In Mathematical biosciences and engineering : MBE

Liang Xiao, Qi Tai Yue, Jin Zhi Yi, Qian Wang Ping

2020-Jun-01

** hybrid support vector machine , inversion method , particle swarm optimization , transient electromagnetic method **

In Mathematical biosciences and engineering : MBE

Zhou Guo, Li Jie, Tang Zhong Hua, Luo Qi Fang, Zhou Yong Quan

2020-May-25

** PID parameter optimization , metaheuristic , nonlinear convergence factor , opposition-based learning , spotted hyena optimizer **

In Seminars in musculoskeletal radiology

Visser Jacob J, Goergen Stacy K, Klein Stefan, Noguerol Teodoro Martín, Pickhardt Perry J, Fayad Laura M, Omoumi Patrick

2020-Aug

In Seminars in musculoskeletal radiology

Liu Fang

2020-Aug

In Physiological measurement ; h5-index 36.0

OBJECTIVE : We present a framework for analyzing the intracranial pressure (ICP) morphology. Analyzing ICP signals is challenging due to the non-linear and non-Gaussian characteristics of the signal dynamics, inevitable corruption with noise and artifacts, and variations in the ICP pulse morphology among individuals with different neurological conditions. Existing frameworks make unrealistic assumptions regarding ICP dynamics and are not tuned for individual patients.

APPROACH : We propose a dynamic Bayesian network (DBN) for automated detection of three major ICP pulsatile components. The proposed model captures the non-linear and non-Gaussian dynamics of the ICP morphology and further adapts to a patient as the individual's ICP measurements are received. To make the approach more robust, we leverage evidence reversal and present an inference algorithm to obtain the posterior distribution over the locations of pulsatile components.

RESULTS : We evaluate our approach on a dataset with over 700 hours of recordings from 66 neurological patients, where the pulsatile components have been annotated in prior studies. The algorithm obtains an accuracy of 96.56%, 92.39%, and 94.04% for detecting each pulsatile component on the test set, showing significant improvements over existing approaches.

SIGNIFICANCE : Continuous ICP monitoring is essential in guiding the treatment of neurological conditions such as traumatic brain injuries. An automated approach for ICP morphology analysis takes a step toward enhancing patient care with minimal supervision. Compared to previous methods, our framework offers several advantages. It learns the parameters that model each patient's ICP in an unsupervised manner, resulting in an accurate morphology analysis. The Bayesian model-based framework provides uncertainty estimates and reveals interesting facts about ICP dynamics. The framework can be readily applied to replace existing morphological analysis methods and support the application of ICP pulse morphological features to aid the monitoring of pathophysiological changes of relevance to the care of patients with acute brain injuries.

Rashidinejad Paria, Hu Xiao, Russell Stuart

2020-Sep-29

Artificial Intelligence in Healthcare, Dynamic Bayesian Network, ICP, Model-Based Probabilistic Inference, Particle Filter, Patient Monitoring

In Journal of stroke and cerebrovascular diseases : the official journal of National Stroke Association

OBJECTIVES : Moyamoya disease is a unique cerebrovascular disorder that is characterized by chronic bilateral stenosis of the internal carotid arteries and by the formation of an abnormal vascular network called moyamoya vessels. In this stury, the authors inspected whether differentiation between patients with moyamoya disease and those with atherosclerotic disease or normal controls might be possible by using deep machine learning technology.

MATERIALS AND METHODS : This study included 84 consecutive patients diagnosed with moyamoya disease at our hospital between April 2009 and July 2016. In each patient, two axial continuous slices of T2-weighed imaging at the level of the basal cistern, basal ganglia, and centrum semiovale were acquired. The image sets were processed by using code written in the programming language Python 3.7. Deep learning with fine tuning developed using VGG16 comprised several layers.

RESULTS : The accuracies of distinguishing between patients with moyamoya disease and those with atherosclerotic disease or controls in the basal cistern, basal ganglia, and centrum semiovale levels were 92.8, 84.8, and 87.8%, respectively.

CONCLUSION : The authors showed excellent results in terms of accuracy of differential diagnosis of moyamoya disease using AI with the conventional T2 weighted images. The authors suggest the possibility of diagnosing moyamoya disease using AI technique and demonstrate the area of interest on which AI focuses while processing magnetic resonance images.

Akiyama Yukinori, Mikami Takeshi, Mikuni Nobuhiro

2020-Sep-25

Artificial intelligence, Deep learning, Diagnostic accuracy, Moyamoya disease

In Journal of stroke and cerebrovascular diseases : the official journal of National Stroke Association

BACKGROUND AND PURPOSE : Accurate prediction using simple and changeable variables is clinically meaningful because some known-predictors, such as stroke severity and patients age cannot be modified with rehabilitative treatment. There are limited clinical prediction rules (CPRs) that have been established using only changeable variables to predict the activities of daily living (ADL) dependence of stroke patients. This study aimed to develop and assess the CPRs using machine learning-based methods to identify ADL dependence in stroke patients.

METHODS : In total, 1125 stroke patients were investigated. We used a maintained database of all stroke patients who were admitted to the convalescence rehabilitation ward of our facility. The classification and regression tree (CART) methodology with only the FIM subscores was used to predict the ADL dependence.

RESULTS : The CART method identified FIM transfer (bed, chair, and wheelchair) (score ≤ 4.0 or > 4.0) as the best single discriminator for ADL dependence. Among those with FIM transfer (bed, chair, and wheelchair) score > 4.0, the next best predictor was FIM bathing (score ≤ 2.0 or > 2.0). Among those with FIM transfer (bed, chair, and wheelchair) score ≤ 4.0, the next predictor was FIM transfer toilet (score ≤ 3 or > 3). The accuracy of the CART model was 0.830 (95% confidence interval, 0.804-0.856).

CONCLUSION : Machine learning-based CPRs with moderate predictive ability for the identification of ADL dependence in the stroke patients were developed.

Iwamoto Yuji, Imura Takeshi, Tanaka Ryo, Imada Naoki, Inagawa Tetsuji, Araki Hayato, Araki Osamu

2020-Sep-26

Activities of daily living, Decision-tree analysis, Prediction, Rehabilitation, Stroke

In Journal of stroke and cerebrovascular diseases : the official journal of National Stroke Association

OBJECTIVE : To build radiomic model in differentiating dissecting aneurysm (DA) from complicated saccular aneurysm (SA) based on high-resolution magnetic resonance imaging (HR-MRI) through machine-learning algorithm.

METHODS : Overall, 851 radiomic features from 77 cases were retrospectively analyzed, and the ElasticNet algorithm was used to build the radiomic model. A clinico-radiological model using clinical features and conventional MRI findings was also built. An integrated model was then built by incorporating the radiomic model and clinico-radiological model. The diagnostic abilities of these models were evaluated using leave one out cross validation and quantified using the receiver operating characteristic (ROC) analysis. The diagnostic performance of radiologists was also evaluated for comparison.

RESULTS : Five features were used to form the radiomic model, which yielded an area under the ROC curve (AUC) of 0.912 (95 % CI 0.846-0.976), sensitivity of 0.852, and specificity of 0.861. The radiomic model achieved a better diagnostic performance than the clinico-radiological model (AUC=0.743, 95 % CI 0.623-0.862), integrated model (AUC=0.888, 95 % CI 0.811-0.965), and even many radiologists.

CONCLUSION : Radiomic features derived from HR-MRI can reliably be used to build a radiomic model for effectively differentiating between DA and complicated SA, and it can provide an objective basis for the selection of clinical treatment plan.

Cao Xin, Xia Wei, Tang Ye, Zhang Bo, Yang Jinming, Zeng Yanwei, Geng Daoying, Zhang Jun

2020-Sep-08

Aneurysm, High-resolution magnetic resonance imaging, Machine-learning, Radiomics

In Computers in biology and medicine

BACKGROUND : Hypertension (HPT) occurs when there is increase in blood pressure (BP) within the arteries, causing the heart to pump harder against a higher afterload to deliver oxygenated blood to other parts of the body.

PURPOSE : Due to fluctuation in BP, 24-h ambulatory blood pressure monitoring has emerged as a useful tool for diagnosing HPT but is limited by its inconvenience. So, an automatic diagnostic tool using electrocardiogram (ECG) signals is used in this study to detect HPT automatically.

METHOD : The pre-processed signals are fed to a convolutional neural network model. The model learns and identifies unique ECG signatures for classification of normal and hypertension ECG signals. The proposed model is evaluated by the 10-fold and leave one out patient based validation techniques.

RESULTS : A high classification accuracy of 99.99% is achieved for both validation techniques. This is one of the first few studies to have employed deep learning algorithm coupled with ECG signals for the detection of HPT. Our results imply that the developed tool is useful in a hospital setting as an automated diagnostic tool, enabling the effortless detection of HPT using ECG signals.

Soh Desmond Chuang Kiat, Ng E Y K, Jahmunah V, Oh Shu Lih, Tan Ru San, Acharya U Rajendra

2020-Sep-17

10-Fold validation, Automated diagnostic tool, Convolutional neural network, Hypertension, Leave one patient out validation, Masked hypertension

In International journal of medical informatics ; h5-index 49.0

OBJECTIVE : This study aims to develop and test a new computer-aided diagnosis (CAD) scheme of chest X-ray images to detect coronavirus (COVID-19) infected pneumonia.

METHOD : CAD scheme first applies two image preprocessing steps to remove the majority of diaphragm regions, process the original image using a histogram equalization algorithm, and a bilateral low-pass filter. Then, the original image and two filtered images are used to form a pseudo color image. This image is fed into three input channels of a transfer learning-based convolutional neural network (CNN) model to classify chest X-ray images into 3 classes of COVID-19 infected pneumonia, other community-acquired no-COVID-19 infected pneumonia, and normal (non-pneumonia) cases. To build and test the CNN model, a publicly available dataset involving 8474 chest X-ray images is used, which includes 415, 5179 and 2,880 cases in three classes, respectively. Dataset is randomly divided into 3 subsets namely, training, validation, and testing with respect to the same frequency of cases in each class to train and test the CNN model.

RESULTS : The CNN-based CAD scheme yields an overall accuracy of 94.5 % (2404/2544) with a 95 % confidence interval of [0.93,0.96] in classifying 3 classes. CAD also yields 98.4 % sensitivity (124/126) and 98.0 % specificity (2371/2418) in classifying cases with and without COVID-19 infection. However, without using two preprocessing steps, CAD yields a lower classification accuracy of 88.0 % (2239/2544).

CONCLUSION : This study demonstrates that adding two image preprocessing steps and generating a pseudo color image plays an important role in developing a deep learning CAD scheme of chest X-ray images to improve accuracy in detecting COVID-19 infected pneumonia.

Heidari Morteza, Mirniaharikandehei Seyedehnafiseh, Khuzani Abolfazl Zargari, Danala Gopichandh, Qiu Yuchen, Zheng Bin

2020-Sep-23

COVID-19 diagnosis, Computer-aided diagnosis, Convolution neural network (CNN), Coronavirus, Disease classification, VGG16 network

In Mathematical biosciences and engineering : MBE

Everett Rebecca, Flores Kevin B, Henscheid Nick, Lagergren John, Larripa Kamila, Li Ding, Nardini John T, Nguyen Phuong T T, Pitman E Bruce, Rutter Erica M

2020-May-19

** Bayesian estimation , cancer heterogeneity , generative adversarial networks , glioblastoma multiforme , machine learning , mathematical oncology , non-parametric estimation , nonlinear mixed effects , spatiotemporal data , tumor growth , variational autoencoders , virtual populations **

In Epilepsy research

Beheshti Iman, Sone Daichi, Maikusa Norihide, Kimura Yukio, Shigemoto Yoko, Sato Noriko, Matsuda Hiroshi

2020-Sep-22

Brain metabolism, Epilepsy, FDG-PET, Lateralization, Machine learning

In Cortex; a journal devoted to the study of the nervous system and behavior

Eyigoz Elif, Courson Melody, Sedeño Lucas, Rogg Katharina, Orozco-Arroyave Juan Rafael, Nöth Elmar, Skodda Sabine, Trujillo Natalia, Rodríguez Mabel, Rusz Jan, Muñoz Edinson, Cardona Juan F, Herrera Eduar, Hesse Eugenia, Ibáñez Agustín, Cecchi Guillermo, García Adolfo M

2020-Sep-08

Automated speech analysis, Cross-linguistic validity, Linguistic assessments, Morphology, “Parkinsons disease”

In Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology

Choi Min Seo, Choi Byeong Su, Chung Seung Yeun, Kim Nalee, Chun Jaehee, Kim Yong Bae, Chang Jee Suk, Kim Jin Sung

2020-Sep-26

Artificial Intelligence, Breast cancer, Clinical Target Volume, Commercial Atlas-based autosegmentation, Deep learning-based autosegmentation, Organs at risk, Radiation Therapy

In Urology ; h5-index 45.0

OBJECTIVE : To improve hypospadias classification system, we hereby, show the use of machine learning/image recognition to increase objectivity of hypospadias recognition and classification. Hypospadias anatomical variables such as meatal location, quality of urethral plate, glans size and ventral curvature have been identified as predictors for post-operative outcomes but there is still significant subjectivity between evaluators.

