In Patient education and counseling ; h5-index 0.0

OBJECTIVE : Serious illness conversations are complex clinical narratives that remain poorly understood. Natural Language Processing (NLP) offers new approaches for identifying hidden patterns within the lexicon of stories that may reveal insights about the taxonomy of serious illness conversations.

METHODS : We analyzed verbatim transcripts from 354 consultations involving 231 patients and 45 palliative care clinicians from the Palliative Care Communication Research Initiative. We stratified each conversation into deciles of "narrative time" based on word counts. We used standard NLP analyses to examine the frequency and distribution of words and phrases indicating temporal reference, illness terminology, sentiment and modal verbs (indicating possibility/desirability).

RESULTS : Temporal references shifted steadily from talking about the past to talking about the future over deciles of narrative time. Conversations progressed incrementally from "sadder" to "happier" lexicon; reduction in illness terminology accounted substantially for this pattern. We observed the following sequence in peak frequency over narrative time: symptom terms, treatment terms, prognosis terms and modal verbs indicating possibility.

CONCLUSIONS : NLP methods can identify narrative arcs in serious illness conversations.

PRACTICE IMPLICATIONS : Fully automating NLP methods will allow for efficient, large scale and real time measurement of serious illness conversations for research, education and system re-design.

Ross Lindsay, Danforth Christopher M, Eppstein Margaret J, Clarfeld Laurence A, Durieux Brigitte N, Gramling Cailin J, Hirsch Laura, Rizzo Donna M, Gramling Robert

2019-Dec-07

Artificial Intelligence, Communication, Conversation, Machine Learning, Narrative Analysis, Natural Language Processing, Palliative Care, Stories

In European neuropsychopharmacology : the journal of the European College of Neuropsychopharmacology ; h5-index 0.0

Camacho Mariam Bonyadi, Vijitbenjaronk Warut D, Anastasio Thomas J

2019-Dec-09

Depression, Drug discovery, Gonadal hormones, Machine learning, Neuropharmacology, Systems biology

In Biomedical engineering online ; h5-index 0.0

BACKGROUND : Infertility and subfertility affect a significant proportion of humanity. Assisted reproductive technology has been proven capable of alleviating infertility issues. In vitro fertilisation is one such option whose success is highly dependent on the selection of a high-quality embryo for transfer. This is typically done manually by analysing embryos under a microscope. However, evidence has shown that the success rate of manual selection remains low. The use of new incubators with integrated time-lapse imaging system is providing new possibilities for embryo assessment. As such, we address this problem by proposing an approach based on deep learning for automated embryo quality evaluation through the analysis of time-lapse images. Automatic embryo detection is complicated by the topological changes of a tracked object. Moreover, the algorithm should process a large number of image files of different qualities in a reasonable amount of time.

METHODS : We propose an automated approach to detect human embryo development stages during incubation and to highlight embryos with abnormal behaviour by focusing on five different stages. This method encompasses two major steps. First, the location of an embryo in the image is detected by employing a Haar feature-based cascade classifier and leveraging the radiating lines. Then, a multi-class prediction model is developed to identify a total cell number in the embryo using the technique of deep learning.

RESULTS : The experimental results demonstrate that the proposed method achieves an accuracy of at least 90% in the detection of embryo location. The implemented deep learning approach to identify the early stages of embryo development resulted in an overall accuracy of over 92% using the selected architectures of convolutional neural networks. The most problematic stage was the 3-cell stage, presumably due to its short duration during development.

CONCLUSION : This research contributes to the field by proposing a model to automate the monitoring of early-stage human embryo development. Unlike in other imaging fields, only a few published attempts have involved leveraging deep learning in this field. Therefore, the approach presented in this study could be used in the creation of novel algorithms integrated into the assisted reproductive technology used by embryologists.

Raudonis Vidas, Paulauskaite-Taraseviciene Agne, Sutiene Kristina, Jonaitis Domas

2019-Dec-12

Deep learning, Embryo development, Image recognition, Location detection, Multi-class prediction

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

BACKGROUND : Assessment and rating of Parkinson's Disease (PD) are commonly based on the medical observation of several clinical manifestations, including the analysis of motor activities. In particular, medical specialists refer to the MDS-UPDRS (Movement Disorder Society - sponsored revision of Unified Parkinson's Disease Rating Scale) that is the most widely used clinical scale for PD rating. However, clinical scales rely on the observation of some subtle motor phenomena that are either difficult to capture with human eyes or could be misclassified. This limitation motivated several researchers to develop intelligent systems based on machine learning algorithms able to automatically recognize the PD. Nevertheless, most of the previous studies investigated the classification between healthy subjects and PD patients without considering the automatic rating of different levels of severity.

METHODS : In this context, we implemented a simple and low-cost clinical tool that can extract postural and kinematic features with the Microsoft Kinect v2 sensor in order to classify and rate PD. Thirty participants were enrolled for the purpose of the present study: sixteen PD patients rated according to MDS-UPDRS and fourteen healthy paired subjects. In order to investigate the motor abilities of the upper and lower body, we acquired and analyzed three main motor tasks: (1) gait, (2) finger tapping, and (3) foot tapping. After preliminary feature selection, different classifiers based on Support Vector Machine (SVM) and Artificial Neural Networks (ANN) were trained and evaluated for the best solution.

RESULTS : Concerning the gait analysis, results showed that the ANN classifier performed the best by reaching 89.4% of accuracy with only nine features in diagnosis PD and 95.0% of accuracy with only six features in rating PD severity. Regarding the finger and foot tapping analysis, results showed that an SVM using the extracted features was able to classify healthy subjects versus PD patients with great performances by reaching 87.1% of accuracy. The results of the classification between mild and moderate PD patients indicated that the foot tapping features were the most representative ones to discriminate (81.0% of accuracy).

CONCLUSIONS : The results of this study have shown how a low-cost vision-based system can automatically detect subtle phenomena featuring the PD. Our findings suggest that the proposed tool can support medical specialists in the assessment and rating of PD patients in a real clinical scenario.

Buongiorno Domenico, Bortone Ilaria, Cascarano Giacomo Donato, Trotta Gianpaolo Francesco, Brunetti Antonio, Bevilacqua Vitoantonio

2019-Dec-12

Artificial neural network, Classification, Feature selection, Finger tapping, Foot tapping, Gait analysis, MDS-UPDRS, Microsoft kinect v2, Parkinson’s disease, Support vector machine

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

BACKGROUND : Machine learning is a branch of Artificial Intelligence that is concerned with the design and development of algorithms, and it enables today's computers to have the property of learning. Machine learning is gradually growing and becoming a critical approach in many domains such as health, education, and business.

METHODS : In this paper, we applied machine learning to the diabetes dataset with the aim of recognizing patterns and combinations of factors that characterizes or explain re-admission among diabetes patients. The classifiers used include Linear Discriminant Analysis, Random Forest, k-Nearest Neighbor, Naïve Bayes, J48 and Support vector machine.

RESULTS : Of the 100,000 cases, 78,363 were diabetic and over 47% were readmitted.Based on the classes that models produced, diabetic patients who are more likely to be readmitted are either women, or Caucasians, or outpatients, or those who undergo less rigorous lab procedures, treatment procedures, or those who receive less medication, and are thus discharged without proper improvements or administration of insulin despite having been tested positive for HbA1c.

CONCLUSION : Diabetic patients who do not undergo vigorous lab assessments, diagnosis, medications are more likely to be readmitted when discharged without improvements and without receiving insulin administration, especially if they are women, Caucasians, or both.

Alloghani Mohamed, Aljaaf Ahmed, Hussain Abir, Baker Thar, Mustafina Jamila, Al-Jumeily Dhiya, Khalaf Mohammed

2019-Dec-12

Algorithms, Diabetes re-admission, HbA1c, Linear discriminant, Machine learning, Support vector machine

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

BACKGROUND : The automatic segmentation of kidneys in medical images is not a trivial task when the subjects undergoing the medical examination are affected by Autosomal Dominant Polycystic Kidney Disease (ADPKD). Several works dealing with the segmentation of Computed Tomography images from pathological subjects were proposed, showing high invasiveness of the examination or requiring interaction by the user for performing the segmentation of the images. In this work, we propose a fully-automated approach for the segmentation of Magnetic Resonance images, both reducing the invasiveness of the acquisition device and not requiring any interaction by the users for the segmentation of the images.

METHODS : Two different approaches are proposed based on Deep Learning architectures using Convolutional Neural Networks (CNN) for the semantic segmentation of images, without needing to extract any hand-crafted features. In details, the first approach performs the automatic segmentation of images without any procedure for pre-processing the input. Conversely, the second approach performs a two-steps classification strategy: a first CNN automatically detects Regions Of Interest (ROIs); a subsequent classifier performs the semantic segmentation on the ROIs previously extracted.

RESULTS : Results show that even though the detection of ROIs shows an overall high number of false positives, the subsequent semantic segmentation on the extracted ROIs allows achieving high performance in terms of mean Accuracy. However, the segmentation of the entire images input to the network remains the most accurate and reliable approach showing better performance than the previous approach.

CONCLUSION : The obtained results show that both the investigated approaches are reliable for the semantic segmentation of polycystic kidneys since both the strategies reach an Accuracy higher than 85%. Also, both the investigated methodologies show performances comparable and consistent with other approaches found in literature working on images from different sources, reducing both the invasiveness of the analyses and the interaction needed by the users for performing the segmentation task.

Bevilacqua Vitoantonio, Brunetti Antonio, Cascarano Giacomo Donato, Guerriero Andrea, Pesce Francesco, Moschetta Marco, Gesualdo Loreto

2019-Dec-12

ADPKD, Convolutional neural network, Deep learning, Magnetic resonance, R-CNN, Semantic segmentation

In Neural networks : the official journal of the International Neural Network Society ; h5-index 0.0

Gao Zhifan, Wang Xin, Sun Shanhui, Wu Dan, Bai Junjie, Yin Youbing, Liu Xin, Zhang Heye, de Albuquerque Victor Hugo C

2019-Nov-30

CT angiography, Fractional flow reserve, LSTM, Learning physical properties, Tree-structured RNN

In Cell ; h5-index 250.0

Pan Chenchen, Schoppe Oliver, Parra-Damas Arnaldo, Cai Ruiyao, Todorov Mihail Ivilinov, Gondi Gabor, von Neubeck Bettina, Böğürcü-Seidel Nuray, Seidel Sascha, Sleiman Katia, Veltkamp Christian, Förstera Benjamin, Mai Hongcheng, Rong Zhouyi, Trompak Omelyan, Ghasemigharagoz Alireza, Reimer Madita Alice, Cuesta Angel M, Coronel Javier, Jeremias Irmela, Saur Dieter, Acker-Palmer Amparo, Acker Till, Garvalov Boyan K, Menze Bjoern, Zeidler Reinhard, Ertürk Ali

2019-Dec-12

antibody, cancer, deep learning, drug targeting, imaging, light-sheet, metastasis, microscopy, tissue clearing, vDISCO

In Neural computation ; h5-index 0.0

Xu Xiaofeng, Tsang Ivor W, Liu Chuancai

2019-Dec-13

In Neural computation ; h5-index 0.0

Waniek Nicolai

2019-Dec-13

In The European journal of neuroscience ; h5-index 0.0

Kiiski Hanni, Bennett Marc, Rueda-Delgado Laura M, Farina Francesca, Knight Rachel, Boyle Rory, Roddy Darren, Grogan Katie, Bramham Jessica, Kelly Clare, Whelan Robert

2019-Dec-13

Adults, Attention-Deficit/Hyperactivity Disorder, Endophenotype, Machine learning, Resting-state EEG

In PloS one ; h5-index 176.0

BACKGROUND : The triage of patients in prehospital care is a difficult task, and improved risk assessment tools are needed both at the dispatch center and on the ambulance to differentiate between low- and high-risk patients. This study validates a machine learning-based approach to generating risk scores based on hospital outcomes using routinely collected prehospital data.

METHODS : Dispatch, ambulance, and hospital data were collected in one Swedish region from 2016-2017. Dispatch center and ambulance records were used to develop gradient boosting models predicting hospital admission, critical care (defined as admission to an intensive care unit or in-hospital mortality), and two-day mortality. Composite risk scores were generated based on the models and compared to National Early Warning Scores (NEWS) and actual dispatched priorities in a prospectively gathered dataset from 2018.

RESULTS : A total of 38203 patients were included from 2016-2018. Concordance indexes (or areas under the receiver operating characteristics curve) for dispatched priorities ranged from 0.51-0.66, while those for NEWS ranged from 0.66-0.85. Concordance ranged from 0.70-0.79 for risk scores based only on dispatch data, and 0.79-0.89 for risk scores including ambulance data. Dispatch data-based risk scores consistently outperformed dispatched priorities in predicting hospital outcomes, while models including ambulance data also consistently outperformed NEWS. Model performance in the prospective test dataset was similar to that found using cross-validation, and calibration was comparable to that of NEWS.

CONCLUSIONS : Machine learning-based risk scores outperformed a widely-used rule-based triage algorithm and human prioritization decisions in predicting hospital outcomes. Performance was robust in a prospectively gathered dataset, and scores demonstrated adequate calibration. Future research should explore the robustness of these methods when applied to other settings, establish appropriate outcome measures for use in determining the need for prehospital care, and investigate the clinical impact of interventions based on these methods.

Spangler Douglas, Hermansson Thomas, Smekal David, Blomberg Hans

2019

In PloS one ; h5-index 176.0

Heinson Ashley I, Ewing Rob M, Holloway John W, Woelk Christopher H, Niranjan Mahesan

2019

In BMC bioinformatics ; h5-index 0.0

BACKGROUND : Calling genetic variations from sequence reads is an important problem in genomics. There are many existing methods for calling various types of variations. Recently, Google developed a method for calling single nucleotide polymorphisms (SNPs) based on deep learning. Their method visualizes sequence reads in the forms of images. These images are then used to train a deep neural network model, which is used to call SNPs. This raises a research question: can deep learning be used to call more complex genetic variations such as structural variations (SVs) from sequence data?

RESULTS : In this paper, we extend this high-level approach to the problem of calling structural variations. We present DeepSV, an approach based on deep learning for calling long deletions from sequence reads. DeepSV is based on a novel method of visualizing sequence reads. The visualization is designed to capture multiple sources of information in the sequence data that are relevant to long deletions. DeepSV also implements techniques for working with noisy training data. DeepSV trains a model from the visualized sequence reads and calls deletions based on this model. We demonstrate that DeepSV outperforms existing methods in terms of accuracy and efficiency of deletion calling on the data from the 1000 Genomes Project.

CONCLUSIONS : Our work shows that deep learning can potentially lead to effective calling of different types of genetic variations that are complex than SNPs.

Cai Lei, Wu Yufeng, Gao Jingyang

2019-Dec-12

Deep learning, Feature extraction, Genetic variations, High-throughput sequencing, Structural variations, Visualization

In PloS one ; h5-index 176.0

da Silva Daniel A, Ten Caten Carla S, Dos Santos Rodrigo P, Fogliatto Flavio S, Hsuan Juliana

2019

In PloS one ; h5-index 176.0

Barger Zeke, Frye Charles G, Liu Danqian, Dan Yang, Bouchard Kristofer E

2019

In Medical physics ; h5-index 59.0

PURPOSE : Prostate cancer (PCa) is a major health concern in aging males, and proper management of the disease depends on accurately interpreting pathology specimens. However, reading prostatectomy histopathology slides, which is basically for staging, is usually time-consuming and differs from reading small biopsy specimens, which is mainly used for diagnosis. Generally, each prostatectomy specimen generates tens of large tissue sections and for each section, the malignant region needs to be delineated to assess the amount of tumor and its burden. With the aim of reducing the workload of pathologists, in this study, we focus on developing a computer-aided diagnosis (CAD) system based on a densely connected convolutional neural network (DenseNet) for whole-slide histopathology images to outline the malignant regions.

METHODS : We use an efficient color normalization process based on ranklet transformation to automatically correct the intensity of the images. Additionally, we use spatial probability to segment the tissue structure regions for different tissue recognition patterns. Based on the segmentation, we incorporate a multidimensional structure into DenseNet to determine if a particular prostatic region is benign or malignant.

RESULTS : As demonstrated by the experimental results with a test set of 2,663 images from 32 whole-slide prostate histopathology images, our proposed system achieved 0.726, 0.6306, and 0.5209 in the average of the Dice coefficient, Jaccard similarity coefficient, and Boundary F1 score measures, respectively. Then, the accuracy, sensitivity, specificity, and the area under the ROC curve (AUC) of the proposed classification method were observed to be 95.0% (2544/2663), 96.7% (1210/1251), 93.9% (1334/1412), and 0.9831, respectively.

DISCUSSIONS : We provide a detailed discussion on how our proposed system demonstrates considerable improvement compared with similar methods considered in previous researches as well as how it can be used for delineating malignant regions.

Chen Chiao-Min, Huang Yao-Sian, Fang Pei-Wei, Liang Cher-Wei, Chang Ruey-Feng

2019-Dec-13

computer-aided diagnosis, deep learning, densely connected network, prostate cancer, whole-slide histopathology image

In Bioinformatics (Oxford, England) ; h5-index 0.0

SUMMARY : MLDSP-GUI (Machine Learning with Digital Signal Processing) is an open-source, alignment-free, ultrafast, computationally lightweight, standalone software tool with an interactive Graphical User Interface (GUI) for comparison and analysis of DNA sequences. MLDSP-GUI is a general-purpose tool that can be used for a variety of applications such as taxonomic classification, disease classification, virus subtype classification, evolutionary analyses, among others.

AVAILABILITY : MLDSP-GUI is open-source, cross-platform compatible, and is available under the terms of the Creative Commons Attribution 4.0 International license (http://creativecommons.org/licenses/by/4.0/). The executable and dataset files are available at https://sourceforge.net/projects/mldsp-gui/.

SUPPLEMENTARY INFORMATION : Supplementary data are available at Bioinformatics online.

Randhawa Gurjit S, Hill Kathleen A, Kari Lila

2019-Dec-13

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% CIs 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

2019-Dec-06

In Current opinion in HIV and AIDS ; h5-index 41.0

PURPOSE OF REVIEW : Update findings regarding polypharmacy among people with HIV (PWH) and consider what research is most needed.

RECENT FINDINGS : Among PWH, polypharmacy is common, occurs in middle age, and is predominantly driven by nonantiretroviral (ARV) medications. Many studies have demonstrated strong associations between polypharmacy and receipt of potentially inappropriate medications (PIMS), but few have considered actual adverse events. Falls, delirium, pneumonia, hospitalization, and mortality are associated with polypharmacy among PWH and risks remain after adjustment for severity of illness.

SUMMARY : Polypharmacy is a growing problem and mechanisms of injury likely include potentially inappropriate medications, total drug burden, known pairwise drug interactions, higher level drug interactions, drug--gene interactions, and drug--substance use interactions (alcohol, extra-medical prescription medication, and drug use). Before we can effectively design interventions, we need to use observational data to gain a better understanding of the modifiable mechanisms of injury. As sicker individuals take more medications, analyses must account for severity of illness. As self-report of substance use may be inaccurate, direct biomarkers, such as phosphatidylethanol (PEth) for alcohol are needed. Large samples including electronic health records, genetics, accurate measures of substance use, and state of the art statistical and artificial intelligence techniques are needed to advance our understanding and inform clinical management of polypharmacy in PWH.

Edelman E Jennifer, Rentsch Christopher T, Justice Amy C

2019-Dec-10

In Clinical and translational gastroenterology ; h5-index 0.0

OBJECTIVES : Application of artificial intelligence in gastrointestinal endoscopy is increasing. The aim of the study was to examine the accuracy of convolutional neural network (CNN) using endoscopic images for evaluating Helicobacter pylori (H. pylori) infection.

METHODS : Patients who received upper endoscopy and gastric biopsies at Sir Run Run Shaw Hospital (January 2015-June 2015) were retrospectively searched. A novel Computer-Aided Decision Support System that incorporates CNN model (ResNet-50) based on endoscopic gastric images was developed to evaluate for H. pylori infection. Diagnostic accuracy was evaluated in an independent validation cohort. H. pylori infection was defined by the presence of H. pylori on immunohistochemistry testing on gastric biopsies and/or a positive 13C-urea breath test.

RESULTS : Of 1,959 patients, 1,507 (77%) including 847 (56%) with H. pylori infection (11,729 gastric images) were assigned to the derivation cohort, and 452 (23%) including 310 (69%) with H. pylori infection (3,755 images) were assigned to the validation cohort. The area under the curve for a single gastric image was 0.93 (95% confidence interval [CI] 0.92-0.94) with sensitivity, specificity, and accuracy of 81.4% (95% CI 79.8%-82.9%), 90.1% (95% CI 88.4%-91.7%), and 84.5% (95% CI 83.3%-85.7%), respectively, using an optimal cutoff value of 0.3. Area under the curve for multiple gastric images (8.3 ± 3.3) per patient was 0.97 (95% CI 0.96-0.99) with sensitivity, specificity, and accuracy of 91.6% (95% CI 88.0%-94.4%), 98.6% (95% CI 95.0%-99.8%), and 93.8% (95% CI 91.2%-95.8%), respectively, using an optimal cutoff value of 0.4.

DISCUSSION : In this pilot study, CNN using multiple archived gastric images achieved high diagnostic accuracy for the evaluation of H. pylori infection.

Zheng Wenfang, Zhang Xu, Kim John J, Zhu Xinjian, Ye Guoliang, Ye Bin, Wang Jianping, Luo Songlin, Li Jingjing, Yu Tao, Liu Jiquan, Hu Weiling, Si Jianmin

2019-Dec-11

In Minerva urologica e nefrologica = The Italian journal of urology and nephrology ; h5-index 0.0

INTRODUCTION : As we enter the era of "big data", an increasing amount of complex health- care data will become available. These data are often redundant, "noisy", and characterized by wide variability. In order to offer a precise and transversal view of a clinical scenario the Artificial Intelligence (AI) with Machine learning (ML) algorithms and Artificial neuron networks (ANNs) process were adopted, with a promising wide diffusion in the near future. The present work aims to provide a comprehensive and critical overview of the current and potential applications of AI and ANNs in Urology.

EVIDENCE ACQUISITION : A non-systematic review of the literature was performed by screening Medline, PubMed, the Cochrane Database, and Embase to detect pertinent studies regarding the application of AI and ANN in Urology.

EVIDENCE SYNTHESIS : The main application of AI in urology is the field of genitourinary cancers. Focusing on prostate cancer, AI was applied for the prediction of prostate biopsy results. For bladder cancer, the prediction of recurrence-free probability and diagnostic evaluation were analysed with ML algorithms. For kidney and testis cancer, anecdotal experiences were reported for staging and prediction of diseases recurrence. More recently, AI has been applied in non- oncological diseases like stones and functional urology.

CONCLUSIONS : AI technologies are growing their role in health care; but, up to now, their "real-life" implementation remains limited. However, in the near future, the potential of AI-driven era could change the clinical practice in Urology, improving overall patient outcomes.

Checcucci Enrico, Autorino Riccardo, Cacciamani Giovanni E, Amparore Daniele, De Cillis Sabrina, Piana Alberto, Piazzolla Pietro, Vezzetti Enrico, Fiori Cristian, Veneziano Domenico, Tewari Ash, Dasgupta Prokar, Hung Andrew, Gill Inderbir, Porpiglia Francesco

2019-Dec-12

In Chemical record (New York, N.Y.) ; h5-index 0.0

Tsuneda Takao

2019-Dec-13

Density functional theory, Exchange-correlation functionals, Machine learning, Physical corrections

In Biometrics ; h5-index 0.0

Wang Yanqing, Zhao Ying-Qi, Zheng Yingye

2019-Dec-13

biomarker, clinical decision rules, false positive fraction, machine learning, true positive fraction

In The International journal of artificial organs ; h5-index 0.0

BACKGROUND : Identifying candidates for left ventricular assist device surgery at risk of right ventricular failure remains difficult. The aim was to identify the most accurate predictors of right ventricular failure among clinical, biological, and imaging markers, assessed by agreement of different supervised machine learning algorithms.

METHODS : Seventy-four patients, referred to HeartWare left ventricular assist device since 2010 in two Italian centers, were recruited. Biomarkers, right ventricular standard, and strain echocardiography, as well as cath-lab measures, were compared among patients who did not develop right ventricular failure (N = 56), those with acute-right ventricular failure (N = 8, 11%) or chronic-right ventricular failure (N = 10, 14%). Logistic regression, penalized logistic regression, linear support vector machines, and naïve Bayes algorithms with leave-one-out validation were used to evaluate the efficiency of any combination of three collected variables in an "all-subsets" approach.

RESULTS : Michigan risk score combined with central venous pressure assessed invasively and apical longitudinal systolic strain of the right ventricular-free wall were the most significant predictors of acute-right ventricular failure (maximum receiver operating characteristic-area under the curve = 0.95, 95% confidence interval = 0.91-1.00, by the naïve Bayes), while the right ventricular-free wall systolic strain of the middle segment, right atrial strain (QRS-synced), and tricuspid annular plane systolic excursion were the most significant predictors of Chronic-RVF (receiver operating characteristic-area under the curve = 0.97, 95% confidence interval = 0.91-1.00, according to naïve Bayes).

CONCLUSION : Apical right ventricular strain as well as right atrial strain provides complementary information, both critical to predict acute-right ventricular failure and chronic-right ventricular failure, respectively.

Bellavia Diego, Iacovoni Attilio, Agnese Valentina, Falletta Calogero, Coronnello Claudia, Pasta Salvatore, Novo Giuseppina, di Gesaro Gabriele, Senni Michele, Maalouf Joseph, Sciacca Sergio, Pilato Michele, Simon Marc, Clemenza Francesco, Gorcsan Sir John

2019-Dec-12

Right ventricle, echocardiography, heart failure, machine learning, strain imaging

In Behavior research methods ; h5-index 0.0

Lynott Dermot, Connell Louise, Brysbaert Marc, Brand James, Carney James

2019-Dec-12

In Knee surgery, sports traumatology, arthroscopy : official journal of the ESSKA ; h5-index 0.0

PURPOSE : Machine-learning methods are flexible prediction algorithms with potential advantages over conventional regression. This study aimed to use machine learning methods to predict post-total knee arthroplasty (TKA) walking limitation, and to compare their performance with that of logistic regression.

METHODS : From the department's clinical registry, a cohort of 4026 patients who underwent elective, primary TKA between July 2013 and July 2017 was identified. Candidate predictors included demographics and preoperative clinical, psychosocial, and outcome measures. The primary outcome was severe walking limitation at 6 months post-TKA, defined as a maximum walk time ≤ 15 min. Eight common regression (logistic, penalized logistic, and ordinal logistic with natural splines) and ensemble machine learning (random forest, extreme gradient boosting, and SuperLearner) methods were implemented to predict the probability of severe walking limitation. Models were compared on discrimination and calibration metrics.

RESULTS : At 6 months post-TKA, 13% of patients had severe walking limitation. Machine learning and logistic regression models performed moderately [mean area under the ROC curves (AUC) 0.73-0.75]. Overall, the ordinal logistic regression model performed best while the SuperLearner performed best among machine learning methods, with negligible differences between them (Brier score difference, < 0.001; 95% CI [- 0.0025, 0.002]).

CONCLUSIONS : When predicting post-TKA physical function, several machine learning methods did not outperform logistic regression-in particular, ordinal logistic regression that does not assume linearity in its predictors.

LEVEL OF EVIDENCE : Prognostic level II.

Pua Yong-Hao, Kang Hakmook, Thumboo Julian, Clark Ross Allan, Chew Eleanor Shu-Xian, Poon Cheryl Lian-Li, Chong Hwei-Chi, Yeo Seng-Jin

2019-Dec-12

Algorithms, Arthroplasty, Artificial intelligence, Knee, Machine learning, Prediction, Replacement

In Operative neurosurgery (Hagerstown, Md.) ; h5-index 0.0

BACKGROUND : Virtual reality surgical simulators provide a safe environment for trainees to practice specific surgical scenarios and allow for self-guided learning. Artificial intelligence technology, including artificial neural networks, offers the potential to manipulate large datasets from simulators to gain insight into the importance of specific performance metrics during simulated operative tasks.

OBJECTIVE : To distinguish performance in a virtual reality-simulated anterior cervical discectomy scenario, uncover novel performance metrics, and gain insight into the relative importance of each metric using artificial neural networks.

METHODS : Twenty-one participants performed a simulated anterior cervical discectomy on the novel virtual reality Sim-Ortho simulator. Participants were divided into 3 groups, including 9 post-resident, 5 senior, and 7 junior participants. This study focused on the discectomy portion of the task. Data were recorded and manipulated to calculate metrics of performance for each participant. Neural networks were trained and tested and the relative importance of each metric was calculated.

RESULTS : A total of 369 metrics spanning 4 categories (safety, efficiency, motion, and cognition) were generated. An artificial neural network was trained on 16 selected metrics and tested, achieving a training accuracy of 100% and a testing accuracy of 83.3%. Network analysis identified safety metrics, including the number of contacts on spinal dura, as highly important.

CONCLUSION : Artificial neural networks classified 3 groups of participants based on expertise allowing insight into the relative importance of specific metrics of performance. This novel methodology aids in the understanding of which components of surgical performance predominantly contribute to expertise.

Mirchi Nykan, Bissonnette Vincent, Ledwos Nicole, Winkler-Schwartz Alexander, Yilmaz Recai, Karlik Bekir, Del Maestro Rolando F

2019-Dec-13

Anterior cervical discectomy, Artificial intelligence, Artificial neural networks, Machine learning, Simulation, Surgical training, Virtual reality

In Current opinion in biomedical engineering ; h5-index 0.0

Background : Wearable sensors (wearables) have been commonly integrated into a wide variety of commercial products and are increasingly being used to collect and process raw physiological parameters into salient digital health information. The data collected by wearables are currently being investigated across a broad set of clinical domains and patient populations. There is significant research occurring in the domain of algorithm development, with the aim of translating raw sensor data into fitness- or health-related outcomes of interest for users, patients, and health care providers.

Objectives : The aim of this review is to highlight a selected group of fitness- and health-related indicators from wearables data and to describe several algorithmic approaches used to generate these higher order indicators.

Methods : A systematic search of the Pubmed database was performed with the following search terms (number of records in parentheses): Fitbit algorithm (18), Apple Watch algorithm (3), Garmin algorithm (5), Microsoft Band algorithm (8), Samsung Gear algorithm (2), Xiaomi MiBand algorithm (1), Huawei Band (Watch) algorithm (2), photoplethysmography algorithm (465), accelerometry algorithm (966), ECG algorithm (8287), continuous glucose monitor algorithm (343). The search terms chosen for this review are focused on algorithms for wearable devices that dominated the commercial wearables market between 2014-2017 and that were highly represented in the biomedical literature. A second set of search terms included categories of algorithms for fitness-related and health-related indicators that are commonly used in wearable devices (e.g. accelerometry, PPG, ECG). These papers covered the following domain areas: fitness; exercise; movement; physical activity; step count; walking; running; swimming; energy expenditure; atrial fibrillation; arrhythmia; cardiovascular; autonomic nervous system; neuropathy; heart rate variability; fall detection; trauma; behavior change; diet; eating; stress detection; serum glucose monitoring; continuous glucose monitoring; diabetes mellitus type 1; diabetes mellitus type 2. All studies uncovered through this search on commercially available device algorithms and pivotal studies on sensor algorithm development were summarized, and a summary table was constructed using references generated by the literature review as described (Table 1).

Conclusions : Wearable health technologies aim to collect and process raw physiological or environmental parameters into salient digital health information. Much of the current and future utility of wearables lies in the signal processing steps and algorithms used to analyze large volumes of data. Continued algorithmic development and advances in machine learning techniques will further increase analytic capabilities. In the context of these advances, our review aims to highlight a range of advances in fitness- and other health-related indicators provided by current wearable technologies.

