Sebastian P, Liyanaarachchi Asiri, Gatti Domenico L, Formosa Brent, Pulvender Rishika, Kuhn Eric R, Ramos Rafael, Naik Akshata R, George Kathleen, Arslanturk Suzan, Taatjes Douglas J, Jena Bhanu P

2020-Mar-19

Differential expansion, Machine learning, Nanoscale imaging, Optical microscopy

In Diagnostics (Basel, Switzerland)

Rodríguez-Ruiz Julieta G, Galván-Tejada Carlos E, Zanella-Calzada Laura A, Celaya-Padilla José M, Galván-Tejada Jorge I, Gamboa-Rosales Hamurabi, Luna-García Huizilopoztli, Magallanes-Quintanar Rafael, Soto-Murillo Manuel A

2020-Mar-17

data mining, depression, depressive episodes, motor activity, night, random forest

In Scientific reports ; h5-index 158.0

Park Keunheung, Kim Jinmi, Lee Jiwoong

2020-Mar-19

In Scientific reports ; h5-index 158.0

Kenville Rouven, Maudrich Tom, Vidaurre Carmen, Maudrich Dennis, Villringer Arno, Nikulin Vadim V, Ragert Patrick

2020-Mar-19

In Scientific reports ; h5-index 158.0

Moshkov Nikita, Mathe Botond, Kertesz-Farkas Attila, Hollandi Reka, Horvath Peter

2020-Mar-19

In Scientific reports ; h5-index 158.0

Stepniewska-Dziubinska Marta M, Zielenkiewicz Piotr, Siedlecki Pawel

2020-Mar-19

In Scientific reports ; h5-index 158.0

Abbas Halim, Garberson Ford, Liu-Mayo Stuart, Glover Eric, Wall Dennis P

2020-Mar-19

In Genetics ; h5-index 66.0

Zhu Yicheng, Ong Cheng Soon, Huttley Gavin A

2020-Mar-19

bioinformatics, context dependent mutation, germline mutation, log-linear model, machine learning, mutagenesis, mutation spectrum, sequence motif analysis

In International journal of medical informatics ; h5-index 49.0

OBJECTIVE : Predicting the risk of falls in advance can benefit the quality of care and potentially reduce mortality and morbidity in the older population. The aim of this study was to construct and validate an electronic health record-based fall risk predictive tool to identify elders at a higher risk of falls.

METHODS : The one-year fall prediction model was developed using the machine-learning-based algorithm, XGBoost, and tested on an independent validation cohort. The data were collected from electronic health records (EHR) of Maine from 2016 to 2018, comprising 265,225 older patients (≥65 years of age).

RESULTS : This model attained a validated C-statistic of 0.807, where 50 % of the identified high-risk true positives were confirmed to fall during the first 94 days of next year. The model also captured in advance 58.01 % and 54.93 % of falls that happened within the first 30 and 30-60 days of next year. The identified high-risk patients of fall showed conditions of severe disease comorbidities, an enrichment of fall-increasing cardiovascular and mental medication prescriptions and increased historical clinical utilization, revealing the complexity of the underlying fall etiology. The XGBoost algorithm captured 157 impactful predictors into the final predictive model, where cognitive disorders, abnormalities of gait and balance, Parkinson's disease, fall history and osteoporosis were identified as the top-5 strongest predictors of the future fall event.

CONCLUSIONS : By using the EHR data, this risk assessment tool attained an improved discriminative ability and can be immediately deployed in the health system to provide automatic early warnings to older adults with increased fall risk and identify their personalized risk factors to facilitate customized fall interventions.

Ye Chengyin, Li Jinmei, Hao Shiying, Liu Modi, Jin Hua, Zheng Le, Xia Minjie, Jin Bo, Zhu Chunqing, Alfreds Shaun T, Stearns Frank, Kanov Laura, Sylvester Karl G, Widen Eric, McElhinney Doff, Ling Xuefeng Bruce

2020-Mar-03

Accidental falls, Aged, Electronic health records, Supervised machine learning

In Diabetes & metabolic syndrome

BACKGROUND AND AIMS : Diabetes has been recognized as a continuing health challenge for the twenty-first century, both in developed and developing countries including Bangladesh. The main objective of this study is to use machine learning (ML) based classifiers for automated detection and classification of diabetes.

METHODS : The diabetes dataset have taken from Bangladesh demographic and health survey, 2011 data having 1569 respondents are 127 diabetes. Two statistical tests as independent t for continuous and chi-square for categorical variables are used to determine the risk factors of diabetes. Six ML-based classifiers as support vector machine, random forest, linear discriminant analysis, logistic regression, k-nearest neighborhood, bagged classification and regression tree (Bagged CART) have been adopted to predict and classify of diabetes.

RESULTS : Our findings show that 11 factors out of 15 factors are significantly associated with diabetes. Bagged CART provides the highest accuracy and area under the curve of 94.3% and 0.600.

CONCLUSIONS : Bagged CART anticipates a very supportive computational resource for classification of diabetes and it would be very helpful to the doctors for making a decision to control diabetes disease in Bangladesh.

Islam Md Merajul, Rahman Md Jahanur, Chandra Roy Dulal, Maniruzzaman Md

2020-Mar-10

Diabetes, Machine learning and Bangladesh

In Drug and alcohol dependence ; h5-index 64.0

AIMS : To determine the accuracy of a wearable sensor to detect and differentiate episodes of self-reported craving and stress in individuals with substance use disorders, and to assess acceptability, barriers, and facilitators to sensor-based monitoring in this population.

METHODS : This was an observational mixed methods pilot study. Adults enrolled in an outpatient treatment program for a substance use disorder wore a non-invasive wrist-mounted sensor for four days and self-reported episodes of stress and craving. Continuous physiologic data (accelerometry, skin conductance, skin temperature, and heart rate) were extracted from the sensors and analyzed via various machine learning algorithms. Semi-structured interviews were conducted upon study completion, and thematic analysis was conducted on qualitative data from semi-structured interviews.

RESULTS : Thirty individuals completed the protocol, and 43 % (N = 13) were female. A total of 41 craving and 104 stress events were analyzed. The differentiation accuracies of the top performing models were as follows: stress vs. non-stress states 74.5 % (AUC 0.82), craving vs. no-craving 75.7 % (AUC 0.82), and craving vs. stress 76.8 % (AUC 0.8). Overall participant perception was positive, and acceptability was high. Emergent themes from the exit interviews included a perception of connectedness and increased mindfulness related to wearing the sensor, both of which were reported as helpful to recovery. Barriers to engagement included interference with other daily wear items, and perceived stigma.