MATERIALS AND METHODS : A hypospadias image database with 1169 anonymized images (837 distal and 332 proximal) was used. Images were standardized (ventral aspect of the penis including the glans, shaft and scrotum) and classified into distal or proximal and uploaded for training with TensorFlow®. Data from the training was outputted to TensorBoard, to assess for the loss function. The model was then run on a set of 29 "Test" images randomly selected. Same set of images were distributed amongst expert clinicians in pediatric urology. Inter and intrarater analysis were performed using Fleiss Kappa statistical analysis using the same 29 images shown to the algorithm.

RESULTS : After training with 627 images, detection accuracy was 60%. With1169 images, accuracy increased to 90%. Inter-rater analysis amongst expert pediatric urologists was k= 0.86 and intra-rater 0.74. Image recognition model emulates the almost perfect inter-rater agreement between experts.

CONCLUSION : Our model emulates expert human classification of patients with distal/proximal hypospadias. Future applicability will be on standardizing the use of these technologies and their clinical applicability. The ability of using variables different than only anatomical will feed deep learning algorithms and possibly better assessments and predictions for surgical outcomes.

Fernandez Nicolas, Lorenzo Armando J, Rickard Mandy, Chua Michael, Pippi-Salle Joao L, Perez Jaime, Braga Luis H, Matava Clyde

2020-Sep-26

artificial intelligence, classification system, hypospadias, machine learning, penile curvature, prognosis

In Molecular cell ; h5-index 132.0

Vangala Pranitha, Murphy Rachel, Quinodoz Sofia A, Gellatly Kyle, McDonel Patrick, Guttman Mitchell, Garber Manuel

2020-Sep-19

chromosome conformation, cis-regulatory elements, dendritic cells, enhancers, genetic variation, innate immunity, machine learning, multiway promoter interactions, single cell, single molecule

In Shock (Augusta, Ga.)

BACKGROUND : Sepsis is a life-threatening condition with high mortality rates. Early detection and treatment are critical to improving outcomes. Our primary objective was to develop artificial intelligence capable of predicting sepsis earlier using a minimal set of streaming physiological data in real-time.

METHODS AND FINDINGS : A total of 29,552 adult patients were admitted to the intensive care unit across five regional hospitals in Memphis, TN over 18 months from January 2017 to July 2018. From these, 5,958 patients were selected after filtering for continuous (minute-by-minute) physiological data availability. A total of 617 (10.4%) patients were identified as sepsis cases, using the Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3) criteria. Physiomarkers, a set of signal processing features, were derived from five physiological data streams including heart rate, respiratory rate, and blood pressure (systolic, diastolic, and mean), captured every minute from the bedside monitors. A support vector machine (SVM) classifier was used for classification. The model accurately predicted sepsis up to a mean and 95% confidence interval of 17.4 ± 0.22 hours before sepsis onset, with an average test accuracy of 83.0% (average sensitivity, specificity, and area under the receiver operating characteristics curve of 0.757, 0.902, and 0.781, respectively).

CONCLUSIONS : This study demonstrates that salient physiomarkers derived from continuous bedside monitoring are temporally and differentially expressed in septic patients. Using this information, minimalistic artificial intelligence models can be developed to predict sepsis earlier in critically ill patients.

Mohammed Akram, Van Wyk Franco, Chinthala Lokesh K, Khojandi Anahita, Davis Robert L, Coopersmith Craig M, Kamaleswaran Rishikesan

2020-Sep-28

In Bipolar disorders

Dargél Aroldo A

2020-Sep-29

Algorithms, Artificial Intelligence, Cyber-Semiology, Digital Music, Digital Phenotyping, Digital Psychiatry, Machine Learning, Mobile apps, Smartphone sensors, mHealth

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

Zhang Daguang, Yang Zhiyong, Jiang Shan, Zhou Zeyang, Meng Maobin, Wang Wei

2020-Sep-29

automatic segmentation, brachytherapy, cervical cancer, convolutional neural networks

In Journal of the European Academy of Dermatology and Venereology : JEADV

BACKGROUND : The integration of machine learning algorithms in decision support tools for physicians is gaining popularity. These tools can tackle the disparities in healthcare access as the technology can be implemented on smartphones. We present the first, large-scale study on patients with skin-of-color, in which the feasibility of a novel mobile health application (mHealth app) was investigated in actual clinical workflows.

OBJECTIVE : To develop a mHealth app to diagnose 40 common skin diseases and test it in clinical settings.

METHODS : A convolutional neural network-based algorithm was trained with clinical images of 40 skin diseases. A smartphone app was generated and validated on 5,014 patients, attending rural and urban outpatient dermatology departments in India. The results of this mHealth app were compared against the dermatologists' diagnoses.

RESULTS : The machine-learning model, in an in silico validation study, demonstrated an overall top-1 accuracy of 76.93±0.88% and mean area-under-curve of 0.95±0.02 on a set of clinical images. In the clinical study, on patients with skin of color, the app achieved an overall top-1 accuracy of 75.07% (95% CI=73.75-76.36), top-3 accuracy of 89.62% (95% CI=88.67-90.52) and mean area-under-curve of 0.90±0.07.

CONCLUSION : This study underscores the utility of artificial intelligence-driven smartphone applications as a point-of-care, clinical decision support tool for dermatological diagnosis for a wide spectrum of skin diseases in patients of the skin of color.

Pangti Rashi, Mathur Jyoti, Chouhan Vikas, Kumar Sharad, Rajput Lavina, Shah Sandesh, Gupta Atula, Dixit Ambika, Dholakia Dhwani, Gupta Sanjeev, Gupta Savera, George Mariam, Sharma Vinod Kumar, Gupta Somesh

2020-Sep-29

Artificial Intelligence, Community Dermatology, Machine Learning, Pattern recognition, mHealth

In Clinical spine surgery

Gutman Michael J, Schroeder Gregory D, Murphy Hamadi, Flanders Adam E, Vaccaro Alexander R

2020-Sep-25

In Mathematical biosciences and engineering : MBE

Sun Guang Xun, Zhou Cheng Jie, Zhao Han Yu, Jin Bo, Gao Zhan

2020-May-12

** biomedical named entity recognition , conditional random field , temporal convolutional network **

In IEEE journal of biomedical and health informatics

Bao Guoqing, Xu Ran, Wang Xiuying, Ji Jianxiong, Wang Linlin, Li Wenjie, Zhang Qing, Huang Bin, Chen Anjing, Kong Beihua, Yang Qifeng, Wang Xinyu, Wang Jian, Li Xingang

2020-Sep-29

In IEEE/ACM transactions on computational biology and bioinformatics

Causey Jason, Li Keyu, Chen Xianghao, Dong Wei, Walker Karl, Qualls Jake, Stubblefield Jonathan, Moore Jason H, Guan Yuanfang, Huang Xiuzhen

2020-Sep-29

In IEEE/ACM transactions on computational biology and bioinformatics

Xie Jiang, Zhao Chang, Sun Jiamin, Li Jiaxin, Yang Fuzhang, Wang Jiao, Nie Qing

2020-Sep-29

In IEEE transactions on medical imaging ; h5-index 74.0

Ding Li, Kuriyan Ajay E, Ramchandran Rajeev S, Wykoff Charles C, Sharma Gaurav

2020-Sep-29

In AJR. American journal of roentgenology

Crombé Amandine, Kind Michèle, Ray-Coquard Isabelle, Isambert Nicolas, Chevreau Christine, André Thierry, Lebbe Celeste, Cesne Axel Le, Bompas Emmanuelle, Piperno-Neumann Sophie, Saada Esma, Bouhamama Amine, Blay Jean-Yves, Italiano Antoine

2020-Sep-29

MRI, Response Evaluation Criteria in Solid Tumors (RECIST), aggressive, antineoplastic agents, fibromatosis, supervised machine learning

In Big data

Karapiperis Christos, Chasapi Anastasia, Angelis Lefteris, Scouras Zacharias G, Mastroberardino Pier G, Tapio Soile, Atkinson Michael J, Ouzounis Christos A

2020-Sep-29

big data analytics, bioinformatics, biomarker discovery, genomics, low-dose ionizing radiation, network science, radiation protection, systems radiobiology

In Big data

Ayachi Riadh, Said Yahia, Atri Mohamed

2020-Sep-29

big data, computer vision, deep learning, image processing

In Movement disorders : official journal of the Movement Disorder Society

BACKGROUND : In polyglutamine (polyQ) disease, the investigation of the prediction of a patient's age at onset (AAO) facilitates the development of disease-modifying intervention and underpins the delay of disease onset and progression. Few polyQ disease studies have evaluated AAO predicted by machine-learning algorithms and linear regression methods.

OBJECTIVE : The objective of this study was to develop a machine-learning model for AAO prediction in the largest spinocerebellar ataxia type 3/Machado-Joseph disease (SCA3/MJD) population from mainland China.

METHODS : In this observational study, we introduced an innovative approach by systematically comparing the performance of 7 machine-learning algorithms with linear regression to explore AAO prediction in SCA3/MJD using CAG expansions of 10 polyQ-related genes, sex, and parental origin.

RESULTS : Similar prediction performance of testing set and training set in each models were identified and few overfitting of training data was observed. Overall, the machine-learning-based XGBoost model exhibited the most favorable performance in AAO prediction over the traditional linear regression method and other 6 machine-learning algorithms for the training set and testing set. The optimal XGBoost model achieved mean absolute error, root mean square error, and median absolute error of 5.56, 7.13, 4.15 years, respectively, in testing set 1, with mean absolute error (4.78 years), root mean square error (6.31 years), and median absolute error (3.59 years) in testing set 2.

CONCLUSION : Machine-learning algorithms can be used to predict AAO in patients with SCA3/MJD. The optimal XGBoost algorithm can provide a good reference for the establishment and optimization of prediction models for SCA3/MJD or other polyQ diseases. © 2020 International Parkinson and Movement Disorder Society.

Peng Linliu, Chen Zhao, Chen Tiankai, Lei Lijing, Long Zhe, Liu Mingjie, Deng Qi, Yuan Hongyu, Zou Guangdong, Wan Linlin, Wang Chunrong, Peng Huirong, Shi Yuting, Wang Puzhi, Peng Yun, Wang Shang, He Lang, Xie Yue, Tang Zhichao, Wan Na, Gong Yiqing, Hou Xuan, Shen Lu, Xia Kun, Li Jinchen, Chen Chao, Zhang Zuping, Qiu Rong, Tang Beisha, Jiang Hong

2020-Sep-29

spinocerebellar ataxia type 3/Machado-Joseph disease; CAG repeats; age at onset prediction; machine learning

In Journal of forensic sciences

Tirado Jhonatan, Mauricio David

2020-Sep-29

MasNet, bruise dating, convolutional neural network, deep learning

In Forensic science, medicine, and pathology

Dobay Akos, Ford Jonathan, Decker Summer, Ampanozi Garyfalia, Franckenberg Sabine, Affolter Raffael, Sieberth Till, Ebert Lars C

2020-Sep-29

Computed tomography, Convolutional neural networks, Deep learning, Forensic sciences, PMCT

In Mathematical biosciences and engineering : MBE

Zhang Xiao Bo, Zhai Dong Hai, Yang Yan, Zhang Yi Ling, Wang Chun Lin

2020-Apr-30

** Parkinson’s disease (PD) , clustering , dimensionality reduction , feature extraction , semi-supervised learning **

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

PURPOSE : Amyloid PET which has been widely used for noninvasive assessment of cortical amyloid burden is visually interpreted in the clinical setting. As a fast and easy-to-use visual interpretation support system, we analyze whether the deep learning-based end-to-end estimation of amyloid burden improves inter-reader agreement as well as the confidence of the visual reading.

METHODS : A total of 121 clinical routines [¹⁸F]Florbetaben PET images were collected for the randomized blind-reader study. The amyloid PET images were visually interpreted by three experts independently blind to other information. The readers qualitatively interpreted images without quantification at the first reading session. After more than 2-week interval, the readers additionally interpreted images with the quantification results provided by the deep learning system. The qualitative assessment was based on a 3-point BAPL score (1: no amyloid load, 2: minor amyloid load, and 3: significant amyloid load). The confidence score for each session was evaluated by a 3-point score (0: ambiguous, 1: probably, and 2: definite to decide).