Witt Daniel, Kellogg Ryan, Snyder Michael, Dunn Jessilyn

2019-Mar

algorithms, digital health, physiologic monitoring, wearables

In Applications in plant sciences ; h5-index 0.0

Premise : When plants are exposed to stress conditions, irreversible damage can occur, negatively impacting yields. It is therefore important to detect stress symptoms in plants, such as the accumulation of anthocyanin, as early as possible.

Methods and Results : Twenty-two regression models in five color spaces were trained to develop a prediction model for plant anthocyanin levels from digital color imaging data. Of these, a quantile random forest regression model trained with standard red, green, blue (sRGB) color space data most accurately predicted the actual anthocyanin levels. This model was then used to noninvasively monitor the spatial and temporal accumulation of anthocyanin in Arabidopsis thaliana leaves.

Conclusions : The digital imaging-based nature of this protocol makes it a low-cost and noninvasive method for the detection of plant stress. Applying a similar protocol to more economically viable crops could lead to the development of large-scale, cost-effective systems for monitoring plant health.

Askey Bryce C, Dai Ru, Lee Won Suk, Kim Jeongim

2019-Nov

anthocyanin, digital color imaging, early stress detection, machine learning

In The EPMA journal ; h5-index 0.0

Barrett Matthew, Boyne Josiane, Brandts Julia, Brunner-La Rocca Hans-Peter, De Maesschalck Lieven, De Wit Kurt, Dixon Lana, Eurlings Casper, Fitzsimons Donna, Golubnitschaja Olga, Hageman Arjan, Heemskerk Frank, Hintzen André, Helms Thomas M, Hill Loreena, Hoedemakers Thom, Marx Nikolaus, McDonald Kenneth, Mertens Marc, Müller-Wieland Dirk, Palant Alexander, Piesk Jens, Pomazanskyi Andrew, Ramaekers Jan, Ruff Peter, Schütt Katharina, Shekhawat Yash, Ski Chantal F, Thompson David R, Tsirkin Andrew, van der Mierden Kay, Watson Chris, Zippel-Schultz Bettina

2019-Dec

Artificial Intelligence, Comorbidities, Diabetes, Disease modelling, Healthcare digitalisation, Healthcare economy, Heart failure, Individualised patient profile, Information and communications technology, Integrated care, Medical ethics, Multi-level diagnostics, Patient engagement, Patient stratification, Predictive preventive personalised participatory medicine, Professional interactome, Societal impact, Therapy monitoring

In The EPMA journal ; h5-index 0.0

Qian Shehua, Golubnitschaja Olga, Zhan Xianquan

2019-Dec

Big data analysis, Biomarkers, Cancer, Chronic inflammation, Collateral pathologies, Epigenetics, Genetics, Global statistics, Individualized patient profile, Inflammatory factors, Machine learning, Modifiable and preventable, Multiomics, Patient stratification, Phenotyping, Predictive preventive personalized medicine, Risk factors

In Plant methods ; h5-index 0.0

Background : The demand for effective use of water resources has increased because of ongoing global climate transformations in the agriculture science sector. Cost-effective and timely distributions of the appropriate amount of water are vital not only to maintain a healthy status of plants leaves but to drive the productivity of the crops and achieve economic benefits. In this regard, employing a terahertz (THz) technology can be more reliable and progressive technique due to its distinctive features. This paper presents a novel, and non-invasive machine learning (ML) driven approach using terahertz waves with a swissto12 material characterization kit (MCK) in the frequency range of 0.75 to 1.1 THz in real-life digital agriculture interventions, aiming to develop a feasible and viable technique for the precise estimation of water content (WC) in plants leaves for 4 days. For this purpose, using measurements observations data, multi-domain features are extracted from frequency, time, time-frequency domains to incorporate three different machine learning algorithms such as support vector machine (SVM), K-nearest neighbour (KNN) and decision-tree (D-Tree).

Results : The results demonstrated SVM outperformed other classifiers using tenfold and leave-one-observations-out cross-validation for different days classification with an overall accuracy of 98.8%, 97.15%, and 96.82% for Coffee, pea shoot, and baby spinach leaves respectively. In addition, using SFS technique, coffee leaf showed a significant improvement of 15%, 11.9%, 6.5% in computational time for SVM, KNN and D-tree. For pea-shoot, 21.28%, 10.01%, and 8.53% of improvement was noticed in operating time for SVM, KNN and D-Tree classifiers, respectively. Lastly, baby spinach leaf exhibited a further improvement of 21.28% in SVM, 10.01% in KNN, and 8.53% in D-tree in overall operating time for classifiers. These improvements in classifiers produced significant advancements in classification accuracy, indicating a more precise quantification of WC in leaves.

Conclusion : Thus, the proposed method incorporating ML using terahertz waves can be beneficial for precise estimation of WC in leaves and can provide prolific recommendations and insights for growers to take proactive actions in relations to plants health monitoring.

Zahid Adnan, Abbas Hasan T, Ren Aifeng, Zoha Ahmed, Heidari Hadi, Shah Syed A, Imran Muhammad A, Alomainy Akram, Abbasi Qammer H

2019

Agriculture, Classification, Machine learning, Plant leaves, Sensing, Terahertz (THz), Water content

In Nature reviews. Rheumatology ; h5-index 74.0

Kingsmore Kathryn M, Grammer Amrie C, Lipsky Peter E

2019-Dec-12

In Scientific reports ; h5-index 158.0

Lameira Adriano R, Eerola Tuomas, Ravignani Andrea

2019-Dec-12

In F1000Research ; h5-index 0.0

Medic Goran, Kosaner Kließ Melodi, Atallah Louis, Weichert Jochen, Panda Saswat, Postma Maarten, El-Kerdi Amer

2019

clinical trials, critical care., hemodynamic instability, infection, machine learning, respiratory distress, sepsis

In Scientific reports ; h5-index 158.0

Cifuentes-Alcobendas Gabriel, Domínguez-Rodrigo Manuel

2019-Dec-12

In BMJ open ; h5-index 0.0

INTRODUCTION : Infants can experience pain similar to adults, and improperly controlled pain stimuli could have a long-term adverse impact on their cognitive and neurological function development. The biggest challenge of achieving good infant pain control is obtaining objective pain assessment when direct communication is lacking. For years, computer scientists have developed many different facial expression-centred machine learning (ML) methods for automatic infant pain assessment. Many of these ML algorithms showed rather satisfactory performance and have demonstrated good potential to be further enhanced for implementation in real-world clinical settings. To date, there is no prior research that has systematically summarised and compared the performance of these ML algorithms. Our proposed meta-analysis will provide the first comprehensive evidence on this topic to guide further ML algorithm development and clinical implementation.

METHODS AND ANALYSIS : We will search four major public electronic medical and computer science databases including Web of Science, PubMed, Embase and IEEE Xplore Digital Library from January 2008 to present. All the articles will be imported into the Covidence platform for study eligibility screening and inclusion. Study-level extracted data will be stored in the Systematic Review Data Repository online platform. The primary outcome will be the prediction accuracy of the ML model. The secondary outcomes will be model utility measures including generalisability, interpretability and computational efficiency. All extracted outcome data will be imported into RevMan V.5.2.1 software and R V3.3.2 for analysis. Risk of bias will be summarised using the latest Prediction Model Study Risk of Bias Assessment Tool.

ETHICS AND DISSEMINATION : This systematic review and meta-analysis will only use study-level data from public databases, thus formal ethical approval is not required. The results will be disseminated in the form of an official publication in a peer-reviewed journal and/or presentation at relevant conferences.

PROSPERO REGISTRATION NUMBER : CRD42019118784.

Cheng Dan, Liu Dianbo, Philpotts Lisa Liang, Turner Dana P, Houle Timothy T, Chen Lucy, Zhang Miaomiao, Yang Jianjun, Zhang Wei, Deng Hao

2019-Dec-11

artificial intelligence, facial expression, infant, machine learning, pain

In IEEE journal of biomedical and health informatics ; h5-index 0.0

Andreassen Borge Solli, Veronesi Federico, Gerard Olivier, Solberg Anne H Schistad, Samset Eigil

2019-Dec-12

In IEEE journal of biomedical and health informatics ; h5-index 0.0

Tunca Can, Salur Gulustu, Ersoy Cem

2019-Dec-11

In IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society ; h5-index 0.0

Zhang Huanghe, Guo Yi, Zanotto Damiano

2019-Dec-10

In IEEE transactions on image processing : a publication of the IEEE Signal Processing Society ; h5-index 0.0

Liu Yang, Lu Zhaoyang, Li Jing, Yang Tao, Yao Chao

2019-Dec-11

In IEEE transactions on image processing : a publication of the IEEE Signal Processing Society ; h5-index 0.0

Yeh Chia-Hung, Huang Chih-Hsiang, Kang Li-Wei

2019-Dec-11

In IEEE transactions on image processing : a publication of the IEEE Signal Processing Society ; h5-index 0.0

Zhang Hengmin, Qian Jianjun, Zhang Bob, Yang Jian, Gong Chen, Wei Yang

2019-Dec-11

In IEEE transactions on medical imaging ; h5-index 74.0

Zheng Li, Liao Pan, Shen Luo, Sheng Jingwei, Teng Pengfei, Luan Guoming, Gao Jia-Hong

2019-Dec-10

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

Kim Dahun, Woo Sanghyun, Lee Joon-Young, Kweon In So

2019-Dec-11

In Plant methods ; h5-index 0.0

Background : Cultivar recognition is a basic work in flower production, research, and commercial application. Chinese large-flowered chrysanthemum (Chrysanthemum × morifolium Ramat.) is miraculous because of its high ornamental value and rich cultural deposits. However, the complicated capitulum structure, various floret types and numerous cultivars hinder chrysanthemum cultivar recognition. Here, we explore how deep learning method can be applied to chrysanthemum cultivar recognition.

Results : We propose deep learning models with two networks VGG16 and ResNet50 to recognize large-flowered chrysanthemum. Dataset A comprising 14,000 images for 103 cultivars, and dataset B comprising 197 images from different years were collected. Dataset A was used to train the networks and determine the calibration accuracy (Top-5 rate of above 98%), and dataset B was used to evaluate the model generalization performance (Top-5 rate of above 78%). Moreover, gradient-weighted class activation mapping (Grad-CAM) visualization and feature clustering analysis were used to explore how the deep learning model recognizes chrysanthemum cultivars.

Conclusion : Deep learning method applied to cultivar recognition is a breakthrough in horticultural science with the advantages of strong recognition performance and high recognition speed. Inflorescence edge areas, disc floret areas, inflorescence colour and inflorescence shape may well be the key factors in model decision-making process, which are also critical in human decision-making.

Liu Zhilan, Wang Jue, Tian Ye, Dai Silan

2019

Chrysanthemum × morifolium Ramat., Deep learning, Grad-CAM, Image recognition

In Frontiers in genetics ; h5-index 62.0

Chen Yilong, Wang Kai, Liao Xiangyun, Qian Yinling, Wang Qiong, Yuan Zhiyong, Heng Pheng-Ann

2019

Channel-UNet, computed tomography, deep learning, liver and tumors segmentation, spatial channel-wise convolution

In Frontiers in neuroscience ; h5-index 72.0

Chen Chen, Cao Xuyu, Tian Lixia

2019

Human Connectome Project, classification, machine learning, multi-label learning, partial correlation, regression, resting state fMRI, resting state functional connection

In Food control ; h5-index 0.0

Tan Ailing, Zhao Yong, Sivashanmugan Kundan, Squire Kenneth, Wang Alan X

2019-Sep

Histamine, Machine Learning, Seafood allergen, Support vector regression, Surface-enhanced Raman scattering, Thin layer chromatography

In Scientific reports ; h5-index 158.0

Mueller-Breckenridge Alan J, Garcia-Alcalde Fernando, Wildum Steffen, Smits Saskia L, de Man Robert A, van Campenhout Margo J H, Brouwer Willem P, Niu Jianjun, Young John A T, Najera Isabel, Zhu Lina, Wu Daitze, Racek Tomas, Hundie Gadissa Bedada, Lin Yong, Boucher Charles A, van de Vijver David, Haagmans Bart L

2019-Dec-11

In Molecular cancer therapeutics ; h5-index 0.0

Cramer Dina, Mazur Johanna, Espinosa Octavio, Schlesner Matthias, Hübschmann Daniel, Eils Roland, Staub Eike

2019-Dec-11

In Journal of psychiatric research ; h5-index 59.0

Ramos-Lima Luis Francisco, Waikamp Vitoria, Antonelli-Salgado Thyago, Passos Ives Calvalcante, Freitas Lucia Helena Machado

2019-Dec-06

Forecasting, Machine learning, Posttraumatic stress disorders, Psychological trauma

In Computer methods and programs in biomedicine ; h5-index 0.0

BACKGROUND AND OBJECTIVE : Electrocardiogram (ECG) is one of the most important tools for assessing cardiac function and detecting potential heart problems. However, most of the current ECG report records remain on the paper, which makes it difficult to preserve and analyze the data. Moreover, paper records could result in the loss significant data, which brings inconvenience to the subsequent clinical diagnosis or artificial intelligence-assisted heart health diagnosis. Taking digital pictures is an intuitive way of preserving these files and can be done simply using smartphones or any other devices with cameras. However, these real scene ECG images often have some image noise that hinders signal extraction. How to eliminate image noise and extract ECG binary image automatically from the noisy and low-quality real scene images of ECG reports is the first problem to be solved in this paper. Next, QRS recognition is implemented on the extracted binary images to determine key points of ECG signals. 1D digital ECG signal is also extracted for accessing the exact values of the extracted points. In light of these tasks, an automatic digital ECG signal extraction and normal QRS recognition from real scene ECG images is proposed in this paper.

METHODS : The normal QRS recognition approach for real scene ECG images in this paper consists of two steps: ECG binary image extraction from ECG images using a new two-layer hierarchical method, and the subsequent QRS recognition based on a novel feature-fusing method. ECG binary image extraction is implemented using sub-channel filters followed by an adaptive filtering algorithm. According to the ratio between pixel and real value of ECG binary image, 1D digital ECG signal is obtained. The normal QRS recognition includes three main steps: establishment of candidate point sets, feature fusion extraction, and QRS recognition. Two datasets are introduced for evaluation including a real scene ECG images dataset and the public Non-Invasive Fetal Electrocardiogram Database (FECG).

RESULTS : Through the experiment on real scene ECG image, the F₁ score for Q, R, S detection is 0.841, 0.992, and 0.891, respectively. The evaluation on the public FECG dataset also proves the robustness of our algorithm, where F₁ score for R is 0.992 (0.996 for thoracic lead) and 0.988 for thoracic S wave.

CONCLUSIONS : The proposed method in this article is a promising tool for automatically extracting digital ECG signals and detecting QRS complex in real scene ECG images with normal QRS.

Wang Shuang, Zhang Shugang, Li Zhen, Huang Lei, Wei Zhiqiang

2019-Nov-30

Adaptive Filter Algorithm (AFA), ECG image, ECG signal extraction, QRS recognition

In Bioresource technology ; h5-index 0.0

Wang Luguang, Long Fei, Liao Wei, Liu Hong

2019-Dec-02

Anaerobic digestion, Machine learning, Methane production, Operational parameters, Prediction

In Water research ; h5-index 0.0

Ma Jun, Ding Yuexiong, Cheng Jack C P, Jiang Feifeng, Xu Zherui

2019-Dec-04

Biochemical oxygen demand, Deep matrix factorization, Deep neural network, Harbor water, Sparse matrix

In Neural networks : the official journal of the International Neural Network Society ; h5-index 0.0

Cao Yanyi, Cao Yuting, Guo Zhenyuan, Huang Tingwen, Wen Shiping

2019-Nov-29

Delayed memristive neural networks, Global exponential synchronization, Pinning control technique, Reaction–diffusion terms

In Cancer letters ; h5-index 85.0

Huang Shigao, Yang Jie, Fong Simon, Zhao Qi

2019-Dec-09

Cancer diagnosis, Deep learning, Deep neural network, Machine learning, Prognosis prediction

In Journal of biotechnology ; h5-index 0.0

Srivastava Pulkit Anupam, Hegg Eric L, Fox Brian G, Yennamalli Ragothaman M

2019-Dec-09

Lytic polysaccharide monooxygenases, long short-term memory, machine learning technique, neural network, proteome

In The Journal of allergy and clinical immunology ; h5-index 0.0

Wu Qingwu, Chen Jianning, Deng Huiyi, Ren Yong, Sun Yueqi, Wang Weihao, Yuan Lianxiong, Hong Haiyu, Zheng Rui, Kong Weifeng, Huang Xuekun, Huang Guifang, Wang Lunji, Zhang Yana, Han Lanqing, Yang Qintai

2019-Dec-09

CRSwNP, WSI, deep learning, eosinophils, pathological classification

In Virology ; h5-index 53.0

Tokunaga Makoto, Miyamoto Yoichi, Suzuki Tatsuya, Otani Mayumi, Inuki Shinsuke, Esaki Tsuyoshi, Nagao Chioko, Mizuguchi Kenji, Ohno Hiroaki, Yoneda Yoshihiro, Okamoto Toru, Oka Masahiro, Matsuura Yoshiharu

2019-Nov-29

Core protein, Flavivirus, High-throughput screening, Nuclear transport, Nucleolus

In PloS one ; h5-index 176.0

Perusquía-Hernández Monica, Ayabe-Kanamura Saho, Suzuki Kenji

2019

In Psychological assessment ; h5-index 0.0

Marsh Herbert W, Huppert Felicia A, Donald James N, Horwood Marcus S, Sahdra Baljinder K

2019-Dec-12

In The journal of physical chemistry. B ; h5-index 0.0

Zhang Kexin, Frank Aaron Terrence

2019-Dec-12

In Journal for immunotherapy of cancer ; h5-index 0.0

BACKGROUND : Although several therapeutic options for patients with renal cell carcinoma (RCC) have been approved over recent years, including immune checkpoint inhibitors, considerable need remains for molecular biomarkers to assess disease prognosis. The higher pharmacokinetic (PK) clearance of checkpoint inhibitors, such as the anti-programmed death-1 (PD-1) therapies nivolumab and pembrolizumab, has been shown to be associated with poor overall survival (OS) across several tumor types. However, determination of PK clearance requires the collection and analysis of post-treatment serum samples, limiting its utility as a prognostic biomarker. This report outlines a translational PK-pharmacodynamic (PD) methodology used to derive a baseline composite cytokine signature correlated with nivolumab clearance using data from three clinical trials in which nivolumab or everolimus was administered.

METHODS : Peripheral serum cytokine (PD) and nivolumab clearance (PK) data from patients with RCC were analyzed using a PK-PD machine-learning model. Nivolumab studies CheckMate 009 (NCT01358721) and CheckMate 025 (NCT01668784) (n = 480) were used for PK-PD analysis model development and cytokine feature selection (training dataset). Validation of the model and assessment of the prognostic value of the cytokine signature was performed using data from CheckMate 010 (NCT01354431) and the everolimus comparator arm of CheckMate 025 (test dataset; n = 453).

RESULTS : The PK-PD analysis found a robust association between the eight top-ranking model-selected baseline inflammatory cytokines and nivolumab clearance (area under the receiver operating characteristic curve = 0.7). The predicted clearance (high vs low) based on the cytokine signature was significantly associated with long-term OS (p < 0.01) across all three studies (training and test datasets). Furthermore, cytokines selected from the model development trials also correlated with OS of the everolimus comparator arm (p < 0.01), suggesting the prognostic nature of the composite cytokine signature for RCC.

CONCLUSIONS : Here, we report a PK-PD translational approach to identify a molecular prognostic biomarker signature based on the correlation with nivolumab clearance in patients with RCC. This composite biomarker signature may provide improved prognostic accuracy of long-term clinical outcome compared with individual cytokine features and could be used to ensure the balance of patient randomization in RCC clinical trials.

Wang Rui, Zheng Junying, Shao Xiao, Ishii Yuko, Roy Amit, Bello Akintunde, Lee Richard, Zhang Joshua, Wind-Rotolo Megan, Feng Yan

2019-Dec-11

Clearance, Composite signature, Cytokine, Nivolumab, Renal cell carcinoma, Translational PK/PD analysis

In Genome biology ; h5-index 114.0

Alquicira-Hernandez Jose, Sathe Anuja, Ji Hanlee P, Nguyen Quan, Powell Joseph E

2019-Dec-12

In BMC health services research ; h5-index 0.0

BACKGROUND : Rising health care costs are a major public health issue. Thus, accurately predicting future costs and understanding which factors contribute to increases in health care expenditures are important. The objective of this project was to predict patients healthcare costs development in the subsequent year and to identify factors contributing to this prediction, with a particular focus on the role of pharmacotherapy.

METHODS : We used 2014-2015 Swiss health insurance claims data on 373'264 adult patients to classify individuals' changes in health care costs. We performed extensive feature generation and developed predictive models using logistic regression, boosted decision trees and neural networks. Based on the decision tree model, we performed a detailed feature importance analysis and subgroup analysis, with an emphasis on drug classes.

RESULTS : The boosted decision tree model achieved an overall accuracy of 67.6% and an area under the curve-score of 0.74; the neural network and logistic regression models performed 0.4 and 1.9% worse, respectively. Feature engineering played a key role in capturing temporal patterns in the data. The number of features was reduced from 747 to 36 with only a 0.5% loss in the accuracy. In addition to hospitalisation and outpatient physician visits, 6 drug classes and the mode of drug administration were among the most important features. Patient subgroups with a high probability of increase (up to 88%) and decrease (up to 92%) were identified.

CONCLUSIONS : Pharmacotherapy provides important information for predicting cost increases in the total population. Moreover, its relative importance increases in combination with other features, including health care utilisation.

Jödicke Annika M, Zellweger Urs, Tomka Ivan T, Neuer Thomas, Curkovic Ivanka, Roos Malgorzata, Kullak-Ublick Gerd A, Sargsyan Hayk, Egbring Marco

2019-Dec-11

Boosted decision tree, Claims data, Health care costs, Health care utilisation, Machine learning, Neural network, Pharmacology

In International journal of health geographics ; h5-index 0.0

BACKGROUND : Considerable number of indoor navigation systems has been proposed to augment people with visual impairments (VI) about their surroundings. These systems leverage several technologies, such as computer-vision, Bluetooth low energy (BLE), and other techniques to estimate the position of a user in indoor areas. Computer-vision based systems use several techniques including matching pictures, classifying captured images, recognizing visual objects or visual markers. BLE based system utilizes BLE beacons attached in the indoor areas as the source of the radio frequency signal to localize the position of the user.

METHODS : In this paper, we examine the performance and usability of two computer-vision based systems and BLE-based system. The first system is computer-vision based system, called CamNav that uses a trained deep learning model to recognize locations, and the second system, called QRNav, that utilizes visual markers (QR codes) to determine locations. A field test with 10 blindfolded users has been conducted while using the three navigation systems.

RESULTS : The obtained results from navigation experiment and feedback from blindfolded users show that QRNav and CamNav system is more efficient than BLE based system in terms of accuracy and usability. The error occurred in BLE based application is more than 30% compared to computer vision based systems including CamNav and QRNav.

CONCLUSIONS : The developed navigation systems are able to provide reliable assistance for the participants during real time experiments. Some of the participants took minimal external assistance while moving through the junctions in the corridor areas. Computer vision technology demonstrated its superiority over BLE technology in assistive systems for people with visual impairments.

Kunhoth Jayakanth, Karkar AbdelGhani, Al-Maadeed Somaya, Al-Attiyah Asma

2019-Dec-11

Computer vision, Indoor navigation, Mobile technology, People with visual impairments

In BMC medical education ; h5-index 0.0

BACKGROUND : Medical education must adapt to different health care contexts, including digitalized health care systems and a digital generation of students in a hyper-connected world. The aims of this study are to identify and synthesize the values that medical educators need to implement in the curricula and to introduce representative educational programs.

METHODS : An integrative review was conducted to combine data from various research designs. We searched for articles on PubMed, Scopus, Web of Science, and EBSCO ERIC between 2011 and 2017. Key search terms were "undergraduate medical education," "future," "twenty-first century," "millennium," "curriculum," "teaching," "learning," and "assessment." We screened and extracted them according to inclusion and exclusion criteria from titles and abstracts. All authors read the full texts and discussed them to reach a consensus about the themes and subthemes. Data appraisal was performed using a modified Hawker 's evaluation form.

RESULTS : Among the 7616 abstracts initially identified, 28 full-text articles were selected to reflect medical education trends and suggest suitable educational programs. The integrative themes and subthemes of future medical education are as follows: 1) a humanistic approach to patient safety that involves encouraging humanistic doctors and facilitating collaboration; 2) early experience and longitudinal integration by early exposure to patient-oriented integration and longitudinal integrated clerkships; 3) going beyond hospitals toward society by responding to changing community needs and showing respect for diversity; and 4) student-driven learning with advanced technology through active learning with individualization, social interaction, and resource accessibility.

CONCLUSIONS : This review integrated the trends in undergraduate medical education in readiness for the anticipated changes in medical environments. The detailed programs introduced in this study could be useful for medical educators in the development of curricula. Further research is required to integrate the educational trends into graduate and continuing medical education, and to investigate the status or effects of innovative educational programs in each medical school or environment.

Han Eui-Ryoung, Yeo Sanghee, Kim Min-Jeong, Lee Young-Hee, Park Kwi-Hwa, Roh Hyerin

2019-Dec-11

Humanities, Integration, Self-directed learning, Societies, Technology, Undergraduate medical education

In BMC medical genomics ; h5-index 0.0

BACKGROUND : Disease comorbidity is popular and has significant indications for disease progress and management. We aim to detect the general disease comorbidity patterns in Chinese populations using a large-scale clinical data set.

METHODS : We extracted the diseases from a large-scale anonymized data set derived from 8,572,137 inpatients in 453 hospitals across China. We built a Disease Comorbidity Network (DCN) using correlation analysis and detected the topological patterns of disease comorbidity using both complex network and data mining methods. The comorbidity patterns were further validated by shared molecular mechanisms using disease-gene associations and pathways. To predict the disease occurrence during the whole disease progressions, we applied four machine learning methods to model the disease trajectories of patients.

RESULTS : We obtained the DCN with 5702 nodes and 258,535 edges, which shows a power law distribution of the degree and weight. It further indicated that there exists high heterogeneity of comorbidities for different diseases and we found that the DCN is a hierarchical modular network with community structures, which have both homogeneous and heterogeneous disease categories. Furthermore, adhering to the previous work from US and Europe populations, we found that the disease comorbidities have their shared underlying molecular mechanisms. Furthermore, take hypertension and psychiatric disease as instance, we used four classification methods to predicte the disease occurrence using the comorbid disease trajectories and obtained acceptable performance, in which in particular, random forest obtained an overall best performance (with F1-score 0.6689 for hypertension and 0.6802 for psychiatric disease).

CONCLUSIONS : Our study indicates that disease comorbidity is significant and valuable to understand the disease incidences and their interactions in real-world populations, which will provide important insights for detection of the patterns of disease classification, diagnosis and prognosis.

Guo Mengfei, Yu Yanan, Wen Tiancai, Zhang Xiaoping, Liu Baoyan, Zhang Jin, Zhang Runshun, Zhang Yanning, Zhou Xuezhong

2019-Dec-12

Complex network, Disease comorbidity, Network medicine

In BMC bioinformatics ; h5-index 0.0

BACKGROUND : Computational compound repositioning has the potential for identifying new uses for existing drugs, and new algorithms and data source aggregation strategies provide ever-improving results via in silico metrics. However, even with these advances, the number of compounds successfully repositioned via computational screening remains low. New strategies for algorithm evaluation that more accurately reflect the repositioning potential of a compound could provide a better target for future optimizations.

RESULTS : Using a text-mined database, we applied a previously described network-based computational repositioning algorithm, yielding strong results via cross-validation, averaging 0.95 AUROC on test-set indications. However, to better approximate a real-world scenario, we built a time-resolved evaluation framework. At various time points, we built networks corresponding to prior knowledge for use as a training set, and then predicted on a test set comprised of indications that were subsequently described. This framework showed a marked reduction in performance, peaking in performance metrics with the 1985 network at an AUROC of .797. Examining performance reductions due to removal of specific types of relationships highlighted the importance of drug-drug and disease-disease similarity metrics. Using data from future timepoints, we demonstrate that further acquisition of these kinds of data may help improve computational results.

CONCLUSIONS : Evaluating a repositioning algorithm using indications unknown to input network better tunes its ability to find emerging drug indications, rather than finding those which have been randomly withheld. Focusing efforts on improving algorithmic performance in a time-resolved paradigm may further improve computational repositioning predictions.

Mayers Michael, Li Tong Shu, Queralt-Rosinach Núria, Su Andrew I

2019-Dec-11

Compound repositioning, Drug central, Heterogeneous network, Machine learning, Semantic Medline database, Semantic network, Unified medical language system

In The Behavioral and brain sciences ; h5-index 0.0

Kelly Laura, Prabhakar Janani, Khemlani Sangeet

2019-12-12

In BMC bioinformatics ; h5-index 0.0

BACKGROUND : Next generation sequencing instruments are providing new opportunities for comprehensive analyses of cancer genomes. The increasing availability of tumor data allows to research the complexity of cancer disease with machine learning methods. The large available repositories of high dimensional tumor samples characterised with germline and somatic mutation data requires advance computational modelling for data interpretation. In this work, we propose to analyze this complex data with neural network learning, a methodology that made impressive advances in image and natural language processing.

RESULTS : Here we present a tumor mutation profile analysis pipeline based on an autoencoder model, which is used to discover better representations of lower dimensionality from large somatic mutation data of 40 different tumor types and subtypes. Kernel learning with hierarchical cluster analysis are used to assess the quality of the learned somatic mutation embedding, on which support vector machine models are used to accurately classify tumor subtypes.

CONCLUSIONS : The learned latent space maps the original samples in a much lower dimension while keeping the biological signals from the original tumor samples. This pipeline and the resulting embedding allows an easier exploration of the heterogeneity within and across tumor types and to perform an accurate classification of tumor samples in the pan-cancer somatic mutation landscape.

Palazzo Martin, Beauseroy Pierre, Yankilevich Patricio

2019-Dec-11

Autoencoder, Cancer genomics, Kernel learning

In BMC bioinformatics ; h5-index 0.0

BACKGROUND : In short-read DNA sequencing experiments, the read coverage is a key parameter to successfully assemble the reads and reconstruct the sequence of the input DNA. When coverage is very low, the original sequence reconstruction from the reads can be difficult because of the occurrence of uncovered gaps. Reference guided assembly can then improve these assemblies. However, when the available reference is phylogenetically distant from the sequencing reads, the mapping rate of the reads can be extremely low. Some recent improvements in read mapping approaches aim at modifying the reference according to the reads dynamically. Such approaches can significantly improve the alignment rate of the reads onto distant references but the processing of insertions and deletions remains challenging.

RESULTS : Here, we introduce a new algorithm to update the reference sequence according to previously aligned reads. Substitutions, insertions and deletions are performed in the reference sequence dynamically. We evaluate this approach to assemble a western-grey kangaroo mitochondrial amplicon. Our results show that more reads can be aligned and that this method produces assemblies of length comparable to the truth while limiting error rate when classic approaches fail to recover the correct length. Finally, we discuss how the core algorithm of this method could be improved and combined with other approaches to analyse larger genomic sequences.

CONCLUSIONS : We introduced an algorithm to perform dynamic alignment of reads on a distant reference. We showed that such approach can improve the reconstruction of an amplicon compared to classically used bioinformatic pipelines. Although not portable to genomic scale in the current form, we suggested several improvements to be investigated to make this method more flexible and allow dynamic alignment to be used for large genome assemblies.