CONCLUSIONS : Wearable sensors can be used to objectively differentiate episodes of craving and stress, and individuals in recovery from substance use disorder are accepting of continuous monitoring with these devices.

Carreiro Stephanie, Chintha Keerthi Kumar, Shrestha Sloke, Chapman Brittany, Smelson David, Indic Premananda

2020-Mar-03

Craving, Sensor, Stress, Substance use disorder, Wearable, mHealth

In European journal of radiology ; h5-index 47.0

PURPOSE : To evaluate a deep learning based image analysis software for the detection and localization of distal radius fractures.

METHOD : A deep learning system (DLS) was trained on 524 wrist radiographs (166 showing fractures). Performance was tested on internal (100 radiographs, 42 showing fractures) and external test sets (200 radiographs, 100 showing fractures). Single and combined views of the radiographs were shown to DLS and three readers. Readers were asked to indicate fracture location with regions of interest (ROI). The DLS yielded scores (range 0-1) and a heatmap. Detection performance was expressed as AUC, sensitivity and specificity at the optimal threshold and compared to radiologists' performance. Heatmaps were compared to radiologists' ROIs.

RESULTS : The DLS showed excellent performance on the internal test set (AUC 0.93 (95% confidence interval (CI) 0.82-0.98) - 0.96 (0.87-1.00), sensitivity 0.81 (0.58-0.95) - 0.90 (0.70-0.99), specificity 0.86 (0.68-0.96) - 1.0 (0.88-1.0)). DLS performance decreased on the external test set (AUC 0.80 (0.71-0.88) - 0.89 (0.81-0.94), sensitivity 0.64 (0.49-0.77) - 0.92 (0.81-0.98), specificity 0.60 (0.45-0.74) - 0.90 (0.78-0.97)). Radiologists' performance was comparable on internal data (sensitivity 0.71 (0.48-0.89) - 0.95 (0.76-1.0), specificity 0.52 (0.32-0.71) - 0.97 (0.82-1.0)) and better on external data (sensitivity 0.88 (0.76-0.96) - 0.98 (0.89-1.0), specificities 0.66 (0.51-0.79) - 1.0 (0.93-1.0), p < 0.05). In over 90%, the areas of peak activation aligned with radiologists' annotations.

CONCLUSIONS : The DLS was able to detect and localize wrist fractures with a performance comparable to radiologists, using only a small dataset for training.

Blüthgen Christian, Becker Anton S, Vittoria de Martini Ilaria, Meier Andreas, Martini Katharina, Frauenfelder Thomas

2020-Mar-09

In Analytical and bioanalytical chemistry

Honrado Carlos, McGrath John S, Reale Riccardo, Bisegna Paolo, Swami Nathan S, Caselli Frederica

2020-Mar-18

Microfluidic impedance cytometry, Multiparametric characterization, Neural networks, Real-time processing, Single-cell analysis

In Scientific reports ; h5-index 158.0

Küpper Charlotte, Stroth Sanna, Wolff Nicole, Hauck Florian, Kliewer Natalia, Schad-Hansjosten Tanja, Kamp-Becker Inge, Poustka Luise, Roessner Veit, Schultebraucks Katharina, Roepke Stefan

2020-Mar-18

In Science translational medicine ; h5-index 138.0

Liu Zhen, Nguyen Quynh P H, Guan Qingxu, Albulescu Alexandra, Erdman Lauren, Mahdaviyeh Yasaman, Kang Jasmine, Ouyang Hong, Hegele Richard G, Moraes Theo, Goldenberg Anna, Dell Sharon D, Mennella Vito

2020-Mar-18

In BMC oral health ; h5-index 40.0

BACKGROUND : Artificial intelligence (AI) is a branch of computer science concerned with building smart software or machines capable of performing tasks that typically require human intelligence. We present a protocol for the use of AI to fabricate implant-supported monolithic zirconia crowns (MZCs) cemented on customized hybrid abutments.

METHODS : The study protocol consisted of: (1) intraoral scan of the implant position; (2) design of the individual abutment and temporary crown using computer-aided design (CAD) software; (3) milling of the zirconia abutment and the temporary polymethyl-methacrylate (PMMA) crown, with extraoral cementation of the zirconia abutment on the relative titanium bonding base, to generate an individual hybrid abutment; (4) clinical application of the hybrid abutment and the temporary PMMA crown; (5) intraoral scan of the hybrid abutment; (6) CAD of the final crown with automated margin line design using AI; (7) milling, sintering and characterisation of the final MZC; and (8) clinical application of the MZC. The outcome variables were mathematical (quality of the fabrication of the individual zirconia abutment) and clinical, such as (1) quality of the marginal adaptation, (2) of interproximal contact points and (3) of occlusal contacts, (4) chromatic integration, (5) survival and (6) success of MZCs. A careful statistical analysis was performed.

RESULTS : 90 patients (35 males, 55 females; mean age 53.3 ± 13.7 years) restored with 106 implant-supported MZCs were included in the study. The follow-up varied from 6 months to 3 years. The quality of the fabrication of individual hybrid abutments revealed a mean deviation of 44 μm (± 6.3) between the original CAD design of the zirconia abutment, and the mesh of the zirconia abutment captured intraorally at the end of the provisionalization. At the delivery of the MZCs, the marginal adaptation, quality of interproximal and occlusal contacts, and aesthetic integration were excellent. The three-year cumulative survival and success of the MZCs were 99.0% and 91.3%, respectively.

CONCLUSIONS : AI seems to represent a reliable tool for the restoration of single implants with MZCs cemented on customised hybrid abutments via a full digital workflow. Further studies are needed to confirm these positive results.