RESULTS : Inter-reader agreements for the visual reading based on a 3-point scale (BAPL score) calculated by Fleiss kappa coefficients were 0.46 and 0.76 for the visual reading without and with the deep learning system, respectively. For the two reading sessions, the confidence score of visual reading was improved at the visual reading session with the output (1.27 ± 0.078 for visual reading-only session vs. 1.66 ± 0.63 for a visual reading session with the deep learning system).

CONCLUSION : Our results highlight the impact of deep learning-based one-step amyloid burden estimation system on inter-reader agreement and confidence of reading when applied to clinical routine amyloid PET reading.

Kim Ji-Young, Oh Dongkyu, Sung Kiyoung, Choi Hongyoon, Paeng Jin Chul, Cheon Gi Jeong, Kang Keon Wook, Lee Dong Young, Lee Dong Soo

2020-Sep-29

Alzheimer’s disease, Amyloid PET, Deep learning, PET, Visual quantification, [18F]Florbetaben

In Psychopharmacology

RATIONALE : Many people being treated for opioid use disorder continue to use drugs during treatment. This use occurs in patterns that rarely conform to well-defined cycles of abstinence and relapse. Systematic identification and evaluation of these patterns could enhance analysis of clinical trials and provide insight into drug use.

OBJECTIVES : To evaluate such an approach, we analyzed patterns of opioid and cocaine use from three randomized clinical trials of contingency management in methadone-treated participants.

METHODS : Sequences of drug test results were analyzed with unsupervised machine-learning techniques, including hierarchical clustering of categorical results (i.e., whether any samples were positive during each week) and K-means longitudinal clustering of quantitative results (i.e., the proportion positive each week). The sensitivity of cluster membership as an experimental outcome was assessed based on the effects of contingency management. External validation of clusters was based on drug craving and other symptoms of substance use disorder.

RESULTS : In each clinical trial, we identified four clusters of use patterns, which can be described as opioid use, cocaine use, dual use (opioid and cocaine), and partial/complete abstinence. Different clustering techniques produced substantially similar classifications of individual participants, with strong above-chance agreement. Contingency management increased membership in clusters with lower levels of drug use and fewer symptoms of substance use disorder.

CONCLUSIONS : Cluster analysis provides person-level output that is more interpretable and actionable than traditional outcome measures, providing a concrete answer to the question of what clinicians can tell patients about the success rates of new treatments.

Panlilio Leigh V, Stull Samuel W, Bertz Jeremiah W, Burgess-Hull Albert J, Kowalczyk William J, Phillips Karran A, Epstein David H, Preston Kenzie L

2020-Sep-29

Cluster analysis, Cocaine, Contingency management, Methadone, Opioids, Substance use disorder, Treatment outcomes

In Nucleic acids research ; h5-index 217.0

Chen Si-Yi, Yue Tao, Lei Qian, Guo An-Yuan

2020-Sep-29

In Nucleic acids research ; h5-index 217.0

Liu Chun-Jie, Fu Xin, Xia Mengxuan, Zhang Qiong, Gu Zhifeng, Guo An-Yuan

2020-Sep-29

In GigaScience

AIM : To enable a world-leading research dataset of routinely collected clinical images linked to other routinely collected data from the whole Scottish national population. This includes more than 30 million different radiological examinations from a population of 5.4 million and >2 PB of data collected since 2010.

METHODS : Scotland has a central archive of radiological data used to directly provide clinical care to patients. We have developed an architecture and platform to securely extract a copy of those data, link it to other clinical or social datasets, remove personal data to protect privacy, and make the resulting data available to researchers in a controlled Safe Haven environment.

RESULTS : An extensive software platform has been developed to host, extract, and link data from cohorts to answer research questions. The platform has been tested on 5 different test cases and is currently being further enhanced to support 3 exemplar research projects.

CONCLUSIONS : The data available are from a range of radiological modalities and scanner types and were collected under different environmental conditions. These real-world, heterogenous data are valuable for training algorithms to support clinical decision making, especially for deep learning where large data volumes are required. The resource is now available for international research access. The platform and data can support new health research using artificial intelligence and machine learning technologies, as well as enabling discovery science.

Nind Thomas, Sutherland James, McAllister Gordon, Hardy Douglas, Hume Ally, MacLeod Ruairidh, Caldwell Jacqueline, Krueger Susan, Tramma Leandro, Teviotdale Ross, Abdelatif Mohammed, Gillen Kenny, Ward Joe, Scobbie Donald, Baillie Ian, Brooks Andrew, Prodan Bianca, Kerr William, Sloan-Murphy Dominic, Herrera Juan F R, McManus Dan, Morris Carole, Sinclair Carol, Baxter Rob, Parsons Mark, Morris Andrew, Jefferson Emily

2020-Sep-29

AI, Big Data, ML, Radiology

In Studies in health technology and informatics ; h5-index 23.0

Ognjanovic Ivana

2020-Sep-25

Artificial intelligence, expert systems, machine learning, natural processing, speech recognition

In Studies in health technology and informatics ; h5-index 23.0

Knaup Petra, Benning Nils-Hendrik, Seitz Max Wolfgang, Eisenmann Urs

2020-Sep-25

eHealth, interoperability, medical documentation, patient records, telemedicine

In Studies in health technology and informatics ; h5-index 23.0

Ognjanovic Ivana

2020-Sep-25

Health analytics, health data, machine learning, patient similarity, phenotyping, predictive modelling

In JMIR mHealth and uHealth

BACKGROUND : Emotional state in everyday life is an essential indicator of health and well-being. However, daily assessment of emotional states largely depends on active self-reports, which are often inconvenient and prone to incomplete information. Automated detection of emotional states and transitions on a daily basis could be an effective solution to this problem. However, the relationship between emotional transitions and everyday context remains to be unexplored.

OBJECTIVE : This study aims to explore the relationship between contextual information and emotional transitions and states to evaluate the feasibility of detecting emotional transitions and states from daily contextual information using machine learning (ML) techniques.

METHODS : This study was conducted on the data of 18 individuals from a publicly available data set called ExtraSensory. Contextual and sensor data were collected using smartphone and smartwatch sensors in a free-living condition, where the number of days for each person varied from 3 to 9. Sensors included an accelerometer, a gyroscope, a compass, location services, a microphone, a phone state indicator, light, temperature, and a barometer. The users self-reported approximately 49 discrete emotions at different intervals via a smartphone app throughout the data collection period. We mapped the 49 reported discrete emotions to the 3 dimensions of the pleasure, arousal, and dominance model and considered 6 emotional states: discordant, pleased, dissuaded, aroused, submissive, and dominant. We built general and personalized models for detecting emotional transitions and states every 5 min. The transition detection problem is a binary classification problem that detects whether a person's emotional state has changed over time, whereas state detection is a multiclass classification problem. In both cases, a wide range of supervised ML algorithms were leveraged, in addition to data preprocessing, feature selection, and data imbalance handling techniques. Finally, an assessment was conducted to shed light on the association between everyday context and emotional states.

RESULTS : This study obtained promising results for emotional state and transition detection. The best area under the receiver operating characteristic (AUROC) curve for emotional state detection reached 60.55% in the general models and an average of 96.33% across personalized models. Despite the highly imbalanced data, the best AUROC curve for emotional transition detection reached 90.5% in the general models and an average of 88.73% across personalized models. In general, feature analyses show that spatiotemporal context, phone state, and motion-related information are the most informative factors for emotional state and transition detection. Our assessment showed that lifestyle has an impact on the predictability of emotion.

CONCLUSIONS : Our results demonstrate a strong association of daily context with emotional states and transitions as well as the feasibility of detecting emotional states and transitions using data from smartphone and smartwatch sensors.

Sultana Madeena, Al-Jefri Majed, Lee Joon

2020-Sep-29

artificial intelligence, digital biomarkers, digital phenotyping, emotion detection, emotional transition detection, mHealth, mental health, mobile phone, spatiotemporal context, supervised machine learning

In Journal of medical Internet research ; h5-index 88.0

BACKGROUND : Diagnostic delay in rare disease (RD) is common, occasionally lasting up to more than 20 years. In attempting to reduce it, diagnostic support tools have been studied extensively. However, social platforms have not yet been used for systematic diagnostic support. This paper illustrates the development and prototypic application of a social network using scientifically developed questions to match individuals without a diagnosis.

OBJECTIVE : The study aimed to outline, create, and evaluate a prototype tool (a social network platform named RarePairs), helping patients with undiagnosed RDs to find individuals with similar symptoms. The prototype includes a matching algorithm, bringing together individuals with similar disease burden in the lead-up to diagnosis.

METHODS : We divided our project into 4 phases. In phase 1, we used known data and findings in the literature to understand and specify the context of use. In phase 2, we specified the user requirements. In phase 3, we designed a prototype based on the results of phases 1 and 2, as well as incorporating a state-of-the-art questionnaire with 53 items for recognizing an RD. Lastly, we evaluated this prototype with a data set of 973 questionnaires from individuals suffering from different RDs using 24 distance calculating methods.

RESULTS : Based on a step-by-step construction process, the digital patient platform prototype, RarePairs, was developed. In order to match individuals with similar experiences, it uses answer patterns generated by a specifically designed questionnaire (Q53). A total of 973 questionnaires answered by patients with RDs were used to construct and test an artificial intelligence (AI) algorithm like the k-nearest neighbor search. With this, we found matches for every single one of the 973 records. The cross-validation of those matches showed that the algorithm outperforms random matching significantly. Statistically, for every data set the algorithm found at least one other record (match) with the same diagnosis.

CONCLUSIONS : Diagnostic delay is torturous for patients without a diagnosis. Shortening the delay is important for both doctors and patients. Diagnostic support using AI can be promoted differently. The prototype of the social media platform RarePairs might be a low-threshold patient platform, and proved suitable to match and connect different individuals with comparable symptoms. This exchange promoted through RarePairs might be used to speed up the diagnostic process. Further studies include its evaluation in a prospective setting and implementation of RarePairs as a mobile phone app.

Kühnle Lara, Mücke Urs, Lechner Werner M, Klawonn Frank, Grigull Lorenz

2020-Sep-29

artificial intelligence, diagnostic support tool, machine learning, prototype, rare disease, social network

In Mathematical biosciences and engineering : MBE

Jiang Jing Chao, Yu Chun Ling, Xu Xun, Ma Yong Sheng, Liu Ji Kai

2020-Apr-30

** additive manufacturing , connection , deep neural network , machine learning **

In Radiology ; h5-index 91.0

Stib Matthew T, Vasquez Justin, Dong Mary P, Kim Yun Ho, Subzwari Sumera S, Triedman Harold J, Wang Amy, Wang Hsin-Lei Charlene, Yao Anthony D, Jayaraman Mahesh, Boxerman Jerrold L, Eickhoff Carsten, Cetintemel Ugur, Baird Grayson L, McTaggart Ryan A

2020-Sep-29

In Annals of clinical and translational neurology

OBJECTIVE : Subarachnoid hemorrhage (SAH) is often devastating with increased early mortality, particularly in those with presumed delayed cerebral ischemia (DCI). The ability to accurately predict survival for SAH patients during the hospital course would provide valuable information for healthcare providers, patients, and families. This study aims to utilize electronic health record (EHR) data and machine learning approaches to predict the adverse outcome for nontraumatic SAH adult patients.

METHODS : The cohort included nontraumatic SAH patients treated with vasopressors for presumed DCI from a large EHR database, the Cerner Health Facts^® EMR database (2000-2014). The outcome of interest was the adverse outcome, defined as death in hospital or discharged to hospice. Machine learning-based models were developed and primarily assessed by area under the receiver operating characteristic curve (AUC).

RESULTS : A total of 2467 nontraumatic SAH patients (64% female; median age [interquartile range]: 56 [47-66]) who were treated with vasopressors for presumed DCI were included in the study. 934 (38%) patients died or were discharged to hospice. The model achieved an AUC of 0.88 (95% CI, 0.84-0.92) with only the initial 24 h EHR data, and 0.94 (95% CI, 0.92-0.96) after the next 24 h.

INTERPRETATION : EHR data and machine learning models can accurately predict the risk of the adverse outcome for critically ill nontraumatic SAH patients. It is possible to use EHR data and machine learning techniques to help with clinical decision-making.