Ranjard Louis, Wong Thomas K F, Rodrigo Allen G

2019-Dec-11

Amplicon, Assembly, Machine learning, Mitochondrion, Western-grey kangaroo

In Acta anaesthesiologica Scandinavica ; h5-index 37.0

BACKGROUND : Mortality prediction models are applied in the Intensive Care Unit (ICU) to stratify patients into different risk categories and to facilitate benchmarking. To ensure that the correct prediction models are applied for these purposes, the best performing models must be identified. As a first step, we aimed to establish a systematic review of mortality prediction models in critically ill patients.

METHODS : Mortality prediction models were searched in four databases using the following criteria: developed for use in adult ICU patients in high-income countries, with mortality as primary or secondary outcome. Characteristics and performance measures of the models were summarized. Performance was presented in terms of discrimination, calibration and overall performance measures presented in the original publication.

RESULTS : In total, 43 mortality prediction models were included in the final analysis. Fifteen models were only internally validated (35%), 13 externally (30%) and 10 (23%) were both internally and externally validated by the original researchers. Discrimination was assessed in 42 models (98%). Commonly used calibration measures were the Hosmer-Lemeshow test (60%) and the calibration plot (28%). Calibration was not assessed in 11 models (26%). Overall performance was assessed in the Brier score (19%) and the Nagelkerke's R² (4.7%).

CONCLUSIONS : Mortality prediction models have varying methodology, and validation and performance of individual models differ. External validation by the original researchers is often lacking and head-to-head comparisons are urgently needed to identify the best performing mortality prediction models for guiding clinical care and research in different settings and populations.

Keuning Britt E, Kaufmann Thomas, Wiersema Renske, Granholm Anders, Pettilä Ville, Møller Morten Hylander, Christiansen Christian Fynbo, Castela Forte José, Snieder Harold, Keus Frederik, Pleijhuis Rick G, van der Horst Iwan Cc

2019-Dec-12

Intensive Care Unit, critical care, mortality prediction model, performance, risk prediction, scoping review

In Science and engineering ethics ; h5-index 0.0

Morley Jessica, Floridi Luciano, Kinsey Libby, Elhalal Anat

2019-Dec-11

Applied ethics, Artificial intelligence, Data governance, Digital ethics, Ethics of AI, Governance, Machine learning

In Journal of medical systems ; h5-index 48.0

Thabtah Fadi, Mampusti Ella, Peebles David, Herradura Raymund, Varghese Jithin

2019-Dec-11

Accessibility, Cognitive impairment, Data analyses, Dementia, Health informatics, Mobile application, Mobile health

In International journal of computer assisted radiology and surgery ; h5-index 0.0

PURPOSE : In robotic-assisted kidney surgery, computational methods make it possible to augment the surgical scene and potentially improve patient outcome. Most often, soft-tissue registration is a prerequisite for the visualization of tumors and vascular structures hidden beneath the surface. State-of-the-art volume-to-surface registration methods, however, are computationally demanding and require a sufficiently large target surface. To overcome this limitation, the first step toward registration is the extraction of the outer edge of the kidney.

METHODS : To tackle this task, we propose a deep learning-based solution. Rather than working only on the raw laparoscopic images, the network is given depth information and distance fields to predict whether a pixel of the image belongs to an edge. We evaluate our method on expert-labeled in vivo data from the EndoVis sub-challenge 2017 Kidney Boundary Detection and define the current state of the art.

RESULTS : By using a leave-one-out cross-validation, we report results for the most suitable network with a median precision-like, recall-like, and intersection over union (IOU) of 39.5 px, 143.3 px, and 0.3, respectively.

CONCLUSION : We conclude that our approach succeeds in predicting the edges of the kidney, except in instances where high occlusion occurs, which explains the average decrease in the IOU score. All source code, reference data, models, and evaluation results are openly available for download: https://github.com/ghattab/kidney-edge-detection/.

Hattab Georges, Arnold Marvin, Strenger Leon, Allan Max, Arsentjeva Darja, Gold Oliver, Simpfendörfer Tobias, Maier-Hein Lena, Speidel Stefanie

2019-Dec-11

Boundary, Deep learning, Edge, Kidney, Segmentation

In European radiology ; h5-index 62.0

OBJECTIVE : To develop a machine learning-based ultrasound (US) radiomics model for predicting tumour deposits (TDs) preoperatively.

METHODS : From December 2015 to December 2017, 127 patients with rectal cancer were prospectively enrolled and divided into training and validation sets. Endorectal ultrasound (ERUS) and shear-wave elastography (SWE) examinations were conducted for each patient. A total of 4176 US radiomics features were extracted for each patient. After the reduction and selection of US radiomics features , a predictive model using an artificial neural network (ANN) was constructed in the training set. Furthermore, two models (one incorporating clinical information and one based on MRI radiomics) were developed. These models were validated by assessing their diagnostic performance and comparing the areas under the curve (AUCs) in the validation set.

RESULTS : The training and validation sets included 29 (33.3%) and 11 (27.5%) patients with TDs, respectively. A US radiomics ANN model was constructed. The model for predicting TDs showed an accuracy of 75.0% in the validation cohort. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and AUC were 72.7%, 75.9%, 53.3%, 88.0% and 0.743, respectively. For the model incorporating clinical information, the AUC improved to 0.795. Although the AUC of the US radiomics model was improved compared with that of the MRI radiomics model (0.916 vs. 0.872) in the 90 patients with both ultrasound and MRI data (which included both the training and validation sets), the difference was nonsignificant (p = 0.384).

CONCLUSIONS : US radiomics may be a potential model to accurately predict TDs before therapy.

KEY POINTS : • We prospectively developed an artificial neural network model for predicting tumour deposits based on US radiomics that had an accuracy of 75.0%. • The area under the curve of the US radiomics model was improved than that of the MRI radiomics model (0.916 vs. 0.872), but the difference was not significant (p = 0.384). • The US radiomics-based model may potentially predict TDs accurately before therapy, but this model needs further validation with larger samples.

Chen Li-Da, Li Wei, Xian Meng-Fei, Zheng Xin, Lin Yuan, Liu Bao-Xian, Lin Man-Xia, Li Xin, Zheng Yan-Ling, Xie Xiao-Yan, Lu Ming-De, Kuang Ming, Xu Jian-Bo, Wang Wei

2019-Dec-11

Machine learning, Rectal neoplasms, Ultrasonography

In European radiology ; h5-index 62.0

OBJECTIVES : To determine whether diffusion- and perfusion-weighted MRI-based radiomics features can improve prediction of isocitrate dehydrogenase (IDH) mutation and tumor aggressiveness in lower grade gliomas (LGGs) METHODS: Radiomics features (n = 6472) were extracted from multiparametric MRI including conventional MRI, apparent diffusion coefficient (ADC), and normalized cerebral blood volume, acquired on 127 LGG patients with determined IDH mutation status and grade (WHO II or III). Radiomics models were constructed using machine learning-based feature selection and generalized linear model classifiers. Segmentation stability was calculated between two readers using concordance correlation coefficients (CCCs). Diagnostic performance to predict IDH mutation and tumor grade was compared between the multiparametric and conventional MRI radiomics models using the area under the receiver operating characteristics curve (AUC). The models were tested using a temporally independent validation set (n = 28).

RESULTS : The multiparametric MRI radiomics model was optimized with a random forest feature selector, with segmentation stability of a CCC threshold of 0.8. For IDH mutation, multiparametric MR radiomics showed similar performance (AUC 0.795) to the conventional radiomics model (AUC 0.729). In tumor grading, multiparametric model with ADC features showed higher performance (AUC 0.932) than the conventional model (AUC 0.555). The independent validation set showed the same trend with AUCs of 0.747 for IDH prediction and 0.819 for tumor grading with multiparametric MRI radiomics model.

CONCLUSION : Multiparametric MRI radiomics model showed improved diagnostic performance in tumor grading and comparable diagnostic performance in IDH mutation status, with ADC features playing a significant role.

KEY POINTS : • The multiparametric MRI radiomics model was comparable with conventional MRI radiomics model in predicting IDH mutation. • The multiparametric MRI radiomics model outperformed conventional MRI in glioma grading. • Apparent diffusion coefficient played an important role in glioma grading and predicting IDH mutation status using radiomics.

Kim Minjae, Jung So Yeong, Park Ji Eun, Jo Yeongheun, Park Seo Young, Nam Soo Jung, Kim Jeong Hoon, Kim Ho Sung

2019-Dec-11

Glioma, Isocitrate dehydrogenase, Machine learning, Magnetic resonance imaging, Neoplasm grading

In European radiology ; h5-index 62.0

OBJECTIVES : To evaluate whether a computed tomography (CT) radiomics-based machine learning classifier can predict histopathology of lymph nodes (LNs) after post-chemotherapy LN dissection (pcRPLND) in patients with metastatic non-seminomatous testicular germ cell tumors (NSTGCTs).

METHODS : Eighty patients with retroperitoneal LN metastases and contrast-enhanced CT were included into this retrospective study. Resected LNs were histopathologically classified into "benign" (necrosis/fibrosis) or "malignant" (viable tumor/teratoma). On CT imaging, 204 corresponding LNs were segmented and 97 radiomic features per LN were extracted after standardized image processing. The dataset was split into training, test, and validation sets. After stepwise feature reduction based on reproducibility, variable importance, and correlation analyses, a gradient-boosted tree was trained and tuned on the selected most important features using the training and test datasets. Model validation was performed on the independent validation dataset.

RESULTS : The trained machine learning classifier achieved a classification accuracy of 0.81 in the validation dataset with a misclassification of 8 of 36 benign LNs as malignant and 4 of 25 malignant LNs as benign (sensitivity 88%, specificity 72%, negative predictive value 88%). In contrast, a model containing only the LN volume resulted in a classification accuracy of 0.68 with 64% sensitivity and 68% specificity.

CONCLUSIONS : CT radiomics represents an exciting new tool for improved prediction of the presence of malignant histopathology in retroperitoneal LN metastases from NSTGCTs, aiming at reducing overtreatment in this group of young patients. Thus, the presented approach should be combined with established clinical biomarkers and further validated in larger, prospective clinical trials.

KEY POINTS : • Patients with metastatic non-seminomatous testicular germ cell tumors undergoing post-chemotherapy retroperitoneal lymph node dissection of residual lesions show overtreatment in up to 50%. • We assessed whether a CT radiomics-based machine learning classifier can predict histopathology of lymph nodes after post-chemotherapy lymph node dissection. • The trained machine learning classifier achieved a classification accuracy of 0.81 in the validation dataset with a sensitivity of 88% and a specificity of 78%, thus allowing for prediction of the presence of viable tumor or teratoma in retroperitoneal lymph node metastases.

Baessler Bettina, Nestler Tim, Pinto Dos Santos Daniel, Paffenholz Pia, Zeuch Vikram, Pfister David, Maintz David, Heidenreich Axel

2019-Dec-11

Lymph nodes, Testicular neoplasms, Tomography

In Der Radiologe ; h5-index 0.0

CLINICAL/METHODOLOGICAL ISSUE : Artificial intelligence (AI) is being increasingly used in the field of radiology. The aim of this review is to illustrate the developments expected in the next 5 to 10 years as well as possible advantages and risks.

STANDARD RADIOLOGICAL METHODS : Currently, all computed tomography (CT) images are reconstructed using programmed algorithms. Pathologies are detected by the radiologist with a high expenditure of time and evaluated using standardized procedures.

METHODOLOGICAL INNOVATIONS : AI can potentially provide a significant improvement to all these standard procedures in the future. CT reconstructions can be significantly enhanced using generative adversarial networks (GAN). Histology can be evaluated using radiomics or deep learning (DL)-based image analysis and the prognosis of the patient can be predicted highly individualized.

PERFORMANCE : The performance of the networks is strongly influenced by data quality and requires extensive validation. The ability and willingness of the manufacturers to integrate these into the existing RIS/PACS systems is also decisive.

EVALUATION : AI will have a large impact on the daily clinical work of radiologists. However, publications on the risks of the technology and on adequate validation are still lacking. In addition to opening new fields of application, further research regarding possible risks is warranted.

PRACTICAL RECOMMENDATIONS : In the next 5 to 10 years, AI will improve and facilitate work in clinical practice. The integration of the applications into the existing RIS/PACS systems is expected to take place via app stores and/or existing teleradiology networks.

Haubold Johannes

2019-Dec-11

Deep learning, Image analysis, Radiomics, Risks, Validation

In Health informatics journal ; h5-index 25.0

Raef Behnaz, Maleki Masoud, Ferdousi Reza

2019-Dec-12

assisted reproductive technology, embryo transfer, machine learning, prediction model, ranking algorithms

In Neuroradiology ; h5-index 0.0

PURPOSE : To analyze the implementation of deep learning software for the detection and worklist prioritization of acute intracranial hemorrhage on non-contrast head CT (NCCT) in various clinical settings at an academic medical center.

METHODS : Urgent NCCT scans were reviewed by the Aidoc (Tel Aviv, Israel) neural network software. All cases flagged by the software as positive for acute intracranial hemorrhage on the neuroradiology worklist were prospectively included in this assessment. The scans were classified regarding presence and type of hemorrhage, whether these were initial or follow-up scans, and patient visit location, including trauma/emergency, inpatient, and outpatient departments.

RESULTS : During the 2 months of enrollment, 373 NCCT scans were flagged by the Aidoc software for possible intracranial hemorrhage out of 2011 scans analyzed (18.5%). Among the flagged cases, 275 (72.4%) were positive; 290 (77.7%) were inpatient cases, 75 (20.1%) were trauma/emergency cases, and eight (2.1%) were outpatient cases, and 229 of 373 (62.5%) were follow-up cases, of which 219 (95.6%) inpatient cases. Among the 144 new cases flagged for hemorrhage, 66 (44.4%) were positive, of which 39 (58.2%) were trauma/emergency cases. The overall sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were 88.7%, 94.2% and 73.7%, 97.7%, and 93.4%, respectively. The accuracy of the intracranial hemorrhage detection was significantly higher for emergency cases than for inpatient cases (96.5% versus 89.4%).

CONCLUSION : This study reveals that the performance of the deep learning software for acute intracranial hemorrhage detection varies depending upon the patient visit location. Furthermore, a substantial portion of flagged cases were follow-up exams, the majority of which were inpatient exams. These findings can help optimize the artificial intelligence-driven clincical workflow.

Ginat Daniel T

2019-Dec-11

CT, Deep learning, Intracranial hemorrhage, Neural networks

In Data in brief ; h5-index 0.0

Hubert-Moy Laurence, Thibault Jeanne, Fabre Elodie, Rozo Clémence, Arvor Damien, Corpetti Thomas, Rapinel Sébastien

2019-Dec

Big data, Crop modeling, LPIS, MODIS, Time-series analysis, Vegetation index

In BioMed research international ; h5-index 102.0

Mao Yifei, Yang Yuansheng

2019

In BioMed research international ; h5-index 102.0

Yaman Emine, Subasi Abdulhamit

2019

In BioMed research international ; h5-index 102.0

Yousufi Musyyab, Amir Muhammad, Javed Umer, Tayyib Muhammad, Abdullah Suheel, Ullah Hayat, Qureshi Ijaz Mansoor, Alimgeer Khurram Saleem, Akram Muhammad Waseem, Khan Khan Bahadar

2019

In Fertility research and practice ; h5-index 0.0

Background : Polycystic ovary syndrome (PCOS) is characterized by hyperandrogenemia, oligo-anovulation, and numerous ovarian cysts. Hospital electronic medical records provide an avenue for investigating polycystic ovary morphology commonly seen in PCOS at a large scale. The purpose of this study was to develop and evaluate the performance of two machine learning text algorithms, for classification of polycystic ovary morphology (PCOM) in pelvic ultrasounds.

Methods : Pelvic ultrasound reports from patients at Boston Medical Center between October 1, 2003 and December 12, 2016 were included for analysis, which resulted in 39,093 ultrasound reports from 25,535 unique women. Following the 2003 Rotterdam Consensus Criteria for polycystic ovary syndrome, 2000 randomly selected ultrasounds were expert labeled for PCOM status as present, absent, or unidentifiable (not able to be determined from text alone). An ovary was marked as having PCOM if there was mention of numerous peripheral follicles or if the volume was greater than 10 ml in the absence of a dominant follicle or other confounding pathology. Half of the labeled data was used to develop and refine the algorithms, and the other half was used as a test set for evaluating its accuracy.

Results : On the evaluation set of 1000 random US reports, the accuracy of the classifiers were 97.6% (95% CI: 96.5, 98.5%) and 96.1% (94.7, 97.2%). Both models were more adept at identifying PCOM-absent ultrasounds than either PCOM-unidentifiable or PCOM-present ultrasounds. The two classifiers estimated prevalence of PCOM within the whole set of 39,093 ultrasounds to be 44% PCOM-absent, 32% PCOM-unidentifiable, and 24% PCOM-present.

Conclusions : Although accuracy measured on the test set and inter-rater agreement between the two classifiers (Cohen's Kappa = 0.988) was high, a major limitation of our approach is that it uses the ultrasound report text as a proxy and does not directly count follicles from the ultrasound images themselves.

Cheng Jay Jojo, Mahalingaiah Shruthi

2019

Data mining, Electronic medical record, Machine learning, Polycystic ovary syndrome, Ultrasound

In Royal Society open science ; h5-index 0.0

Cunningham Ryan, Sánchez María B, Butler Penelope B, Southgate Matthew J, Loram Ian D

2019-Nov

SATCo, cerebral palsy, deep learning, feature tracking, pose estimation, video analysis

In Royal Society open science ; h5-index 0.0

Min Yong, Jiang Tingjun, Jin Cheng, Li Qu, Jin Xiaogang

2019-Nov

controlled experiment, echo chamber, polarization, privacy protection, social network

In Oxidative medicine and cellular longevity ; h5-index 0.0

Masania Jinit, Faustmann Gernot, Anwar Attia, Hafner-Giessauf Hildegard, Rajpoot Nasir, Grabher Johanna, Rajpoot Kashif, Tiran Beate, Obermayer-Pietsch Barbara, Winklhofer-Roob Brigitte M, Roob Johannes M, Rabbani Naila, Thornalley Paul J

2019

In Computational and mathematical methods in medicine ; h5-index 0.0

Nas Serkan, Koyuncu Melik

2019

In Abdominal radiology (New York) ; h5-index 0.0

PURPOSE : To predict the histologic grade of small clear cell renal cell carcinomas (ccRCCs) using texture analysis and machine learning algorithms.

METHODS : Fifty-two noncontrast (NC), 26 corticomedullary (CM) phase, and 35 nephrographic (NG) phase CTs of small (< 4 cm) surgically resected ccRCCs were retrospectively identified. Surgical pathology classified the tumors as low- or high-Fuhrman histologic grade. The axial image with the largest cross-sectional tumor area was exported and segmented. Six histogram and 31 texture (gray-level co-occurrences (GLC) and gray-level run-lengths (GLRL)) features were calculated for each tumor in each phase. T testing compared feature values in low- and high-grade ccRCCs, with a (Benjamini-Hochberg) false discovery rate of 10%. Area under the receiver operating curve (AUC) was calculated for each feature to assess prediction of low- and high-grade ccRCCs in each phase. Histogram, texture, and combined histogram and texture data sets were used to train and test four algorithms (k-nearest neighbor (KNN), support vector machine (SVM), random forests, and decision tree) with tenfold cross-validation; AUCs were calculated for each algorithm in each phase to assess prediction of low- and high-grade ccRCCs.

RESULTS : Zero, 23, and 0 features in the NC, CM, and NG phases had statistically significant differences between low and high-grade ccRCCs. CM histogram skewness and GLRL short run emphasis had the highest AUCs (0.82) in predicting histologic grade. All four algorithms had the highest AUCs (0.97) predicting histologic grade using CM histogram features. The algorithms' AUCs decreased using histogram or texture features from NC or NG phases.

CONCLUSION : The histologic grade of small ccRCCs can be accurately predicted with machine learning algorithms using CM histogram features, which outperform NC and NG phase image data.

Haji-Momenian Shawn, Lin Zixian, Patel Bhumi, Law Nicole, Michalak Adam, Nayak Anishsanjay, Earls James, Loew Murray

2019-Dec-10

Clear cell renal cell carcinoma, Histology, Machine learning, Texture

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

Grzybowski Andrzej, Brona Piotr, Lim Gilbert, Ruamviboonsuk Paisan, Tan Gavin S W, Abramoff Michael, Ting Daniel S W

2019-Dec-10

In Molecular psychiatry ; h5-index 103.0

Elliott Maxwell L, Belsky Daniel W, Knodt Annchen R, Ireland David, Melzer Tracy R, Poulton Richie, Ramrakha Sandhya, Caspi Avshalom, Moffitt Terrie E, Hariri Ahmad R

2019-Dec-10

In Scientific reports ; h5-index 158.0

Forkel Matthias, Drüke Markus, Thurner Martin, Dorigo Wouter, Schaphoff Sibyll, Thonicke Kirsten, von Bloh Werner, Carvalhais Nuno

2019-Dec-10

In Journal of neural engineering ; h5-index 52.0

Al-Fahad Rakib, Yeasin Mohammed, M Bidelman Gavin

2019-Dec-11

Categorical speech perception, functional connectivity, machine learning, speech processing, stability selection

In PloS one ; h5-index 176.0

Abbas Hasan T, Alic Lejla, Erraguntla Madhav, Ji Jim X, Abdul-Ghani Muhammad, Abbasi Qammer H, Qaraqe Marwa K

2019

In Biomedizinische Technik. Biomedical engineering ; h5-index 0.0

Polat Hasan, Aluçlu Mehmet Ufuk, Özerdem Mehmet Siraç

2019-Dec-11

EEG, deep learning, epilepsy, epileptic aura, time-frequency representation

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

Hassan Teena, Seus Dominik, Wollenberg Johannes, Weitz Katharina, Kunz Miriam, Lautenbacher Stefan, Garbas Jens-Uwe, Schmid Ute

2019-Dec-09

In IEEE transactions on bio-medical engineering ; h5-index 0.0

Wang Mingliang, Lian Chunfeng, Yao Dongren, Zhang Daoqiang, Liu Mingxia, Shen Dinggang

2019-Dec-06

In Cell reports ; h5-index 119.0

Lawrenson Kate, Fonseca Marcos A S, Liu Annie Y, Segato Dezem Felipe, Lee Janet M, Lin Xianzhi, Corona Rosario I, Abbasi Forough, Vavra Kevin C, Dinh Huy Q, Gill Navjot Kaur, Seo Ji-Heui, Coetzee Simon, Lin Yvonne G, Pejovic Tanja, Mhawech-Fauceglia Paulette, Rowat Amy C, Drapkin Ronny, Karlan Beth Y, Hazelett Dennis J, Freedman Matthew L, Gayther Simon A, Noushmehr Houtan

2019-Dec-10

RNA-seq, SOX18, dual origins, fallopian tube secretory epithelial cell, high-grade serous ovarian cancer, machine learning, one-class logistic regression models, ovarian surface epithelial cell, single-cell RNA-seq, super enhancers, transcription factors

In Cell reports ; h5-index 119.0

Sakellaropoulos Theodore, Vougas Konstantinos, Narang Sonali, Koinis Filippos, Kotsinas Athanassios, Polyzos Alexander, Moss Tyler J, Piha-Paul Sarina, Zhou Hua, Kardala Eleni, Damianidou Eleni, Alexopoulos Leonidas G, Aifantis Iannis, Townsend Paul A, Panayiotidis Mihalis I, Sfikakis Petros, Bartek Jiri, Fitzgerald Rebecca C, Thanos Dimitris, Mills Shaw Kenna R, Petty Russell, Tsirigos Aristotelis, Gorgoulis Vassilis G

2019-Dec-10

DNN, deep neural networks, drug response prediction, machine learning, precision medicine

In Proceedings of the National Academy of Sciences of the United States of America ; h5-index 0.0

Yuan Ye, Bar-Joseph Ziv

2019-Dec-10

causality inference, deep learning, gene interactions

In Journal of chemical information and modeling ; h5-index 0.0

Zheng Shuangjia, Rao Jiahua, Zhang Zhongyue, Xu Jun, Yang Yuedong

2019-Dec-11

In Journal of chemical information and modeling ; h5-index 0.0

Sundar Vikram, Colwell Lucy

2019-Dec-11

In The Prostate ; h5-index 42.0

INTRODUCTION : The 2019 Coffey-Holden Prostate Cancer Academy (CHPCA) Meeting, "Prostate Cancer Research: The Next Generation," was held 20 to 23 June, 2019, in Los Angeles, California.

METHODS : The CHPCA Meeting is an annual conference held by the Prostate Cancer Foundation, that is uniquely structured to stimulate intense discussion surrounding topics most critical to accelerating prostate cancer research and the discovery of new life-extending treatments for patients. The 7th Annual CHPCA Meeting was attended by 86 investigators and concentrated on many of the most promising new treatment opportunities and next-generation research technologies.

RESULTS : The topics of focus at the meeting included: new treatment strategies and novel agents for targeted therapies and precision medicine, new treatment strategies that may synergize with checkpoint immunotherapy, next-generation technologies that visualize tumor microenvironment (TME) and molecular pathology in situ, multi-omics and tumor heterogeneity using single cells, 3D and TME models, and the role of extracellular vesicles in cancer and their potential as biomarkers.

DISCUSSION : This meeting report provides a comprehensive summary of the talks and discussions held at the 2019 CHPCA Meeting, for the purpose of globally disseminating this knowledge and ultimately accelerating new treatments and diagnostics for patients with prostate cancer.

Miyahira Andrea K, Sharp Adam, Ellis Leigh, Jones Jennifer, Kaochar Salma, Larman H Benjamin, Quigley David A, Ye Huihui, Simons Jonathan W, Pienta Kenneth J, Soule Howard R

2019-Dec-11

artificial intelligence, cancer immunotherapy, precision medicine, therapeutics, tumor genomics

In JAMA network open ; h5-index 0.0

Importance : Inpatient overcrowding is associated with delays in care, including the deferral of surgical care until beds are available to accommodate postoperative patients. Timely patient discharge is critical to address inpatient overcrowding and requires coordination among surgeons, nurses, case managers, and others. This is difficult to achieve without early identification and systemwide transparency of discharge candidates and their respective barriers to discharge.

Objective : To validate the performance of a clinically interpretable feedforward neural network model that could improve the discharge process by predicting which patients would be discharged within 24 hours and their clinical and nonclinical barriers.

Design, Setting, and Participants : This prognostic study included adult patients discharged from inpatient surgical care from May 1, 2016, to August 31, 2017, at a quaternary care teaching hospital. Model performance was assessed with standard cross-validation techniques. The model's performance was compared with a baseline model using historical procedure median length of stay to predict discharges. In prospective cohort analysis, the feedforward neural network model was used to make predictions on general surgical care floors with 63 beds. If patients were not discharged when predicted, the causes of delay were recorded.

Main Outcomes and Measures : The primary outcome was the out-of-sample area under the receiver operating characteristic curve of the model. Secondary outcomes included the causes of discharge delay and the number of avoidable bed-days.

Results : The model was trained on 15 201 patients (median [interquartile range] age, 60 [46-70] years; 7623 [50.1%] men) discharged from inpatient surgical care. The estimated out-of-sample area under the receiver operating characteristic curve of the model was 0.840 (SD, 0.008; 95% CI, 0.839-0.844). Compared with the baseline model, the neural network model had higher sensitivity (52.5% vs 56.6%) and specificity (51.7% vs 82.6%). The neural network model identified 65 barriers to discharge. In the prospective study of 605 patients, causes of delays included clinical barriers (41 patients [30.1%]), variation in clinical practice (30 patients [22.1%]), and nonclinical reasons (65 patients [47.8%]). Summing patients who were not discharged owing to variation in clinical practice and nonclinical reasons, 128 bed-days, or 1.2 beds per day, were classified as avoidable.

Conclusions and Relevance : This cohort study found that a neural network model could predict daily inpatient surgical care discharges and their barriers. The model identified systemic causes of discharge delays. Such models should be studied for their ability to increase the timeliness of discharges.

Safavi Kyan C, Khaniyev Taghi, Copenhaver Martin, Seelen Mark, Zenteno Langle Ana Cecilia, Zanger Jonathan, Daily Bethany, Levi Retsef, Dunn Peter

2019-Dec-02

In JAMA surgery ; h5-index 69.0

Importance : Surgeons make complex, high-stakes decisions under time constraints and uncertainty, with significant effect on patient outcomes. This review describes the weaknesses of traditional clinical decision-support systems and proposes that artificial intelligence should be used to augment surgical decision-making.

Observations : Surgical decision-making is dominated by hypothetical-deductive reasoning, individual judgment, and heuristics. These factors can lead to bias, error, and preventable harm. Traditional predictive analytics and clinical decision-support systems are intended to augment surgical decision-making, but their clinical utility is compromised by time-consuming manual data management and suboptimal accuracy. These challenges can be overcome by automated artificial intelligence models fed by livestreaming electronic health record data with mobile device outputs. This approach would require data standardization, advances in model interpretability, careful implementation and monitoring, attention to ethical challenges involving algorithm bias and accountability for errors, and preservation of bedside assessment and human intuition in the decision-making process.

Conclusions and Relevance : Integration of artificial intelligence with surgical decision-making has the potential to transform care by augmenting the decision to operate, informed consent process, identification and mitigation of modifiable risk factors, decisions regarding postoperative management, and shared decisions regarding resource use.

Loftus Tyler J, Tighe Patrick J, Filiberto Amanda C, Efron Philip A, Brakenridge Scott C, Mohr Alicia M, Rashidi Parisa, Upchurch Gilbert R, Bihorac Azra

2019-Dec-11

In Khirurgiia ; h5-index 0.0

Nikolaev A E, Chernina V Yu, Blokhin I A, Shapiev A N, Gonchar A P, Gombolevskiy V A, Petraikin A V, Silin A Yu, Petrova G D, Morozov S P

2019

artificial intelligence, computed tomography, low-dose computed tomography, lung cancer screening, machine learning, neural network, thorax

In JMIR aging ; h5-index 0.0

BACKGROUND : Intelligent assistants (IAs), also known as intelligent agents, use artificial intelligence to help users achieve a goal or complete a task. IAs represent a potential solution for providing older adults with individualized assistance at home, for example, to reduce social isolation, serve as memory aids, or help with disease management. However, to design IAs for health that are beneficial and accepted by older adults, it is important to understand their beliefs about IAs, how they would like to interact with IAs for consumer health, and how they desire to integrate IAs into their homes.

OBJECTIVE : We explore older adults' mental models and beliefs about IAs, the tasks they want IAs to support, and how they would like to interact with IAs for consumer health. For the purpose of this study, we focus on IAs in the context of consumer health information management and search.

METHODS : We present findings from an exploratory, qualitative study that investigated older adults' perspectives of IAs that aid with consumer health information search and management tasks. Eighteen older adults participated in a multiphase, participatory design workshop in which we engaged them in discussion, brainstorming, and design activities that helped us identify their current challenges managing and finding health information at home. We also explored their beliefs and ideas for an IA to assist them with consumer health tasks. We used participatory design activities to identify areas in which they felt IAs might be useful, but also to uncover the reasoning behind the ideas they presented. Discussions were audio-recorded and later transcribed. We compiled design artifacts collected during the study to supplement researcher transcripts and notes. Thematic analysis was used to analyze data.

RESULTS : We found that participants saw IAs as potentially useful for providing recommendations, facilitating collaboration between themselves and other caregivers, and for alerts of serious illness. However, they also desired familiar and natural interactions with IAs (eg, using voice) that could, if need be, provide fluid and unconstrained interactions, reason about their symptoms, and provide information or advice. Other participants discussed the need for flexible IAs that could be used by those with low technical resources or skills.