Lerner Henriette, Mouhyi Jaafar, Admakin Oleg, Mangano Francesco

2020-Mar-19

Artificial intelligence, Full digital workflow, Individual hybrid abutments, Marginal adaptation, Monolithic zirconia crowns, Success, Survival

In Circulation. Arrhythmia and electrophysiology

Okada David R, Miller Jason, Chrispin Jonathan, Prakosa Adityo, Trayanova Natalia, Jones Steven, Maggioni Mauro, Wu Katherine C

2020-Mar-18

spatial complexity; risk stratification

In Pharmaceutics

Van Hauwermeiren Daan, Stock Michiel, De Beer Thomas, Nopens Ingmar

2020-Mar-16

continuous manufacturing, data-driven, granulation, kernel mean embedding, kernel methods, machine learning, particle size distributions, predictive modeling, process modeling, wet granulation

ArXiv Preprint

Dong Wang, Yuan Zhang, Kexin Zhang, Liwei Wang

2020-03-20

In Metabolites

Peeters Laura, Van der Auwera Anastasia, Beirnaert Charlie, Bijttebier Sebastiaan, Laukens Kris, Pieters Luc, Hermans Nina, Foubert Kenn

2020-Mar-16

Caryophyllaceae, Herniaria hirsuta, dynamic metabolomics, machine learning, saponins, urolithiasis

ArXiv Preprint

Szu-Yeu Hu, Shuhang Wang, Wei-Hung Weng, JingChao Wang, XiaoHong Wang, Arinc Ozturk, Qian Li, Viksit Kumar, Anthony E. Samir

2020-03-20

In Journal of neural engineering ; h5-index 52.0

Jin Weina, Fatehi Mostafa, Abhishek Kumar, Mallya Mayur, Toyota Brian, Hamarneh Ghassan

2020-Mar-19

Brain radiomics, Deep learning, Glioma imaging, Machine learning

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

Acharya Jyotibdha, Basu Arindam

2020-Mar-18

In IEEE/ACM transactions on computational biology and bioinformatics

Tayara Hilal, Chong Kil

2020-Mar-18

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

Jeong Ji-Hoon, Shim Kyung-Hwan, Kim Dong-Joo, Lee Seong-Whan

2020-Mar-18

In IEEE transactions on image processing : a publication of the IEEE Signal Processing Society

Yang Zhengeng, Yu Hongshan, Feng Mingtao, Sun Wei, Lin Xuefei, Sun Mingui, Mao Zhi-Hong, Mian Ajmal

2020-Mar-18

In International journal of environmental research and public health ; h5-index 73.0

Feng Xiang, Wei Yaojia, Pan Xianglin, Qiu Longhui, Ma Yongmei

2020-Mar-16

academic emotion, academic emotion classification algorithm, academic emotion classification method, subjective well-being

In Radiology ; h5-index 91.0

Li Lin, Qin Lixin, Xu Zeguo, Yin Youbing, Wang Xin, Kong Bin, Bai Junjie, Lu Yi, Fang Zhenghan, Song Qi, Cao Kunlin, Liu Daliang, Wang Guisheng, Xu Qizhong, Fang Xisheng, Zhang Shiqin, Xia Juan, Xia Jun

2020-Mar-19

ArXiv Preprint

Insaf Setitra, Noureddine Aouaa, Abdelkrim Meziane, Afef Benrabia, Houria Kaced, Hanene Belabassi, Sara Ait Ziane, Nadia Henda Zenati, Oualid Djekkoune

2020-03-20

In Journal of medical Internet research ; h5-index 88.0

BACKGROUND : In chronical neurological diseases, especially in multiple sclerosis (MS), clinical assessment of motor dysfunction is crucial to monitor patients' disease. Traditional scales are not sensitive enough to detect slight changes. Video recordings of patient performance are more accurate and increase reliability in severity ratings. With these recordings automated, quantitative disability assessments by machine learning algorithms (MLA) may be created. Creation of these algorithms involves non-healthcare professionals, which is a challenge for keeping data privacy. Autoencoders may overcome this issue.

OBJECTIVE : The aim of this proof of concept study was to test whether coded frame vectors of autoencoders contain relevant information for analysing videos of motor performance of MS patients.

METHODS : In this study, twenty pre-rated videos of patients performing the finger-to-nose test (FNT) were recorded. An autoencoder created encoded frame vectors from the original videos and decoded the videos again. Original and decoded videos were shown to 10 neurologists of an academic MS centre in Basel, Switzerland. Neurologists tested whether these 200 videos in total were human-readable after decoding and rated the severity grade of each original and decoded video according to the Neurostatus-EDSS definitions of limb ataxia. Furthermore, the neurologists tested whether ratings were equivalent between original and decoded videos.

RESULTS : In total, 172 from 200 (86%) videos had sufficient quality to be ratable. The intra-rater agreement between the original and decoded videos was 0.317 (Cohen's weighted kappa). The average difference of ratings between original and decoded videos was 0.26 , in which the original videos were rated as more severe. The inter-rater agreement between the original and decoded videos was 0.459 (Cohen's weighted kappa) and 0.302 (Cohen's weighted kappa), respectively. The agreement was higher when no deficits or very severe deficits were present.

CONCLUSIONS : The vast majority of videos decoded by an auto-encoder contained clinically relevant information and had a fair intra-rater agreement with the original video. Autoencoders are a potential method for enabling the use of patient videos while preserving data privacy, especially when non-healthcare professionals are involved.

CLINICALTRIAL :

D’Souza Marcus, Van Munster Caspar E P, Dorn Jonas, Dorier Alexis, Kamm Christian P, Steinheimer Saskia, Dahlke Frank, Uitdehaag Bernard M J, Kappos Ludwig, Johnson Matthew

2020-Mar-19

In Radiology ; h5-index 91.0

Li Lin, Qin Lixin, Xu Zeguo, Yin Youbing, Wang Xin, Kong Bin, Bai Junjie, Lu Yi, Fang Zhenghan, Song Qi, Cao Kunlin, Liu Daliang, Wang Guisheng, Xu Qizhong, Fang Xisheng, Zhang Shiqin, Xia Juan, Xia Jun

2020-Mar-19

In American journal of public health ; h5-index 90.0

Walter Dror, Ophir Yotam, Jamieson Kathleen Hall

2020-Mar-19

In The journal of physical chemistry letters ; h5-index 129.0

Gu Geun Ho, Noh Juhwan, Kim Sungwon, Back Seoin, Ulissi Zachary W, Jung Yousung

2020-Mar-19

In Thoracic cancer

BACKGROUND : IBM Watson for Oncology (WFO) provides physicians with evidence-based treatment options. This study was designed to explore the concordance of the suggested therapeutic regimen for advanced non-small cell lung (NSCLC) cancer patients between the updated version of WFO and physicians in our department, in order to reflect the differences of cancer treatment between China and the United States.

METHODS : Retrospective data from 165 patients with advanced NSCLC from September 2014 to March 2018 were entered manually into WFO. WFO recommendations were provided in three categories: recommended, for consideration, and not recommended. Concordance was analyzed by comparing the treatment decisions proposed by WFO with the real treatment. Potential influenced factors were also analyzed.