Yu Duo, Williams George W, Aguilar David, Yamal José-Miguel, Maroufy Vahed, Wang Xueying, Zhang Chenguang, Huang Yuefan, Gu Yuxuan, Talebi Yashar, Wu Hulin

2020-Sep-29

In The British journal of surgery

BACKGROUND : Lymph node metastasis (LNM) in gastric cancer is a prognostic factor and has implications for the extent of lymph node dissection. The lymphatic drainage of the stomach involves multiple nodal stations with different risks of metastases. The aim of this study was to develop a deep learning system for predicting LNMs in multiple nodal stations based on preoperative CT images in patients with gastric cancer.

METHODS : Preoperative CT images from patients who underwent gastrectomy with lymph node dissection at two medical centres were analysed retrospectively. Using a discovery patient cohort, a system of deep convolutional neural networks was developed to predict pathologically confirmed LNMs at 11 regional nodal stations. To gain understanding about the networks' prediction ability, gradient-weighted class activation mapping for visualization was assessed. The performance was tested in an external cohort of patients by analysis of area under the receiver operating characteristic (ROC) curves (AUC), sensitivity and specificity.

RESULTS : The discovery and external cohorts included 1172 and 527 patients respectively. The deep learning system demonstrated excellent prediction accuracy in the external validation cohort, with a median AUC of 0·876 (range 0·856-0·893), sensitivity of 0·743 (0·551-0·859) and specificity of 0·936 (0·672-0·966) for 11 nodal stations. The imaging models substantially outperformed clinicopathological variables for predicting LNMs (median AUC 0·652, range 0·571-0·763). By visualizing nearly 19 000 subnetworks, imaging features related to intratumoral heterogeneity and the invasive front were found to be most useful for predicting LNMs.

CONCLUSION : A deep learning system for the prediction of LNMs was developed based on preoperative CT images of gastric cancer. The models require further validation but may be used to inform prognosis and guide individualized surgical treatment.

Jin C, Jiang Y, Yu H, Wang W, Li B, Chen C, Yuan Q, Hu Y, Xu Y, Zhou Z, Li G, Li R

2020-Sep-29

In Diagnostic and interventional radiology (Ankara, Turkey)

PURPOSE : Lymphovascular invasion (LVI) and perineural invasion (PNI) are associated with poor prognosis in gastric cancers. In this work, we aimed to investigate the potential role of computed tomography (CT) texture analysis in predicting LVI and PNI in patients with tubular gastric adenocarcinoma (GAC) using a machine learning (ML) approach.

METHODS : Sixty-eight patients who underwent total gastrectomy with curative (R0) resection and D2-lymphadenectomy were included in this retrospective study. Texture features were extracted from the portal venous phase CT images. Dimension reduction was first done with a reproducibility analysis by two radiologists. Then, a feature selection algorithm was used to further reduce the high-dimensionality of the radiomic data. Training and test splits were created with 100 random samplings. ML-based classifications were done using adaptive boosting, k-nearest neighbors, Naive Bayes, neural network, random forest, stochastic gradient descent, support vector machine, and decision tree. Predictive performance of the ML algorithms was mainly evaluated using the mean area under the curve (AUC) metric.

RESULTS : Among 271 texture features, 150 features had excellent reproducibility, which were included in the further feature selection process. Dimension reduction steps yielded five texture features for LVI and five for PNI. Considering all eight ML algorithms, mean AUC and accuracy ranges for predicting LVI were 0.777-0.894 and 76%-81.5%, respectively. For predicting PNI, mean AUC and accuracy ranges were 0.482-0.754 and 54%-68.2%, respectively. The best performances for predicting LVI and PNI were achieved with the random forest and Naive Bayes algorithms, respectively.

CONCLUSION : ML-based CT texture analysis has a potential for predicting LVI and PNI of the tubular GACs. Overall, the method was more successful in predicting LVI than PNI.

Yardımcı Aytül Hande, Koçak Burak, Turan Bektaş Ceyda, Sel İpek, Yarıkkaya Enver, Dursun Nevra, Bektaş Hasan, Usul Afşar Çiğdem, Gürsu Rıza Umar, Kılıçkesmez Özgür

2020-Sep-29

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

Ong Mei-Sing, Klann Jeffrey G, Lin Kueiyu Joshua, Maron Bradley A, Murphy Shawn N, Natter Marc D, Mandl Kenneth D

2020-Sep-29

computable phenotype, machine learning, pulmonary hypertension

In Multivariate behavioral research

Huang Po-Hsien

2020-Sep-29

Structural equation modeling, factor analysis, lasso, penalized least squares, polychoric correlation

In Minerva cardioangiologica

Dias Roger D, Shah Julie A, Zenati Marco A

2020-Sep-29

In Journal of Korean medical science

BACKGROUND : This study aimed to investigate the effect of antiviral therapy following influenza outpatient episodes on the incidence of hospitalized pneumonia episodes, one of secondary complications of influenza.

METHODS : In the National Health Insurance Research Database, data from July 2013 to June 2018 were used. All of the claim data with diagnoses of influenza and pneumonia were converted to episodes of care after applying 100 days of window period. With the 100-day episodes of care, the characteristics of influenza outpatient episodes and antiviral therapy for influenza, the incidence of hospitalized pneumonia episodes following influenza, and the effect of antiviral therapy for influenza on hospitalized pneumonia episodes were investigated.

RESULTS : The crude incidence rate of hospitalized pneumonia after influenza infection was 0.57% in both males and females. Factors affecting hospitalized pneumonia included age, income level except self-employed highest (only in females), municipality, medical institution type, precedent chronic diseases except hepatitis (only in females) and antiviral therapy. In the 2017 flu season, the relative risk was 0.38 (95% confidence interval [CI], 0.29-0.50) in males aged 0-9 and 0.43 (95% CI, 0.32-0.57) in females aged 0-9 without chronic diseases, and it was 0.51 (95% CI, 0.42-0.61) in males aged 0-9 and 0.42 (95% CI, 0.35-0.50) in females aged 0-9 with one or more chronic diseases in the aspect of the effect of antiviral therapy on pneumonia. It suggests that antiviral therapy may decrease the incidence of pneumonia after influenza infection.

CONCLUSION : After outpatient episode incidence of influenza, antiviral treatment has been shown to reduce the incidence of hospitalized pneumonia, especially in infants and children, during pandemic season 2017. Antiviral therapy for influenza is recommended to minimize burden caused by influenza virus infection and to reduce pneumonia. In addition, medical costs of hospitalization may decrease by antiviral therapy, especially in infants and children.

Byeon Kyeong Hyang, Kim Jaiyong, Choi Bo Youl, Kim Jin Yong, Lee Nakyoung

2020-Sep-28

Antiviral Treatment, Episode of Care, Influenza, Pneumonia

In Magnetic resonance in medicine ; h5-index 66.0

PURPOSE : To accelerate T₂ mapping with highly sparse sampling by integrating deep learning image priors with low-rank and sparse modeling.

METHODS : The proposed method achieves high-speed T₂ mapping by highly sparsely sampling (k, TE)-space. Image reconstruction from the undersampled data was done by exploiting the low-rank structure and sparsity in the T₂ -weighted image sequence and image priors learned from training data. The image priors for a single TE were generated from the public Human Connectome Project data using a tissue-based deep learning method; the image priors were then transferred to other TEs using a generalized series-based method. With these image priors, the proposed reconstruction method used a low-rank model and a sparse model to capture subject-dependent novel features.

RESULTS : The proposed method was evaluated using experimental data obtained from both healthy subjects and tumor patients using a turbo spin-echo sequence. High-quality T₂ maps at the resolution of 0.9 × 0.9 × 3.0 mm³ were obtained successfully from highly undersampled data with an acceleration factor of 8. Compared with the existing compressed sensing-based methods, the proposed method produced significantly reduced reconstruction errors. Compared with the deep learning-based methods, the proposed method recovered novel features better.

CONCLUSION : This paper demonstrates the feasibility of learning T₂ -weighted image priors for multiple TEs using tissue-based deep learning and generalized series-based learning. A new method was proposed to effectively integrate these image priors with low-rank and sparse modeling to reconstruct high-quality images from highly undersampled data. The proposed method will supplement other acquisition-based methods to achieve high-speed T₂ mapping.

Meng Ziyu, Guo Rong, Li Yudu, Guan Yue, Wang Tianyao, Zhao Yibo, Sutton Brad, Li Yao, Liang Zhi-Pei

2020-Sep-29

T2 mapping, deep learning, low-rank modeling, quantitative imaging, sparse modeling

In Medical physics ; h5-index 59.0

PURPOSE : Clinical sites utilizing MRI-only simulation imaging for prostate radiotherapy planning typically use fiducial markers for pretreatment patient positioning and alignment. Fiducial markers appear as small signal voids in MRI images and are often difficult to discern. Existing clinical methods for fiducial marker localization require multiple MRI sequences and/or manual interaction and specialized expertise. In this study, we develop a robust method for automatic fiducial marker detection in MRI simulation images of the prostate and quantify the prostate organ localization accuracy using automatically detected fiducial markers in MRI for pretreatment alignment using cone beam CT (CBCT) images.

METHODS AND MATERIALS : In this study, a deep learning-based algorithm was used to convert MRI images into labelled fiducial marker volumes. 77 prostate cancer patients who received marker implantation prior to MRI and CT simulation imaging were selected for this study. Multiple-Echo T₁ -VIBE MRI images were acquired, and images were stratified (at the patient level) based on the presence of intraprostatic calcifications. Ground truth (GT) contours were defined by an expert on MRI using CT images. Training was done using the pix2pix generative adversarial network (GAN) image-to-image translation package and model testing was done using five-fold cross validation. For performance comparison, an experienced medical dosimetrist and a medical physicist each manually contoured fiducial markers in MRI images. The percent of correct detections and F₁ classification scores are reported for markers detected using the automatic detection algorithm and human observers. The patient positioning errors were quantified by calculating the target registration errors (TREs) from fiducial marker driven rigid registration between MRI and CBCT images. TREs were quantified for fiducial marker contours defined on MRI by the automatic detection algorithm and the two expert human observers.

RESULTS : 96% of implanted fiducial markers were correctly identified using the automatic detection algorithm. Two expert raters correctly identified 97% and 96% of fiducial markers, respectively. The F₁ classification score was 0.68, 0.75 and 0.72 for the automatic detection algorithm and two human raters, respectively. The main source of false discoveries was intraprostatic calcifications. The mean TRE differences between alignments from automatic detection algorithm and human detected markers and GT were less than 1 mm.

CONCLUSIONS : We have developed a deep learning-based approach to automatically detect fiducial markers in MRI-only simulation images in a clinically representative patient cohort. The automatic detection algorithm-predicted markers can allow for patient setup with similar accuracy to independent human observers.

Singhrao Kamal, Fu Jie, Parikh Neil R, Mikaeilian Argin G, Ruan Dan, Kishan Amar U, Lewis John H

2020-Sep-28

Deep Learning, Fiducial Markers, MRI in treatment planning, MRI-Only Simulation

In Mathematical biosciences and engineering : MBE

Liang Qiao Kang, Peng Jian Zhong, Li Zheng Wei, Xie Da Qi, Sun Wei, Wang Yao Nan, Zhang Dan

2020-Apr-23

** binarization algorithm , character recognition , deep learning , recurrent neural network , table image recognition **

In International journal of medical informatics ; h5-index 49.0

OBJECTIVE : This study aims to develop and test a new computer-aided diagnosis (CAD) scheme of chest X-ray images to detect coronavirus (COVID-19) infected pneumonia.

METHOD : CAD scheme first applies two image preprocessing steps to remove the majority of diaphragm regions, process the original image using a histogram equalization algorithm, and a bilateral low-pass filter. Then, the original image and two filtered images are used to form a pseudo color image. This image is fed into three input channels of a transfer learning-based convolutional neural network (CNN) model to classify chest X-ray images into 3 classes of COVID-19 infected pneumonia, other community-acquired no-COVID-19 infected pneumonia, and normal (non-pneumonia) cases. To build and test the CNN model, a publicly available dataset involving 8474 chest X-ray images is used, which includes 415, 5179 and 2,880 cases in three classes, respectively. Dataset is randomly divided into 3 subsets namely, training, validation, and testing with respect to the same frequency of cases in each class to train and test the CNN model.

RESULTS : The CNN-based CAD scheme yields an overall accuracy of 94.5 % (2404/2544) with a 95 % confidence interval of [0.93,0.96] in classifying 3 classes. CAD also yields 98.4 % sensitivity (124/126) and 98.0 % specificity (2371/2418) in classifying cases with and without COVID-19 infection. However, without using two preprocessing steps, CAD yields a lower classification accuracy of 88.0 % (2239/2544).

CONCLUSION : This study demonstrates that adding two image preprocessing steps and generating a pseudo color image plays an important role in developing a deep learning CAD scheme of chest X-ray images to improve accuracy in detecting COVID-19 infected pneumonia.