CONCLUSIONS : From our findings, we present a discussion of three key components of participants' mental models, including the people, behaviors, and interactions they described that were important for IAs for consumer health information management and seeking. We then discuss the role of access, transparency, caregivers, and autonomy in design for addressing participants' concerns about privacy and trust as well as its role in assisting others that may interact with an IA on the older adults' behalf.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID) : RR2-10.1145/3240925.3240972.

Martin-Hammond Aqueasha, Vemireddy Sravani, Rao Kartik

2019-Dec-11

aging in place, artificial intelligence, chatbots, co-design, conversational agents, digital health, elderly, health information seeking, intelligent assistants, participatory design

In Nano letters ; h5-index 188.0

Wiecha Peter R, Muskens Otto L

2019-Dec-11

In OSA continuum ; h5-index 0.0

Henn Mark-Alexander, Zhou Hui, Barnes Bryan M

2019-Sep-15

In Journal of medical imaging (Bellingham, Wash.) ; h5-index 0.0

Nalawade Sahil, Murugesan Gowtham K, Vejdani-Jahromi Maryam, Fisicaro Ryan A, Bangalore Yogananda Chandan G, Wagner Ben, Mickey Bruce, Maher Elizabeth, Pinho Marco C, Fei Baowei, Madhuranthakam Ananth J, Maldjian Joseph A

2019-Oct

convolutional neural network, deep learning, isocitrate dehydrogenase, magnetic resonance imaging, segmentation, tumor classification

In Journal of surgical education ; h5-index 0.0

OBJECTIVE : Assessment of physiological tremor during neurosurgical procedures may provide further insights into the composites of surgical expertise. Virtual reality platforms may provide a mechanism for the quantitative assessment of physiological tremor. In this study, a virtual reality simulator providing haptic feedback was used to study physiological tremor in a simulated tumor resection task with participants from a "skilled" group and a "novice" group.

DESIGN : The task involved using a virtual ultrasonic aspirator to remove a series of virtual brain tumors with different visual and tactile characteristics without causing injury to surrounding tissue. Power spectral density analysis was employed to quantitate hand tremor during tumor resection. Statistical t test was used to determine tremor differences between the skilled and novice groups obtained from the instrument tip x, y, z coordinates, the instrument roll, pitch, yaw angles, and the instrument haptic force applied during tumor resection.

SETTING : The study was conducted at the Neurosurgical Simulation and Artificial Intelligence Learning Centre, Montreal Neurological Institute and Hospital, McGill University, Montreal, Canada.

PARTICIPANTS : The skilled group comprised 23 neurosurgeons and senior residents and the novice group comprised 92 junior residents and medical students.

RESULTS : The spectral analysis allowed quantitation of physiological tremor during virtual reality tumor resection. The skilled group displayed smaller physiological tremor than the novice group in all cases. In 3 out of 7 cases the difference was statistically significant.

CONCLUSIONS : The first investigation of the application of a virtual reality platform is presented for the quantitation of physiological tremor during a virtual reality tumor resection task. The goal of introducing such methodology to assess tremor is to highlight its potential educational application in neurosurgical resident training and in helping to further define the psychomotor skill set of surgeons.

Siyar Samaneh, Azarnoush Hamed, Rashidi Saeid, Del Maestro Rolando F

2019-Dec-07

NeuroTouch/NeuroVR, Patient Care, Practice-Based Learning and Improvement, Systems-Based Practice, neurosurgery, physiological tremor, simulation, tumor resection, virtual reality

In Journal of medical imaging (Bellingham, Wash.) ; h5-index 0.0

Bermudez Noguera Camilo, Bao Shunxing, Petersen Kalen J, Lopez Alexander M, Reid Jacqueline, Plassard Andrew J, Zald David H, Claassen Daniel O, Dawant Benoit M, Landman Bennett A

2019-Oct

automatic image segmentation, deep learning, dentate nucleus, magnetic resonance imaging, multisequence Imaging

In Frontiers in medicine ; h5-index 0.0

Dimitriou Neofytos, Arandjelović Ognjen, Caie Peter D

2019

cancer, computer vision, digital pathology, image analysis, machine learning, oncology, personalized pathology

In Frontiers in bioengineering and biotechnology ; h5-index 0.0

Ma Xibo, Chen Lei, Yang Yingcheng, Zhang Weiqi, Wang Peixia, Zhang Kun, Zheng Bo, Zhu Lin, Sun Zheng, Zhang Shuai, Guo Yingkun, Liang Minmin, Wang Hongyang, Tian Jie

2019

an artificial intelligent signal amplification system, early diagnosis of precancerous lesions, fluorescent molecular tomography, in vivo detection of non-coding RNA, stem cell tracing

In Frontiers in chemistry ; h5-index 0.0

Thafar Maha, Raies Arwa Bin, Albaradei Somayah, Essack Magbubah, Bajic Vladimir B

2019

artificial intelligence, bioinformatics, deep learning, drug repurposing, drug-target binding affinity, drug-target interaction, information integration, machine learning

In Frontiers in chemistry ; h5-index 0.0

Lee Jihyeun, Kumar Surendra, Lee Sang-Yoon, Park Sung Jean, Kim Mi-Hyun

2019

“Alzheimers disease”, S100, classification, consensus vote, feature selection, ligand-based virtual screening, machine learning, random forest

In Frontiers in chemistry ; h5-index 0.0

Lima Marilia N N, Cassiano Gustavo C, Tomaz Kaira C P, Silva Arthur C, Sousa Bruna K P, Ferreira Leticia T, Tavella Tatyana A, Calit Juliana, Bargieri Daniel Y, Neves Bruno J, Costa Fabio T M, Andrade Carolina Horta

2019

Plasmodium falciparum, machine learning, malaria, multi-target, shape-based, virtual screening

In Frontiers in oncology ; h5-index 0.0

Chen Wujie, Wang Siwen, Dong Di, Gao Xuning, Zhou Kefeng, Li Jiaying, Lv Bin, Li Hailin, Wu Xiangjun, Fang Mengjie, Tian Jie, Xu Maosheng

2019

advanced gastric cancer, diffusion-weighted imaging, lymph node metastasis, magnetic resonance imaging, radiomics

In F1000Research ; h5-index 0.0

Medic Goran, Kosaner Kließ Melodi, Atallah Louis, Weichert Jochen, Panda Saswat, Postma Maarten, El-Kerdi Amer

2019

clinical trials, critical care., hemodynamic instability, infection, machine learning, respiratory distress, sepsis

In Frontiers in genetics ; h5-index 62.0

Mubeen Sarah, Hoyt Charles Tapley, Gemünd André, Hofmann-Apitius Martin, Fröhlich Holger, Domingo-Fernández Daniel

2019

benchmarking, databases, machine learning, pathway enrichment, statistical hypothesis testing

In Frontiers in genetics ; h5-index 62.0

Ju Yuqi, Yuan Liangliang, Yang Yang, Zhao Hai

2019

RNA–protein binding sites, bidirectional LSTM neural network, convolutional neural network, deep learning, sequence labeling

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

BACKGROUND : With the character of high incidence, high prevalence and high mortality, stroke has brought a heavy burden to families and society in China. In 2009, the Ministry of Health of China launched the China national stroke screening and intervention program, which screens stroke and its risk factors and conducts high-risk population interventions for people aged above 40 years old all over China. In this program, stroke risk factors include hypertension, diabetes, dyslipidemia, smoking, lack of exercise, apparently overweight and family history of stroke. People with more than two risk factors or history of stroke or transient ischemic attack (TIA) are considered as high-risk. However, it is impossible for this criterion to classify stroke risk levels for people with unknown values in fields of risk factors. The missing of stroke risk levels results in reduced efficiency of stroke interventions and inaccuracies in statistical results at the national level. In this paper, we use 2017 national stroke screening data to develop stroke risk classification models based on machine learning algorithms to improve the classification efficiency.

METHOD : Firstly, we construct training set and test sets and process the imbalance training set based on oversampling and undersampling method. Then, we develop logistic regression model, Naïve Bayesian model, Bayesian network model, decision tree model, neural network model, random forest model, bagged decision tree model, voting model and boosting model with decision trees to classify stroke risk levels.

RESULT : The recall of the boosting model with decision trees is the highest (99.94%), and the precision of the model based on the random forest is highest (97.33%). Using the random forest model (recall: 98.44%), the recall will be increased by about 2.8% compared with the method currently used, and several thousands more people with high risk of stroke can be identified each year.

CONCLUSION : Models developed in this paper can improve the current screening method in the way that it can avoid the impact of unknown values, and avoid unnecessary rescreening and intervention expenditures. The national stroke screening program can choose classification models according to the practice need.

Li Xuemeng, Bian Di, Yu Jinghui, Li Mei, Zhao Dongsheng

2019-Dec-10

Machine learning models, National Stroke Screening, Risk level classification

In Frontiers in genetics ; h5-index 62.0

Zhu Qiang, Jiang Xingpeng, Zhu Qing, Pan Min, He Tingting

2019

In Frontiers in genetics ; h5-index 62.0

Ma Yingjun, He Tingting, Jiang Xingpeng

2019

feature projection, graph non-negative matrix factorization, kernel neighborhood similarity, lncRNA-protein interaction, neighborhood completion

In Frontiers in genetics ; h5-index 62.0

Luo Xiao, Chi Weilai, Deng Minghua

2019

convolutional neural networks, deep neural networks, interpretation, motif inference, network pruning

In Frontiers in genetics ; h5-index 62.0

Liu Yang, Wang Duolin, He Fei, Wang Juexin, Joshi Trupti, Xu Dong

2019

deep learning, genome-wide association study, genomic selection, genotype contribution, soybean

In Frontiers in psychiatry ; h5-index 0.0

Stoyanov Drozdstoy, Kandilarova Sevdalina, Paunova Rositsa, Barranco Garcia Javier, Latypova Adeliya, Kherif Ferath

2019

classification, functional MRI, machine learning, psychopathology, validation

In Frontiers in aging neuroscience ; h5-index 64.0

Feng Qi, Song Qiaowei, Wang Mei, Pang PeiPei, Liao Zhengluan, Jiang Hongyang, Shen Dinggang, Ding Zhongxiang

2019

Alzheimer’s disease, amnestic mild cognitive impairment, hippocampus, machine learning, magnetic resonance imaging, radiomics

In Frontiers in neurorobotics ; h5-index 0.0

Jin Shaowei, Liu Huaping, Wang Bowen, Sun Fuchun

2019

acoustic features, interactive perception, kernel k nearest neighbor, object recognition, objects in containers, open environment

In Frontiers in neuroscience ; h5-index 72.0

Nielsen Søren F V, Madsen Kristoffer H, Vinberg Maj, Kessing Lars V, Siebner Hartwig R, Miskowiak Kamilla W

2019

cognitive dysfunction, erythropoietin, functional magnetic resonance imaging, machine learning, mood disorders

In Proceedings. Mathematical, physical, and engineering sciences ; h5-index 0.0

Chen Qipin, Hao Wenrui

2019-Nov

homotopy method, machine learning, neural network, training algorithm

In Cancer management and research ; h5-index 0.0

Objective : The purpose of this study was to evaluate the cost-effectiveness of the combined use of afatinib and epidermal growth factor receptor (EGFR) testing versus gemcitabine-cisplatin as the first-line treatment for patients with non-small cell lung cancer (NSCLC) in China.

Methods : A decision-analytic model, based on clinical phase III trials, was developed to simulate patient transitions. Direct costs were estimated from the perspective of the Chinese healthcare system. Quality-adjusted life-years (QALYs) and incremental cost-effectiveness ratios (ICER) were calculated over a 5-year lifetime horizon. Model robustness was conducted in sensitivity analyses.

Results : For the base case, EGFR mutation testing followed by afatinib treatment for advanced NSCLC increased 0.15 QALYs compared with standard chemotherapy at an additional cost of $5069.12. The ICER for afatinib maintenance was $33,416.39 per QALY gained. The utility of PFS and the cost of afatinib had the most important impact on the ICER. Scenario analyses suggested that when a patient assistance program (PAP) was available, ICER decreased to $22,972.52/QALY lower than the willingness-to-pay (WTP) threshold of China ($26,508/QALY).

Conclusion : Our results suggest that gene-guided maintenance therapy with afatinib with the PAP might be a cost-effective treatment option compared with gemcitabine - cisplatin in China.

You Ruxu, Liu Jinyu, Wu David Bin-Chia, Qian XinYu, Lyu Boxiang, Zhang Yu, Luo Nan

2019

Afatinib, EGER mutation testing, Economic analysis, NSCLC, incremental cost-effectiveness ratio

In The Journal of chemical physics ; h5-index 0.0

Terayama Kei, Shinobu Ai, Tsuda Koji, Takemura Kazuhiro, Kitao Akio

2019-Dec-07

In Journal of oral pathology & medicine : official publication of the International Association of Oral Pathologists and the American Academy of Oral Pathology ; h5-index 0.0

BACKGROUND : Despite their high accuracy to recognize oral potentially malignant disorders (OPMDs) with cancer risk, non-invasive oral assays are poor in discerning whether the risk is high or low. However, it is critical to identify the risk levels, since high-risk patients need active intervention, while low-risk ones simply need to be follow-up. This study aimed at developing a personalized computational model to predict cancer risk level of OPMDs and explore its potential web application in OPMDs screening.

METHODS : Each enrolled patient was subjected to the following procedure: personal information collection, non-invasive oral examination, oral tissue biopsy and histopathological analysis, treatment and follow-up. Patients were randomly divided into a training set (N=159) and a test set (N=107). Random forest was used to establish classification models. A baseline model (model-B) and a personalized model (model-P) were created. The former used the non-invasive scores only, while the latter was incremented with appropriate personal features.

RESULTS : We compared the respective performance of cancer risk level prediction by model-B, model-P and clinical experts. Our data suggested that all three have a similar level of specificity around 90%. In contrast, the sensitivity of model-P is beyond 80% and superior to the other two. The improvement of sensitivity by model-P reduced the misclassification of high-risk patients as low-risk ones. We deployed model-P in web.opmd-risk.com, which can be freely and conveniently accessed.

CONCLUSION : We have proposed a novel machine-learning model for precise and cost-effective OPMDs screening, which integrates clinical examinations, machine learning and information technology.

Wang Xiangjian, Yang Jin, Wei Changlei, Zhou Gang, Wu Lanyan, Gao Qinghong, He Xin, Shi Jiahong, Mei Yingying, Liu Ying, Shi Xueke, Wu Fanglong, Luo Jingjing, Guo Yiqing, Zhou Qizhi, Yin Jiaxin, Hu Tao, Lin Mei, Liang Zhi, Zhou Hongmei

2019-Dec-10

Cancer risk level prediction, Non-invasive screening, Oral potentially malignant disorders, Personalized model, Web application

In Journal of microscopy ; h5-index 0.0

Ilett M, Wills J, Rees P, Sharma S, Micklethwaite S, Brown A, Brydson R, Hondow N

2019-Dec-11

Automated imaging, agglomeration, machine learning, nanoparticles

In Advances in experimental medicine and biology ; h5-index 0.0

Murray Jo-Anne

2019

Biomedical, Open online courses (MOOC)

In Intensive care medicine experimental ; h5-index 0.0

BACKGROUND : Prognosticating the course of diseases to inform decision-making is a key component of intensive care medicine. For several applications in medicine, new methods from the field of artificial intelligence (AI) and machine learning have already outperformed conventional prediction models. Due to their technical characteristics, these methods will present new ethical challenges to the intensivist.

RESULTS : In addition to the standards of data stewardship in medicine, the selection of datasets and algorithms to create AI prognostication models must involve extensive scrutiny to avoid biases and, consequently, injustice against individuals or groups of patients. Assessment of these models for compliance with the ethical principles of beneficence and non-maleficence should also include quantification of predictive uncertainty. Respect for patients' autonomy during decision-making requires transparency of the data processing by AI models to explain the predictions derived from these models. Moreover, a system of continuous oversight can help to maintain public trust in this technology. Based on these considerations as well as recent guidelines, we propose a pathway to an ethical implementation of AI-based prognostication. It includes a checklist for new AI models that deals with medical and technical topics as well as patient- and system-centered issues.

CONCLUSION : AI models for prognostication will become valuable tools in intensive care. However, they require technical refinement and a careful implementation according to the standards of medical ethics.

Beil Michael, Proft Ingo, van Heerden Daniel, Sviri Sigal, van Heerden Peter Vernon

2019-Dec-10

Artificial intelligence, Intensive care, Machine learning, Medical ethics, Prognostication

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

Mundt Marion, Thomsen Wolf, Witter Tom, Koeppe Arnd, David Sina, Bamer Franz, Potthast Wolfgang, Markert Bernd

2019-Dec-11

Data augmentation, Data simulation, IMU, Inertial sensors, Machine learning

In Biomechanics and modeling in mechanobiology ; h5-index 36.0

Hashemi Mohammad Saber, Baniassadi Majid, Baghani Mostafa, George Daniel, Remond Yves, Sheidaei Azadeh

2019-Dec-10

Anisotropic hyperelastic material, Artificial neural network (ANN), Finite element analysis (FEA), Mechanical homogenization, Optimization

In Journal of medical systems ; h5-index 48.0

Park Jong-Uk, Kang Dong-Won, Erdenebayar Urtnasan, Kim Yoon-Ji, Cha Kyoung-Chul, Lee Kyoung-Joung

2019-Dec-10

Biofeedback, Blood pressure (BP), Cardiopulmonary resuscitation (CPR), Earlobe photoplethysmography (ear PPG), Long short-term memory (LSTM)

In Journal of medical systems ; h5-index 48.0

Bellini Valentina, Guzzon Marco, Bigliardi Barbara, Mordonini Monica, Filippelli Serena, Bignami Elena

2019-Dec-10

Anesthesia, Artificial intelligence, Big data, Block time, Hospital administration, Machine learning, Operating room, Operating room efficiency, Perioperative, Recovery room, Robotic assisted surgery, Scheduling

In Environmental monitoring and assessment ; h5-index 0.0

Danandeh Mehr Ali, Safari Mir Jafar Sadegh

2019-Dec-10

Genetic programming, Hybrid models, Rainfall, Stochastic modelling

In European radiology ; h5-index 62.0

OBJECTIVES : To evaluate the diagnostic performance of a deep learning algorithm for automated detection of small ¹⁸F-FDG-avid pulmonary nodules in PET scans, and to assess whether novel block sequential regularized expectation maximization (BSREM) reconstruction affects detection accuracy as compared to ordered subset expectation maximization (OSEM) reconstruction.

METHODS : Fifty-seven patients with 92 ¹⁸F-FDG-avid pulmonary nodules (all ≤ 2 cm) undergoing PET/CT for oncological (re-)staging were retrospectively included and a total of 8824 PET images of the lungs were extracted using OSEM and BSREM reconstruction. Per-slice and per-nodule sensitivity of a deep learning algorithm was assessed, with an expert readout by a radiologist/nuclear medicine physician serving as standard of reference. Receiver-operator characteristic (ROC) curve of OSEM and BSREM were assessed and the areas under the ROC curve (AUC) were compared. A maximum standardized uptake value (SUV_max)-based sensitivity analysis and a size-based sensitivity analysis with subgroups defined by nodule size was performed.

RESULTS : The AUC of the deep learning algorithm for nodule detection using OSEM reconstruction was 0.796 (CI 95%; 0.772-0.869), and 0.848 (CI 95%; 0.828-0.869) using BSREM reconstruction. The AUC was significantly higher for BSREM compared to OSEM (p = 0.001). On a per-slice analysis, sensitivity and specificity were 66.7% and 79.0% for OSEM, and 69.2% and 84.5% for BSREM. On a per-nodule analysis, the overall sensitivity of OSEM was 81.5% compared to 87.0% for BSREM.

CONCLUSIONS : Our results suggest that machine learning algorithms may aid detection of small ¹⁸F-FDG-avid pulmonary nodules in clinical PET/CT. AI performed significantly better on images with BSREM than OSEM.

KEY POINTS : • The diagnostic value of deep learning for detecting small lung nodules (≤ 2 cm) in PET images using BSREM and OSEM reconstruction was assessed. • BSREM yields higher SUV _maxof small pulmonary nodules as compared to OSEM reconstruction. • The use of BSREM translates into a higher detectability of small pulmonary nodules in PET images as assessed with artificial intelligence.

Schwyzer Moritz, Martini Katharina, Benz Dominik C, Burger Irene A, Ferraro Daniela A, Kudura Ken, Treyer Valerie, von Schulthess Gustav K, Kaufmann Philipp A, Huellner Martin W, Messerli Michael

2019-Dec-10

Artificial intelligence, Deep learning, Diagnostic imaging, Neoplasm Metastasis, Positron-emission tomography

In Academic radiology ; h5-index 0.0

Mahajan Vidur, Venugopal Vasantha Kumar, Murugavel Murali, Mahajan Harsh

2020-Jan

Accuracy, Artificial Intelligence, Deployment, Testing, Validation

In Academic radiology ; h5-index 0.0

Borstelmann Stephen M

2020-Jan

AI, Artificial Intelligence, Data Science, Machine Learning, Radiology, Review, Statistics

In Academic radiology ; h5-index 0.0

Mazurowski Maciej A

2020-Jan

Algorithm development, Artificial intelligence, Ethics, Machine learning

In Academic radiology ; h5-index 0.0

Chan Stephen, Bailey Janet, Ros Pablo R

2020-Jan

academic radiology, academic-industry partnerships, artificial intelligence

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

BACKGROUND : The probability of heart failure during the perioperative period is 2% on average and it is as high as 17% when accompanied by cardiovascular diseases in China. It has been the most significant cause of postoperative death of patients. However, the patient is managed by the flow of information during the operation, but a lot of clinical information can make it difficult for medical staff to identify the information relevant to patient care. There are major practical and technical barriers to understand perioperative complications.

METHODS : In this work, we present three machine learning methods to estimate risks of heart failure, which extract intraoperative vital signs monitoring data into different modal representations (statistical learning representation, text learning representation, image learning representation). Firstly, we extracted features of vital signs monitoring data of surgical patients by statistical analysis. Secondly, the vital signs data is converted into text information by Piecewise Approximate Aggregation (PAA) and Symbolic Aggregate Approximation (SAX), then Latent Dirichlet Allocation (LDA) model is used to extract text topics of patients for heart failure prediction. Thirdly, the vital sign monitoring time series data of the surgical patient is converted into a grid image by using the grid representation, and then the convolutional neural network is directly used to identify the grid image for heart failure prediction. We evaluated the proposed methods in the monitoring data of real patients during the perioperative period.

RESULTS : In this paper, the results of our experiment demonstrate the Gradient Boosting Decision Tree (GBDT) classifier achieves the best results in the prediction of heart failure by statistical feature representation. The sensitivity, specificity and the area under the curve (AUC) of the best method can reach 83, 85 and 84% respectively.

CONCLUSIONS : The experimental results demonstrate that representation learning model of vital signs monitoring data of intraoperative patients can effectively capture the physiological characteristics of postoperative heart failure.

Chen Yuwen, Qi Baolian

2019-Dec-09

Heart failure, Machine learning, Perioperative period

In BMC evolutionary biology ; h5-index 0.0

BACKGROUND : Eukaryotes acquired the trait of oxygenic photosynthesis through endosymbiosis of the cyanobacterial progenitor of plastid organelles. Despite recent advances in the phylogenomics of Cyanobacteria, the phylogenetic root of plastids remains controversial. Although a single origin of plastids by endosymbiosis is broadly supported, recent phylogenomic studies are contradictory on whether plastids branch early or late within Cyanobacteria. One underlying cause may be poor fit of evolutionary models to complex phylogenomic data.

RESULTS : Using Posterior Predictive Analysis, we show that recently applied evolutionary models poorly fit three phylogenomic datasets curated from cyanobacteria and plastid genomes because of heterogeneities in both substitution processes across sites and of compositions across lineages. To circumvent these sources of bias, we developed CYANO-MLP, a machine learning algorithm that consistently and accurately phylogenetically classifies ("phyloclassifies") cyanobacterial genomes to their clade of origin based on bioinformatically predicted function-informative features in tRNA gene complements. Classification of cyanobacterial genomes with CYANO-MLP is accurate and robust to deletion of clades, unbalanced sampling, and compositional heterogeneity in input tRNA data. CYANO-MLP consistently classifies plastid genomes into a late-branching cyanobacterial sub-clade containing single-cell, starch-producing, nitrogen-fixing ecotypes, consistent with metabolic and gene transfer data.

CONCLUSIONS : Phylogenomic data of cyanobacteria and plastids exhibit both site-process heterogeneities and compositional heterogeneities across lineages. These aspects of the data require careful modeling to avoid bias in phylogenomic estimation. Furthermore, we show that amino acid recoding strategies may be insufficient to mitigate bias from compositional heterogeneities. However, the combination of our novel tRNA-specific strategy with machine learning in CYANO-MLP appears robust to these sources of bias with high accuracy in phyloclassification of cyanobacterial genomes. CYANO-MLP consistently classifies plastids as late-branching Cyanobacteria, consistent with independent evidence from signature-based approaches and some previous phylogenetic studies.

Lawrence Travis J, Amrine Katherine Ch, Swingley Wesley D, Ardell David H

2019-Dec-09

Cyanobacteria, Machine learning, Plastids, Primary endosymbiosis, tRNAs

In Lifestyle genomics ; h5-index 0.0

BACKGROUND : Body composition is increasingly being recognized as an important prognostic factor for health outcomes across cancer, liver cirrhosis, and critically ill patients. Computed tomography (CT) scans, when taken as part of routine care, provide an excellent opportunity to precisely measure the quantity and quality of skeletal muscle and adipose tissue. However, manual analysis of CT scans is costly and time-intensive, limiting the widespread adoption of CT-based measurements of body composition.

SUMMARY : Advances in deep learning have demonstrated excellent success in biomedical image analysis. Several recent publications have demonstrated excellent accuracy in comparison to human raters for the measurement of skeletal muscle, visceral adipose, and subcutaneous adipose tissue from the lumbar vertebrae region, indicating that analysis of body composition may be successfully automated using deep neural networks. Key Messages: The high accuracy and drastically improved speed of CT body composition analysis (<1 s/scan for neural networks vs. 15 min/scan for human analysis) suggest that neural networks may aid researchers and clinicians in better understanding the role of body composition in clinical populations by enabling cost-effective, large-scale research studies. As the role of body composition in clinical settings and the field of automated analysis advance, it will be critical to examine how clinicians interact with these systems and to evaluate whether these technologies are beneficial in improving treatment and health outcomes for patients.

Paris Michael T

2019-Dec-10

Automated body composition analysis, Computed tomography, Deep learning, Sarcopenia

In Neural networks : the official journal of the International Neural Network Society ; h5-index 0.0

O’Shea Alison, Lightbody Gordon, Boylan Geraldine, Temko Andriy

2019-Nov-30

Convolutional neural networks, EEG, Neonatal seizure detection, Weak labels

In NeuroImage ; h5-index 117.0

Brown Robert A, Fetco Dumitru, Fratila Robert, Fadda Giulia, Jiang Shangge, Alkhawajah Nuha M, Yeh E Ann, Banwell Brenda, Bar-Or Amit, Arnold Douglas L

2019-Dec-07

In Journal of dentistry ; h5-index 59.0

OBJECTIVES : In this pilot study, we applied deep convolutional neural networks (CNNs) to detect caries lesions in Near-Infrared-Light Transillumination (NILT) images.

METHODS : 226 extracted posterior permanent human teeth (113 premolars, 113 molars) were allocated to groups of 2 + 2 teeth, and mounted in a pilot-tested diagnostic model in a dummy head. NILT images of single-tooth-segments were generated using DIAGNOcam (KaVo, Biberach). For each segment (on average 435 × 407 × 3 pixels), occlusal and/or proximal caries lesions were annotated by two experienced dentists using an in-house developed digital annotation tool. The pixel-based annotations were translated into binary class levels. We trained two state-of-the-art CNNs (Resnet18, Resnext50) and validated them via 10-fold cross validation. During the training process, we applied data augmentation (random resizing, rotations and flipping) and one-cycle-learning rate policy, setting the minimum and maximum learning rates to 10^-5 and 10^-3, respectively. Metrics for model performance were the area-under-the-receiver-operating-characteristics-curve (AUC), sensitivity, specificity, and positive/negative predictive values (PPV/NPV). Feature visualization was additionally applied to assess if the CNNs built on features dentists would also use.

RESULTS : The tooth-level prevalence of caries lesions was 41%. The two models performed similar on predicting caries on tooth segments of NILT images. The marginal better model with respect to AUC was Resnext50, where we retrained the last 9 network layers, using the Adam optimizer, a learning rate of 0.5 × 10^-4, and a batch size of 10. The mean (95% CI) AUC was 0.74 (0.66-0.82). Sensitivity and specificity were 0.59 (0.47-0.70) and 0.76 (0.68-0.84) respectively. The resulting PPV was 0.63 (0.51-0.74), the NPV 0.73 (0.65-0.80). Visual inspection of model predictions found the model to be sensitive to areas affected by caries lesions.

CONCLUSIONS : A moderately deep CNN trained on a limited amount of NILT image data showed satisfying discriminatory ability to detect caries lesions.

CLINICAL SIGNIFICANCE : CNNs may be useful to assist NILT-based caries detection. This could be especially relevant in non-conventional dental settings, like schools, care homes or rural outpost centers.

Schwendicke Falk, Elhennawy Karim, Paris Sebastian, Friebertshäuser Philipp, Krois Joachim

2019-Dec-07

Artificial Intelligence, Caries, Diagnostics, Digital imaging/radiology, Mathematical modeling

In Human mutation ; h5-index 53.0

Kulandaisamy A, Zaucha Jan, Sakthivel Ramasamy, Frishman Dmitrij, Michael Gromiha M

2019-Dec-10

disease-causing, machine learning, missense variant, mutation, neutral, transmembrane proteins

In Medical physics ; h5-index 59.0

PURPOSE : We propose a novel domain specific loss, which is a differentiable loss function based on the dose volume histogram, and combine it with an adversarial loss for the training of deep neural networks. In this study, we trained a neural network for generating Pareto optimal dose distributions, and evaluate the effects of the domain specific loss on the model performance.

METHODS : In this study, 3 loss functions-mean squared error (MSE) loss, dose volume histogram (DVH) loss, and adversarial (ADV) loss-were used to train and compare 4 instances of the neural network model: 1) MSE, 2) MSE+ADV, 3) MSE+DVH, and 4) MSE+DVH+ADV. The data for 70 prostate patients, including the planning target volume (PTV), and the organs-at-risk (OAR) were acquired as 96 x 96 x 24 dimension arrays at 5 mm³ voxel size. The dose influence arrays were calculated for 70 prostate patients, using a 7 equidistant coplanar beam setup. Using a scalarized multicriteria optimization for intensity modulated radiation therapy, 1200 Pareto surface plans per patient were generated by pseudo-randomizing the PTV and OAR tradeoff weights. With 70 patients, the total number of plans generated was 84,000 plans. We divided the data into 54 training, 6 validation, and 10 testing patients. Each model was trained for a total of 100,000 iterations, with a batch size of 2. All models used the Adam optimizer, with a learning rate of 1×10^-3 .

RESULTS : Training for 100,000 iterations took 1.5 days (MSE), 3.5 days (MSE+ADV), 2.3 days (MSE+DVH), 3.8 days (MSE+DVH+ADV). After training, the prediction time of each model is 0.052 seconds. Quantitatively, the MSE+DVH+ADV model had the lowest prediction error of 0.038 (conformation), 0.026 (homogeneity), 0.298 (R50), 1.65% (D95), 2.14% (D98), 2.43% (D99). The MSE model had the worst prediction error of 0.134 (conformation), 0.041 (homogeneity), 0.520 (R50), 3.91% (D95), 4.33% (D98), 4.60% (D99). For both the mean dose PTV error and the max dose PTV, Body, Bladder and rectum error, the MSE+DVH+ADV outperformed all other models. Regardless of model, all predictions have an average mean and max dose error less than 2.8% and 4.2%, respectively.