RESULTS : Overall, the treatment recommendations were concordant in 73.3% (121/165) of cases. When two alternative drugs such as icotinib and nedaplatin were included as "for consideration," the total consistency could be elevated from 73.3% to 90.3%(149/165). The logistic regression analysis showed that gender (P = 0.096), ECOG (P = 0.0.502), smoking (P = 0.455), and pathology (P = 0.633) had no effect on consistency, but stages (P = 0.019), including stage ≤III (77.8%, 21/27) and stage IV (93.5%, 129/138) had significant effects on consistency.

CONCLUSIONS : In China, most of the treatment recommendations of WFO are consistent with the real world treatment. Factors such as patient preferences, prices, drug approval and medical insurance are also taken into consideration, and they ultimately affect the inconsistency. To be comprehensively and rapidly applied in China, localization needs to be accelerated by WFO.

Yao Shuyang, Wang Ruotian, Qian Kun, Zhang Yi

2020-Mar-19

Advanced disease, Watson for Oncology, artificial intelligence, concordance, non-small cell lung cancer

In Aging ; h5-index 49.0

Zhao Cui, Liang Ying, Chen Ting, Zhong Yihua, Li Xianglong, Wei Jing, Li Chunlin, Zhang Xu

2020-Mar-19

aging, cognition, machine learning, white matter lesions (WMLs)

In Health informatics journal ; h5-index 25.0

Wingfield Benjamin, Miller Shane, Yogarajah Pratheepan, Kerr Dermot, Gardiner Bryan, Seneviratne Sudarshi, Samarasinghe Pradeepa, Coleman Sonya

2020-Mar-19

autism spectrum disorder, decision support system, machine learning

In Journal of medicinal chemistry ; h5-index 88.0

van Oosten Luuk Nico, Klein Christian D

2020-Mar-19

In Australian and New Zealand journal of public health

INTRODUCTION : A Melanoma Screening Summit was held in Brisbane, Australia, to review evidence regarding current approaches for early detection of melanomas and explore new opportunities.

RESULTS : Formal population-based melanoma screening is not carried out in Australia, but there is evidence of considerable opportunistic screening as well as early detection. Biopsy rates are rising and most melanomas are now diagnosed when in situ. Based on evidence review and expert opinion, the Summit attendees concluded that there is currently insufficient information in terms of comparative benefits, harms and costs to support change from opportunistic to systematic screening. Assessment of gains in precision and cost-effectiveness of integrating total body imaging, artificial intelligence algorithms and genetic risk information is required, as well as better understanding of clinical and molecular features of thin fatal melanomas.

CONCLUSIONS : Research is needed to understand how to further optimise early detection of melanoma in Australia. Integrating risk-based population stratification and more precise diagnostic tests is likely to improve the balance of benefits and harms of opportunistic screening, pending assessment of cost-effectiveness. Implications for public health: The Summit Group identified that the personal and financial costs to the community of detecting and treating melanoma are rising, and this may be mitigated by developing and implementing a more systematic process for diagnosing melanoma.

Janda Monika, Cust Anne E, Neale Rachel E, Aitken Joanne F, Baade Peter D, Green Adele C, Khosrotehrani Kiarash, Mar Victoria, Soyer H Peter, Whiteman David C

2020-Mar-19

early detection, melanoma, prevention, screening, skin cancer

In Journal of magnetic resonance imaging : JMRI

Gonçalves Fabrício Guimarães, Chawla Sanjeev, Mohan Suyash

2020-Mar-19

arterial spin labeling, artificial intelligence, chemical exchange saturation transfer, diffusion weighted imaging, dynamic contrast enhancement, dynamic susceptibility contrast, glioblastoma, perfusion weighted imaging, proton MR spectroscopy

In International journal of molecular sciences ; h5-index 102.0

Muscat Stefano, Pallante Lorenzo, Stojceski Filip, Danani Andrea, Grasso Gianvito, Deriu Marco Agostino

2020-Mar-16

Alzheimer’s disease, Amyloid β, S-shape, ensemble docking, molecular dynamics, natural compounds

In Journal of medical systems ; h5-index 48.0

Santosh K C

2020-Mar-18

Active learning, Artificial intelligence, COVID-19, Cross-population train/test models, Machine learning, Multitudinal and multimodal data

ArXiv Preprint

Rafael T. Sousa, Lucas A. Pereira, Anderson S. Soares

2020-03-20

In International journal of neonatal screening

Peng Gang, Tang Yishuo, Cowan Tina M, Enns Gregory M, Zhao Hongyu, Scharfe Curt

2020-Mar

Random Forest, false positive, inborn metabolic disorders, machine learning, newborn screening, second-tier testing, tandem mass spectrometry

In Quantitative imaging in medicine and surgery

Background : Recently, the paradigm of computed tomography (CT) reconstruction has shifted as the deep learning technique evolves. In this study, we proposed a new convolutional neural network (called ADAPTIVE-NET) to perform CT image reconstruction directly from a sinogram by integrating the analytical domain transformation knowledge.

Methods : In the proposed ADAPTIVE-NET, a specific network layer with constant weights was customized to transform the sinogram onto the CT image domain via analytical back-projection. With this new framework, feature extractions were performed simultaneously on both the sinogram domain and the CT image domain. The Mayo low dose CT (LDCT) data was used to validate the new network. In particular, the new network was compared with the previously proposed residual encoder-decoder (RED)-CNN network. For each network, the mean square error (MSE) loss with and without VGG-based perceptual loss was compared. Furthermore, to evaluate the image quality with certain metrics, the noise correlation was quantified via the noise power spectrum (NPS) on the reconstructed LDCT for each method.

Results : CT images that have clinically relevant dimensions of 512×512 can be easily reconstructed from a sinogram on a single graphics processing unit (GPU) with moderate memory size (e.g., 11 GB) by ADAPTIVE-NET. With the same MSE loss function, the new network is able to generate better results than the RED-CNN. Moreover, the new network is able to reconstruct natural looking CT images with enhanced image quality if jointly using the VGG loss.

Conclusions : The newly proposed end-to-end supervised ADAPTIVE-NET is able to reconstruct high-quality LDCT images directly from a sinogram.

Ge Yongshuai, Su Ting, Zhu Jiongtao, Deng Xiaolei, Zhang Qiyang, Chen Jianwei, Hu Zhanli, Zheng Hairong, Liang Dong

2020-Feb

CT reconstruction, Computed tomography (CT), convolutional neural network (CNN), domain transformation, low dose CT reconstruction

In Quantitative imaging in medicine and surgery

Background : This article aims to develop and assess the radiomics paradigm for predicting colorectal cancer liver metastasis (CRLM) from the primary tumor.