Heidari Morteza, Mirniaharikandehei Seyedehnafiseh, Khuzani Abolfazl Zargari, Danala Gopichandh, Qiu Yuchen, Zheng Bin

2020-Sep-23

COVID-19 diagnosis, Computer-aided diagnosis, Convolution neural network (CNN), Coronavirus, Disease classification, VGG16 network

In International journal of computer assisted radiology and surgery

PURPOSE : Data augmentation is a common technique to overcome the lack of large annotated databases, a usual situation when applying deep learning to medical imaging problems. Nevertheless, there is no consensus on which transformations to apply for a particular field. This work aims at identifying the effect of different transformations on polyp segmentation using deep learning.

METHODS : A set of transformations and ranges have been selected, considering image-based (width and height shift, rotation, shear, zooming, horizontal and vertical flip and elastic deformation), pixel-based (changes in brightness and contrast) and application-based (specular lights and blurry frames) transformations. A model has been trained under the same conditions without data augmentation transformations (baseline) and for each of the transformation and ranges, using CVC-EndoSceneStill and Kvasir-SEG, independently. Statistical analysis is performed to compare the baseline performance against results of each range of each transformation on the same test set for each dataset.

RESULTS : This basic method identifies the most adequate transformations for each dataset. For CVC-EndoSceneStill, changes in brightness and contrast significantly improve the model performance. On the contrary, Kvasir-SEG benefits to a greater extent from the image-based transformations, especially rotation and shear. Augmentation with synthetic specular lights also improves the performance.

CONCLUSION : Despite being infrequently used, pixel-based transformations show a great potential to improve polyp segmentation in CVC-EndoSceneStill. On the other hand, image-based transformations are more suitable for Kvasir-SEG. Problem-based transformations behave similarly in both datasets. Polyp area, brightness and contrast of the dataset have an influence on these differences.

Sánchez-Peralta Luisa F, Picón Artzai, Sánchez-Margallo Francisco M, Pagador J Blas

2020-Sep-28

Data augmentation, Deep learning, Polyp segmentation, Semantic segmentation, Transformations

In Archives of osteoporosis

El Miedany Yasser

2020-Sep-28

Adjustment, Artificial intelligence, BMD, Clinical risk factors, FRAX, Fracture probability, Intervention thresholds, Osteoporosis, Risk assessment, Screening

In Journal of assisted reproduction and genetics ; h5-index 39.0

Swain Jason, VerMilyea Matthew Tex, Meseguer Marcos, Ezcurra Diego

2020-Sep-29

AI, algorithms, embryos, fertility

In Cureus

Sathyakumar Kaviya, Munoz Michael, Singh Jaikaran, Hussain Nowair, Babu Benson A

2020-Aug-25

artificial intelligence, computer-aided detection, convolutional neural networks, deep learning artificial intelligence, deep neural network, ensemble neural network, lung cancer, lung nodule

In Current pathobiology reports

Purpose of Review : Computational and mathematical modeling have become a critical part of understanding in-host infectious disease dynamics and predicting effective treatments. In this review, we discuss recent findings pertaining to the biological mechanisms underlying infectious diseases, including etiology, pathogenesis, and the cellular interactions with infectious agents. We present advances in modeling techniques that have led to fundamental disease discoveries and impacted clinical translation.

Recent Findings : Combining mechanistic models and machine learning algorithms has led to improvements in the treatment of Shigella and tuberculosis through the development of novel compounds. Modeling of the epidemic dynamics of malaria at the within-host and between-host level has afforded the development of more effective vaccination and antimalarial therapies. Similarly, in-host and host-host models have supported the development of new HIV treatment modalities and an improved understanding of the immune involvement in influenza. In addition, large-scale transmission models of SARS-CoV-2 have furthered the understanding of coronavirus disease and allowed for rapid policy implementations on travel restrictions and contract tracing apps.

Summary : Computational modeling is now more than ever at the forefront of infectious disease research due to the COVID-19 pandemic. This review highlights how infectious diseases can be better understood by connecting scientists from medicine and molecular biology with those in computer science and applied mathematics.

Jenner Adrianne L, Aogo Rosemary A, Davis Courtney L, Smith Amber M, Craig Morgan

2020-Sep-24

Bacteria, Computational modeling, Infectious diseases, Mathematics, Parasites, Viruses

In Conference on Computer Vision and Pattern Recognition Workshops. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Workshops

Nunez Elvis, Joshi Shantanu H

2020-Jun

In Applied soft computing

Karthik R, Menaka R, M Hariharan

2020-Sep-23

CNN, COVID-19, Chest X-ray, Deep learning, Pneumonia

In Aging ; h5-index 49.0

Ma Wenjuan, Wang Xin, Xu Guijun, Liu Zheng, Yin Zhuming, Xu Yao, Wu Haixiao, Baklaushev Vladimir P, Peltzer Karl, Sun Henian, Kharchenko Natalia V, Qi Lisha, Mao Min, Li Yanbo, Liu Peifang, Chekhonin Vladimir P, Zhang Chao

2020-Sep-28

artificial intelligence, breast neoplasms, early detection, neoplasm metastasis

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

Yao Haicheng, Yang Weidong, Cheng Wen, Tan Yu Jun, See Hian Hian, Li Si, Ali Hashina Parveen Anwar, Lim Brian Z H, Liu Zhuangjian, Tee Benjamin C K

2020-Sep-28

electronic skin, machine learning, robotics, sensor, wearable

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

McClelland James L, Hill Felix, Rudolph Maja, Baldridge Jason, Schütze Hinrich

2020-Sep-28

artificial intelligence, cognitive neuroscience, deep learning, natural language understanding, situation models

In Mathematical biosciences and engineering : MBE

Zhang Zhi Chang, Zhang Min Yu, Zhou Tong, Qiu Yan Long

2020-Mar-24

** Chinese clinical event detection , Chinese clinical narratives , adversarial training network , class imbalance problem , medical artificial intelligence , pre-trained language model , semantic understanding , transfer learning **

In Current pathobiology reports

Purpose of Review : Computational and mathematical modeling have become a critical part of understanding in-host infectious disease dynamics and predicting effective treatments. In this review, we discuss recent findings pertaining to the biological mechanisms underlying infectious diseases, including etiology, pathogenesis, and the cellular interactions with infectious agents. We present advances in modeling techniques that have led to fundamental disease discoveries and impacted clinical translation.

Recent Findings : Combining mechanistic models and machine learning algorithms has led to improvements in the treatment of Shigella and tuberculosis through the development of novel compounds. Modeling of the epidemic dynamics of malaria at the within-host and between-host level has afforded the development of more effective vaccination and antimalarial therapies. Similarly, in-host and host-host models have supported the development of new HIV treatment modalities and an improved understanding of the immune involvement in influenza. In addition, large-scale transmission models of SARS-CoV-2 have furthered the understanding of coronavirus disease and allowed for rapid policy implementations on travel restrictions and contract tracing apps.

Summary : Computational modeling is now more than ever at the forefront of infectious disease research due to the COVID-19 pandemic. This review highlights how infectious diseases can be better understood by connecting scientists from medicine and molecular biology with those in computer science and applied mathematics.

Jenner Adrianne L, Aogo Rosemary A, Davis Courtney L, Smith Amber M, Craig Morgan

2020-Sep-24

Bacteria, Computational modeling, Infectious diseases, Mathematics, Parasites, Viruses

In Journal of clinical pathology

Stathonikos Nikolaos, Nguyen Tri Q, van Diest Paul J

2020-Sep-28

computer systems, computer-assisted, health care, hospital, image processing, medical informatics computing, pathology department, quality assurance

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

PURPOSE : CDK12 aberrations have been reported as a biomarker of response to immunotherapy for metastatic castration-resistant prostate cancer (mCRPC). Herein, we characterize CDK12-mutated mCRPC, presenting clinical, genomic, and tumor-infiltrating lymphocyte data.

EXPERIMENTAL DESIGN : Patients with mCRPC consented to the molecular analyses of diagnostic and metastatic CRPC biopsies. Genomic analyses involved targeted next generation (MiSeqTM; Illumina) and exome sequencing (NovaSeqTM; Illumina). Tumor-infiltrating lymphocytes (TIL) were assessed by validated immunocytochemistry coupled with deep learning-based artificial intelligence analyses including multiplex immunofluorescence assays for CD4, CD8, and FOXP3 evaluating TIL subsets. The control group comprised a randomly selected mCRPC cohort with sequencing and clinical data available.

RESULTS : Biopsies from 913 patients underwent targeted sequencing between Feb/15 and Oct/19. Forty-three patients (4.7%) had tumors with CDK12 alterations. CDK12 altered cancers had distinctive features, with some revealing high chromosomal break numbers in exome sequencing. Biallelic CDK12-aberrant mCRPC had shorter overall survival from diagnosis than controls (5.1 years [95% CI: 4.0, 7.9] vs 6.4 years [95% CI: 5.7, 7.8]; HR=1.65 [95% CI: 1.07, 2.53]; P=0.02). Median intratumoral CD3+ cell density was higher in CDK12 cancers, although this was not statistically significant (203.7 versus 86.7 cells/mm2, P=0.07). This infiltrate primarily comprised CD4+FOXP3- cells (50.5 versus 6.2 cells/mm2, P<0.0001), where high counts tended to be associated with worse survival from diagnosis (HR=1.64; 95% CI: [0.95, 2.84], P=0.077) in the overall population.

CONCLUSIONS : CDK12-altered mCRPCs have worse prognosis with these tumors surprisingly being primarily enriched for CD4+FOXP3- cells that seem to associate with worse outcome and may be immunosuppressive.

Rescigno Pasquale, Gurel Bora, Pereira Rita, Crespo Mateus, Rekowski Jan, Rediti Mattia, Barrero Maialen, Mateo Joaquin, Bianchini Diletta, Messina Carlo, Fenor de la Maza M D, Chandran Khobe, Carmichael Juliet, Guo Christina, Paschalis Alec, Sharp Adam, Seed George, Figueiredo Ines, Lambros Maryou Bk, Miranda Susana, Ferreira Ana, Bertan Claudia, Riisnaes Ruth, Porta Nuria, Yuan Wei, Carreira Suzanne, de Bono Johann S

2020-Sep-28

In HPB : the official journal of the International Hepato Pancreato Biliary Association

BACKGROUND : Bile duct injury is a serious surgical complication of laparoscopic cholecystectomy. The aim of this study was to identify distinct visual gaze patterns associated with the prompt detection of bile duct injury risk during laparoscopic cholecystectomy.

METHODS : Twenty-nine participants viewed a laparoscopic cholecystectomy that led to a serious bile duct injury ('BDI video') and an uneventful procedure ('control video') and reported when an error was perceived that could result in bile duct injury. Outcome parameters include fixation sequences on anatomical structures and eye tracking metrics. Surgeons were stratified into two groups based on performance and compared.

RESULTS : The 'early detector' group displayed reduced common bile duct dwell time in the first half of the BDI video, as well as increased cystic duct dwell time and Calot's triangle glances count during Calot's triangle dissection in the control video. Machine learning based classification of fixation sequences demonstrated clear separability between early and late detector groups.

CONCLUSION : There are discernible differences in gaze patterns associated with early recognition of impending bile duct injury. The results could be transitioned into real time and used as an intraoperative early warning system and in an educational setting to improve surgical safety and performance.

Sharma Chetanya, Singh Harsmirat, Orihuela-Espina Felipe, Darzi Ara, Sodergren Mikael H

2020-Sep-26

In Schizophrenia research ; h5-index 61.0

BACKGROUND : Accurately diagnosing schizophrenia is still challenging due to the lack of validated biomarkers. Here, we aimed to investigate whether radiomic features in bilateral hippocampal subfields from magnetic resonance images (MRIs) can differentiate patients with schizophrenia from healthy controls (HCs).

METHODS : A total of 152 participants with MRI (86 schizophrenia and 66 HCs) were allocated to training (n = 106) and test (n = 46) sets. Radiomic features (n = 642) from the bilateral hippocampal subfields processed with automatic segmentation techniques were extracted from T1-weighted MRIs. After feature selection, various combinations of classifiers (logistic regression, extra-trees, AdaBoost, XGBoost, or support vector machine) and subsampling were trained. The performance of the classifier was validated in the test set by determining the area under the curve (AUC). Furthermore, the association between selected radiomic features and clinical symptoms in schizophrenia was assessed.