CONCLUSION : The MSE+DVH+ADV model performed the best in these categories, illustrating the importance of both human and learned domain knowledge. Expert human domain specific knowledge can be the largest driver in the performance improvement, and adversarial learning can be used to further capture nuanced attributes in the data. The real-time prediction capabilities allow for a physician to quickly navigate the tradeoff space for a patient, and produce a dose distribution as a tangible endpoint for the dosimetrist to use for planning. This is expected to considerably reduce the treatment planning time, allowing for clinicians to focus their efforts on the difficult and demanding cases.

Nguyen Dan, McBeth Rafe, Sadeghnejad Barkousaraie Azar, Bohara Gyanendra, Shen Chenyang, Jia Xun, Jiang Steve

2019-Dec-10

In Microorganisms ; h5-index 0.0

Kus Pelin, Gurcan Metin N, Beamer Gillian

2019-Dec-07

algorithm, granuloma, machine learning, necrosis, tuberculosis

In European heart journal. Cardiovascular pharmacotherapy ; h5-index 0.0

BACKGROUND : Most clinical risk stratification models are based on measurement at a single time-point rather than serial measurements. Artificial intelligence (AI) is able to predict one-dimensional outcomes from multi-dimensional datasets. Using data from GARFIELD-AF registry, a new AI model was developed for predicting clinical outcomes in atrial fibrillation (AF) patients up to 1 year based on sequential measures of PT-INR within 30 days of enrolment.

METHODS AND RESULTS : Patients with newly diagnosed AF who were treated with vitamin K antagonists (VKA) and had at least 3 measurements of PT-INR taken over the first 30 days after prescription were analyzed. The AI model was constructed with multilayer neural network including long short-term memory (LSTM) and one-dimensional convolution layers. The neural network was trained using PT-INR measurements within days 0-30 after starting treatment and clinical outcomes over days 31-365 in a derivation cohort (cohorts 1-3; n = 3185). Accuracy of the AI model at predicting major bleed, stroke/SE, and death was assessed in a validation cohort (cohorts 4-5; n = 1523). The model's c-statistic for predicting major bleed, stroke/SE, and all-cause death was 0.75, 0.70, and 0.61, respectively.

CONCLUSIONS : Using serial PT-INR values collected within 1 month after starting VKA, the new AI model performed better than time in therapeutic range (TTR) at predicting clinical outcomes occurring up to 12 months thereafter. Serial PT-INR values contain important information that can be analyzed by computer to help predict adverse clinical outcomes.

Goto Shinichi, Goto Shinya, Pieper Karen S, Bassand Jean-Pierre, Camm A John, Fitzmaurice David A, Goldhaber Samuel Z, Haas Sylvia, Parkhomenko Alexander, Oto Ali, Misselwitz Frank, Turpie Alexander G G, Verheugt Freek W A, Fox Keith A A, Gersh Bernard J, Kakkar Ajay K

2019-Dec-10

artificial intelligence (AI), atrial fibrillation (AF), machine learning

In Bioinformatics (Oxford, England) ; h5-index 0.0

MOTIVATION : Over the past years, significant resources have been invested into formalizing biomedical ontologies. Formal axioms in ontologies have been developed and used to detect and ensure ontology consistency, find unsatisfiable classes, improve interoperability, guide ontology extension through the application of axiom-based design patterns, and encode domain background knowledge. The domain knowledge in biomedical ontologies may also have the potential to provide background knowledge for machine learning and predictive modelling.

RESULTS : We use ontology-based machine learning methods to evaluate the contribution of formal axioms and ontology meta-data to the prediction of protein-protein interactions and gene-disease associations. We find that the background knowledge provided by the Gene Ontology and other ontologies significantly improves the performance of ontology-based prediction models through provision of domain-specific background knowledge. Furthermore, we find that the labels, synonyms and definitions in ontologies can also provide background knowledge that may be exploited for prediction. The axioms and meta-data of different ontologies contribute to improving data analysis in a context-specific manner. Our results have implications on the further development of formal knowledge bases and ontologies in the life sciences, in particular as machine learning methods are more frequently being applied. Our findings motivate the need for further development, and the systematic, application-driven evaluation and improvement, of formal axioms in ontologies.

AVAILABILITY : https://github.com/bio-ontology-research-group/tsoe.

Smaili Fatima Zohra, Gao Xin, Hoehndorf Robert

2019-Dec-10

In Magyar onkologia ; h5-index 0.0

Vályi-Nagy István, Peták István

2019-Dec-09

In PloS one ; h5-index 176.0

Garcia-Marti Irene, Zurita-Milla Raul, Swart Arno

2019

In JMIR mental health ; h5-index 0.0

BACKGROUND : New technologies are set to profoundly change the way we understand and manage psychiatric disorders, including obsessive-compulsive disorder (OCD). Developments in imaging and biomarkers, along with medical informatics, may well allow for better assessments and interventions in the future. Recent advances in the concept of digital phenotype, which involves using computerized measurement tools to capture the characteristics of a given psychiatric disorder, is one paradigmatic example.

OBJECTIVE : The impact of new technologies on health professionals' practice in OCD care remains to be determined. Recent developments could disrupt not just their clinical practices, but also their beliefs, ethics, and representations, even going so far as to question their professional culture. This study aimed to conduct an extensive review of new technologies in OCD.

METHODS : We conducted the review by looking for titles in the PubMed database up to December 2017 that contained the following terms: [Obsessive] AND [Smartphone] OR [phone] OR [Internet] OR [Device] OR [Wearable] OR [Mobile] OR [Machine learning] OR [Artificial] OR [Biofeedback] OR [Neurofeedback] OR [Momentary] OR [Computerized] OR [Heart rate variability] OR [actigraphy] OR [actimetry] OR [digital] OR [virtual reality] OR [Tele] OR [video].

RESULTS : We analyzed 364 articles, of which 62 were included. Our review was divided into 3 parts: prediction, assessment (including diagnosis, screening, and monitoring), and intervention.

CONCLUSIONS : The review showed that the place of connected objects, machine learning, and remote monitoring has yet to be defined in OCD. Smartphone assessment apps and the Web Screening Questionnaire demonstrated good sensitivity and adequate specificity for detecting OCD symptoms when compared with a full-length structured clinical interview. The ecological momentary assessment procedure may also represent a worthy addition to the current suite of assessment tools. In the field of intervention, CBT supported by smartphone, internet, or computer may not be more effective than that delivered by a qualified practitioner, but it is easy to use, well accepted by patients, reproducible, and cost-effective. Finally, new technologies are enabling the development of new therapies, including biofeedback and virtual reality, which focus on the learning of coping skills. For them to be used, these tools must be properly explained and tailored to individual physician and patient profiles.

Ferreri Florian, Bourla Alexis, Peretti Charles-Siegfried, Segawa Tomoyuki, Jaafari Nemat, Mouchabac Stéphane

2019-Dec-10

biofeedback, digital biomarkers, digital phenotyping, ecological momentary assessment, machine learning, mobile health, obsessive-compulsive disorder, virtual reality

In The British journal of radiology ; h5-index 0.0

Hardy Maryann, Harvey Hugh

2019-Dec-10

In ACS applied materials & interfaces ; h5-index 147.0

Zhang Xiangyu, Zhang Kexin, Lee Yongjin

2019-Dec-10

In Health informatics journal ; h5-index 25.0

Wong Zoie Shui-Yee, So H Y, Kwok Belinda Sc, Lai Mavis Ws, Sun David Tf

2019-Dec-10

artificial intelligence, hospital incident reporting, medication errors, patient safety, text mining

In Environmental toxicology and chemistry ; h5-index 0.0

Krämer Stefan, Busch Wibke, Schüttler Andreas

2019-Dec-09

consistency, estrogens, gene expression, self-organizing map, toxicogenomics

In Japanese journal of radiology ; h5-index 0.0

BACKGROUND AND PURPOSE : The purpose of this study was to compare the diagnostic performance between apparent diffusion coefficient (ADC) analysis of one-point measurement and whole-tumor measurement, including radiomics for differentiating pleomorphic adenoma (PA) from carcinoma ex pleomorphic adenoma (CXPA), and to evaluate the impact of inter-operator segmentation variability.

MATERIALS AND METHODS : One hundred and fifteen patients with PA and 22 with CXPA were included. Four radiologists with different experience independently placed one-point and whole-tumor ROIs and a radiomics-predictive model was constructed from the extracted imaging features. We calculated the area under the receiver-operator characteristic curve (AUC) for the diagnostic performance of imaging features and the radiomics-predictive model.

RESULTS : AUCs of the imaging features from whole-tumor varied between readers (0.50-0.89). The most experienced radiologist (Reader 1) produced significantly high AUCs than less experienced radiologists (Reader 3 and 4; P = 0.01 and 0.009). AUCs were higher for the radiomics-predictive model (0.82-0.87) than for one-point (0.66-0.79) in all readers.

CONCLUSION : Some imaging features of whole-tumor and radiomics-predictive model had higher diagnostic performance than one-point. The diagnostic performance of imaging features from whole-tumor alone varied depending on operator experience. Operator experience appears less likely to affect diagnostic performance in the radiomics-predictive model.

Wada Takeshi, Yokota Hajime, Horikoshi Takuro, Starkey Jay, Hattori Shinya, Hashiba Jun, Uno Takashi

2019-Dec-09

Carcinoma ex pleomorphic adenoma, Diagnostic performance, Machine learning, Pleomorphic adenoma, Radiomics

In Journal of clinical medicine ; h5-index 0.0

Cao Yang, Raoof Mustafa, Montgomery Scott, Ottosson Johan, Näslund Ingmar

2019-Dec-05

bariatric surgery, conventional neural network, deep learning, health-related quality of life, prediction

In Journal of medical systems ; h5-index 48.0

Garcia-Carretero Rafael, Vigil-Medina Luis, Barquero-Perez Oscar, Ramos-Lopez Javier

2019-Dec-09

Cardiovascular risk, LASSO regression, Machine learning, Pulse wave velocity

In Neuroradiology ; h5-index 0.0

PURPOSE : To evaluate whether diffusion tensor imaging (DTI) radiomics with machine learning improves the prediction of isocitrate dehydrogenase (IDH) mutation status of lower-grade gliomas beyond radiomic features from conventional MRI and DTI histogram parameters.

METHODS : A total of 168 patients with pathologically confirmed lower-grade gliomas were retrospectively enrolled. A total of 158 and 253 radiomic features were extracted from DTI (DTI radiomics) and conventional MRI (T1-weighted image with contrast enhancement, T2-weighted image, and FLAIR [conventional radiomics]), respectively. The random forest models for predicting IDH status were trained with variable combinations as follows: (1) DTI radiomics, (2) conventional radiomics, (3) conventional radiomics + DTI radiomics, and (4) conventional radiomics + DTI histogram. The models were validated with nested cross-validation. The predictive performances of those models were compared by using area under the curve (AUC) from receiver operating characteristic analysis, and 95% confidence interval (CI) was calculated.

RESULTS : Adding DTI radiomics to conventional radiomics significantly improved the accuracy of IDH status subtyping (AUC, 0.900 [95% CI, 0.855-0.945], p = 0.006), whereas adding DTI histogram parameters yielded nonsignificant trend toward improvement (0.869 [95% CI, 0.816-0.922], p = 0.150) compared with the model with conventional radiomics alone (0.835 [95% CI, 0.773-0.896]). The performance of the model consisting of both DTI and conventional radiomics was significantly superior than that of model consisting of both DTI histogram parameters and conventional radiomics (0.900 vs 0.869, p = 0.040).

CONCLUSION : DTI radiomics with machine learning can help improve the subtyping of IDH status beyond conventional radiomics and DTI histogram parameters in patients with lower-grade gliomas.

Park Chae Jung, Choi Yoon Seong, Park Yae Won, Ahn Sung Soo, Kang Seok-Gu, Chang Jong-Hee, Kim Se Hoon, Lee Seung-Koo

2019-Dec-09

Diffusion tensor imaging, Isocitrate dehydrogenase, Lower-grade glioma, Machine learning, Radiomics

In Der Radiologe ; h5-index 0.0

CLINICAL ISSUE : The reproducible and exhaustive extraction of information from radiological images is a central task in the practice of radiology. Dynamic developments in the fields of artificial intelligence (AI) and machine learning are introducing new methods for this task. Radiomics is one such method and offers new opportunities and challenges for the future of radiology.

METHODOLOGICAL INNOVATIONS : Radiomics describes the quantitative evaluation, interpretation, and clinical assessment of imaging markers in radiological data. Components of a radiomics analysis are data acquisition, data preprocessing, data management, segmentation of regions of interest, computation and selection of imaging markers, as well as the development of a radiomics model used for diagnosis and prognosis. This article explains these components and aims at providing an introduction to the field of radiomics while highlighting existing limitations.

MATERIALS AND METHODS : This article is based on a selective literature search with the PubMed search engine.

ASSESSMENT : Even though radiomics applications have yet to arrive in routine clinical practice, the quantification of radiological data in terms of radiomics is underway and will increase in the future. This holds the potential for lasting change in the discipline of radiology. Through the successful extraction and interpretation of all the information encoded in radiological images the next step in the direction of a more personalized, future-oriented form of medicine can be taken.

Murray Jacob M, Kaissis Georgios, Braren Rickmer, Kleesiek Jens

2019-Dec-09

Artificial intelligence, Artificial neural networks, Machine learning, Personalized medicine, Radiogenomics

In Translational vision science & technology ; h5-index 0.0

Purpose : This study describes the initial development of a deep learning algorithm, ROP.AI, to automatically diagnose retinopathy of prematurity (ROP) plus disease in fundal images.

Methods : ROP.AI was trained using 6974 fundal images from Australasian image databases. Each image was given a diagnosis as part of real-world routine ROP screening and classified as normal or plus disease. The algorithm was trained using 80% of the images and validated against the remaining 20% within a hold-out test set. Performance in diagnosing plus disease was evaluated against an external set of 90 images. Performance in detecting pre-plus disease was also tested. As a screening tool, the algorithm's operating point was optimized for sensitivity and negative predictive value, and its performance reevaluated.

Results : For plus disease diagnosis within the 20% hold-out test set, the algorithm achieved a 96.6% sensitivity, 98.0% specificity, and 97.3% ± 0.7% accuracy. Area under the receiver operating characteristic curve was 0.993. Within the independent test set, the algorithm achieved a 93.9% sensitivity, 80.7% specificity, and 95.8% negative predictive value. For detection of pre-plus and plus disease, the algorithm achieved 81.4% sensitivity, 80.7% specificity, and 80.7% negative predictive value. Following the identification of an optimized operating point, the algorithm diagnosed plus disease with a 97.0% sensitivity and 97.8% negative predictive value.

Conclusions : ROP.AI is a deep learning algorithm able to automatically diagnose ROP plus disease with high sensitivity and negative predictive value.

Translational Relevance : In the context of increasing global disease burden, future development may improve access to ROP diagnosis and care.

Tan Zachary, Simkin Samantha, Lai Connie, Dai Shuan

2019-Nov

artificial intelligence, deep learning, retinopathy of prematurity

In Cancer informatics ; h5-index 0.0

Schomberg John

2019

Chemical informatics, machine learning, oral cancer, pathway analysis, random forest, traditional chinese medicine, virtual screening

In Nature methods ; h5-index 152.0

Gainza P, Sverrisson F, Monti F, Rodolà E, Boscaini D, Bronstein M M, Correia B E

2019-Dec-09

In Nature biotechnology ; h5-index 151.0

Ochoa David, Jarnuczak Andrew F, Viéitez Cristina, Gehre Maja, Soucheray Margaret, Mateus André, Kleefeldt Askar A, Hill Anthony, Garcia-Alonso Luz, Stein Frank, Krogan Nevan J, Savitski Mikhail M, Swaney Danielle L, Vizcaíno Juan A, Noh Kyung-Min, Beltrao Pedro

2019-Dec-09

In Scientific reports ; h5-index 158.0

Manicka Santosh, Levin Michael

2019-Dec-09

In Translational psychiatry ; h5-index 60.0

Zhuo Chuanjun, Li Gongying, Lin Xiaodong, Jiang Deguo, Xu Yong, Tian Hongjun, Wang Wenqiang, Song Xueqin

2019-Dec-09

In Journal of neurointerventional surgery ; h5-index 49.0

BACKGROUND AND PURPOSE : The Alberta Stroke Program Early CT Score (ASPECTS) is a widely used measure of ischemic change on non-contrast CT. Although predictive of long-term outcome, ASPECTS is limited by its modest interobserver agreement. One potential solution to this is the use of machine learning strategies, such as e-ASPECTS, to detect ischemia. Here, we compared e-ASPECTS with manual scoring by experienced neuroradiologists for all 10 individual ASPECTS regions.

MATERIALS AND METHODS : We retrospectively reviewed 178 baseline non-contrast CT scans from patients with acute ischemic stroke undergoing endovascular thrombectomy. All scans were reviewed by two independent neuroradiologists with a third reader arbitrating disagreements for a consensus read. Each ASPECTS region was scored individually. All scans were then evaluated using a machine learning-based software package (e-ASPECTS, Brainomix). Interobserver agreement between readers and the software for each region was calculated with a kappa statistic.

RESULTS : The median ASPECTS was 9 for manual scoring and 8.5 for e-ASPECTS, with an overall agreement of κ=0.248. Regional agreement varied from κ=0.094 (M1) to κ=0.555 (lentiform), with better performance in subcortical regions. When corrected for the low number of infarcts in any given region, prevalence-adjusted bias-adjusted kappa ranged from 0.483 (insula) to 0.888 (M3), with greater agreement for cortical areas. Intraclass correlation coefficients were between 0.09 (M1) and 0.556 (lentiform).

CONCLUSION : Manual scoring and e-ASPECTS had fair agreement in our dataset on a per-region basis. This warrants further investigation using follow-up scans or MRI as the gold standard measure of true ASPECTS.

Neuhaus Ain, Seyedsaadat Seyed Mohammad, Mihal David, Benson John, Mark Ian, Kallmes David F, Brinjikji Waleed

2019-Dec-09

CT, stroke, thrombectomy

In International journal of molecular sciences ; h5-index 102.0

Ding Haitao, Luo Wei, Yu Yong, Chen Bo

2019-Dec-03

artificial neural network, cofactor regeneration, dye decolorization, glucose 1-dehydrogenase, modeling, multiple linear regression, random forest, triphenylmethane reductase

In BMJ open ; h5-index 0.0

INTRODUCTION : Diabetic retinopathy (DR) is a common microvascular complication of diabetes mellitus and the leading cause of impaired vision in adults worldwide. Early detection and treatment for DR could improve patient outcomes. Traditional methods of detecting DR include the gold standard Early Treatment Diabetic Retinopathy Study seven standard fields fundus photography, ophthalmoscopy and slit-lamp biomicroscopy. These modalities can be expensive, difficult to access and require involvement of specialised healthcare professionals. With the development of mobile phone technology, there is a growing interest in their use for DR identification as this approach is potentially more affordable, accessible and easier to use. Smartphones can be employed in a variety of ways for ophthalmoscopy including the use of smartphone camera, various attachments and artificial intelligence for obtaining and grading of retinal images. The aim of this scoping review is to determine the diagnostic test accuracy of various smartphone ophthalmoscopy approaches for detecting DR in diabetic patients.

METHODS AND ANALYSIS : We will perform an electronic search of MEDLINE, Embase and Cochrane Library for literature published from 2000 onwards. Two reviewers will independently analyse studies for eligibility and assess study quality using the QUADAS-2 tool. Data for a 2⨉2 contingency table will be extracted. If possible, we will pool sensitivity and specificity data using the random-effects model and construct a summary receiver operating characteristic curve. In case of high heterogeneity, we will present the findings narratively. Subgroup analysis and sensitivity analysis will be performed where appropriate.

ETHICS AND DISSEMINATION : This scoping review aims to provide an overview of smartphone ophthalmoscopy in DR identification. It will present findings on the accuracy of smartphone ophthalmoscopy in detecting DR, identify gaps in the literature and provide recommendations for future research. This review does not require ethical approval as we will not collect primary data.

Tan Choon Han, Quah Willie-Henri, Tan Colin S H, Smith Helen, Tudor Car Lorainne

2019-Dec-08

diabetic retinopathy, ophthalmology, telemedicine

In Academic radiology ; h5-index 0.0

RATIONALE AND OBJECTIVES : To evaluate the noninvasive predictive performance of deep learning features based on staging CT for sentinel lymph node (SLN) metastasis of breast cancer.

MATERIALS AND METHODS : A total of 348 breast cancer patients were enrolled in this study, with their SLN metastases pathologically confirmed. All patients received contrast-enhanced CT preoperative examinations and CT images were segmented and analyzed to extract deep features. After the feature selection, deep learning signature was built with the selected key features. The performance of the deep learning signatures was assessed with respect to discrimination, calibration, and clinical usefulness in the primary cohort (184 patients from January 2016 to March 2017) and then validated in the independent validation cohort (164 patients from April 2017 to December 2018).

RESULTS : Ten deep learning features were automatically selected in the primary cohort to establish the deep learning signature of SLN metastasis. The deep learning signature shows favorable discriminative ability with an area under curve of 0.801 (95% confidence interval: 0.736-0.867) in primary cohort and 0.817 (95% confidence interval: 0.751-0.884) in validation cohort. To further distinguish the number of metastatic SLNs (1-2 or more than two metastatic SLN), another deep learning signature was constructed and also showed moderate performance (area under curve 0.770).

CONCLUSION : We developed the deep learning signatures for preoperative prediction of SLN metastasis status and numbers (1-2 or more than two metastatic SLN) in patients with breast cancer. The deep learning signature may potentially provide a noninvasive approach to assist clinicians in predicting SLN metastasis in patients with breast cancer.

Yang Xiaojun, Wu Lei, Ye Weitao, Zhao Ke, Wang Yingyi, Liu Weixiao, Li Jiao, Li Hanxiao, Liu Zaiyi, Liang Changhong

2019-Dec-06

Breast cancer, Computed tomography, Deep learning, Sentinel lymph node metastasis

In The Science of the total environment ; h5-index 0.0

Hosseini Farzaneh Sajedi, Choubin Bahram, Mosavi Amir, Nabipour Narjes, Shamshirband Shahaboddin, Darabi Hamid, Haghighi Ali Torabi

2019-Nov-21

Bayesian, Ensemble machine learning, Flash-flood, Hazard, Simulated annealing

In Academic radiology ; h5-index 0.0

RATIONALE AND OBJECTIVES : Our primary aim was to improve radiology reports by increasing concordance of target lesion measurements with oncology records using radiology preprocessors (RP). Faster notification of incidental actionable findings to referring clinicians and clinical radiologist exam interpretation time savings with RPs quantifying tumor burden were also assessed.

MATERIALS AND METHODS : In this prospective quality improvement initiative, RPs annotated lesions before radiologist interpretation of CT exams. Clinical radiologists then hyperlinked approved measurements into interactive reports during interpretations. RPs evaluated concordance with our tumor measurement radiologist, the determinant of tumor burden. Actionable finding detection and notification times were also deduced. Clinical radiologist interpretation times were calculated from established average CT chest, abdomen, and pelvis interpretation times.

RESULTS : RPs assessed 1287 body CT exams with 812 follow-up CT chest, abdomen, and pelvis studies; 95 (11.7%) of which had 241 verified target lesions. There was improved concordance (67.8% vs. 22.5%) of target lesion measurements. RPs detected 93.1% incidental actionable findings with faster clinician notification by a median time of 1 hour (range: 15 minutes-16 hours). Radiologist exam interpretation times decreased by 37%.

CONCLUSIONS : This workflow resulted in three-fold improved target lesion measurement concordance with oncology records, earlier detection and faster notification of incidental actionable findings to referring clinicians, and decreased exam interpretation times for clinical radiologists. These findings demonstrate potential roles for automation (such as AI) to improve report value, worklist prioritization, and patient care.

Do Huy M, Spear Lillian G, Nikpanah Moozhan, Mirmomen S Mojdeh, Machado Laura B, Toscano Alexandra P, Turkbey Baris, Bagheri Mohammad Hadi, Gulley James L, Folio Les R

2020-Jan

Actionable findings, Artificial intelligence, Cancer clinical trials, Radiology preprocessors, Tumor quantification

In Academic radiology ; h5-index 0.0

OBJECTIVES : Noise, commonly encountered on computed tomography (CT) images, can impact diagnostic accuracy. To reduce the image noise, we developed a deep-learning reconstruction (DLR) method that integrates deep convolutional neural networks into image reconstruction. In this phantom study, we compared the image noise characteristics, spatial resolution, and task-based detectability on DLR images and images reconstructed with other state-of-the art techniques.

METHODS : We scanned a phantom harboring cylindrical modules with different contrast on a 320-row detector CT scanner. Phantom images were reconstructed with filtered back projection, hybrid iterative reconstruction, model-based iterative reconstruction, and DLR. The standard deviation of the CT number and the noise power spectrum were calculated for noise characterization. The 10% modulation-transfer function (MTF) level was used to evaluate spatial resolution; task-based detectability was assessed using the model observer method.

RESULTS : On images reconstructed with DLR, the noise was lower than on images subjected to other reconstructions, especially at low radiation dose settings. Noise power spectrum measurements also showed that the noise amplitude was lower, especially for low-frequency components, on DLR images. Based on the MTF, spatial resolution was higher on model-based iterative reconstruction image than DLR image, however, for lower-contrast objects, the MTF on DLR images was comparable to images reconstructed with other methods. The machine observer study showed that at reduced radiation-dose settings, DLR yielded the best detectability.

CONCLUSION : On DLR images, the image noise was lower, and high-contrast spatial resolution and task-based detectability were better than on images reconstructed with other state-of-the art techniques. DLR also outperformed other methods with respect to task-based detectability.

Higaki Toru, Nakamura Yuko, Zhou Jian, Yu Zhou, Nemoto Takuya, Tatsugami Fuminari, Awai Kazuo

2020-Jan

Phantoms, X-ray computed tomography, artificial intelligence, imaging, machine learning, neural networks

In Academic radiology ; h5-index 0.0

Harvey H Benjamin, Gowda Vrushab

2020-Jan

Artificial intelligence, FDA, Medical Device, Policy, Radiology, Regulation

In Academic radiology ; h5-index 0.0

Abdullah Selwan, Rothenberg Steven, Siegel Eliot, Kim Woojin

2020-Jan

Bitcoin, Blockchain, Ethereum, Machine learning, Radiology

In Academic radiology ; h5-index 0.0

Grimm Lars J, Mazurowski Maciej A

2020-Jan

MRI, breast cancer, deep learning, radiogenomics

In Academic radiology ; h5-index 0.0

Waite Stephen, Farooq Zerwa, Grigorian Arkadij, Sistrom Christopher, Kolla Srinivas, Mancuso Anthony, Martinez-Conde Susana, Alexander Robert G, Kantor Alan, Macknik Stephen L

2020-Jan

Artificial intelligence, Attention, Expertise, Gist, Holistic processing, Perceptual learning, Radiology, Visual perception, Visual search

In Academic radiology ; h5-index 0.0

RATIONALE AND OBJECTIVES : Artificial intelligence (AI) is playing a growing role in the field of radiology. This article seeks to help readers quantify its impact when put into practice, using a lung nodule flagger as an example.

MATERIALS AND METHODS : The one-time and ongoing costs associated with AI are explored. Costs are divided into three categories: direct costs, costs associated with operational changes, and downstream costs. Examples of each are provided.

RESULTS : A framework for estimating the financial impact of AI is provided.

CONCLUSION : The impact of AI is quantifiable, but estimates of its financial impact may not be portable across contexts. Different organizations may implement AI in different ways due to differences in clinical practices. Furthermore, different organizations have different hurdle rates for their investments. Finally, international cost-effectiveness analyses may not be generalizable due to differences in both practice patterns and the valuation placed upon quality. When quantifying the impact of AI, organizations should consider relying upon pilots and data from other similarly-situated organizations.

Powell Adam C

2020-Jan

AI, Artificial intelligence, Cost, Financial impact, Radiology, Time-value of money

In Preventive veterinary medicine ; h5-index 37.0

Romero M Pilar, Chang Yu-Mei, Brunton Lucy A, Parry Jessica, Prosser Alison, Upton Paul, Rees Eleanor, Tearne Oliver, Arnold Mark, Stevens Kim, Drewe Julian A

2019-Nov-30

Bovine tuberculosis, Classification tree, England, Logistic regression, Machine learning, Risk factors

In Journal of electrocardiology ; h5-index 0.0

BACKGROUND : The electrocardiogram (ECG) has been widely used in the diagnosis of heart disease such as arrhythmia due to its simplicity and non-invasive nature. Arrhythmia can be classified into many types, including life-threatening and non-life-threatening. Accurate detection of arrhythmic types can effectively prevent heart disease and reduce mortality.

METHODS : In this study, a novel deep learning method for classification of cardiac arrhythmia according to deep residual network (ResNet) is presented. We developed a 31-layer one-dimensional (1D) residual convolutional neural network. The algorithm includes four residual blocks, each of which consists of three 1D convolution layers, three batch normalization (BP) layers, three rectified linear unit (ReLU) layers, and an "identity shortcut connections" structure. In addition, we propose to use 2-lead ECG signals in combination with deep learning methods to automatically identify five different types of heartbeats.

RESULTS : We have obtained an average accuracy, sensitivity and positive predictivity of 99.06%, 93.21% and 96.76% respectively for single-lead ECG heartbeats. In the 2-lead datasets, the results show that the deep ResNet model has high classification performance, achieving an accuracy of 99.38%, sensitivity of 94.54%, and specificity of 98.14%.

CONCLUSION : The proposed method can be used as an adjunct tool to assist clinicians in their diagnosis.

Li Zhi, Zhou Dengshi, Wan Li, Li Jian, Mou Wenfeng

2019-Nov-22

2-Lead, Arrhythmia, Deep learning, ECG signals, Heartbeat classification, Residual convolutional neural network

In Mechanisms of ageing and development ; h5-index 0.0

Aman Yahyah, Frank Johannes, Lautrup Sofie Hindkjær, Matysek Adrian, Niu Zhangming, Yang Guang, Shi Liu, Bergersen Linda H, Storm-Mathisen Jon, Rasmussen Lene J, Bohr Vilhelm A, Nilsen Hilde, Fang Evandro F

2019-Dec-05

Alzheimer’s disease, NAD(+), age-related diseases, ageing, artificial intelligence, mitophagy

In The Science of the total environment ; h5-index 0.0

Guo Chuanbo, Chen Yushun, Xia Wentong, Qu Xiao, Yuan Hui, Xie Songguang, Lin Lian-Shin

2019-Nov-18

Eutrophication, Heavy metals, Multivariate analysis, Self-organizing Map, South-to-North Water Diversion Project, Water quality safety

In The Science of the total environment ; h5-index 0.0

Zhou Yanlai, Chang Li-Chiu, Chang Fi-John

2019-Oct-31

Air quality, Artificial intelligence, Bayesian Uncertainty Processor, Probabilistic forecast, Taipei City

arxiv preprint

Sai P. Selvaraj, Sandeep Konam

2019-12-10

In The Science of the total environment ; h5-index 0.0

Dong Xianghong, Ju Tao, Grenouillet Gaël, Laffaille Pascal, Lek Sovan, Liu Jiashou

2019-Nov-02

Aquatic invasive species, Ensemble predicting, Habitat-suitability, Invasion risk, Management strategies, Species distribution models

arxiv preprint

Victoria Lin, Jeffrey M. Girard, Louis-Philippe Morency

2019-12-10

In Chemosphere ; h5-index 0.0

Qi Chongchong, Ly Hai-Bang, Chen Qiusong, Le Tien-Thinh, Le Vuong Minh, Pham Binh Thai

2019-Nov-25

Flocculation and dewatering, Mineral processing tailings, Monte Carlo simulations, PSO and ANFIS, Polymer, Principal component analysis

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) ; h5-index 0.0

PURPOSE : To demonstrate the strength of an innovative knowledge-based model-building method for radiotherapy planning using hypofractionated, multi-target prostate patients.