Methods : This retrospective study included 100 patients from the First Hospital of Jilin University from June 2017 to December 2017. The 100 patients comprised 50 patients with and 50 without CRLM. The maximum-level enhanced computed tomography (CT) image of primary cancer in the portal venous phase of each patient was selected as the original image data. To automatically implement radiomics-related paradigms, we developed a toolkit called Radiomics Intelligent Analysis Toolkit (RIAT).

Results : With RIAT, the model based on logistic regression (LR) using both the radiomics and clinical information signatures showed the maximum net benefit. The area under the curve (AUC) value was 0.90±0.02 (sensitivity =0.85±0.02, specificity =0.79±0.04) for the training set, 0.86±0.11 (sensitivity =0.85±0.09, specificity =0.75±0.19) for the verification set, 0.906 (95% CI, 0.840-0.971; sensitivity =0.81, specificity =0.84) for the cross-validation set, and 0.899 (95% CI, 0.761-1.000; sensitivity =0.78, specificity =0.91) for the test set.

Conclusions : The radiomics nomogram-based LR with clinical risk and radiomics features allows for a more accurate classification of CRLM using CT images with RIAT.

Li Mingyang, Li Xueyan, Guo Yu, Miao Zheng, Liu Xiaoming, Guo Shuxu, Zhang Huimao

2020-Feb

Radiomics, colorectal cancer liver metastasis (CRLM), machine learning, nomogram

In Quantitative imaging in medicine and surgery

Background : To evaluate the potential of clinical-based model, a biparametric MRI-based radiomics model and a clinical-radiomics combined model for predicting clinically significant prostate cancer (PCa).

Methods : In total, 381 patients with clinically suspicious PCa were included in this retrospective study; of those, 199 patients did not have PCa upon biopsy, while 182 patients had PCa. All patients underwent 3.0-T MRI examinations with the same acquisition parameters, and clinical risk factors associated with PCa (age, prostate volume, serum PSA, etc.) were collected. We randomly stratified the training and test sets using a 6:4 ratio. The radiomic features included gradient-based histogram features, grey-level co-occurrence matrix (GLCM), run-length matrix (RLM), and grey-level size zone matrix (GLSZM). Three models were developed using multivariate logistic regression analysis to predict clinically significant PCa: a clinical model, a radiomics model and a clinical-radiomics combined model. The diagnostic performance and clinical net benefit of each model were compared via receiver operating characteristic (ROC) curve analysis and decision curves, respectively.

Results : Both the radiomics model (AUC: 0.98) and the clinical-radiomics combined model (AUC: 0.98) achieved greater predictive efficacy than the clinical model (AUC: 0.79). The decision curve analysis also showed that the radiomics model and combined model had higher net benefits than the clinical model.

Conclusions : Compared with the evaluation of clinical risk factors associated with PCa only, the radiomics-based machine learning model can improve the predictive accuracy for clinically significant PCa, in terms of both diagnostic performance and clinical net benefit.

Li Mengjuan, Chen Tong, Zhao Wenlu, Wei Chaogang, Li Xiaobo, Duan Shaofeng, Ji Libiao, Lu Zhihua, Shen Junkang

2020-Feb

Prostate cancer, classification, clinical risk factors, machine learning, radiomics

In IEEE journal of translational engineering in health and medicine

Gautam Arvind, Panwar Madhuri, Biswas Dwaipayan, Acharyya Amit

2020

CNN, LSTM, joint angle prediction, movement classification, sEMG, signal processing, transfer learning

In The American economic review

Deryugina Tatyana, Heutel Garth, Miller Nolan H, Molitor David, Reif Julian

2019-Dec

I12, J14, Q51, Q53

In Journal of interpersonal violence

Yu Meihua, Huang Lingling, Mao Jiaqi, Dna Gese, Luo Siyang

2020-Mar-19

automatic negative thoughts, childhood maltreatment, culture, genetics, resilience

In Expert opinion on drug safety

Ruiz Diaz Juan Carlos, Frenkel Daniel, Aronow Wilbert S

2020-Mar-19

Antipsychotics, QT interval prolongation, arrhythmias, atypical antipsychotics, first generation, second generation, sudden cardiac death, torsades de pointes, typical antipsychotics

In Metabolomics : Official journal of the Metabolomic Society

INTRODUCTION : The use of 2D NMR data sources (COSY in this paper) allows to reach general metabolomics results which are at least as good as the results obtained with 1D NMR data, and this with a less advanced and less complex level of pre-processing. But a major issue still exists and can largely slow down a generalized use of 2D data sources in metabolomics: the experiment duration.

OBJECTIVE : The goal of this paper is to overcome the experiment duration issue in our recently published MIC strategy by considering faster 2D COSY acquisition techniques: a conventional COSY with a reduced number of transients and the use of the Non-Uniform Sampling (NUS) method. These faster alternatives are all submitted to novel 2D pre-processing workflows and to Metabolomic Informative Content analyses. Eventually, results are compared to those obtained with conventional COSY spectra.

METHODS : To pre-process the 2D data sources, the Global Peak List (GPL) workflow and the Vectorization workflow are used. To compare this data sources and to detect the more informative one(s), MIC (Metabolomic Informative Content) indexes are used, based on clustering and inertia measures of quality.

RESULTS : Results are discussed according to a multi-factor experimental design (which is unsupervised and based on human urine samples). Descriptive PCA results and MIC indexes are shown, leading to the direct and objective comparison of the different data sets.

CONCLUSION : In conclusion, it is demonstrated that conventional COSY spectra recorded with only one transient per increment and COSY spectra recorded with 50% of non-uniform sampling provide very similar MIC results as the initial COSY recorded with four transients, but in a much shorter time. Consequently, using techniques like the reduction of the number of transients or NUS can really open the door to a potential high-throughput use of 2D COSY spectra in metabolomics.

Féraud Baptiste, Martineau Estelle, Leenders Justine, Govaerts Bernadette, de Tullio Pascal, Giraudeau Patrick

2020-Mar-18

2D NMR, 2D pre-processing workflows, COSY spectra, Global peak list, Metabolomic informative content (MIC), Non-uniform sampling (NUS), Vectorization

In Journal of medical systems ; h5-index 48.0

Santosh K C

2020-Mar-18

Active learning, Artificial intelligence, COVID-19, Cross-population train/test models, Machine learning, Multitudinal and multimodal data

In BMC cancer

BACKGROUND : As the number of PET/CT scanners increases and FDG PET/CT becomes a common imaging modality for oncology, the demands for automated detection systems on artificial intelligence (AI) to prevent human oversight and misdiagnosis are rapidly growing. We aimed to develop a convolutional neural network (CNN)-based system that can classify whole-body FDG PET as 1) benign, 2) malignant or 3) equivocal.