RESULTS : Thirty radiomic features were identified to differentiate participants with schizophrenia from HCs. In the training set, the AUC exhibited poor to good performance (range: 0.683-0.861). The best performing radiomics model in the test set was achieved by the mutual information feature selection and logistic regression with an AUC, accuracy, sensitivity, and specificity of 0.821 (95% confidence interval 0.681-0.961), 82.1%, 76.9%, and 70%, respectively. Greater maximum values in the left cornu ammonis 1-3 subfield were associated with a higher severity of positive symptoms and general psychopathology in participants with schizophrenia.

CONCLUSION : Radiomic features from hippocampal subfields may be useful biomarkers for identifying schizophrenia.

Park Yae Won, Choi Dongmin, Lee Joonho, Ahn Sung Soo, Lee Seung-Koo, Lee Sang-Hyuk, Bang Minji

2020-Sep-25

Artificial intelligence, Hippocampus, Machine learning, Magnetic resonance imaging, Radiomics, Schizophrenia

In Current problems in diagnostic radiology

Chu Linda C, Park Seyoun, Kawamoto Satomi, Yuille Alan L, Hruban Ralph H, Fishman Elliot K

2020-Aug-26

In Surgery ; h5-index 54.0

BACKGROUND : Our previous work classified a taxonomy of needle driving gestures during a vesicourethral anastomosis of robotic radical prostatectomy in association with tissue tears and patient outcomes. Herein, we train deep learning-based computer vision to automate the identification and classification of suturing gestures for needle driving attempts.

METHODS : Two independent raters manually annotated live suturing video clips to label timepoints and gestures. Identification (2,395 videos) and classification (511 videos) datasets were compiled to train computer vision models to produce 2- and 5-class label predictions, respectively. Networks were trained on inputs of raw red/blue/green pixels as well as optical flow for each frame. We explore the effect of different recurrent models (long short-term memory versus convolutional long short-term memory). All models were trained on 80/20 train/test splits.

RESULTS : We observe that all models are able to reliably predict either the presence of a gesture (identification, area under the curve: 0.88) as well as the type of gesture (classification, area under the curve: 0.87) at significantly above chance levels. For both gesture identification and classification datasets, we observed no effect of recurrent classification model choice on performance.

CONCLUSION : Our results demonstrate computer vision's ability to recognize features that not only can identify the action of suturing but also distinguish between different classifications of suturing gestures. This demonstrates the potential to utilize deep learning computer vision toward future automation of surgical skill assessment.

Luongo Francisco, Hakim Ryan, Nguyen Jessica H, Anandkumar Animashree, Hung Andrew J

2020-Sep-25

In Progress in brain research

Barbosa Breda João, Van Eijgen Jan, Stalmans Ingeborg

2020

Adaptive optics, Artificial intelligence, Doppler OCT, Glaucoma, OCT-A, OCTA, Retinal oximetry, Vascular

In Systematic reviews

BACKGROUND : Expenditure on driver-related behavioral interventions and road use policy is often justified by their impact on the frequency of fatal and serious injury crashes. Given the rarity of fatal and serious injury crashes, offense history, and crash history of drivers are sometimes used as an alternative measure of the impact of interventions and changes to policy. The primary purpose of this systematic review was to assess the rigor of statistical modeling used to predict fatal and serious crashes from offense history and crash history using a purpose-made quality assessment tool. A secondary purpose was to explore study outcomes.

METHODS : Only studies that used observational data and presented a statistical model of crash prediction from offense history or crash history were included. A quality assessment tool was developed for the systematic evaluation of statistical quality indicators across studies. The search was conducted in June 2019.

RESULTS : One thousand one hundred and five unique records were identified, 252 full texts were screened for inclusion, resulting in 20 studies being included in the review. The results indicate substantial and important limitations in the modeling methods used. Most studies demonstrated poor statistical rigor ranging from low to middle quality. There was a lack of confidence in published findings due to poor variable selection, poor adherence to statistical assumptions relating to multicollinearity, and lack of validation using new data.

CONCLUSIONS : It was concluded that future research should consider machine learning to overcome correlations in the data, use rigorous vetting procedures to identify predictor variables, and validate statistical models using new data to improve utility and generalizability of models.

SYSTEMATIC REVIEW REGISTRATION : PROSPERO CRD42019137081.

Slikboer Reneta, Muir Samuel D, Silva S S M, Meyer Denny

2020-Sep-28

Crash, Crash history, Driver offenses, Offense, Quality assessment tool, Statistical modeling, Statistics, Systematic review, Traffic

In Current medical imaging

BACKGROUND : Traditional endoscopy is an invasive and painful method of examining the gastrointestinal tract (GIT) not supported by the physicians and patients. To handle this issue, video endoscopy (VE) or wireless capsule endoscopy (WCE) is recommended and utilized for GIT examination. Furthermore, manual assessment of captured images is not possible for an expert physician because it's a time taking task to analyze thousands of images thoroughly. Hence, there comes the need for a Computer-Aided-Diagnosis (CAD) method to help doctors in the analysis of images. Many researchers have proposed techniques for automated recognition and classification of abnormality in captured images.

INTRODUCTION : In this article, existing methods for automated classification, segmentation and detection of several GI diseases are discussed. Paper gives a comprehensive detail about these state-of-the-art methods. Furthermore, literature is divided into several subsections based on preprocessing techniques, segmentation techniques, handcrafted features based techniques and deep learning based techniques. Finally, issues, challenges and limitations are also undertaken.

CONCLUSION : This comprehensive review article combines information related to a number of GI diseases diagnosis methods at one place. Study of this article will facilitate the researchers to develop new algorithms and approaches for early detection of GI diseases detection with more promising results as compared to the existing ones of literature.

RESULTS : A comparative analysis of different approaches for the detection and classification of GI infections.

Naz Javeria, Sharif Muhammad, Yasmin Mussarat, Raza Mudassar, Khan Muhammad Attique

2020-Sep-28

Computer aided design (CAD), Convolutional Neural Network (CNN), Gastrointestinal Tract (GIT), Handcrafted features. , Machine learning, Wireless Capsule Endoscopy (WCE)

In Human factors

OBJECTIVE : The goal of this study is to assess machine learning for predicting procedure performance from operator and procedure characteristics.

BACKGROUND : Procedures are vital for the performance and safety of high-risk industries. Current procedure design guidelines are insufficient because they rely on subjective assessments and qualitative analyses that struggle to integrate and quantify the diversity of factors that influence procedure performance.

METHOD : We used data from a 25-participant study with four procedures, conducted on a high-fidelity oil extraction simulation to develop logistic regression (LR), random forest (RF), and decision tree (DT) algorithms that predict procedure step performance from operator, step, readability, and natural language processing-based features. Features were filtered using the Boruta approach. The algorithms were trained and optimized with a repeated 10-fold cross-validation. After training, inference was performed using variable importance and partial dependence plots.

RESULTS : The RF, DT, and LR algorithms with all features had an area under the receiver operating characteristic curve (AUC) of 0.78, 0.77, and 0.75, respectively, and significantly outperformed the LR with only operator features (LROP), with an AUC of 0.61. The most important features were experience, familiarity, total words, and character-based metrics. The partial dependence plots showed that steps with fewer words, abbreviations, and characters were correlated with correct step performance.

CONCLUSION : Machine learning algorithms are a promising approach for predicting step-level procedure performance, with acknowledged limitations on interpolating to nonobserved data, and may help guide procedure design after validation with additional data on further tasks.

APPLICATION : After validation, the inferences from these models can be used to generate procedure design alternatives.

McDonald Anthony D, Ade Nilesh, Peres S Camille

2020-Sep-28

decision tree, machine learning, operator performance, procedure design, random forest

In Mathematical biosciences and engineering : MBE

Phi Khanh Phung Cong, Tran Duc-Tan, Duong Van Tu, Thinh Nguyen Hong, Tran Duc-Nghia

2020-Mar-11

** acceleration , classification , cow , monitoring , sensor **

In Applied soft computing

Karthik R, Menaka R, M Hariharan

2020-Sep-23

CNN, COVID-19, Chest X-ray, Deep learning, Pneumonia

In Optics express

Gibson Graham M, Johnson Steven D, Padgett Miles J

2020-Sep-14

In Optics express

Chen Linfei, Peng BoYan, Gan Wenwen, Liu Yuanqian

2020-Sep-14

In Optics express

Li Jiaosheng, Zhang Qinnan, Zhong Liyun, Tian Jindong, Pedrini Giancarlo, Lu Xiaoxu

2020-Sep-14

In Optics express

Dardikman-Yoffe Gili, Eldar Yonina C

2020-Sep-14

In Optics express

Peng Zhaoqiang, Jian Jianan, Wen Hongqiao, Gribok Andrei, Wang Mohan, Liu Hu, Huang Sheng, Mao Zhi-Hong, Chen Kevin P

2020-Sep-14

In Diagnostics (Basel, Switzerland)

Sriporn Krit, Tsai Cheng-Fa, Tsai Chia-En, Wang Paohsi

2020-Sep-24

activation function (Mish), convolutional neural network, deep learning, image classification, image processing, malaria, optimization methods

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

Cha Gi-Wook, Moon Hyeun Jun, Kim Young-Min, Hong Won-Hwa, Hwang Jung-Ha, Park Won-Jun, Kim Young-Chan

2020-Sep-24

construction waste management, demolition waste management, leave-one-out cross-validation, prediction model, random forest, small data

In Behavioral sciences (Basel, Switzerland)

BACKGROUND : The present study investigated the role of temperament and attachment security in predicting individual differences in the five factor personality traits among adults. As previous studies suggested the potential moderating role of attachment in the association between temperament and personality traits, the present study sought to examine an interactionist model combining attachment and temperament in explaining individual differences in personality traits.

METHODS : A sample of 1871 participants (1151 women and 719 men) completed self-report measures of adult attachment style (the Relationships Questionnaire-RQ), temperament dimension (the Fisher Temperament Inventory-FTI), and personality domain (the Five Factor Model-FFM).

RESULTS : Partial correlational analyses revealed associations between attachment security and each of the five domains of the FFM, and few associations between some temperament dimensions and several domains of the FFM. Moderated regression analyses showed that attachment security moderated the associations between temperament dimensions and the Agreeableness domain of the FFM. Among secure individuals, those with higher scores on the Curious/Energetic, Cautious/Social Norm Compliant and Prosocial/Empathetic scales exhibited higher Agreeableness scores, whereas among insecure individuals, those with higher scores on the Analytic/Tough-minded scale exhibited lower scores on the Agreeableness scale.

CONCLUSION : Overall, the current study provides evidence in support of the substantive role of social-environmental factors (Adult Attachment) as a moderating element bridging temperament-related personality elements and a number of their FFM manifestations.

Barel Efrat, Mizrachi Yonathan, Nachmani Mayyan

2020-Sep-24

attachment, personality, temperament

In Microorganisms

Higgins Daleniece, Mukherjee Nabanita, Pal Chandan, Sulaiman Irshad M, Jiang Yu, Hanna Samir, Dunn John R, Karmaus Wilfried, Banerjee Pratik

2020-Sep-24

Salmonella, antibiotic resistance, virulence, virulotyping

In Mathematical biosciences and engineering : MBE

Liu Zuo Zhi, Wang Xiao Tian, Yuan Quan

2020-Jun-15

** dictionary learning , neural spike detection , sparse feature , sparse representation **

In Frontiers in systems neuroscience

Liu Junxiu, Wu Guopei, Luo Yuling, Qiu Senhui, Yang Su, Li Wei, Bi Yifei

2020

EEG, convolutional neural network, deep neural network, emotion recognition, sparse autoencoder

In Applied soft computing

Ezzat Dalia, Hassanien Aboul Ella, Ella Hassan Aboul

2020-Sep-22

Convolutional neural networks, Deep learning, Gravitational search algorithm, Hyperparameters optimization, SARS-CoV-2, Transfer learning

In The Lancet. Digital health

Background : The COVID-19 pandemic has affected millions of individuals and caused hundreds of thousands of deaths worldwide. Predicting mortality among patients with COVID-19 who present with a spectrum of complications is very difficult, hindering the prognostication and management of the disease. We aimed to develop an accurate prediction model of COVID-19 mortality using unbiased computational methods, and identify the clinical features most predictive of this outcome.

Methods : In this prediction model development and validation study, we applied machine learning techniques to clinical data from a large cohort of patients with COVID-19 treated at the Mount Sinai Health System in New York City, NY, USA, to predict mortality. We analysed patient-level data captured in the Mount Sinai Data Warehouse database for individuals with a confirmed diagnosis of COVID-19 who had a health system encounter between March 9 and April 6, 2020. For initial analyses, we used patient data from March 9 to April 5, and randomly assigned (80:20) the patients to the development dataset or test dataset 1 (retrospective). Patient data for those with encounters on April 6, 2020, were used in test dataset 2 (prospective). We designed prediction models based on clinical features and patient characteristics during health system encounters to predict mortality using the development dataset. We assessed the resultant models in terms of the area under the receiver operating characteristic curve (AUC) score in the test datasets.