MATERIAL AND METHODS : An initial RapidPlan model was trained using 48 patients who received 60 Gy to prostate (PTV60) and 44 Gy to pelvic nodes (PTV44) in 20 fractions. To improve the model's goodness-of-fit, an intermediate model was generated using the dose-volume histograms of best-spared organs-at-risk (OARs) of the initial model. Using the intermediate model and manual tweaking, all 48 cases were re-planned. The final model, trained using these re-plans, was validated on 50 additional patients. The validated final model was used to determine any planning advantage of using three arcs instead of two on 16 VMAT cases and tested on 25 additional cases to determine efficacy for single-PTV (PTV60-only) treatment planning.

RESULTS : For model validation, PTV V_95% of 99.9% was obtained by both clinical and knowledge-based planning. D_1% was lower for model plans: by 1.23 Gy (PTV60, CI = [1.00, 1.45]), and by 2.44 Gy (PTV44, CI = [1.72, 3.16]). OAR sparing was superior for knowledge-based planning: ΔD_mean = 3.70 Gy (bladder, CI = [2.83, 4.57]), and 3.22 Gy (rectum, CI = [2.48, 3.95]); ΔD_2% = 1.17 Gy (bowel bag, CI = [0.64, 1.69]), and 4.78 Gy (femoral heads, CI = [3.90, 5.66]). Using three arcs instead of two, improvements in OAR sparing and PTV coverage were statistically significant, but of magnitudes < 1 Gy. The model failed at reliable DVH predictions for single PTV plans.

CONCLUSIONS : Our knowledge-based model delivers efficient, consistent plans with excellent PTV coverage and improved OAR sparing compared to clinical plans.

Chatterjee Avishek, Serban Monica, Faria Sergio, Souhami Luis, Cury Fabio, Seuntjens Jan

2019-Dec-06

Automatic planning, Knowledge-based, Machine learning, Prostate radiotherapy

In Progress in biophysics and molecular biology ; h5-index 0.0

Sohail Ayesha, Arif Fatima

2019-Dec-06

Algorithms, Evolutionary bioinformatics, Machine learning, Support vector machine learning

In Journal of clinical hypertension (Greenwich, Conn.) ; h5-index 0.0

Kanegae Hiroshi, Suzuki Kenji, Fukatani Kyohei, Ito Tetsuya, Harada Nakahiro, Kario Kazuomi

2019-Dec-09

artificial intelligence, hypertension, machine learning, prediction model

In Medical physics ; h5-index 59.0

PURPOSE : Dual-energy computed tomography (DECT) has shown great potential in many clinical applications. By incorporating the information from two different energy spectra, DECT provides higher contrast and reveals more material differences of tissues compared to conventional single energy CT (SECT). Recent researches show that automatic multi-organ segmentation of DECT data can improve DECT clinical applications. However, most segmentation methods are designed for SECT, while DECT has been significantly less in research. Therefore, a novel approach is required that is able to take full advantage of the extra information provided by DECT.

METHODS : In the scope of this work, we proposed four 3D fully convolutional neural network algorithms for the automatic segmentation of DECT data. We incorporated the extra energy information differently and embedded the merge of information in each of the network architectures.

RESULTS : Quantitative evaluation using 45 thorax/abdomen DECT datasets acquired with aclinical dual-source CT system was investigated. The segmentation of six thoracic and abdominal organs (left and right lungs, liver, spleen, and left and right kidneys) were evaluated using a 5-fold cross-validation strategy. In all of the tests, we achieved the best average Dice coefficients of 98 %for the right lung, 98 % for the left lung, 96 % for the liver, 92 % for the spleen, 95 % for the right kidney, 93 % for the left kidney, respectively. The network architectures exploiting dual energy spectra outperform deep learning for SECT.

CONCLUSION : The results of the cross-validation show that our methods are feasible and promising. Successful tests on special clinical cases reveal that our methods have high adaptability in the practical application.

Chen Shuqing, Zhong Xia, Hu Shiyang, Dorn Sabrina, Kachelrieß Marc, Lell Michael, Maier Andreas

2019-Dec-09

DECT, FCN, Multi-organ, U-Net, deep learning

In Advances in neonatal care : official journal of the National Association of Neonatal Nurses ; h5-index 0.0

BACKGROUND : Peripheral intravenous catheters connected to an infusion pump are necessary for the delivery of fluids, nutrition, and medications to hospitalized neonates but are not without complications. These adverse events contribute to hospital-acquired patient harm. An artificial intelligence theory called fuzzy logic may allow the use of appropriate variables to predict infusion failure.

PURPOSE : This innovative study aimed to develop an intravenous infusion nanotechnology monitoring system that would alert the nurse to impending peripheral intravenous infusion failure.

METHODS : An intravenous infusion nanotechnology monitoring system, using predictor variables of pressure, pH, and oxygen saturation used in a fuzzy logic alarm algorithm was developed to alert the nurse to impending peripheral intravenous infusion failure.

FINDINGS : The developed intravenous infusion nanotechnology monitoring system is composed of a peripheral intravenous catheter with nanotechnology multimodal sensor, an intravenous pump, a fuzzy logic algorithm, and alarm. For example, using this system, an elevated in-line pressure, a low pH, and a low venous oxygen level would generate an alarm for possible impending infusion failure.

IMPLICATIONS FOR PRACTICE : With further development, this technology may help nurses predict and prevent adverse outcomes from intravenous infusions. This work shows how nurses can be content experts and innovators of technology that they use to make clinical decisions.

IMPLICATIONS FOR RESEARCH : After regulatory approval, a randomized controlled trial may be performed to investigate whether interventions at the time of an alarm would result in fewer adverse outcomes and improve safety.

Bosque Elena M

2019-Dec-06

In Journal of X-ray science and technology ; h5-index 0.0

BACKGROUND AND OBJECTIVE : Since CAD (Computer Aided Diagnosis) system can make it easier and more efficient to interpret CT (Computer Tomography) images, it has gained much attention and developed rapidly in recent years. This article reviews recent CAD techniques for pulmonary nodule detection and diagnosis in CT Images.

METHODS : CAD systems can be classified into computer-aided detection (CADe) and computer-aided diagnosis (CADx) systems. This review reports recent researches of both systems, including the database, technique, innovation and experimental results of each work. Multi-task CAD systems, which can handle segmentation, false positive reduction, malignancy prediction and other tasks at the same time. The commercial CAD systems are also briefly introduced.

RESULTS : We have found that deep learning based CAD is the mainstream of current research. The reported sensitivity of deep learning based CADe systems ranged between 80.06% and 94.1% with an average 4.3 false-positive (FP) per scan when using LIDC-IDRI dataset, and between 94.4% and 97.9% with an average 4 FP/scan when using LUNA16 dataset, respectively. The overall accuracy of deep learning based CADx systems ranged between 86.84% and 92.3% with an average AUC of 0.956 reported when using LIDC-IDRI dataset.

CONCLUSIONS : We summarized the current tendency and limitations as well as future challenges in this field. The development of CAD needs to meet the rigid clinical requirements, such as high accuracy, strong robustness, high efficiency, fine-grained analysis and classification, and to provide practical clinical functions. This review provides helpful information for both engineering researchers and radiologists to learn the latest development of CAD systems.

Wang Yu, Wu Bo, Zhang Nan, Liu Jiabao, Ren Fei, Zhao Liqin

2019-Dec-02

Pulmonary nodules, computer-aided detection (CADe), computer-aided diagnosis \n(CADx), multi-task CAD

In Work (Reading, Mass.) ; h5-index 0.0

BACKGROUND : Stumbles are common accidents that can result in falls and serious injuries, particularly in the workplace where back and forth movements are involved and in offices where high heels are imperative. Currently, the characteristics of plantar pressure during a stumble and the differences between stumbling and a normal gait remain unclear.

OBJECTIVE : This paper is aimed at providing insights into the feasibility of the data mining technique for interventions in stumble-related occupational safety issues.

METHODS : The characteristics of plantar pressure distribution during stumbling and normal gait were analyzed by using the power spectrum density (PSD) and the Support Vector Machine (SVM). The PSD, a novel pattern recognition feature, was used to mathematically describe the image signal. The SVM, a powerful data mining technique, was used as the classifier to recognize a stumble. Dynamic plantar pressures were measured from twelve healthy participants as they walked.

RESULTS : The plantar pressures of the stumbling gaits had significantly different patterns compared to the normal ones, from either a qualitative or quantitative perspective. The mean recognition accuracy of the proposed method reached 96.7% .

CONCLUSIONS : This study helps better understand stumbles and provides a theoretical basis for stumble-related occupational injuries. In addition, the stumble is the precursor of a fall and the research on stumble recognition would be of value to predict and provide warnings of falls and to design anti-fall devices for potential victims.

Niu Jianwei, Zheng Yanling, Liu Haixiao, Chen Xiao, Ran Linghua

2019-Dec-03

Gait recognition, SVM, artificial intelligence, power spectrum density

In The Science of the total environment ; h5-index 0.0

Costache Romulus, Hong Haoyuan, Pham Quoc Bao

2019-Oct-08

Bâsca Chiojdului catchment, Ensemble models, Flash-flood potential index, Machine learning models, Statistical index

arxiv preprint

Zhuo Wang, Wei Zhang, Ning Liu, Jianyong Wang

2019-12-10

In Cancer biomarkers : section A of Disease markers ; h5-index 0.0

BACKGROUND : Head and neck squamous cell carcinoma (HNSCC) is the seventh most common type of cancer around the world. The aim of this study was to seek the long non-coding RNAs (lncRNAs) acting as diagnostic and prognostic biomarker of HNSCC.

METHODS : Base on TCGA dataset, the differentially expressed mRNAs (DEmRNAs) and lncRNAs (DElncRNAs) were identified between HNSCC and normal tissue. The machine learning and survival analysis were performed to estimate the potential diagnostic and prognostic value of lncRNAs for HNSCC. We also build the co-expression network and functional annotation. The expression of selected candidate mRNAs and lncRNAs were validated by Quantitative real time polymerase chain reaction (qRT-PCR).

RESULTS : A total of 3363 DEmRNAs (1822 down-regulated and 1541 up-regulated mRNAs) and 32 DElncRNAs (13 down-regulated and 19 up-regulated lncRNAs) between HNSCC and normal tissue were obtained. A total of 13 lncRNAs (IL12A.AS1, RP11.159F24.6, RP11.863P13.3, LINC00941, FOXCUT, RNF144A.AS1, RP11.218E20.3, HCG22, HAGLROS, LINC01615, RP11.351J23.1, AC024592.9 and MIR9.3HG) were defined as optimal diagnostic lncRNAs biomarkers for HNSCC. The area under curve (AUC) of the support vector machine (SVM) model, decision tree model and random forests model and were 0.983, 0.842 and 0.983, and the specificity and sensitivity of the three model were 95.5% and 96.2%, 77.3% and 97.6% and 93.2% and 97.8%, respectively. Among them, AC024592.9, LINC00941, LINC01615 and MIR9-3HG was not only an optimal diagnostic lncRNAs biomarkers, but also related to survival time. The focal adhesion, ECM-receptor interaction, pathways in cancer and cytokine-cytokine receptor interaction were four significantly enriched pathways in DEmRNAs co-expressed with the identified optimal diagnostic lncRNAs. But for most of the selected DEmRNAs and DElncRNAs, the expression was consistent with our integrated analysis results, including LINC00941, LINC01615, FOXCUT, TGA6 and MMP13.

CONCLUSION : AC024592.9, LINC00941, LINC01615 and MIR9-3HG was not only an optimal diagnostic lncRNAs biomarkers, but also were a prognostic lncRNAs biomarkers.

Hu Ying, Guo Geyang, Li Junjun, Chen Jie, Tan Pingqing

2019-Nov-22

Head and neck squamous cell carcinoma, diagnostic, machine learning, prognostic

In JMIR medical informatics ; h5-index 23.0

BACKGROUND : The quality of health care is continuously improving and is expected to improve further because of the advancement of machine learning and knowledge-based techniques along with innovation and availability of wearable sensors. With these advancements, health care professionals are now becoming more interested and involved in seeking scientific research evidence from external sources for decision making relevant to medical diagnosis, treatments, and prognosis. Not much work has been done to develop methods for unobtrusive and seamless curation of data from the biomedical literature.

OBJECTIVE : This study aimed to design a framework that can enable bringing quality publications intelligently to the users' desk to assist medical practitioners in answering clinical questions and fulfilling their informational needs.

METHODS : The proposed framework consists of methods for efficient biomedical literature curation, including the automatic construction of a well-built question, the recognition of evidence quality by proposing extended quality recognition model (E-QRM), and the ranking and summarization of the extracted evidence.

RESULTS : Unlike previous works, the proposed framework systematically integrates the echelons of biomedical literature curation by including methods for searching queries, content quality assessments, and ranking and summarization. Using an ensemble approach, our high-impact classifier E-QRM obtained significantly improved accuracy than the existing quality recognition model (1723/1894, 90.97% vs 1462/1894, 77.21%).

CONCLUSIONS : Our proposed methods and evaluation demonstrate the validity and rigorousness of the results, which can be used in different applications, including evidence-based medicine, precision medicine, and medical education.

Afzal Muhammad, Hussain Maqbool, Malik Khalid Mahmood, Lee Sungyoung

2019-Dec-09

biomedical research, clinical decision support systems, data curation, deep learning, evidence-based medicine, machine learning, precision medicine

In Journal of translational medicine ; h5-index 0.0

BACKGROUND : This study aimed to establish and validate a nomogram for predicting brain metastasis in patients with bladder cancer (BCa) and assess various treatment modalities using a primary cohort comprising 234 patients with clinicopathologically-confirmed BCa from 2004 to 2015 in the National Cancer Database.

METHODS : Machine learning method and Cox model were used for nomogram construction. For BCa patients with brain metastasis, surgery of the primary site, chemotherapy, radiation therapy, palliative care, brain confinement of metastatic sites, and the Charlson/Deyo Score were predictive features identified for building the nomogram.

RESULTS : For the original 169 patients considered in the model, the areas under the receiver operating characteristic curve (AUC) were 0.823 (95% CI 0.758-0.889, P < 0.001) and 0.854 (95% CI 0.785-0.924, P < 0.001) for 0.5- and 1-year overall survival respectively. In the validation cohort, the nomogram displayed similar AUCs of 0.838 (95% CI 0.738-0.937, P < 0.001) and 0.809 (95% CI 0.680-0.939, P < 0.001), respectively. The high and low risk groups had median survivals of 1.91 and 5.09 months for the training cohort and 1.68 and 8.05 months for the validation set, respectively (both P < 0.0001).

CONCLUSIONS : Our prognostic nomogram provides a useful tool for overall survival prediction as well as assessing the risk and optimal treatment for BCa patients with brain metastasis.

Yao Zhixian, Zheng Zhong, Ke Wu, Wang Renjie, Mu Xingyu, Sun Feng, Wang Xiang, Garg Shivank, Shi Wenyin, He Yinyan, Liu Zhihong

2019-Dec-09

Bladder cancer, Brain metastasis, Machine learning, Nomogram, Overall survival

In Journal of clinical oncology : official journal of the American Society of Clinical Oncology ; h5-index 0.0

PURPOSE : Extranodal extension (ENE) is a well-established poor prognosticator and an indication for adjuvant treatment escalation in patients with head and neck squamous cell carcinoma (HNSCC). Identification of ENE on pretreatment imaging represents a diagnostic challenge that limits its clinical utility. We previously developed a deep learning algorithm that identifies ENE on pretreatment computed tomography (CT) imaging in patients with HNSCC. We sought to validate our algorithm performance for patients from a diverse set of institutions and compare its diagnostic ability to that of expert diagnosticians.

METHODS : We obtained preoperative, contrast-enhanced CT scans and corresponding pathology results from two external data sets of patients with HNSCC: an external institution and The Cancer Genome Atlas (TCGA) HNSCC imaging data. Lymph nodes were segmented and annotated as ENE-positive or ENE-negative on the basis of pathologic confirmation. Deep learning algorithm performance was evaluated and compared directly to two board-certified neuroradiologists.

RESULTS : A total of 200 lymph nodes were examined in the external validation data sets. For lymph nodes from the external institution, the algorithm achieved an area under the receiver operating characteristic curve (AUC) of 0.84 (83.1% accuracy), outperforming radiologists' AUCs of 0.70 and 0.71 (P = .02 and P = .01). Similarly, for lymph nodes from the TCGA, the algorithm achieved an AUC of 0.90 (88.6% accuracy), outperforming radiologist AUCs of 0.60 and 0.82 (P < .0001 and P = .16). Radiologist diagnostic accuracy improved when receiving deep learning assistance.

CONCLUSION : Deep learning successfully identified ENE on pretreatment imaging across multiple institutions, exceeding the diagnostic ability of radiologists with specialized head and neck experience. Our findings suggest that deep learning has utility in the identification of ENE in patients with HNSCC and has the potential to be integrated into clinical decision making.

Kann Benjamin H, Hicks Daniel F, Payabvash Sam, Mahajan Amit, Du Justin, Gupta Vishal, Park Henry S, Yu James B, Yarbrough Wendell G, Burtness Barbara A, Husain Zain A, Aneja Sanjay

2019-Dec-09

In Expert review of neurotherapeutics ; h5-index 0.0

Kwon Churl-Su, Jetté Nathalie, Ghatan Saadi

2019-Dec-09

Epilepsy, artificial intelligence, deep brain stimulation (DBS), neuromodulation, responsive neurostimulation (RNS), stimulation

In Molecular informatics ; h5-index 0.0

Miyazaki Yu, Ono Naoaki, Huang Ming, Altaf-Ul-Amin Md, Kanaya Shigehiko

2019-Dec-09

BACE1, GCNN, cathepsin D, ligand selectivity, mapping of principal components

In NPJ digital medicine ; h5-index 0.0

Dauvin Antonin, Donado Carolina, Bachtiger Patrik, Huang Ke-Chun, Sauer Christopher Martin, Ramazzotti Daniele, Bonvini Matteo, Celi Leo Anthony, Douglas Molly J

2019

Acute kidney injury, Anaemia, Chronic kidney disease, Computational models, Data integration

In NPJ microgravity ; h5-index 0.0

Schlotman Taylor E, Lehnhardt Kris R, Abercromby Andrew F, Easter Benjamin D, Downs Meghan E, Akers L T C Kevin S, Convertino Victor A

2019

Biomedical engineering, Physiology, Translational research

In GMS journal for medical education ; h5-index 0.0

Ehlers Claudia, Wiesener Nadine, Teichgräber Ulf, Guntinas-Lichius Orlando

2019

Ambulatory-oriented medicine (AoM), Canadian Medical Education Directions of Specialist (CanMEDS) rolls, Clinic-oriented medicine (KoM), Flexner model, JENa professional interest-Oriented Studies (JENOS), JUH-specific lecturer and student information system (DOSIS), Master Plan 2020, bottom-up strategy, constructive alignment, costs, curriculum, deep learning, evaluations, identification, incentives, interactivity, learning portfolio, longitudinal curriculum, mapping, medical didactic programmes, mentoring, organisational difficulties, performance-based compensation, practical orientation, professional interest orientation, reduction of the curriculum, reform, reinforcement of ambulatory and general medicine, research-oriented Medicine (FoM), resources, scientific orientation, small group modules, student centered learning

In BioMed research international ; h5-index 102.0

Peng Liu, Guo Jin-Cheng, Long Lin, Pan Feng, Zhao Jian-Mei, Xu Li-Yan, Li En-Min

2019

In The Science of the total environment ; h5-index 0.0

Yan Hao, Zhang Jixiong, Zhou Nan, Li Meng

2019-Nov-06

Adaptive boosting algorithm, Back propagation neural network, Coal strength alteration, Genetic algorithm, Predictive model

arxiv preprint

Sai P. Selvaraj, Sandeep Konam

2019-12-10

In Light, science & applications ; h5-index 0.0

Luo Yi, Mengu Deniz, Yardimci Nezih T, Rivenson Yair, Veli Muhammed, Jarrahi Mona, Ozcan Aydogan

2019

Applied optics, Optical techniques, Other photonics

In Journal of healthcare engineering ; h5-index 0.0

Dhahri Habib, Al Maghayreh Eslam, Mahmood Awais, Elkilani Wail, Faisal Nagi Mohammed

2019

In IEEE signal processing letters ; h5-index 0.0

Özdenizci Ozan, Wang Ye, Koike-Akino Toshiaki, Erdoğmuş Deniz

2019-May

EEG, adversarial learning, biometrics, convolutional networks, invariant representation, person identification

In International journal of methods in psychiatric research ; h5-index 0.0

OBJECTIVES : Embedded in the Collaborative Research Center "Fear, Anxiety, Anxiety Disorders" (CRC-TRR58), this bicentric clinical study aims at identifying biobehavioral markers of treatment (non-)response by applying machine learning methodology with an external cross-validation protocol. We hypothesize that a priori prediction of treatment (non-)response is possible in a second, independent sample based on multimodal markers.

METHODS : One-session virtual reality exposure treatment (VRET) with patients with spider phobia was conducted on two sites. Clinical, neuroimaging, and genetic data were assessed at baseline, post-treatment and after 6 months. The primary and secondary outcomes defining treatment response are as follows: 30% reduction regarding the individual score in the Spider Phobia Questionnaire and 50% reduction regarding the individual distance in the behavioral avoidance test.

RESULTS : N = 204 patients have been included (n = 100 in Würzburg, n = 104 in Münster). Sample characteristics for both sites are comparable.

DISCUSSION : This study will offer cross-validated theranostic markers for predicting the individual success of exposure-based therapy. Findings will support clinical decision-making on personalized therapy, bridge the gap between basic and clinical research, and bring stratified therapy into reach. The study is registered at ClinicalTrials.gov (ID: NCT03208400).

Schwarzmeier Hanna, Leehr Elisabeth Johanna, Böhnlein Joscha, Seeger Fabian Reinhard, Roesmann Kati, Gathmann Bettina, Herrmann Martin J, Siminski Niklas, Junghöfer Markus, Straube Thomas, Grotegerd Dominik, Dannlowski Udo

2019-Dec-08

machine learning, spider phobia, theranostic markers

In Suicide & life-threatening behavior ; h5-index 0.0

OBJECTIVE : There is growing interest in the development of composite precision treatment rules (PTRs) to guide the selection of the treatments most likely to be helpful for individual patients. We present here the results of an effort to develop a preliminary PTR for Collaborative Assessment and Management of Suicidality (CAMS) relative to enhanced-care as usual based on secondary analysis of the Operation Worth Living (OWL) randomized controlled trial. The outcome of interest is eliminating suicide ideation (SI) within 3 months of initiating treatment.

METHOD : A state-of-the-art ensemble machine learning method was used to develop the PTR among the n = 148 U.S. Soldiers (predominately male and White, age range 18-48) OWL patients.

RESULTS : We estimated that CAMS was the better treatment for 77.8% of patients and that treatment assignment according to the PTR would result in a 13.6% (95% CI: 0.9%-26.3%) increase in 3-month SI remission compared to random treatment assignment.

CONCLUSIONS : Although promising, results are limited by the small sample size, restrictive baseline assessment, and inability to evaluate effects on suicidal behaviors or disaggregate based on history of suicidal behaviors. Replication is needed in larger samples with comprehensive baseline assessments, longer-term follow-ups, and more extensive outcomes.

Kessler Ronald C, Chalker Samantha A, Luedtke Alex R, Sadikova Ekaterina, Jobes David A

2019-Dec-09

In Briefings in bioinformatics ; h5-index 0.0

MOTIVATION : Biological systems function through dynamic interactions among genes and their products, regulatory circuits and metabolic networks. Our development of the Pathway Tools software was motivated by the need to construct biological knowledge resources that combine these many types of data, and that enable users to find and comprehend data of interest as quickly as possible through query and visualization tools. Further, we sought to support the development of metabolic flux models from pathway databases, and to use pathway information to leverage the interpretation of high-throughput data sets.

RESULTS : In the past 4 years we have enhanced the already extensive Pathway Tools software in several respects. It can now support metabolic-model execution through the Web, it provides a more accurate gap filler for metabolic models; it supports development of models for organism communities distributed across a spatial grid; and model results may be visualized graphically. Pathway Tools supports several new omics-data analysis tools including the Omics Dashboard, multi-pathway diagrams called pathway collages, a pathway-covering algorithm for metabolomics data analysis and an algorithm for generating mechanistic explanations of multi-omics data. We have also improved the core pathway/genome databases management capabilities of the software, providing new multi-organism search tools for organism communities, improved graphics rendering, faster performance and re-designed gene and metabolite pages.

AVAILABILITY : The software is free for academic use; a fee is required for commercial use. See http://pathwaytools.com.

CONTACT : pkarp@ai.sri.com.

SUPPLEMENTARY INFORMATION : Supplementary data are available at Briefings in Bioinformatics online.

Karp Peter D, Midford Peter E, Billington Richard, Kothari Anamika, Krummenacker Markus, Latendresse Mario, Ong Wai Kit, Subhraveti Pallavi, Caspi Ron, Fulcher Carol, Keseler Ingrid M, Paley Suzanne M

2019-Dec-08

Computational genomics, metabolic models, metabolic pathways, systems biology

In Briefings in bioinformatics ; h5-index 0.0

Chiu Yu-Chiao, Chen Hung-I Harry, Gorthi Aparna, Mostavi Milad, Zheng Siyuan, Huang Yufei, Chen Yidong

2019-Dec-08

cancer, deep learning, drug discovery, pharmacogenomics, precision oncology

In Artificial intelligence in medicine ; h5-index 34.0

BACKGROUND : Any ailment in our organs can be visualized by using different modality signals and images. Hospitals are encountering a massive influx of large multimodality patient data to be analysed accurately and with context understanding. The deep learning techniques, like convolution neural networks (CNN), long short-term memory (LSTM), autoencoders, deep generative models and deep belief networks have already been applied to efficiently analyse possible large collections of data. Application of these methods to medical signals and images can aid the clinicians in clinical decision making.

PURPOSE : The aim of this study was to explore its potential application mechanism to the abalone basal ganglia neurons in rats based on deep learning.

PATIENTS AND METHODS : Firstly, in the GEO database, we obtained data on rat anesthesia, performing differential analysis, co-expression analysis, and enrichment analysis, and then we received the relevant module genes. Besides, the potential regulation of multi-factors on the module was calculated by hypergeometric test, and a series of ncRNA and TF were identified. Finally, we screened the target genes of anesthetized rats to gain insight into the potential role of anesthesia in rat basal lateral nucleus neurons.

RESULTS : A total of 535 differentially expressed genes in rats were obtained, involving Mafb and Ryr2. These genes are clustered into 17 anesthesia-related expression disorder modules. At the same time, the biological processes favored by the module are regulation of neuron apoptotic process and transforming growth factor beta2 production. Pivot analysis found that 39 ncRNAs and 4 TFs drive anesthesia-related disorders. Finally, the mechanism of action was analyzed and predicted. The module was regulated by Acvr1. We believe that miR-384-5p in anesthetized rats can activate the TGF-beta signaling pathway. Further, it promotes anesthesia and causes exposure to the basal ganglia neuron damage of the amygdala.

CONCLUSION : In this study, the imbalance module was used to explore the multi-factor-mediated anesthesia application mechanism, which provided new methods and ideas for subsequent research. The results suggest that miR-384-5p can promote anesthesia damage to the abalone basal ganglia neurons in rats through a variety of biological processes and signaling pathways. This result lays a solid theoretical foundation for biologists to explore the application mechanism of anesthesiology further.

Wang Zhen, Du Xiaoyan, Yang Yang, Zhang Guoqing

2019-Nov

Anesthesia, Basal lateral nucleus neurons, Dysfunction module, Multifactorial

In Artificial intelligence in medicine ; h5-index 34.0

Gao Shang, Qiu John X, Alawad Mohammed, Hinkle Jacob D, Schaefferkoetter Noah, Yoon Hong-Jun, Christian Blair, Fearn Paul A, Penberthy Lynne, Wu Xiao-Cheng, Coyle Linda, Tourassi Georgia, Ramanathan Arvind

2019-Nov

Cancer pathology reports, Clinical reports, Deep learning, Natural language processing, Text classification

In Artificial intelligence in medicine ; h5-index 34.0

Singh Deepak, Singh Pradeep, Singh Sisodia Dilip

2019-Nov

Multi-kernel learning, Multifactorial evolutionary algorithm, Multitask learning, Virulent protein

In ISA transactions ; h5-index 0.0

Zhang Ying, Zhang Rongrong, Ma Qunfei, Wang Yanhao, Wang Qingqing, Huang Zihao, Huang Linyan

2019-Dec-02

Air quality prediction, Feature selection, Machine learning, Model fusion

arxiv preprint

Zhuo Wang, Wei Zhang, Ning Liu, Jianyong Wang

2019-12-10

In Artificial intelligence in medicine ; h5-index 34.0

Vrbaški Dunja, Vrbaški Milan, Kupusinac Aleksandar, Ivanović Darko, Stokić Edita, Ivetić Dragan, Doroslovački Ksenija

2019-Nov

Artificial neural network, Decision tree, Linear regression, Metabolic syndrome, Random forest

In Artificial intelligence in medicine ; h5-index 34.0

Abdel-Basset Mohamed, Mohamed Mai, Elhoseny Mohamed, Son Le Hoang, Chiclana Francisco, Zaied Abd El-Nasser H

2019-Nov

Bipolar, Bipolar disorder diseases, Cosine similarity measure, Multi-attribute decision making

In Artificial intelligence in medicine ; h5-index 34.0

Talo Muhammed

2019-Nov

CNN, Deep learning, Histopathology, Medical image classification, Transfer learning

In Artificial intelligence in medicine ; h5-index 34.0

BACKGROUND AND OBJECTIVE : Cerebral stroke has become a significant global public health issue in recent years. The ideal solution to this concern is to prevent in advance by controlling related metabolic factors. However, it is difficult for medical staff to decide whether special precautions are needed for a potential patient only based on the monitoring of physiological indicators unless they are obviously abnormal. This paper will develop a hybrid machine learning approach to predict cerebral stroke for clinical diagnosis based on the physiological data with incompleteness and class imbalance.

METHODS : Two steps are involved in the whole process. Firstly, random forest regression is adopted to impute missing values before classification. Secondly, an automated hyperparameter optimization(AutoHPO) based on deep neural network(DNN) is applied to stroke prediction on an imbalanced dataset.

RESULTS : The medical dataset contains 43,400 records of potential patients which includes 783 occurrences of stroke. The false negative rate from our prediction approach is only 19.1%, which has reduced by an average of 51.5% in comparison to other traditional approaches. The false positive rate, accuracy and sensitivity predicted by the proposed approach are respectively 33.1, 71.6, and 67.4%.

CONCLUSION : The approach proposed in this paper has effectively reduced the false negative rate with a relatively high overall accuracy, which means a successful decrease in the misdiagnosis rate for stroke prediction. The results are more reliable and valid as the reference in stroke prognosis, and also can be acquired conveniently at a low cost.

Liu Tianyu, Fan Wenhui, Wu Cheng

2019-Nov

AutoHPO, Class imbalance, Clinical decision, Hybrid machine learning, Stroke prediction

In The journal of physical chemistry. B ; h5-index 0.0

Adorf Carl Simon, Moore Timothy C, Melle Yannah J U, Glotzer Sharon C

2019-Dec-08

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

PURPOSE : This study proposes an automated prostate cancer (PC) lesion characterization method based on the deep neural network to determine tumor burden on ⁶⁸Ga-PSMA-11 PET/CT to potentially facilitate the optimization of PSMA-directed radionuclide therapy.