METHODS : This retrospective study investigated 3485 sequential patients with malignant or suspected malignant disease, who underwent whole-body FDG PET/CT at our institute. All the cases were classified into the 3 categories by a nuclear medicine physician. A residual network (ResNet)-based CNN architecture was built for classifying patients into the 3 categories. In addition, we performed a region-based analysis of CNN (head-and-neck, chest, abdomen, and pelvic region).

RESULTS : There were 1280 (37%), 1450 (42%), and 755 (22%) patients classified as benign, malignant and equivocal, respectively. In the patient-based analysis, CNN predicted benign, malignant and equivocal images with 99.4, 99.4, and 87.5% accuracy, respectively. In region-based analysis, the prediction was correct with the probability of 97.3% (head-and-neck), 96.6% (chest), 92.8% (abdomen) and 99.6% (pelvic region), respectively.

CONCLUSION : The CNN-based system reliably classified FDG PET images into 3 categories, indicating that it could be helpful for physicians as a double-checking system to prevent oversight and misdiagnosis.

Kawauchi Keisuke, Furuya Sho, Hirata Kenji, Katoh Chietsugu, Manabe Osamu, Kobayashi Kentaro, Watanabe Shiro, Shiga Tohru

2020-Mar-17

Convolutional neural network, Deep learning, FDG, PET

In BMC bioinformatics

BACKGROUND : DNA methylation (DNAm) is an epigenetic regulator of gene expression programs that can be altered by environmental exposures, aging, and in pathogenesis. Traditional analyses that associate DNAm alterations with phenotypes suffer from multiple hypothesis testing and multi-collinearity due to the high-dimensional, continuous, interacting and non-linear nature of the data. Deep learning analyses have shown much promise to study disease heterogeneity. DNAm deep learning approaches have not yet been formalized into user-friendly frameworks for execution, training, and interpreting models. Here, we describe MethylNet, a DNAm deep learning method that can construct embeddings, make predictions, generate new data, and uncover unknown heterogeneity with minimal user supervision.

RESULTS : The results of our experiments indicate that MethylNet can study cellular differences, grasp higher order information of cancer sub-types, estimate age and capture factors associated with smoking in concordance with known differences.

CONCLUSION : The ability of MethylNet to capture nonlinear interactions presents an opportunity for further study of unknown disease, cellular heterogeneity and aging processes.

Levy Joshua J, Titus Alexander J, Petersen Curtis L, Chen Youdinghuan, Salas Lucas A, Christensen Brock C

2020-Mar-17

DNA methylation, Deep learning, Embedding, High performance computing, Supervised, Transfer learning, Unsupervised, Workflow automation

In BMC bioinformatics

BACKGROUND : Lung cancer is the leading cause of cancer-related deaths in both men and women in the United States, and it has a much lower five-year survival rate than many other cancers. Accurate survival analysis is urgently needed for better disease diagnosis and treatment management.

RESULTS : In this work, we propose a survival analysis system that takes advantage of recently emerging deep learning techniques. The proposed system consists of three major components. 1) The first component is an end-to-end cellular feature learning module using a deep neural network with global average pooling. The learned cellular representations encode high-level biologically relevant information without requiring individual cell segmentation, which is aggregated into patient-level feature vectors by using a locality-constrained linear coding (LLC)-based bag of words (BoW) encoding algorithm. 2) The second component is a Cox proportional hazards model with an elastic net penalty for robust feature selection and survival analysis. 3) The third commponent is a biomarker interpretation module that can help localize the image regions that contribute to the survival model's decision. Extensive experiments show that the proposed survival model has excellent predictive power for a public (i.e., The Cancer Genome Atlas) lung cancer dataset in terms of two commonly used metrics: log-rank test (p-value) of the Kaplan-Meier estimate and concordance index (c-index).

CONCLUSIONS : In this work, we have proposed a segmentation-free survival analysis system that takes advantage of the recently emerging deep learning framework and well-studied survival analysis methods such as the Cox proportional hazards model. In addition, we provide an approach to visualize the discovered biomarkers, which can serve as concrete evidence supporting the survival model's decision.

Cui Lei, Li Hansheng, Hui Wenli, Chen Sitong, Yang Lin, Kang Yuxin, Bo Qirong, Feng Jun

2020-Mar-18

Cell detection, Deep learning, Feature learning, Survival analysis

In Proceedings. Biological sciences

Ding Manyu, Wang Tianyi, Ko Albert Min-Shan, Chen Honghai, Wang Hui, Dong Guanghui, Lu Hongliang, He Wei, Wangdue Shargan, Yuan Haibing, He Yuanhong, Cai Linhai, Chen Zujun, Hou Guangliang, Zhang Dongju, Zhang Zhaoxia, Cao Peng, Dai Qingyan, Feng Xiaotian, Zhang Ming, Wang Hongru, Yang Melinda A, Fu Qiaomei

2020-Mar-25

Tibetan prehistory, ancient DNA, population genetics of humans

In International journal of environmental research and public health ; h5-index 73.0

Castillo-Olea Cristián, Garcia-Zapirain Soto Begonya, Zuñiga Clemente

2020-Mar-15

machine learning, prevalence, sarcopenia level

ArXiv Preprint

Brandon Carter, Siddhartha Jain, Jonas Mueller, David Gifford

2020-03-19

In International journal of environmental research and public health ; h5-index 73.0

Hsu Chi-Chieh, Gu Ming, Lee Tian-Shyug, Lu Chi-Jie

2020-Mar-15

BMI, CEI, MARS, Sit-and-reach, Sit-ups, Sleep duration, Sleep quality

ArXiv Preprint

Ryan Hoque, Daniel Seita, Ashwin Balakrishna, Aditya Ganapathi, Ajay Kumar Tanwani, Nawid Jamali, Katsu Yamane, Soshi Iba, Ken Goldberg

2020-03-19

In Biomolecules

Bemister-Buffington Joseph, Wolf Alex J, Raschka Sebastian, Kuhn Leslie A

2020-Mar-14

GPCR activity determinants, MLxtend, ProFlex, allostery, coupled residues, feature selection, flexibility analysis, pattern classification