Findings : Using the development dataset (n=3841) and a systematic machine learning framework, we developed a COVID-19 mortality prediction model that showed high accuracy (AUC=0·91) when applied to test datasets of retrospective (n=961) and prospective (n=249) patients. This model was based on three clinical features: patient's age, minimum oxygen saturation over the course of their medical encounter, and type of patient encounter (inpatient vs outpatient and telehealth visits).

Interpretation : An accurate and parsimonious COVID-19 mortality prediction model based on three features might have utility in clinical settings to guide the management and prognostication of patients affected by this disease. External validation of this prediction model in other populations is needed.

Funding : National Institutes of Health.

Yadaw Arjun S, Li Yan-Chak, Bose Sonali, Iyengar Ravi, Bunyavanich Supinda, Pandey Gaurav

2020-Oct

In Neuropsychiatric disease and treatment

Background : The outbreak of the 2019 novel coronavirus disease (COVID-19) not only caused physical abnormalities, but also caused psychological distress, especially for undergraduate students who are facing the pressure of academic study and work. We aimed to explore the prevalence rate of probable anxiety and probable insomnia and to find the risk factors among a longitudinal study of undergraduate students using the approach of machine learning.

Methods : The baseline data (T1) were collected from freshmen who underwent psychological evaluation at two months after entering the university. At T2 stage (February 10th to 13th, 2020), we used a convenience cluster sampling to assess psychological state (probable anxiety was assessed by general anxiety disorder-7 and probable insomnia was assessed by insomnia severity index-7) based on a web survey. We integrated information attained at T1 stage to predict probable anxiety and probable insomnia at T2 stage using a machine learning algorithm (XGBoost).

Results : Finally, we included 2009 students (response rate: 80.36%). The prevalence rate of probable anxiety and probable insomnia was 12.49% and 16.87%, respectively. The XGBoost algorithm predicted 1954 out of 2009 students (translated into 97.3% accuracy) and 1932 out of 2009 students (translated into 96.2% accuracy) who suffered anxiety and insomnia symptoms, respectively. The most relevant variables in predicting probable anxiety included romantic relationship, suicidal ideation, sleep symptoms, and a history of anxiety symptoms. The most relevant variables in predicting probable insomnia included aggression, psychotic experiences, suicidal ideation, and romantic relationship.

Conclusion : Risks for probable anxiety and probable insomnia among undergraduate students can be identified at an individual level by baseline data. Thus, timely psychological intervention for anxiety and insomnia symptoms among undergraduate students is needed considering the above factors.

Ge Fenfen, Zhang Di, Wu Lianhai, Mu Hongwei

2020

COVID-19, anxiety, cohort, insomnia, machine learning

In The Lancet. Digital health

Background : Prompt identification of patients suspected to have COVID-19 is crucial for disease control. We aimed to develop a deep learning algorithm on the basis of chest CT for rapid triaging in fever clinics.

Methods : We trained a U-Net-based model on unenhanced chest CT scans obtained from 2447 patients admitted to Tongji Hospital (Wuhan, China) between Feb 1, 2020, and March 3, 2020 (1647 patients with RT-PCR-confirmed COVID-19 and 800 patients without COVID-19) to segment lung opacities and alert cases with COVID-19 imaging manifestations. The ability of artificial intelligence (AI) to triage patients suspected to have COVID-19 was assessed in a large external validation set, which included 2120 retrospectively collected consecutive cases from three fever clinics inside and outside the epidemic centre of Wuhan (Tianyou Hospital [Wuhan, China; area of high COVID-19 prevalence], Xianning Central Hospital [Xianning, China; area of medium COVID-19 prevalence], and The Second Xiangya Hospital [Changsha, China; area of low COVID-19 prevalence]) between Jan 22, 2020, and Feb 14, 2020. To validate the sensitivity of the algorithm in a larger sample of patients with COVID-19, we also included 761 chest CT scans from 722 patients with RT-PCR-confirmed COVID-19 treated in a makeshift hospital (Guanggu Fangcang Hospital, Wuhan, China) between Feb 21, 2020, and March 6, 2020. Additionally, the accuracy of AI was compared with a radiologist panel for the identification of lesion burden increase on pairs of CT scans obtained from 100 patients with COVID-19.

Findings : In the external validation set, using radiological reports as the reference standard, AI-aided triage achieved an area under the curve of 0·953 (95% CI 0·949-0·959), with a sensitivity of 0·923 (95% CI 0·914-0·932), specificity of 0·851 (0·842-0·860), a positive predictive value of 0·790 (0·777-0·803), and a negative predictive value of 0·948 (0·941-0·954). AI took a median of 0·55 min (IQR: 0·43-0·63) to flag a positive case, whereas radiologists took a median of 16·21 min (11·67-25·71) to draft a report and 23·06 min (15·67-39·20) to release a report. With regard to the identification of increases in lesion burden, AI achieved a sensitivity of 0·962 (95% CI 0·947-1·000) and a specificity of 0·875 (95 %CI 0·833-0·923). The agreement between AI and the radiologist panel was high (Cohen's kappa coefficient 0·839, 95% CI 0·718-0·940).

Interpretation : A deep learning algorithm for triaging patients with suspected COVID-19 at fever clinics was developed and externally validated. Given its high accuracy across populations with varied COVID-19 prevalence, integration of this system into the standard clinical workflow could expedite identification of chest CT scans with imaging indications of COVID-19.

Funding : Special Project for Emergency of the Science and Technology Department of Hubei Province, China.

Wang Minghuan, Xia Chen, Huang Lu, Xu Shabei, Qin Chuan, Liu Jun, Cao Ying, Yu Pengxin, Zhu Tingting, Zhu Hui, Wu Chaonan, Zhang Rongguo, Chen Xiangyu, Wang Jianming, Du Guang, Zhang Chen, Wang Shaokang, Chen Kuan, Liu Zheng, Xia Liming, Wang Wei

2020-Oct

In International journal of medical informatics ; h5-index 49.0

BACKGROUND : With the recent advances in computational science, machine-learning methods have been increasingly used in medical research. Because such projects usually require both a clinician and a computational data scientist, there is a need for interdisciplinary research collaboration. However, there has been no published analysis of research collaboration networks in cardiovascular medicine using machine intelligence.

METHODS : Co-authorship network analysis was conducted on 2857 research articles published between 2009 and 2019. Bibliographic data were collected from the Web of Science, and the co-authorship networks were represented as undirected multigraphs. The network density, average degree, clustering coefficient, and number of communities were calculated, and the chronological changes were assessed. Thereafter, the leading authors were identified according to the centrality metrics. Finally, we investigated the significance of the characteristics of the co-authorship network in the largest component via a Monte Carlo simulation with the Barabasi-Albert model.

RESULTS : The co-authorship network of the entire period consisted of 13,979 nodes and 68,668 weighted edges. A time-series analysis revealed a linear correlation between the number of nodes and the number of edges (R² = 0.9937, p < 0.001). Additionally, the number of communities was linearly correlated with the number of nodes (R² = 0.9788, p < 0.001). The average shortest path increased by a greater degree than the logarithm of the number of nodes, indicating the scale-free structure of the network. We identified D. Berman as the most central author with regard to the degree centrality and closeness centrality. S. Neubauer was the top-ranking author with regard to the betweenness centrality. Among the 22 authors who were ranked in the top 10 for any centrality, 14 authors (63.6%) had a medical degree (medical doctor, MD). The remaining eight non-MD researchers had a PhD in computational science-related fields. The number of communities detected in the Barabasi-Albert model simulation was similar to that for the largest component of the real network (6.21 ± 0.07 vs. 6, p = 0.096).

CONCLUSIONS : A co-authorship network analysis revealed a structure of collaboration networks in the application of machine learning in the field of cardiovascular disease, which can be useful for planning future scientific collaboration.

Higaki Akinori, Uetani Teruyoshi, Ikeda Shuntaro, Yamaguchi Osamu

2020-Sep-19

Cardiovascular research, Co-authorship network analysis, Machine learning, Natural language processing, Social network analysis

In World journal of gastroenterology ; h5-index 103.0

BACKGROUND : Efforts should be made to develop a deep-learning diagnosis system to distinguish pancreatic cancer from benign tissue due to the high morbidity of pancreatic cancer.

AIM : To identify pancreatic cancer in computed tomography (CT) images automatically by constructing a convolutional neural network (CNN) classifier.

METHODS : A CNN model was constructed using a dataset of 3494 CT images obtained from 222 patients with pathologically confirmed pancreatic cancer and 3751 CT images from 190 patients with normal pancreas from June 2017 to June 2018. We established three datasets from these images according to the image phases, evaluated the approach in terms of binary classification (i.e., cancer or not) and ternary classification (i.e., no cancer, cancer at tail/body, cancer at head/neck of the pancreas) using 10-fold cross validation, and measured the effectiveness of the model with regard to the accuracy, sensitivity, and specificity.

RESULTS : The overall diagnostic accuracy of the trained binary classifier was 95.47%, 95.76%, 95.15% on the plain scan, arterial phase, and venous phase, respectively. The sensitivity was 91.58%, 94.08%, 92.28% on three phases, with no significant differences (χ² = 0.914, P = 0.633). Considering that the plain phase had same sensitivity, easier access, and lower radiation compared with arterial phase and venous phase , it is more sufficient for the binary classifier. Its accuracy on plain scans was 95.47%, sensitivity was 91.58%, and specificity was 98.27%. The CNN and board-certified gastroenterologists achieved higher accuracies than trainees on plain scan diagnosis (χ² = 21.534, P < 0.001; χ² = 9.524, P < 0.05; respectively). However, the difference between CNN and gastroenterologists was not significant (χ² = 0.759, P = 0.384). In the trained ternary classifier, the overall diagnostic accuracy of the ternary classifier CNN was 82.06%, 79.06%, and 78.80% on plain phase, arterial phase, and venous phase, respectively. The sensitivity scores for detecting cancers in the tail were 52.51%, 41.10% and, 36.03%, while sensitivity for cancers in the head was 46.21%, 85.24% and 72.87% on three phases, respectively. Difference in sensitivity for cancers in the head among the three phases was significant (χ² = 16.651, P < 0.001), with arterial phase having the highest sensitivity.

CONCLUSION : We proposed a deep learning-based pancreatic cancer classifier trained on medium-sized datasets of CT images. It was suitable for screening purposes in pancreatic cancer detection.

Ma Han, Liu Zhong-Xin, Zhang Jing-Jing, Wu Feng-Tian, Xu Cheng-Fu, Shen Zhe, Yu Chao-Hui, Li You-Ming

2020-Sep-14

Computed tomography, Convolutional neural networks, Deep learning, Pancreatic cancer

In The Lancet. Digital health

Zhou Yadi, Wang Fei, Tang Jian, Nussinov Ruth, Cheng Feixiong

2020-Sep-18

In NeuroImage. Clinical

OBJECTIVE : Focal cortical dysplasia (FCD) is the most common epileptogenic developmental malformation and a prevalent cause of surgically amenable epilepsy. While cellular and molecular biology data suggest that FCD lesional characteristics lie along a spectrum, this notion remains to be verified in vivo. We tested the hypothesis that machine learning applied to MRI captures FCD lesional variability at a mesoscopic scale.

METHODS : We studied 46 patients with histologically verified FCD Type II and 35 age- and sex-matched healthy controls. We applied consensus clustering, an unsupervised learning technique that identifies stable clusters based on bootstrap-aggregation, to 3 T multicontrast MRI (T1-weighted MRI and FLAIR) features of FCD normalized with respect to distributions in controls.

RESULTS : Lesions were parcellated into four classes with distinct structural profiles variably expressed within and across patients: Class-1 with isolated white matter (WM) damage; Class-2 combining grey matter (GM) and WM alterations; Class-3 with isolated GM damage; Class-4 with GM-WM interface anomalies. Class membership was replicated in two independent datasets. Classes with GM anomalies impacted local function (resting-state fMRI derived ALFF), while those with abnormal WM affected large-scale connectivity (assessed by degree centrality). Overall, MRI classes reflected typical histopathological FCD characteristics: Class-1 was associated with severe WM gliosis and interface blurring, Class-2 with severe GM dyslamination and moderate WM gliosis, Class-3 with moderate GM gliosis, Class-4 with mild interface blurring. A detection algorithm trained on class-informed data outperformed a class-naïve paradigm.