METHODS : We collected ⁶⁸Ga-PSMA-11 PET/CT images from 193 patients with metastatic PC at three medical centers. For proof-of-concept, we focused on the detection of pelvis bone and lymph node lesions. A deep neural network (triple-combining 2.5D U-Net) was developed for the automated characterization of these lesions. The proposed method simultaneously extracts features from axial, coronal, and sagittal planes, which mimics the workflow of physicians and reduces computational and memory requirements.

RESULTS : Among all the labeled lesions, the network achieved 99% precision, 99% recall, and an F1 score of 99% on bone lesion detection and 94%, precision 89% recall, and an F1 score of 92% on lymph node lesion detection. The segmentation accuracy is lower than the detection. The performance of the network was correlated with the amount of training data.

CONCLUSION : We developed a deep neural network to characterize automatically the PC lesions on ⁶⁸Ga-PSMA-11 PET/CT. The preliminary test within the pelvic area confirms the potential of deep learning methods. Increasing the amount of training data should further enhance the performance of the proposed method and may ultimately allow whole-body assessments.

Zhao Yu, Gafita Andrei, Vollnberg Bernd, Tetteh Giles, Haupt Fabian, Afshar-Oromieh Ali, Menze Bjoern, Eiber Matthias, Rominger Axel, Shi Kuangyu

2019-Dec-07

Deep learning, Lesion detection, PET/CT, PSMA, Prostate cancer

In Meat science ; h5-index 0.0

Shahinfar Saleh, Al-Mamun Hawlader A, Park Byoungho, Kim Sidong, Gondro Cedric

2019-Nov-12

Carcass traits, GWAS, Genetic algorithm, Hanwoo Beef Cattle, Machine learning, Marbling score, SMOTE

In Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology ; h5-index 0.0

BACKGROUND : Deep learning-based auto-segmented contours (DC) aim to alleviate labour intensive contouring of organs at risk (OAR) and clinical target volumes (CTV). Most previous DC validation studies have a limited number of expert observers for comparison and/or use a validation dataset related to the training dataset. We determine if DC models are comparable to Radiation Oncologist (RO) inter-observer variability on an independent dataset.

METHODS : Expert contours (EC) were created by multiple ROs for central nervous system (CNS), head and neck (H&N), and prostate radiotherapy (RT) OARs and CTVs. DCs were generated using deep learning-based auto-segmentation software trained by a single RO on publicly available data. Contours were compared using Dice Similarity Coefficient (DSC) and 95% Hausdorff distance (HD).

RESULTS : Sixty planning CT scans had 2-4 ECs, for a total of 60 CNS, 53 H&N, and 50 prostate RT contour sets. The mean DC and EC contouring times were 0.4 vs 7.7 min for CNS, 0.6 vs 26.6 min for H&N, and 0.4 vs 21.3 min for prostate RT contours. There were minimal differences in DSC and 95% HD involving DCs for OAR comparisons, but more noticeable differences for CTV comparisons.

CONCLUSIONS : The accuracy of DCs trained by a single RO is comparable to expert inter-observer variability for the RT planning contours in this study. Use of deep learning-based auto-segmentation in clinical practice will likely lead to significant benefits to RT planning workflow and resources.

Wong Jordan, Fong Allan, McVicar Nevin, Smith Sally, Giambattista Joshua, Wells Derek, Kolbeck Carter, Giambattista Jonathan, Gondara Lovedeep, Alexander Abraham

2019-Dec-05

Machine learning, Radiotherapy

In Medical hypotheses ; h5-index 0.0

Şişik Fatih, Sert Eser

2019-Nov-18

Brain tumor segmentation, Extreme learning machine, Magnetic resonance imaging, Raspberry Pi, Segmentation, Significantly fast and robust fuzzy C-means clustering

In Current opinion in biotechnology ; h5-index 0.0

Rana Pratip, Berry Carter, Ghosh Preetam, Fong Stephen S

2019-Dec-05

In Scientific reports ; h5-index 158.0

Bermant Peter C, Bronstein Michael M, Wood Robert J, Gero Shane, Gruber David F

2019-Dec-06

In The journal of applied laboratory medicine ; h5-index 0.0

BACKGROUND : Accurate diagnosis of Alzheimer disease (AD) involving less invasive molecular procedures and at reasonable cost is an unmet medical need. We identified a serum miRNA signature for AD that is less invasive than a measure in cerebrospinal fluid.

METHODS : From the Oxford Project to Investigate Memory and Aging (OPTIMA) study, 96 serum samples were profiled by a multiplex (>500 analytes) microRNA (miRNA) reverse transcription quantitative PCR analysis, including 51 controls, 32 samples from patients with AD, and 13 samples from patients with mild cognitive impairment (MCI). Clinical diagnosis of a subset of AD and the controls was confirmed by postmortem (PM) histologic examination of brain tissue. In a machine learning approach, the AD and control samples were split 70:30 as the training and test cohorts. A multivariate random forest statistical analysis was applied to construct and test a miRNA signature for AD identification. In addition, the MCI participants were included in the test cohort to assess whether the signature can identify early AD patients.

RESULTS : A 12-miRNA signature for AD identification was constructed in the training cohort, demonstrating 76.0% accuracy in the independent test cohort with 90.0% sensitivity and 66.7% specificity. The signature, however, was not able to identify MCI participants. With a subset of AD and control participants with PM-confirmed diagnosis status, a separate 12-miRNA signature was constructed. Although sample size was limited, the PM-confirmed signature demonstrated improved accuracy of 85.7%, largely owing to improved specificity of 80.0% with comparable sensitivity of 88.9%.

CONCLUSION : Although additional and more diverse cohorts are needed for further clinical validation of the robustness, the miRNA signature appears to be a promising blood test to diagnose AD.

Zhao Xuemei, Kang John, Svetnik Vladimir, Warden Donald, Wilcock Gordon, David Smith A, Savage Mary J, Laterza Omar F

2019-Dec-06

In Hospital pediatrics ; h5-index 0.0

OBJECTIVES : The rate of pediatric 7-day unplanned readmissions is often seen as a measure of quality of care, with high rates indicative of the need for improvement of quality of care. In this study, we used machine learning on electronic health records to study predictors of pediatric 7-day readmissions. We ranked predictors by clinical significance, as determined by the magnitude of the least absolute shrinkage and selection operator regression coefficients.

METHODS : Data consisting of 50 241 inpatient and observation encounters at a single tertiary pediatric hospital were retrieved; 50% of these patients' data were used for building a least absolute shrinkage and selection operator regression model, whereas the other half of the data were used for evaluating model performance. The categories of variables included were demographics, social determinants of health, severity of illness and acuity, resource use, diagnoses, medications, psychosocial factors, and other variables such as primary care no show.

RESULTS : Previous hospitalizations and readmissions, medications, multiple comorbidities, longer current and previous lengths of stay, certain diagnoses, and previous emergency department use were the most significant predictors modifying a patient's risk of 7-day pediatric readmission. The model achieved an area under the curve of 0.778 (95% confidence interval 0.763-0.793).

CONCLUSIONS : Predictors such as medications, previous and current health care resource use, history of readmissions, severity of illness and acuity, and certain psychosocial factors modified the risk of unplanned 7-day readmissions. These predictors are mostly unmodifiable, indicating that intervention plans on high-risk patients may be developed through discussions with patients and parents to identify underlying modifiable causal factors of readmissions.

Ehwerhemuepha Louis, Pugh Karen, Grant Alex, Taraman Sharief, Chang Anthony, Rakovski Cyril, Feaster William

2019-Dec-06

In Anticancer research ; h5-index 0.0

BACKGROUND/AIM : Osteosarcoma is the most malignant type of bone tumor. Patients with osteosarcoma metastases have a poorer prognosis than those without metastases. Thus, the prognosis of osteosarcoma patients with metastases must be improved.

MATERIALS AND METHODS : The present study investigated the inhibitory effects of 6-hydroxythiobinupharidine isolated from Nuphar pumilum on migration of LM8 murine osteosarcoma cells by a migration assay and also examined the expression of proteins related to actin dynamics by western blot. The present study also developed an automatic cell counting system using machine learning to count migrated cells by Fiji and Trainable Weka Segmentation.

RESULTS : 6-Hydroxythiobinupharidine inhibited migration of LM8 osteosarcoma cells in a dose-dependent manner, and decreased protein expression of Lin11, Isl-1, and Mec-3 domain kinase 1 (LIMK1) and the levels of phosphorylated Cofilin.

CONCLUSION : 6-Hydroxythiobinupharidine suppressed migration of LM8 osteosarcoma cells by decreasing expression of LIMK1. 6-Hydroxythiobinupharidine could be potentially used as an anti-metastatic compound.

Yoshizawa Masato, Nakamura Seikou, Sugiyama Yuki, Tamai Shiori, Ishida Yukiko, Sueyoshi Mari, Toda Yuki, Hosogi Shigekuni, Yano Yoshitaka, Ashihara Eishi

2019-Dec

6-hydroxythiobinupharidine, Cofilin, LIMK, Osteosarcoma, machine learning, metastasis

In Best practice & research. Clinical rheumatology ; h5-index 0.0

Kataria Suchitra, Ravindran Vinod

2019-Aug

Artificial intelligence, Big data, Data analytics, Digital health, Machine learning, Robotics, Wearable devices

In Systematic reviews ; h5-index 0.0

BACKGROUND : The growing number of medical literature and textual data in online repositories led to an exponential increase in the workload of researchers involved in citation screening for systematic reviews. This work aims to combine machine learning techniques and data preprocessing for class imbalance to identify the outperforming strategy to screen articles in PubMed for inclusion in systematic reviews.

METHODS : We trained four binary text classifiers (support vector machines, k-nearest neighbor, random forest, and elastic-net regularized generalized linear models) in combination with four techniques for class imbalance: random undersampling and oversampling with 50:50 and 35:65 positive to negative class ratios and none as a benchmark. We used textual data of 14 systematic reviews as case studies. Difference between cross-validated area under the receiver operating characteristic curve (AUC-ROC) for machine learning techniques with and without preprocessing (delta AUC) was estimated within each systematic review, separately for each classifier. Meta-analytic fixed-effect models were used to pool delta AUCs separately by classifier and strategy.

RESULTS : Cross-validated AUC-ROC for machine learning techniques (excluding k-nearest neighbor) without preprocessing was prevalently above 90%. Except for k-nearest neighbor, machine learning techniques achieved the best improvement in conjunction with random oversampling 50:50 and random undersampling 35:65.

CONCLUSIONS : Resampling techniques slightly improved the performance of the investigated machine learning techniques. From a computational perspective, random undersampling 35:65 may be preferred.

Lanera Corrado, Berchialla Paola, Sharma Abhinav, Minto Clara, Gregori Dario, Baldi Ileana

2019-Dec-06

Classification, Indexed search engine, Machine learning, Text mining, Unbalanced data, systematic review

In World journal of surgical oncology ; h5-index 0.0

BACKGROUND : The evaluation of thyroid nodules with ultrasonography has created a large burden for radiologists. Artificial intelligence technology has been rapidly developed in recent years to reduce the cost of labor and improve the differentiation of thyroid malignancies. This study aimed to investigate the diagnostic performance of a novel computer-aided diagnosing system (CADs: S-detect) for the ultrasound (US) interpretation of thyroid nodule subtypes in a specialized thyroid center.

METHODS : Our study prospectively included 180 thyroid nodules that underwent ultrasound interpretation. The CADs and radiologist assessed all nodules. The ultrasonographic features of different subtypes were analyzed, and the diagnostic performances of the CADs and radiologist were compared.

RESULTS : There were seven subtypes of thyroid nodules, among which papillary thyroid cancer (PTC) accounted for 50.6% and follicular thyroid carcinoma (FTC) accounted for 2.2%. Among all thyroid nodules, the CADs presented a higher sensitivity and lower specificity than the radiologist (90.5% vs 81.1%; 41.2% vs 83.5%); the radiologist had a higher accuracy than the CADs (82.2% vs 67.2%) for diagnosing malignant thyroid nodules. The accuracy of the CADs was not as good as that of the radiologist in diagnosing PTCs (70.9% vs 82.1%). The CADs and radiologist presented accuracies of 43.8% and 60.9% in identifying FTCs, respectively.

CONCLUSIONS : The ultrasound CADs presented a higher sensitivity for identifying malignant thyroid nodules than experienced radiologists. The CADs was not as good as experienced radiologists in a specialized thyroid center in identifying PTCs. Radiologists maintained a higher specificity than the CADs for FTC detection.

Xia Shujun, Yao Jiejie, Zhou Wei, Dong Yijie, Xu Shangyan, Zhou Jianqiao, Zhan Weiwei

2019-Dec-06

CADs, Experienced radiologists, Thyroid nodule

In Journal of neurosurgery ; h5-index 64.0

OBJECTIVE : Automatic segmentation of vestibular schwannomas (VSs) from MRI could significantly improve clinical workflow and assist in patient management. Accurate tumor segmentation and volumetric measurements provide the best indicators to detect subtle VS growth, but current techniques are labor intensive and dedicated software is not readily available within the clinical setting. The authors aim to develop a novel artificial intelligence (AI) framework to be embedded in the clinical routine for automatic delineation and volumetry of VS.

METHODS : Imaging data (contrast-enhanced T1-weighted [ceT1] and high-resolution T2-weighted [hrT2] MR images) from all patients meeting the study's inclusion/exclusion criteria who had a single sporadic VS treated with Gamma Knife stereotactic radiosurgery were used to create a model. The authors developed a novel AI framework based on a 2.5D convolutional neural network (CNN) to exploit the different in-plane and through-plane resolutions encountered in standard clinical imaging protocols. They used a computational attention module to enable the CNN to focus on the small VS target and propose a supervision on the attention map for more accurate segmentation. The manually segmented target tumor volume (also tested for interobserver variability) was used as the ground truth for training and evaluation of the CNN. We quantitatively measured the Dice score, average symmetric surface distance (ASSD), and relative volume error (RVE) of the automatic segmentation results in comparison to manual segmentations to assess the model's accuracy.

RESULTS : Imaging data from all eligible patients (n = 243) were randomly split into 3 nonoverlapping groups for training (n = 177), hyperparameter tuning (n = 20), and testing (n = 46). Dice, ASSD, and RVE scores were measured on the testing set for the respective input data types as follows: ceT1 93.43%, 0.203 mm, 6.96%; hrT2 88.25%, 0.416 mm, 9.77%; combined ceT1/hrT2 93.68%, 0.199 mm, 7.03%. Given a margin of 5% for the Dice score, the automated method was shown to achieve statistically equivalent performance in comparison to an annotator using ceT1 images alone (p = 4e-13) and combined ceT1/hrT2 images (p = 7e-18) as inputs.

CONCLUSIONS : The authors developed a robust AI framework for automatically delineating and calculating VS tumor volume and have achieved excellent results, equivalent to those achieved by an independent human annotator. This promising AI technology has the potential to improve the management of patients with VS and potentially other brain tumors.

Shapey Jonathan, Wang Guotai, Dorent Reuben, Dimitriadis Alexis, Li Wenqi, Paddick Ian, Kitchen Neil, Bisdas Sotirios, Saeed Shakeel R, Ourselin Sebastien, Bradford Robert, Vercauteren Tom

2019-Dec-06

AI = artificial intelligence, ASSD = average symmetric surface distance, CNN = convolutional neural network, DL = deep learning, GK = Gamma Knife, HDL = hardness-weighted Dice loss, MRI, RVE = relative volume error, SRS = stereotactic radiosurgery, SpvA = supervised attention module, VS = vestibular schwannoma, artificial intelligence, ceT1 = contrast-enhanced T1-weighted, convolutional neural network, hrT2 = high-resolution T2-weighted, oncology, segmentation, tumor, vestibular schwannoma

In Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society ; h5-index 0.0

Wang Huiquan, Ahmed S Nizam, Mandal Mrinal

2019-Nov-13

Computer-aided detection, Convolutional neural network, Deep learning, Focal cortical dysplasia, Magnetic resonance imaging

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

Acharya Bipin Kumar, Chen Wei, Ruan Zengliang, Pant Gobind Prasad, Yang Yin, Shah Lalan Prasad, Cao Chunxiang, Xu Zhiwei, Dhimal Meghnath, Lin Hualiang

2019-Dec-02

Nepal, machine learning, scrub typhus, suitability mapping

In Cancer letters ; h5-index 85.0

Zongyi Yin, Xiaowu Li

2019-Dec-04

CAR-T therapy, PD-1, cancer vaccine, immune checkpoint inhibitor, targeting drug

In Electrophoresis ; h5-index 0.0

Liang Jie, Mu Taotao

2019-Dec-07

Cloud platform, Deep learning, Mixture recognition, Raman spectrometer, Recognition algorithm

In Journal of pediatric endocrinology & metabolism : JPEM ; h5-index 0.0

Jung Mo Kyung, Yu Jeesuk, Lee Ji-Eun, Kim Se Young, Kim Hae Soon, Yoo Eun-Gyong

2019-Dec-07

Turner syndrome, growth hormone, height outcome

In Medical physics ; h5-index 59.0

PURPOSE : Computed tomography for the reconstruction of region of interest (ROI) has advantages in reducing the x-ray dose and the use of a small detector. However, standard analytic reconstruction methods such as filtered back projection (FBP) suffer from severe cupping artifacts, and existing model-based iterative reconstruction methods require extensive computations. Recently, we proposed a deep neural network to learn the cupping artifacts, but the network was not generalized well for different ROIs due to the singularities in the corrupted images. Therefore, there is an increasing demand for a neural network that works well for any ROI size.

METHOD : Two types of neural networks are designed. The first type learns ROI size-specific cupping artifacts from FBP images, whereas the second type network is for the inversion of the truncated Hilbert transform from the truncated differentiated backprojection (DBP) data. Their generalizabilities for different ROI sizes, pixel sizes, detector pitch and starting angles for a short scan are then investigated.

RESULTS : Experimental results show that the new type of neural networks significantly outperform existing iterative methods for all ROI sizes despite significantly lower runtime complexity. In addition, performance improvement is consistent across different acquisition scenarios.

CONCLUSIONS : Since the proposed method consistently surpasses existing methods, it can be used as a general CT reconstruction engine for many practical applications without compromising possible detector truncation.

Han Yoseob, Ye Jong Chul

2019-Dec

Hilbert transform, deep learning, differentiated backprojection, interior tomography, region of interest (ROI) reconstruction

In Medical physics ; h5-index 59.0

De Man Quinten, Haneda Eri, Claus Bernhard, Fitzgerald Paul, De Man Bruno, Qian Guhan, Shan Hongming, Min James, Sabuncu Mert, Wang Ge

2019-Dec

computed tomography, deep learning, machine learning, sinogram

In Biotechnology progress ; h5-index 0.0

Ren Jun, Zhou Roland, Farrow Michael, Peiris Ramila, Alosi Tim, Guenard Rob, Romero-Torres Saly

2019-Dec-07

Batch similarity, KNN, Process evaluation, Quality investigation

In International journal of mental health nursing ; h5-index 0.0

Smith Marianne, Dietrich Bryce Jensen, Bai Er-Wei, Bockholt Henry Jeremy

2019-Dec-06

depression, geriatric psychiatry, health serves for the aged, machine learning, phonetics

In Interdisciplinary sciences, computational life sciences ; h5-index 0.0

Zhang Peng, Meng Jun, Luan Yushi, Liu Chanjuan

2019-Dec-06

CNN, Ensemble learning, IndRNN, Interaction, Prediction, miRNA–lncRNA

In Neurotoxicity research ; h5-index 0.0

Stoyanov Drozdstoy

2019-Dec-06

bio-markers, classification, machine learning, mental disorders

In Journal of medical systems ; h5-index 48.0

Liu Jian, Wang Jian, Ruan Weiwei, Lin Chengshan, Chen Daguo

2019-Dec-07

Bone mineral density, Deep learning, Medical diagnosis, Osteoporosis, U-net model, X-ray image

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

Wang Ying, Du Zhicheng, Lawrence Wayne R, Huang Yun, Deng Yu, Hao Yuantao

2019-Dec-02

hepatitis B virus, machine learning, prediction

In European radiology ; h5-index 62.0

Chassagnon Guillaume, Vakalopolou Maria, Paragios Nikos, Revel Marie-Pierre

2019-Dec-06

Deep learning, Lung, Machine learning, Thorax

In European radiology ; h5-index 62.0

OBJECTIVE : To develop a deep learning-based artificial intelligence (AI) scheme for predicting the likelihood of the ground-glass nodule (GGN) detected on CT images being invasive adenocarcinoma (IA) and also compare the accuracy of this AI scheme with that of two radiologists.

METHODS : First, we retrospectively collected 828 histopathologically confirmed GGNs of 644 patients from two centers. Among them, 209 GGNs are confirmed IA and 619 are non-IA, including 409 adenocarcinomas in situ and 210 minimally invasive adenocarcinomas. Second, we applied a series of pre-preprocessing techniques, such as image resampling, rescaling and cropping, and data augmentation, to process original CT images and generate new training and testing images. Third, we built an AI scheme based on a deep convolutional neural network by using a residual learning architecture and batch normalization technique. Finally, we conducted an observer study and compared the prediction performance of the AI scheme with that of two radiologists using an independent dataset with 102 GGNs.

RESULTS : The new AI scheme yielded an area under the receiver operating characteristic curve (AUC) of 0.92 ± 0.03 in classifying between IA and non-IA GGNs, which is equivalent to the senior radiologist's performance (AUC 0.92 ± 0.03) and higher than the score of the junior radiologist (AUC 0.90 ± 0.03). The Kappa value of two sets of subjective prediction scores generated by two radiologists is 0.6.

CONCLUSIONS : The study result demonstrates using an AI scheme to improve the performance in predicting IA, which can help improve the development of a more effective personalized cancer treatment paradigm.

KEY POINTS : • The feasibility of using a deep learning method to predict the likelihood of the ground-glass nodule being invasive adenocarcinoma. • Residual learning-based CNN model improves the performance in classifying between IA and non-IA nodules. • Artificial intelligence (AI) scheme yields higher performance than radiologists in predicting invasive adenocarcinoma.

Gong Jing, Liu Jiyu, Hao Wen, Nie Shengdong, Zheng Bin, Wang Shengping, Peng Weijun

2019-Dec-06

Carcinoma, Computer-assisted image interpretation, Lung neoplasms, Multiple pulmonary nodules, X-Ray computed tomography scanners

In Journal of medical systems ; h5-index 48.0

Kang Chang-Hoon, Erdenebayar Urtnasan, Park Jong-Uk, Lee Kyoung-Joung

2019-Dec-06

Deep learning, Long short-term memory (LSTM), Multi-class classification, Sleep apnea and hypopnea

In Graefe's archive for clinical and experimental ophthalmology = Albrecht von Graefes Archiv fur klinische und experimentelle Ophthalmologie ; h5-index 0.0

PURPOSE : To develop a deep learning (DL) model for automated detection of glaucoma and to compare diagnostic capability against hand-craft features (HCFs) based on spectral domain optical coherence tomography (SD-OCT) peripapillary retinal nerve fiber layer (pRNFL) images.

METHODS : A DL model with pre-trained convolutional neural network (CNN) based was trained using a retrospective training set of 1501 pRNFL OCT images, which included 690 images from 153 glaucoma patients and 811 images from 394 normal subjects. The DL model was further tested in an independent test set of 50 images from 50 glaucoma patients and 52 images from 52 normal subjects. A customized software was used to extract and measure HCFs including pRNFL thickness in average and four different sectors. Area under the receiver operator characteristics (AROC) curves was calculated to compare the diagnostic capability between DL model and hand-crafted pRNFL parameters.

RESULTS : In this study, the DL model achieved an AROC of 0.99 [CI: 0.97 to 1.00] which was significantly larger than the AROC values of all other HCFs (AROCs 0.661 with 95% CI 0.549 to 0.772 for temporal sector, AROCs 0.696 with 95% CI 0.549 to 0.799 for nasal sector, AROCs 0.913 with 95% CI 0.855 to 0.970 for superior sector, AROCs 0.938 with 95% CI 0.894 to 0.982 for inferior sector, and AROCs 0.895 with 95% CI 0.832 to 0.957 for average).

CONCLUSION : Our study demonstrated that DL models based on pre-trained CNN are capable of identifying glaucoma with high sensitivity and specificity based on SD-OCT pRNFL images.

Zheng Ce, Xie Xiaolin, Huang Longtao, Chen Binyao, Yang Jianling, Lu Jiewei, Qiao Tong, Fan Zhun, Zhang Mingzhi

2019-Dec-07

Deep learning, Glaucoma, Peripapillary retinal nerve fiber layer, Spectral domain optical coherence tomography

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

PURPOSE : Although most deep learning (DL) studies have reported excellent classification accuracy, these studies usually target typical Alzheimer's disease (AD) and normal cognition (NC) for which conventional visual assessment performs well. A clinically relevant issue is the selection of high-risk subjects who need active surveillance among equivocal cases. We validated the clinical feasibility of DL compared with visual rating or quantitative measurement for assessing the diagnosis and prognosis of subjects with equivocal amyloid scans.

METHODS : ¹⁸F-florbetaben scans of 430 cases (85 NC, 233 mild cognitive impairment, and 112 AD) were assessed through visual rating-based, quantification-based, and DL-based methods. DL was trained using 280 two-dimensional PET images (80%) and tested by randomly assigning the remaining (70 cases, 20%) cases and a clinical validation set of 54 equivocal cases. In the equivocal cases, we assessed the agreement among the visual rating, quantification, and DL and compared the clinical outcome according to each modality-based amyloid status.

RESULTS : The visual reading was positive in 175 cases, equivocal in 54 cases, and negative in 201 cases. The composite SUVR cutoff value was 1.32 (AUC 0.99). The subject-level performance of DL using the test set was 100%. Among the 54 equivocal cases, 37 cases were classified as positive (Eq(deep+)) by DL, 40 cases were classified by a second-round visual assessment, and 40 cases were classified by quantification. The DL- and quantification-based classifications showed good agreement (83%, κ = 0.59). The composite SUVRs differed between Eq(deep+) (1.47 [0.13]) and Eq(deep-) (1.29 [0.10]; P < 0.001). DL, but not the visual rating, showed a significant difference in the Mini-Mental Status Examination score change during the follow-up between Eq(deep+) (- 4.21 [0.57]) and Eq(deep-) (- 1.74 [0.76]; P = 0.023) (mean duration, 1.76 years).

CONCLUSIONS : In visually equivocal scans, DL was more related to quantification than to visual assessment, and the negative cases selected by DL showed no decline in cognitive outcome. DL is useful for clinical diagnosis and prognosis assessment in subjects with visually equivocal amyloid scans.

Son Hye Joo, Oh Jungsu S, Oh Minyoung, Kim Soo Jong, Lee Jae-Hong, Roh Jee Hoon, Kim Jae Seung

2019-Dec-06

18F-florbetaben PET, Alzheimer’s disease, Amyloid, Deep learning, Equivocal scan

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

OBJECTIVES : The introduction of the 2016 WHO classification of CNS tumors has made the combined molecular and histopathological characterization of tumors a pivotal part of glioma patient management. Recent publications on radiogenomics-based prediction of the mutational status have demonstrated the predictive potential of imaging-based, non-invasive tissue characterization algorithms. Hence, the aim of this study was to assess the potential of multiparametric ¹⁸F-FET PET-MRI including MR fingerprinting accelerated with machine learning and radiomic algorithms to predict tumor grading and mutational status of patients with cerebral gliomas.

MATERIALS AND METHODS : 42 patients with suspected primary brain tumor without prior surgical or systemic treatment or biopsy underwent an ¹⁸F-FET PET-MRI examination. To differentiate the mutational status and the WHO grade of the cerebral tumors, support vector machine and random forest were trained with the radiomics signature of the multiparametric PET-MRI data including MR fingerprinting. Surgical sampling served as a gold standard for histopathological reference and assessment of mutational status.

RESULTS : The 5-fold cross-validated area under the curve in predicting the ATRX mutation was 85.1%, MGMT mutation was 75.7%, IDH1 was 88.7%, and 1p19q was 97.8%. The area under the curve of differentiating low-grade glioma vs. high-grade glioma was 85.2%.

CONCLUSION : ¹⁸F-FET PET-MRI and MR fingerprinting enable high-quality imaging-based tumor decoding and phenotyping for differentiation of low-grade vs. high-grade gliomas and for prediction of the mutational status of ATRX, IDH1, and 1p19q. These initial results underline the potential of ¹⁸F-FET PET-MRI to serve as an alternative to invasive tissue characterization.

Haubold Johannes, Demircioglu Aydin, Gratz Marcel, Glas Martin, Wrede Karsten, Sure Ulrich, Antoch Gerald, Keyvani Kathy, Nittka Mathias, Kannengiesser Stephan, Gulani Vikas, Griswold Mark, Herrmann Ken, Forsting Michael, Nensa Felix, Umutlu Lale

2019-Dec-06

1p19q, ATRX, FET PET, Glioma, IDH1, MR fingerprinting, PET-MRI, Radiomics

In Der Radiologe ; h5-index 0.0

BACKGROUND : Artificial intelligence (AI) is increasingly applied in the field of breast imaging.

OBJECTIVES : What are the main areas where AI is applied in breast imaging and what AI and computer-aided diagnosis (CAD) systems are already available?

MATERIALS AND METHODS : Basic literature and vendor-supplied information are screened for relevant information, which is then pooled, structured and discussed from the perspective of breast imaging.

RESULTS : Original CAD systems in mammography date almost 25 years back. They are much more widely applied in the United States than in Europe. The initial CAD systems exhibited limited diagnostic abilities and disproportionally high rates of false positive results. Since 2012, deep learning mechanisms have been applied and expand the application possibilities of AI.

CONCLUSION : To date there is no algorithm that has beyond doubt been proven to outperform double reporting by two certified breast radiologists. AI could, however, in the foreseeable future, take over the following tasks: preselection of abnormal examinations to substantially reduce workload of the radiologists by either excluding normal findings from human review or by replacing the double reader in screening. Furthermore, the establishment of radio-patho-genomic correlations and their translation into clinical practice is hardly conceivable without AI.

Bennani-Baiti B, Baltzer P A T

2019-Dec-06

Breast neoplasms, Computer-aided diagnosis, Early detection of cancer, Mammography, Screening

In Der Radiologe ; h5-index 0.0

BACKGROUND : The methods of machine learning and artificial intelligence are slowly but surely being introduced in everyday medical practice. In the future, they will support us in diagnosis and therapy and thus improve treatment for the benefit of the individual patient. It is therefore important to deal with this topic and to develop a basic understanding of it.

OBJECTIVES : This article gives an overview of the exciting and dynamic field of machine learning and serves as an introduction to some methods primarily from the realm of supervised learning. In addition to definitions and simple examples, limitations are discussed.

CONCLUSIONS : The basic principles behind the methods are simple. Nevertheless, due to their high dimensional nature, the factors influencing the results are often difficult or impossible to understand by humans. In order to build confidence in the new technologies and to guarantee their safe application, we need explainable algorithms and prospective effectiveness studies.