ArXiv Preprint

Tianyi Zhang, Yun Gu, Xiaolin Huang, Enmei Tu, Jie Yang

2020-03-19

In Physics in medicine and biology

Lin Yu-Chun, Huang Hsuan-Ming

2020-Mar-18

deep learning, diffusion-weighted magnetic resonance imaging, image denoising

In Cell reports ; h5-index 119.0

Reker Daniel, Shi Yunhua, Kirtane Ameya R, Hess Kaitlyn, Zhong Grace J, Crane Evan, Lin Chih-Hsin, Langer Robert, Traverso Giovanni

2020-Mar-17

data science, drug delivery, excipient-drug interactions, food-drug interactions, inactive ingredients, machine learning, pharmacokinetics, pharmacology, virtual screening

In Revista brasileira de psiquiatria (Sao Paulo, Brazil : 1999)

Borrione Lucas, Bellini Helena, Razza Lais Boralli, Avila Ana G, Baeken Chris, Brem Anna-Katharine, Busatto Geraldo, Carvalho Andre F, Chekroud Adam, Daskalakis Zafiris J, Deng Zhi-De, Downar Jonathan, Gattaz Wagner, Loo Colleen, Lotufo Paulo A, Martin Maria da Graça M, McClintock Shawn M, O’Shea Jacinta, Padberg Frank, Passos Ives C, Salum Giovanni A, Vanderhasselt Marie-Anne, Fraguas Renerio, Benseñor Isabela, Valiengo Leandro, Brunoni Andre R

2020-Mar-16

In Molecules (Basel, Switzerland)

Matsuzaka Yasunari, Hosaka Takuomi, Ogaito Anna, Yoshinari Kouichi, Uesawa Yoshihiro

2020-Mar-13

DeepSnap, QSAR, aryl hydrocarbon receptor, chemical structure, deep learning, machine learning

ArXiv Preprint

Yonghui Zhang, Ke Gu

2020-03-19

In PloS one ; h5-index 176.0

Lin Erin, Qin Rongjun, Edgerton Jared, Kong Deren

2020

In Neural computation

Frazier-Logue Noah, Hanson Stephen José

2020-Mar-18

In Neural computation

Mofrad Asieh Abolpour, Yazidi Anis, Hammer Hugo L, Arntzen Erik

2020-Mar-18

In Neural computation

Gao Jing, Li Peng, Chen Zhikui, Zhang Jianing

2020-Mar-18

In Bioinformatics (Oxford, England)

MOTIVATION : The Protein Data Bank (PDB), the ultimate source for data in structural biology, is inherently imbalanced. To alleviate biases, virtually all structural biology studies use non-redundant subsets of the PDB, which include only a fraction of the available data. An alternative approach, dubbed redundancy-weighting, down-weights redundant entries rather than discarding them. This approach may be particularly helpful for Machine Learning (ML) methods that use the PDB as their source for data.Methods for Secondary Structure Prediction (SSP) have greatly improved over the years with recent studies achieving above 70% accuracy for 8-class (DSSP) prediction. As these methods typically incorporate machine learning techniques, training on redundancy-weighted datasets might improve accuracy, as well as pave the way toward larger and more informative secondary structure alphabets.

RESULTS : This article compares the SSP performances of Deep Learning (DL) models trained on either redundancy-weighted or non-redundant datasets. We show that training on redundancy-weighted sets consistently results in better prediction of 3-class (HCE), 8-class (DSSP) and 13-class (STR2) secondary structures.

AVAILABILITY : Data and DL models are available in http://meshi1.cs.bgu.ac.il/rw.

Sidi Tomer, Keasar Chen

2020-Mar-18

In JMIR medical informatics ; h5-index 23.0

BACKGROUND : Cardiac arrest is the most serious death-related event in intensive care units (ICUs), but it is not easily predicted because of the complex and time-dependent data characteristics of intensive care patients. Given the complexity and time dependence of ICU data, deep learning-based methods are expected to provide a good foundation for developing risk prediction models based on large clinical records.

OBJECTIVE : This study aimed to implement a deep learning model that estimates the distribution of cardiac arrest risk probability over time based on clinical data and assesses its potential.

METHODS : A retrospective study of 759 ICU patients was conducted between January 2013 and July 2015. A character-level gated recurrent unit with a Weibull distribution algorithm was used to develop a real-time prediction model. Fivefold cross-validation testing (training set: 80% and validation set: 20%) determined the consistency of model accuracy. The time-dependent area under the curve (TAUC) was analyzed based on the aggregation of 5 validation sets.

RESULTS : The TAUCs of the implemented model were 0.963, 0.942, 0.917, 0.875, 0.850, 0.842, and 0.761 before cardiac arrest at 1, 8, 16, 24, 32, 40, and 48 hours, respectively. The sensitivity was between 0.846 and 0.909, and specificity was between 0.923 and 0.946. The distribution of risk between the cardiac arrest group and the non-cardiac arrest group was generally different, and the difference rapidly increased as the time left until cardiac arrest reduced.

CONCLUSIONS : A deep learning model for forecasting cardiac arrest was implemented and tested by considering the cumulative and fluctuating effects of time-dependent clinical data gathered from a large medical center. This real-time prediction model is expected to improve patient's care by allowing early intervention in patients at high risk of unexpected cardiac arrests.

Kim Junetae, Park Yu Rang, Lee Jeong Hoon, Lee Jae-Ho, Kim Young-Hak, Huh Jin Won

2020-Mar-18

Weibull distribution, cardiac arrest, deep learning, forecasting, gated recurrent unit, intensive care units

In Nano letters ; h5-index 188.0

Wang Tian-Yu, Meng Jia-Lin, Rao Ming-Yi, He Zhen-Yu, Chen Lin, Zhu Hao, Sun Qing-Qing, Ding Shi-Jin, Bao Wen-Zhong, Zhou Peng, Zhang David Wei

2020-Mar-23

artificial neural network, information transmission, memristor array, wearable electronics

In American journal of transplantation : official journal of the American Society of Transplantation and the American Society of Transplant Surgeons

Farris Alton B, Moghe Ishita, Wu Simon, Hogan Julien, Cornell Lynn D, Alexander Mariam P, Kers Jesper, Demetris Anthony J, Levenson Richard M, Tomaszewski John, Barisoni Laura, Yagi Yukako, Solez Kim

2020-Mar-17

In Integrative psychological & behavioral science

Sætra Henrik Skaug

2020-Mar-17

Artificial intelligence, Cooperation, Cultural psychology, Deception, Social robots