Kleesiek Jens, Murray Jacob M, Strack Christian, Kaissis Georgios, Braren Rickmer

2019-Dec-06

Artificial neural networks, Deep learning, Digital literacy, Machine learning, New technologies

In TAG. Theoretical and applied genetics. Theoretische und angewandte Genetik ; h5-index 0.0

Jiang Shuqin, Cheng Qian, Yan Jun, Fu Ran, Wang Xiangfeng

2019-Dec-06

In Scientific reports ; h5-index 158.0

Balu Aditya, Nallagonda Sahiti, Xu Fei, Krishnamurthy Adarsh, Hsu Ming-Chen, Sarkar Soumik

2019-Dec-06

In The Science of the total environment ; h5-index 0.0

Yadav Basant, Gupta Pankaj Kumar, Patidar Nitesh, Himanshu Sushil Kumar

2019-Nov-24

Artificial neural network, Genetic algorithm, Machine learning, Mutual information, Support vector machine, Urbanization

In Journal of biomechanics ; h5-index 0.0

Liang Liang, Mao Wenbin, Sun Wei

2019-Nov-26

Computational fluid dynamics, Deep neural network, Hemodynamic analysis, Machine learning

In Computational biology and chemistry ; h5-index 0.0

Apurva Mehta, Mazumdar Himanshu

2019-Nov-15

Evolutionary, Low identity, Protein secondary structure, Protein structural class, Random Forest, Structural classification of proteins (SCOP)

In Neuroscience ; h5-index 0.0

Moezzi Bahar, Pratti Latha Madhuri, Hordacre Brenton, Graetz Lynton, Berryman Carolyn, Lavrencic Louise M, Ridding Michael C, Keage Hannah A D, McDonnell Mark D, Goldsworthy Mitchell R

2019-Dec-01

aging, electroencephalography, functional connectivity, machine learning, resting-state

In The British journal of psychiatry : the journal of mental science ; h5-index 0.0

Brown Christian, Story Giles William, Mourão-Miranda Janaina, Baker Justin Taylor

2019-Dec-06

Artificial intelligence, biomarkers, information technologies, silicon valley, technology

In Cancer imaging : the official publication of the International Cancer Imaging Society ; h5-index 0.0

BACKGROUND : The Liver Imaging Reporting and Data System (LI-RADS) and European Association for the Study of the Liver (EASL) criteria are widely used for diagnosing hepatocellular carcinoma (HCC). Radiomics allows further quantitative tumor heterogeneity profiling. This study aimed to compare the diagnostic accuracies of the version 2018 (v2018) EASL, LI-RADS criteria and radiomics models for HCC in high-risk patients.

METHODS : Ethical approval by the institutional review board and informed consent were obtained for this study. From July 2015 to September 2018, consecutive high-risk patients were enrolled in our tertiary care hospital and underwent gadoxetic acid-enhanced magnetic resonance (MR) imaging and subsequent hepatic surgery. We constructed a multi-sequence-based three-dimensional whole-tumor radiomics signature by least absolute shrinkage and selection operator model and multivariate logistic regression analysis. The diagnostic accuracies of the radiomics signature was validated in an independent cohort and compared with the EASL and LI-RADS criteria reviewed by two independent radiologists.

RESULTS : Two hundred twenty-nine pathologically confirmed nodules (173 HCCs, mean size: 5.74 ± 3.17 cm) in 211 patients were included. Among them, 201 patients (95%) were infected with hepatitis B virus (HBV). The sensitivity and specificity were 73 and 71% for the radiomics signature, 91 and 71% for the EASL criteria, and 86 and 82% for the LI-RADS criteria, respectively. The areas under the receiver operating characteristic curves (AUCs) of the radiomics signature (0.810), LI-RADS (0.841) and EASL criteria (0.811) were comparable.

CONCLUSIONS : In HBV-predominant high-risk patients, the multi-sequence-based MR radiomics signature, v2018 EASL and LI-RADS criteria demonstrated comparable overall accuracies for HCC.

Jiang Hanyu, Liu Xijiao, Chen Jie, Wei Yi, Lee Jeong Min, Cao Likun, Wu Yuanan, Duan Ting, Li Xin, Ma Ling, Song Bin

2019-Dec-05

Carcinoma, Diagnosis, Gadolinium ethoxybenzyl DTPA, Guideline, Hepatocellular, Machine learning

In Acta neuropathologica communications ; h5-index 48.0

Wharton S B, Wang D, Parikh C, Matthews F E, Brayne C, Ince P G

2019-Dec-05

In Atherosclerosis ; h5-index 71.0

BACKGROUND AND AIMS : Intravascular ultrasound (IVUS)-derived morphological criteria are poor predictors of the functional significance of intermediate coronary stenosis. IVUS-based supervised machine learning (ML) algorithms were developed to identify lesions with a fractional flow reserve (FFR) ≤0.80 (vs. >0.80).

METHODS : A total of 1328 patients with 1328 non-left main coronary lesions were randomized into training and test sets in a 4:1 ratio. Masked IVUS images were generated by an automatic segmentation model, and 99 computed IVUS features and six clinical variables (age, gender, body surface area, vessel type, involved segment, and involvement of the proximal left anterior descending artery) were used for ML training with 5-fold cross-validation. Diagnostic performances of the binary classifiers (L2 penalized logistic regression, artificial neural network, random forest, AdaBoost, CatBoost, and support vector machine) for detecting ischemia-producing lesions were evaluated using the non-overlapping test samples.

RESULTS : In the classification of test set lesions into those with an FFR ≤0.80 vs. >0.80, the overall diagnostic accuracies for predicting an FFR ≤0.80 were 82% with L2 penalized logistic regression, 80% with artificial neural network, 83% with random forest, 83% with AdaBoost, 81% with CatBoost, and 81% with support vector machine (AUCs: 0.84-0.87). With exclusion of the 28 lesions with borderline FFR of 0.75-0.80, the overall accuracies for the test set were 86% with L2 penalized logistic regression, 85% with an artificial neural network, 87% with random forest, 87% with AdaBoost, 85% with CatBoost, and 85% with support vector machine.

CONCLUSIONS : The IVUS-based ML algorithms showed good diagnostic performance for identifying ischemia-producing lesions, and may reduce the need for pressure wires.

Lee June-Goo, Ko Jiyuon, Hae Hyeonyong, Kang Soo-Jin, Kang Do-Yoon, Lee Pil Hyung, Ahn Jung-Min, Park Duk-Woo, Lee Seung-Whan, Kim Young-Hak, Lee Cheol Whan, Park Seong-Wook, Park Seung-Jung

2019-Nov-02

Artificial intelligence, Fractional flow reserve, Intravascular ultrasound, Machine learning

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

BACKGROUND : Machine learning can assist with multiple tasks during systematic reviews to facilitate the rapid retrieval of relevant references during screening and to identify and extract information relevant to the study characteristics, which include the PICO elements of patient/population, intervention, comparator, and outcomes. The latter requires techniques for identifying and categorising fragments of text, known as named entity recognition.

METHODS : A publicly available corpus of PICO annotations on biomedical abstracts is used to train a named entity recognition model, which is implemented as a recurrent neural network. This model is then applied to a separate collection of abstracts for references from systematic reviews within biomedical and health domains. The occurrences of words tagged in the context of specific PICO contexts are used as additional features for a relevancy classification model. Simulations of the machine learning-assisted screening are used to evaluate the work saved by the relevancy model with and without the PICO features. Chi-squared and statistical significance of positive predicted values are used to identify words that are more indicative of relevancy within PICO contexts.

RESULTS : Inclusion of PICO features improves the performance metric on 15 of the 20 collections, with substantial gains on certain systematic reviews. Examples of words whose PICO context are more precise can explain this increase.

CONCLUSIONS : Words within PICO tagged segments in abstracts are predictive features for determining inclusion. Combining PICO annotation model into the relevancy classification pipeline is a promising approach. The annotations may be useful on their own to aid users in pinpointing necessary information for data extraction, or to facilitate semantic search.

Brockmeier Austin J, Ju Meizhi, Przybyła Piotr, Ananiadou Sophia

2019-Dec-05

Active learning, Evidence-based medicine, Logistic regression, Machine learning, Systematic review, Text mining

In Genomics, proteomics & bioinformatics ; h5-index 0.0

Li Xiang, Guo Ning, Li Quanzheng

2019-Dec-03

Big data, Health informatics, Machine learning, Neuroimaging, fMRI

In Genomics, proteomics & bioinformatics ; h5-index 0.0

Ludwig Nicole, Fehlmann Tobias, Kern Fabian, Gogol Manfred, Maetzler Walter, Deutscher Stephanie, Gurlit Simone, Schulte Claudia, von Thaler Anna-Katharina, Deuschle Christian, Metzger Florian, Berg Daniela, Suenkel Ulrike, Keller Verena, Backes Christina, Lenhof Hans-Peter, Meese Eckart, Keller Andreas

2019-Dec-03

Alzheimer’s disease, Biomarker, Gene regulation, Neurodegeneration, Non-coding RNAs, miRNAs

In Journal of microbiological methods ; h5-index 0.0

Marongiu Luigi, Shain Eric, Shain Kevin, Allgayer Heike

2019-Dec-03

Assay accuracy, High throughput, SVM, Validation, maxRatio, qPCR

In Spine ; h5-index 57.0

STUDY DESIGN : Retrospective analysis of magnetic resonance imaging (MRI) OBJECTIVE.: To evaluate the performance of our convolutional neural network (CNN) in differentiating between spinal schwannoma and meningioma on MRI. We compared the performance of the CNN and that of two expert radiologists.

SUMMARY OF BACKGROUND DATA : Preoperative discrimination between spinal schwannomas and meningiomas is crucial because different surgical procedures are required for their treatment. A deep-learning approach based on CNNs is gaining interest in the medical imaging field.

METHODS : We retrospectively reviewed data from patients with spinal schwannoma and meningioma who had undergone MRI and tumor resection. There were 50 patients with schwannoma and 34 patients with meningioma. Sagittal T2-weighted magnetic resonance imaging (T2WI) and sagittal contrast-enhanced T1-weighted magnetic resonance imaging (T1WI) were used for the CNN training and validation. The deep learning framework Tensorflow were used to construct the CNN architecture. To evaluate the performance of the CNN, we plotted the receiver operating characteristic (ROC) curve and calculated the area under the curve (AUC). We calculated and compared the sensitivity, specificity, and accuracy of the diagnosis by the CNN and two board-certified radiologists.

RESULTS : . The AUC of ROC curves of the CNN based on T2WI and contrast-enhanced T1WI were 0.876 and 0.870, respectively. The sensitivity of the CNN based on T2WI was 78%; 100% for radiologist 1; and 95% for radiologist 2. The specificity was 82%, 26%, and 42%, respectively. The accuracy was 80%, 69%, and 73%, respectively. By contrast, the sensitivity of the CNN based on contrast-enhanced T1WI was 85%; 100% for radiologist 1; and 96% for radiologist 2. The specificity was 75%, 56, and 58%, respectively. The accuracy was 81, 82, and 81%, respectively.

CONCLUSIONS : We have successfully differentiated spinal schwannomas and meningiomas using the CNN with high diagnostic accuracy comparable to that of experienced radiologists.

LEVEL OF EVIDENCE : 4.

Maki Satoshi, Furuya Takeo, Horikoshi Takuro, Yokota Hajime, Mori Yasukuni, Ota Joji, Kawasaki Yohei, Miyamoto Takuya, Norimoto Masaki, Okimatsu Sho, Shiga Yasuhiro, Inage Kazuhide, Orita Sumihisa, Takahashi Hiroshi, Suyari Hiroki, Uno Takashi, Ohtori Seiji

2019-Dec-05

In The journal of physical chemistry. A ; h5-index 0.0

Nayak Sanjay, Bhattacharjee Satadeep, Choi Jung-Hae, Lee Seung-Cheol

2019-Dec-06

In Journal of chemical information and modeling ; h5-index 0.0

Li Yibo, Hu Jianxing, Wang Yanxing, Zhang Liang-Ren, Zhou Jielong, Liu Zhen-Ming

2019-Dec-06

In Analytical chemistry ; h5-index 0.0

Huang Ying-Chen, Chung Hsin-Hsiang, Dutkiewicz Ewelina, Chen Chih-Lin, Hsieh Hua-Yi, Chen Bo-Rong, Wang Ming-Yang, Hsu Cheng-Chih

2019-Dec-06

In British journal of haematology ; h5-index 64.0

Haferlach Torsten, Schmidts Ines

2019-Dec-06

AML diagnosis and management, acute myeloid leukaemia, artificial intelligence, multidisciplinary diagnostics, precision medicine

In Medical physics ; h5-index 59.0

PURPOSE : Various dose calculation algorithms are available for radiation therapy for cancer patients. However, these algorithms are faced with the tradeoff between efficiency and accuracy. The fast algorithms are generally less accurate, while the accurate dose engines are often time consuming. In this work, we try to resolve this dilemma by exploring deep learning (DL) for dose calculation.

METHODS : We developed a new radiotherapy dose calculation engine based on a modified Hierarchically Densely Connected U-net (HD U-net) model and tested its feasibility with prostate intensity-modulated radiation therapy (IMRT) cases. Mapping from an IMRT fluence map domain to a 3D dose domain requires a deep neural network of complicated architecture and a huge training dataset. To solve this problem, we first project the fluence maps to the dose domain using a broad beam ray-tracing algorithm, and then we use the HD U-net to map the ray-tracing dose distribution into an accurate dose distribution calculated using a collapsed cone convolution/superposition (CS) algorithm. The model is trained on 70 patients with 5-fold cross validation, and tested on a separate 8 patients.

RESULTS : It takes about one second to compute a 3D dose distribution for a typical 7-field prostate IMRT plan, which can be further reduced to achieve real-time dose calculation by optimizing the network. The average Gamma passing rate between DL and CS dose distributions for the 8 test patients are 98.5% (±1.6%) at 1mm/1% and 99.9% (±0.1%) at 2mm/2%. For comparison of various clinical evaluation criteria (dose-volume points) for IMRT plans between two dose distributions, the average difference for dose criteria is less than 0.25 Gy while for volume criteria is less than 0.16%, showing that the DL dose distributions are clinically identical to the CS dose distributions.

CONCLUSIONS : We have shown the feasibility of using DL for calculating radiotherapy dose distribution with high accuracy and efficiency.

Xing Yixun, Nguyen Dan, Lu Weiguo, Yang Ming, Jiang Steve

2019-Dec-06

Deep learning, Dose calculation, Radiotherapy

In Bioinformatics (Oxford, England) ; h5-index 0.0

MOTIVATION : Spatial transcriptomics technology is increasingly being applied because it enables the measurement of spatial gene expression in an intact tissue along with imaging morphology of the same tissue. However, current analysis methods for spatial transcriptomics data do not use image pixel information, thus missing the quantitative links between gene expression and tissue morphology.

RESULTS : We developed a user-friendly deep learning software, SpaCell, to integrate millions of pixel intensity values with thousands of gene expression measurements from spatially-barcoded spots in a tissue. We show the integration approach outperforms the use of gene-count data alone or imaging data alone to build deep learning models to identify cell types or predict labels of tissue images with high resolution and accuracy.

AVAILABILITY : The SpaCell package is open source under a MIT license and it is available at https://github.com/BiomedicalMachineLearning/SpaCell.

SUPPLEMENTARY INFORMATION : Supplementary data are available at Bioinformatics online.

Tan Xiao, Su Andrew, Tran Minh, Nguyen Quan

2019-Dec-06

In Stroke ; h5-index 83.0

Dhar Rajat, Falcone Guido J, Chen Yasheng, Hamzehloo Ali, Kirsch Elayna P, Noche Rommell B, Roth Kilian, Acosta Julian, Ruiz Andres, Phuah Chia-Ling, Woo Daniel, Gill Thomas M, Sheth Kevin N, Lee Jin-Moo

2019-Dec-06

biology, biomarkers, brain edema, cerebral hemorrhage, deep learning

In Journal of endourology ; h5-index 0.0

Ikeda Atsushi, Nosato Hirokazu, Kochi Yuta, Kojima Takahiro, Kawai Koji, Sakanashi Hidenori, Murakawa Masahiro, Nishiyama Hiroyuki

2019-Dec-06

In Environmental monitoring and assessment ; h5-index 0.0

Sheehan Emma V, Bridger Danielle, Nancollas Sarah J, Pittman Simon J

2019-Dec-05

Monitoring, aquaculture, ecosystem function, motion detection, mussel farm, pelagic, video analysis

In Annals of biomedical engineering ; h5-index 52.0

Casella Alessandro, Moccia Sara, Frontoni Emanuele, Paladini Dario, De Momi Elena, Mattos Leonardo S

2019-Dec-05

Adversarial networks, Deep learning, Fetoscopy, Intraoperative-image segmentation

In Metabolomics : Official journal of the Metabolomic Society ; h5-index 0.0

INTRODUCTION : With chronic kidney disease (CKD), kidney becomes damaged overtime and fails to clean blood. Around 15% of US adults have CKD and nine in ten adults with CKD do not know they have it.

OBJECTIVE : Early prediction and accurate monitoring of CKD may improve care and decrease the frequent progression to end-stage renal disease. There is an urgent demand to discover specific biomarkers that allow for monitoring of early-stage CKD, and response to treatment.

METHOD : To discover such biomarkers, shotgun high throughput was applied to the detection of serum metabolites biomarker discovery for early stages of CKD from 703 participants. Ultra performance liquid chromatography coupled with high-definition mass spectrometry (UPLC-HDMS)-based metabolomics was used for the determination of 703 fasting serum samples from five stages of CKD patients and age-matched healthy controls.

RESULTS AND CONCLUSION : We discovered a set of metabolite biomarkers using a series of classic and neural network based machine learning techniques. This set of metabolites can separate early CKD stage patents from normal subjects with high accuracy. Our study illustrates the power of machine learning methods in metabolite biomarker study.

Guo Yan, Yu Hui, Chen Danqian, Zhao Ying-Yong

2019-Dec-05

Chronic kidney disease, Deep learning, Glomerular filtration rate, Machine learning, Metabolite

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

INTRODUCTION : Immunotherapy has improved outcomes for patients with non-small cell lung cancer (NSCLC), yet durable clinical benefit (DCB) is experienced in only a fraction of patients. Here, we test the hypothesis that radiomics features from baseline pretreatment ¹⁸F-FDG PET/CT scans can predict clinical outcomes of NSCLC patients treated with checkpoint blockade immunotherapy.

METHODS : This study included 194 patients with histologically confirmed stage IIIB-IV NSCLC with pretreatment PET/CT images. Radiomics features were extracted from PET, CT, and PET+CT fusion images based on minimum Kullback-Leibler divergence (KLD) criteria. The radiomics features from 99 retrospective patients were used to train a multiparametric radiomics signature (mpRS) to predict DCB using an improved least absolute shrinkage and selection operator (LASSO) method, which was subsequently validated in both retrospective (N = 47) and prospective test cohorts (N = 48). Using these cohorts, the mpRS was also used to predict progression-free survival (PFS) and overall survival (OS) by training nomogram models using multivariable Cox regression analyses with additional clinical characteristics incorporated.

RESULTS : The mpRS could predict patients who will receive DCB, with areas under receiver operating characteristic curves (AUCs) of 0.86 (95%CI 0.79-0.94), 0.83 (95%CI 0.71-0.94), and 0.81 (95%CI 0.68-0.92) in the training, retrospective test, and prospective test cohorts, respectively. In the same three cohorts, respectively, nomogram models achieved C-indices of 0.74 (95%CI 0.68-0.80), 0.74 (95%CI 0.66-0.82), and 0.77 (95%CI 0.69-0.84) to predict PFS and C-indices of 0.83 (95%CI 0.77-0.88), 0.83 (95%CI 0.71-0.94), and 0.80 (95%CI 0.69-0.91) to predict OS.

CONCLUSION : PET/CT-based signature can be used prior to initiation of immunotherapy to identify NSCLC patients most likely to benefit from immunotherapy. As such, these data may be leveraged to improve more precise and individualized decision support in the treatment of patients with advanced NSCLC.

Mu Wei, Tunali Ilke, Gray Jhanelle E, Qi Jin, Schabath Matthew B, Gillies Robert J

2019-Dec-05

Immunotherapy, Machine learning, Non-small cell lung cancer (NSCLC), PET/CT, Radiomics

In Annals of translational medicine ; h5-index 0.0

Zhang Zhongheng, Mo Lei, Huang Chen, Xu Ping

2019-Oct

Logistic regression, TensorFlow, gradient descent

In Risk management and healthcare policy ; h5-index 0.0

Background : This study proposes the use of machine learning algorithms to improve the accuracy of type 2 diabetes predictions using non-invasive risk score systems.

Methods : We evaluated and compared the prediction accuracies of existing non-invasive risk score systems using the data from the REACTION study (Risk Evaluation of Cancers in Chinese Diabetic Individuals: A Longitudinal Study). Two simple risk scores were established on the bases of logistic regression. Machine learning techniques (ensemble methods) were used to improve prediction accuracies by combining the individual score systems.

Results : Existing score systems from Western populations performed worse than the scores from Eastern populations in general. The two newly established score systems performed better than most existing scores systems but a little worse than the Chinese score system. Using ensemble methods with model selection algorithms yielded better prediction accuracy than all the simple score systems.

Conclusion : Our proposed machine learning methods can be used to improve the accuracy of screening the undiagnosed type 2 diabetes and identifying the high-risk patients.

Liu Yujia, Ye Shangyuan, Xiao Xianchao, Sun Chenglin, Wang Gang, Wang Guixia, Zhang Bo

2019

machine learning, prediction, risk score, stacking, type 2 diabetes, voting

In The journal of glaciology ; h5-index 0.0

Scheick Jessica, Enderlin Ellyn M, Hamilton Gordon

2019-Jun

calving, ice-ocean interactions, icebergs, remote sensing

In Proceedings of the National Academy of Sciences of the United States of America ; h5-index 0.0

Northcutt Adam J, Kick Daniel R, Otopalik Adriane G, Goetz Benjamin M, Harris Rayna M, Santin Joseph M, Hofmann Hans A, Marder Eve, Schulz David J

2019-Dec-05

RNA-seq, expression profiling, qPCR, stomatogastric

In Journal of autoimmunity ; h5-index 65.0

Catalina Michelle D, Owen Katherine A, Labonte Adam C, Grammer Amrie C, Lipsky Peter E

2019-Dec-02

Autoimmune disease, Epigenetics, Gene expression, Genome wide association study, Machine learning, Systemic lupus erythematosus

In Healthcare management forum ; h5-index 0.0

Randhawa Gurprit K, Jackson Mary

2020-Jan

In Der Radiologe ; h5-index 0.0

CLINICAL/METHODICAL ISSUE : In view of the diagnostic complexity and the large number of examinations, modern radiology is challenged to identify clinically significant prostate cancer (PCa) with high sensitivity and specificity. Meanwhile overdiagnosis and overtreatment of clinically nonsignificant carcinomas need to be avoided.

STANDARD RADIOLOGICAL METHODS : Increasingly, international guidelines recommend multiparametric magnetic resonance imaging (mpMRI) as first-line investigation in patients with suspected PCa.

METHODICAL INNOVATIONS : Image interpretation according to the PI-RADS criteria is limited by interobserver variability. Thus, rapid developments in the field of automated image analysis tools, including radiomics and artificial intelligence (AI; machine learning, deep learning), give hope for further improvement in patient care.

PERFORMANCE : AI focuses on the automated detection and classification of PCa, but it also attempts to stratify tumor aggressiveness according to the Gleason score. Recent studies present good to very good results in radiomics or AI-supported mpMRI diagnosis. Nevertheless, these systems are not widely used in clinical practice.

ACHIEVEMENTS AND PRACTICAL RECOMMENDATIONS : In order to apply these innovative technologies, a growing awareness for the need of structured data acquisition, development of robust systems and an increased acceptance of AI as diagnostic support are needed. If AI overcomes these obstacles, it may play a key role in the quantitative and reproducible image-based diagnosis of ever-increasing prostate MRI examination volumes.

Hamm Charlie Alexander, Beetz Nick Lasse, Savic Lynn Jeanette, Penzkofer Tobias

2019-Dec-04

Deep learning, Machine learning, Multiparametric magnetic resonance imaging, Prostate cancer, Quantitative imaging

In Database : the journal of biological databases and curation ; h5-index 0.0

Zheng Lei, Huang Shenghui, Mu Nengjiang, Zhang Haoyue, Zhang Jiayu, Chang Yu, Yang Lei, Zuo Yongchun

2019-Jan-01

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

BACKGROUND : Clinical named entity recognition (CNER) is important for medical information mining and establishment of high-quality knowledge map. Due to the different text features from natural language and a large number of professional and uncommon clinical terms in Chinese electronic medical records (EMRs), there are still many difficulties in clinical named entity recognition of Chinese EMRs. It is of great importance to eliminate semantic interference and improve the ability of autonomous learning of internal features of the model under the small training corpus.

METHODS : From the perspective of deep learning, we integrated the attention mechanism into neural network, and proposed an improved clinical named entity recognition method for Chinese electronic medical records called BiLSTM-Att-CRF, which could capture more useful information of the context and avoid the problem of missing information caused by long-distance factors. In addition, medical dictionaries and part-of-speech (POS) features were also introduced to improve the performance of the model.

RESULTS : Based on China Conference on Knowledge Graph and Semantic Computing (CCKS) 2017 and 2018 Chinese EMRs corpus, our BiLSTM-Att-CRF model finally achieved better performance than other widely-used models without additional features(F1-measure of 85.4% in CCKS 2018, F1-measure of 90.29% in CCKS 2017), and achieved the best performance with POS and dictionary features (F1-measure of 86.11% in CCKS 2018, F1-measure of 90.48% in CCKS 2017). In particular, the BiLSTM-Att-CRF model had significant effect on the improvement of Recall.

CONCLUSIONS : Our work preliminarily confirmed the validity of attention mechanism in discovering key information and mining text features, which might provide useful ideas for future research in clinical named entity recognition of Chinese electronic medical records. In the future, we will explore the deeper application of attention mechanism in neural network.

Li Luqi, Zhao Jie, Hou Li, Zhai Yunkai, Shi Jinming, Cui Fangfang

2019-Dec-05

Attention mechanism, Chinese electronic medical records, Named entity recognition

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

BACKGROUND : Accurately recognizing rare diseases based on symptom description is an important task in patient triage, early risk stratification, and target therapies. However, due to the very nature of rare diseases, the lack of historical data poses a great challenge to machine learning-based approaches. On the other hand, medical knowledge in automatically constructed knowledge graphs (KGs) has the potential to compensate the lack of labeled training examples. This work aims to develop a rare disease classification algorithm that makes effective use of a knowledge graph, even when the graph is imperfect.

METHOD : We develop a text classification algorithm that represents a document as a combination of a "bag of words" and a "bag of knowledge terms," where a "knowledge term" is a term shared between the document and the subgraph of KG relevant to the disease classification task. We use two Chinese disease diagnosis corpora to evaluate the algorithm. The first one, HaoDaiFu, contains 51,374 chief complaints categorized into 805 diseases. The second data set, ChinaRe, contains 86,663 patient descriptions categorized into 44 disease categories.

RESULTS : On the two evaluation data sets, the proposed algorithm delivers robust performance and outperforms a wide range of baselines, including resampling, deep learning, and feature selection approaches. Both classification-based metric (macro-averaged F₁ score) and ranking-based metric (mean reciprocal rank) are used in evaluation.

CONCLUSION : Medical knowledge in large-scale knowledge graphs can be effectively leveraged to improve rare diseases classification models, even when the knowledge graph is incomplete.

Li Xuedong, Wang Yue, Wang Dongwu, Yuan Walter, Peng Dezhong, Mei Qiaozhu

2019-Dec-05

Extremely imbalanced data, Knowledge graph, Machine learning, Rare disease diagnosis, Text classification

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

BACKGROUND : To detect attributes of medical concepts in clinical text, a traditional method often consists of two steps: named entity recognition of attributes and then relation classification between medical concepts and attributes. Here we present a novel solution, in which attribute detection of given concepts is converted into a sequence labeling problem, thus attribute entity recognition and relation classification are done simultaneously within one step.

METHODS : A neural architecture combining bidirectional Long Short-Term Memory networks and Conditional Random fields (Bi-LSTMs-CRF) was adopted to detect various medical concept-attribute pairs in an efficient way. We then compared our deep learning-based sequence labeling approach with traditional two-step systems for three different attribute detection tasks: disease-modifier, medication-signature, and lab test-value.

RESULTS : Our results show that the proposed method achieved higher accuracy than the traditional methods for all three medical concept-attribute detection tasks.

CONCLUSIONS : This study demonstrates the efficacy of our sequence labeling approach using Bi-LSTM-CRFs on the attribute detection task, indicating its potential to speed up practical clinical NLP applications.

Xu Jun, Li Zhiheng, Wei Qiang, Wu Yonghui, Xiang Yang, Lee Hee-Jin, Zhang Yaoyun, Wu Stephen, Xu Hua

2019-Dec-05

Clinical notes, Information extraction, Natural language processing

In Klinische Monatsblatter fur Augenheilkunde ; h5-index 0.0

BACKGROUND : Human corneal grafts from organ culture need to have more than 2000 endothelial cells/mm² to be suitable for transplantation. Measurement of the endothelial cell density is complicated by invisible cell borders in phase contrast microscopy, as well as by limited areas for counting due to folds in the Descemet membrane of the swollen corneal grafts. To date, no automated counting method for measuring the endothelial cell density exists. The neuronal network U-Net has already proven itself in automated segmentation of specular microscopy images of human corneal endothelium. The aim of this study was the application of the U-Net in the quality control of human corneal grafts.

MATERIAL AND METHODS : Training of the U-Net was performed using 100 manually tagged endothelial cell images of corneal grafts from the Lions eye bank in Baden-Württemberg. Another 100 images were obtained for testing the precision of measurements of the U-Net. These were adjudged manually by a) an experienced investigator and b) a less experienced ophthalmologist. The endothelial cells in identical images were then counted automatically by the trained U-Net. Comparison with the manually counted results was drawn by Pearson correlation.

RESULTS : The correlation coefficient between the U-Net and the experienced investigator as gold standard was 0.9. The correlation coefficient between the less experienced ophthalmologist and the gold standard was only 0.81. Both correlations were statistically highly significant (p < 0.0001).

DISCUSSION : The strong correlation between the U-Net and the gold standard points out that, given medical approval, effective assistance for eye banks is possible in quality control by automated counting. This could improve objectivity and efficiency of work flow.

Heinzelmann Sonja, Daniel Moritz Claudius, Maier Philip Christian, Reinhard Thomas, Böhringer Daniel

2019-Dec

In Klinische Monatsblatter fur Augenheilkunde ; h5-index 0.0

Reisdorf Sven

2019-Dec

In Journal of physics. Condensed matter : an Institute of Physics journal ; h5-index 0.0

Lentz Levi, Kolpak Alexie

2019-Dec-05

band gap, density functional theory, machine learning

In Nurse education in practice ; h5-index 36.0

Rodger Daniel, Stewart-Lord Adéle

2019-Nov-23

Debate, Education, Healthcare professionals, Organ donation, Qualitative

In Genomics, proteomics & bioinformatics ; h5-index 0.0

Chen Shanyu, He Zhipeng, Han Xinyin, He Xiaoyu, Li Ruilin, Zhu Haidong, Zhao Dan, Dai Chuangchuang, Zhang Yu, Lu Zhonghua, Chi Xuebin, Niu Beifang

2019-Dec-02

Big data, Brain connectomes, Brain science, Deep learning, High-performance computing

In International journal of biological macromolecules ; h5-index 0.0

Hasan Md Mehedi, Manavalan Balachandran, Khatun Mst Shamima, Kurata Hiroyuki

2019-Dec-02

DNA methylation, Linear regression, Machine learning, N4-methylcytosine site, Sequence encoding

In PloS one ; h5-index 176.0

Amarbayasgalan Tsatsral, Park Kwang Ho, Lee Jong Yun, Ryu Keun Ho

2019

In PloS one ; h5-index 176.0

Punjabi Arjun, Martersteck Adam, Wang Yanran, Parrish Todd B, Katsaggelos Aggelos K

2019