In Molecular genetics and genomics : MGG

Singh Noor Pratap, Vinod P K

2020-Mar-17

Data integration, Epigenetic regulation, Multi-omics, Multiple kernel learning, RNASeq, Renal cell carcinoma, Tumor stage prediction

In Biomolecules

Yoo Duck Kyun, Lee Seung Ryul, Jung Yushin, Han Haejun, Lee Hwa Kyoung, Han Jerome, Kim Soohyun, Chae Jisu, Ryu Taehoon, Chung Junho

2020-Mar-08

antibody discovery, c-Met, machine learning, next-generation sequencing, phage display, random forest

ArXiv Preprint

Julian Lo, Morgan Heisler, Vinicius Vanzan, Sonja Karst, Ivana Zadro Matovinovic, Sven Loncaric, Eduardo V. Navajas, Mirza Faisal Beg, Marinko V. Sarunic

2020-03-19

In Database : the journal of biological databases and curation

Ahmed Zeeshan, Mohamed Khalid, Zeeshan Saman, Dong XinQi

2020-Jan-01

In Frontiers in bioengineering and biotechnology

Mukherjee Satanik, Nazemi Majid, Jonkers Ilse, Geris Liesbet

2020

bone remodeling, cartilage degeneration, data driven approach, finite element modeling, gene regulatory network, in silico modeling

In Frontiers in oncology

Feng Zhan, Zhang Lixia, Qi Zhong, Shen Qijun, Hu Zhengyu, Chen Feng

2020

BAP1 mutation, CT, clear cell renal cell carcinoma, machine learning, radiomics

In Applications in plant sciences

Premise : Large-scale efforts to digitize herbaria have resulted in more than 18 million publicly available Plantae images on sites such as iDigBio. The automation of image post-processing will lead to time savings in the digitization of biological specimens, as well as improvements in data quality. Here, new and modified neural network methodologies were developed to automatically detect color reference charts (CRC), enabling the future automation of various post-processing tasks.

Methods and Results : We used 1000 herbarium specimen images from 52 herbaria to test our novel neural network model, ColorNet, which was developed to identify CRCs smaller than 4 cm², resulting in a 30% increase in accuracy over the performance of other state-of-the-art models such as Faster R-CNN. For larger CRCs, we propose modifications to Faster R-CNN to increase inference speed.

Conclusions : Our proposed neural networks detect a range of CRCs, which may enable the automation of post-processing tasks found in herbarium digitization workflows, such as image orientation or white balance correction.

Ledesma Dakila A, Powell Caleb A, Shaw Joey, Qin Hong

2020-Mar

automation, digitization, herbarium, machine learning, natural history collections, specimen images

In F1000Research

Cheong Jin Hyun, Brooks Sawyer, Chang Luke J

2019

Python toolbox, affective computing, facial expressions, head-mounted camera, synchronization

In Frontiers in pharmacology

Wan Fangping, Li Shuya, Tian Tingzhong, Lei Yipin, Zhao Dan, Zeng Jianyang

2020

L1000 gene expression profiles, machine learning, semi-supervised neural network, synthetic lethality, target identification

In Neuropsychiatric disease and treatment

Background : A growing body of research suggests that major depressive disorder (MDD) is one of the most common psychiatric conditions associated with suicide ideation (SI). However, how a combination of easily accessible variables built a utility clinically model to estimate the probability of an individual patient with SI via machine learning is limited.

Methods : We used the electronic medical record database from a hospital located in western China. A total of 1916 Chinese patients with MDD were included. Easily accessible data (demographic, clinical, and biological variables) were collected at admission (on the first day of admission) and were used to distinguish SI with MDD from non-SI using a machine learning algorithm (neural network).

Results : The neural network algorithm distinguished 1356 out of 1916 patients translating into 70.08% accuracy (70.68% sensitivity and 67.09% specificity) and an area under the curve (AUC) of 0.76. The most relevant predictor variables in identifying SI from non-SI included free thyroxine (FT4), the total scores of Hamilton Depression Scale (HAMD), vocational status, and free triiodothyronine (FT3).

Conclusion : Risk for SI among patients with MDD can be identified at an individual subject level by integrating demographic, clinical, and biological variables as possible as early during hospitalization (at admission).

Ge Fenfen, Jiang Jingwen, Wang Yue, Yuan Cui, Zhang Wei

2020

depression, machine learning, real-world, suicide ideation

In mBio

Petzke Mary M, Volyanskyy Konstantin, Mao Yong, Arevalo Byron, Zohn Raphael, Quituisaca Johanna, Wormser Gary P, Dimitrova Nevenka, Schwartz Ira

2020-Mar-17

Borrelia burgdorferi\n, Lyme disease, diagnostics, random forest, transcriptome

In Clinical microbiology and infection : the official publication of the European Society of Clinical Microbiology and Infectious Diseases

OBJECTIVES : Previous studies reported inconsistent results between pneumonia and meteorological factors. We aimed to identify principal meteorological factors associated with pneumonia and to estimate the effect size and lag time.

METHODS : This is a nationwide population-based study using a healthcare claims database merged with a weather database in eight metropolitan cities in Korea. We applied a stepwise approach using the Granger causality test and generalized additive model to elucidate the association between weekly pneumonia incidence (WPI) and meteorological factors/air pollutants (MFAP). Impulse response function was used to examine the time lag.

RESULTS : In total, 2,011,424 cases of pneumonia were identified from 2007 to 2017. Among MFAP, diurnal temperature range (DTR), humidity, and particulate matter ≤2.5 μm in diameter (PM_2.5) had the lowest Akaike information criterion (0.40) and showed statistically significant associations with WPI (p<0.001 for all 3 MFAPs). The association of DTR and WPI showed an inverted U pattern for bacterial and unspecified pneumonia, whereas for viral pneumonia, WPI increased gradually in a more linear manner with DTR and no substantial decline. Humidity showed a consistent pattern in all three pneumonia categories. WPI steeply increased up to 10-20 μg/m³ of PM_2.5 but did not show a further increase in higher concentrations. Based on the result, we examined the effect of MFAP in different lag times up to 3 weeks.

CONCLUSIONS : DTR, humidity, and PM_2.5 were identified as MFAP most closely associated with WPI. With the model, we were able to visualize the effect-time association of MFAP and WPI.

Huh Kyungmin, Hong Jinwook, Jung Jaehun

2020-Mar-14

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

Ning Xia, Zhang Chi, Wang Kai, Zhao Zhongming, Mathé Ewy

2020-Mar-18

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