SIGNIFICANCE : Machine learning applied to widely available MRI contrasts uncovers FCD Type II variability at a mesoscopic scale and identifies tissue classes with distinct structural dimensions, functional and histopathological profiles. Integrating in vivo staging of FCD traits with automated lesion detection is likely to inform the development of novel personalized treatments.

Lee Hyo M, Gill Ravnoor S, Fadaie Fatemeh, Cho Kyoo H, Guiot Marie C, Hong Seok-Jun, Bernasconi Neda, Bernasconi Andrea

2020-Sep-18

Cortical dysplasia, Epilepsy, MRI

In Computer methods and programs in biomedicine

BACKGROUND AND OBJECTIVE : In medical imaging, population studies have to overcome the differences that exist between individuals to identify invariant image features that can be used for diagnosis purposes. In functional neuroimaging, an appealing solution to identify neural coding principles that hold at the population level is inter-subject pattern analysis, i.e. to learn a predictive model on data from multiple subjects and evaluate its generalization performance on new subjects. Although it has gained popularity in recent years, its widespread adoption is still hampered by the blatant lack of a formal definition in the literature. In this paper, we precisely introduce the first principled formalization of inter-subject pattern analysis targeted at multivariate group analysis of functional neuroimaging.

METHODS : We propose to frame inter-subject pattern analysis as a multi-source transductive transfer question, thus grounding it within several well defined machine learning settings and broadening the spectrum of usable algorithms. We describe two sets of inter-subject brain decoding experiments that use several open datasets: a magneto-encephalography study with 16 subjects and a functional magnetic resonance imaging paradigm with 100 subjects. We assess the relevance of our framework by performing model comparisons, where one brain decoding model exploits our formalization while others do not.

RESULTS : The first set of experiments demonstrates the superiority of a brain decoder that uses subject-by-subject standardization compared to state of the art models that use other standardization schemes, making the case for the interest of the transductive and the multi-source components of our formalization The second set of experiments quantitatively shows that, even after such transformation, it is more difficult for a brain decoder to generalize to new participants rather than to new data from participants available in the training phase, thus highlighting the transfer gap that needs to be overcome.

CONCLUSION : This paper describes the first formalization of inter-subject pattern analysis as a multi-source transductive transfer learning problem. We demonstrate the added value of this formalization using proof-of-concept experiments on several complementary functional neuroimaging datasets. This work should contribute to popularize inter-subject pattern analysis for functional neuroimaging population studies and pave the road for future methodological innovations.

Wang Qi, Artières Thierry, Takerkart Sylvain

2020-Sep-11

Functional neuroimaging, Machine learning, Neuroinformatics, Population studies

In Computers in biology and medicine

Sreejith S, Khanna Nehemiah H, Kannan A

2020-Sep-18

Chaotic maps, Class imbalance, Classification, Clinical decision support system, Feature selection, Multi Verse Optimisation, SMOTE

In Computers in biology and medicine

Pacal Ishak, Karaboga Dervis, Basturk Alper, Akay Bahriye, Nalbantoglu Ufuk

2020-Sep-17

Colon cancer, Colorectal cancer, Convolutional neural networks, Deep learning, Inflammatory bowel diseases, Medical image analysis, Rectal cancer

In Molecular biology and evolution

Policarpo Maxime, Fumey Julien, Lafargeas Philippe, Naquin Delphine, Thermes Claude, Naville Magali, Dechaud Corentin, Volff Jean-Nicolas, Cabau Cedric, Klopp Christophe, Møller Peter Rask, Bernatchez Louis, García-Machado Erik, Rétaux Sylvie, Casane Didier

2020-Sep-28

cavefishes, eye-specific genes, machine learning, molecular dating, pseudogenization, relaxed selection

In PloS one ; h5-index 176.0

Minallah Nasru, Tariq Mohsin, Aziz Najam, Khan Waleed, Rehman Atiq Ur, Belhaouari Samir Brahim

2020

In Journal of X-ray science and technology

BACKGROUND : Automatic segmentation of individual tooth root is a key technology for the reconstruction of the three-dimensional dental model from Cone Beam Computed Tomography (CBCT) images, which is of great significance for the orthodontic, implant and other dental diagnosis and treatment planning.

OBJECTIVES : Currently, tooth root segmentation is mainly done manually because of the similar gray of the tooth root and the alveolar bone from CBCT images. This study aims to explore the automatic tooth root segmentation algorithm of CBCT axial image sequence based on deep learning.

METHODS : We proposed a new automatic tooth root segmentation method based on the deep learning U-net with AGs. Since CBCT sequence has a strong correlation between adjacent slices, a Recurrent neural network (RNN) was applied to extract the intra-slice and inter-slice contexts. To develop and test this new method for automatic segmentation of tooth roots using CBCT images, 24 sets of CBCT sequences containing 1160 images and 5 sets of CBCT sequences containing 361 images were used to train and test the network, respectively.

RESULTS : Applying to the testing dataset, the segmentation accuracy measured by the intersection over union (IOU), dice similarity coefficient (DICE), average precision rate (APR), average recall rate (ARR), and average symmetrical surface distance (ASSD) are 0.914, 0.955, 95.8% , 95.3% , 0.145 mm, respectively.

CONCLUSIONS : The study demonstrates that the new method combining attention U-net with RNN yields the promising results of automatic tooth roots segmentation, which has potential to help improve the segmentation efficiency and accuracy in future clinical practice.

Li Qingqing, Chen Ke, Han Lin, Zhuang Yan, Li Jingtao, Lin Jiangli

2020

RNN, Tooth roots, attention U-net, automatic segmentation, cone beam computed tomography

In IEEE transactions on visualization and computer graphics

Zhang Dongbo, Lu Xuequan, Qin Hong, He Ying

2020-Sep-28

In IEEE transactions on medical imaging ; h5-index 74.0

Wu Huisi, Pan Junquan, Li Zhuoying, Wen Zhenkun, Qin Jing

2020-Sep-28

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

Wu Zhenyu, Wang Haotao, Wang Zhangyang, Wang Zhaowen, Jin Hailin

2020-Sep-28

In World journal of gastroenterology ; h5-index 103.0

Wang Ke-Wei, Dong Ming

2020-Sep-14

Artificial intelligence, Colorectal cancer, Colorectal polyps, Computer-assisted diagnosis, Deep learning

In SN comprehensive clinical medicine

Gaur Uma, Majumder Md Anwarul Azim, Sa Bidyadhar, Sarkar Sankalan, Williams Arlene, Singh Keerti

2020-Sep-22

COVID-19 pandemic, Challenges, Online learning, Opportunities, Preclinical medical education, Remote learning

In Circulation. Arrhythmia and electrophysiology

BACKGROUND : Identification of systolic heart failure among patients presenting to the emergency department (ED) with acute dyspnea is challenging. The reasons for dyspnea are often multifactorial. A focused physical evaluation and diagnostic testing can lack sensitivity and specificity. The objective of this study was to assess the accuracy of an artificial intelligence-enabled ECG to identify patients presenting with dyspnea who have left ventricular systolic dysfunction (LVSD).

METHODS : We retrospectively applied a validated artificial intelligence-enabled ECG algorithm for the identification of LVSD (defined as LV ejection fraction ≤35%) to a cohort of patients aged ≥18 years who were evaluated in the ED at a Mayo Clinic site with dyspnea. Patients were included if they had at least one standard 12-lead ECG acquired on the date of the ED visit and an echocardiogram performed within 30 days of presentation. Patients with prior LVSD were excluded. We assessed the model performance using area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity.

RESULTS : A total of 1606 patients were included. Median time from ECG to echocardiogram was 1 day (Q1: 1, Q3: 2). The artificial intelligence-enabled ECG algorithm identified LVSD with an area under the receiver operating characteristic curve of 0.89 (95% CI, 0.86-0.91) and accuracy of 85.9%. Sensitivity, specificity, negative predictive value, and positive predictive value were 74%, 87%, 97%, and 40%, respectively. To identify an ejection fraction <50%, the area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity were 0.85 (95% CI, 0.83-0.88), 86%, 63%, and 91%, respectively. NT-proBNP (N-terminal pro-B-type natriuretic peptide) alone at a cutoff of >800 identified LVSD with an area under the receiver operating characteristic curve of 0.80 (95% CI, 0.76-0.84).

CONCLUSIONS : The ECG is an inexpensive, ubiquitous, painless test which can be quickly obtained in the ED. It effectively identifies LVSD in selected patients presenting to the ED with dyspnea when analyzed with artificial intelligence and outperforms NT-proBNP. Graphic Abstract: A graphic abstract is available for this article.

Adedinsewo Demilade, Carter Rickey E, Attia Zachi, Johnson Patrick, Kashou Anthony H, Dugan Jennifer L, Albus Michael, Sheele Johnathan M, Bellolio Fernanda, Friedman Paul A, Lopez-Jimenez Francisco, Noseworthy Peter A

2020-Aug

artificial intelligence, cardiomyopathies, dyspnea, electrocardiogram, heart failure

In Journal of chemical information and modeling

Ma Ruimin, Luo Tengfei

2020-Sep-28

In Analytical chemistry

Chen Xuechun, Xun Dejin, Zheng Ruzhang, Zhao Lu, Lu Yuqing, Huang Jun, Wang Rui, Wang Yi

2020-Sep-28

In Current topics in behavioral neurosciences

Oquendo Maria A, Porras-Segovia Alejandro

2020-Sep-29

Suicidal behavior, Suicide, Suicide attempt, Suicide prevention

In Radiological physics and technology

Onodera Shu, Lee Yongbum, Tanaka Yoshitaka

2020-Sep-28

Bedside chest radiography, Flat-panel detectors, Radiation dose, Radiographic image enhancement, Scatter correction processing, X-ray scatter removal grids

In European radiology ; h5-index 62.0

OBJECTIVES : The goal of the present study was to classify the most common types of plain radiographs using a neural network and to validate the network's performance on internal and external data. Such a network could help improve various radiological workflows.

METHODS : All radiographs from the year 2017 (n = 71,274) acquired at our institution were retrieved from the PACS. The 30 largest categories (n = 58,219, 81.7% of all radiographs performed in 2017) were used to develop and validate a neural network (MobileNet v1.0) using transfer learning. Image categories were extracted from DICOM metadata (study and image description) and mapped to the WHO manual of diagnostic imaging. As an independent, external validation set, we used images from other institutions that had been stored in our PACS (n = 5324).

RESULTS : In the internal validation, the overall accuracy of the model was 90.3% (95%CI: 89.2-91.3%), whereas, for the external validation set, the overall accuracy was 94.0% (95%CI: 93.3-94.6%).

CONCLUSIONS : Using data from one single institution, we were able to classify the most common categories of radiographs with a neural network. The network showed good generalizability on the external validation set and could be used to automatically organize a PACS, preselect radiographs so that they can be routed to more specialized networks for abnormality detection or help with other parts of the radiological workflow (e.g., automated hanging protocols; check if ordered image and performed image are the same). The final AI algorithm is publicly available for evaluation and extension.

KEY POINTS : • Data from one single institution can be used to train a neural network for the correct detection of the 30 most common categories of plain radiographs. • The trained model achieved a high accuracy for the majority of categories and showed good generalizability to images from other institutions. • The neural network is made publicly available and can be used to automatically organize a PACS or to preselect radiographs so that they can be routed to more specialized neural networks for abnormality detection.

Dratsch Thomas, Korenkov Michael, Zopfs David, Brodehl Sebastian, Baessler Bettina, Giese Daniel, Brinkmann Sebastian, Maintz David, Pinto Dos Santos Daniel

2020-Sep-28

Artificial intelligence, Machine learning, Radiography

In International journal of computer assisted radiology and surgery

PURPOSE : Bone age assessment is not only an important means of assessing maturity of adolescents, but also plays an indispensable role in the fields of orthodontics, kinematics, pediatrics, forensic science, etc. Most studies, however, do not take into account the impact of background noise on the results of the assessment. In order to obtain accurate bone age, this paper presents an automatic assessment method, for bone age based on deep convolutional neural networks.

METHOD : Our method was divided into two phases. In the image segmentation stage, the segmentation network U-Net was used to acquire the mask image which was then compared with the original image to obtain the hand bone portion after removing the background interference. For the classification phase, in order to further improve the evaluation performance, an attention mechanism was added on the basis of Visual Geometry Group Network (VGGNet). Attention mechanisms can help the model invest more resources in important areas of the hand bone.

RESULT : The assessment model was tested on the RSNA2017 Pediatric Bone Age dataset. The results show that our adjusted model outperforms the VGGNet. The mean absolute error can reach 9.997 months, which outperforms other common methods for bone age assessment.

CONCLUSION : We explored the establishment of an automated bone age assessment method based on deep learning. This method can efficiently eliminate the influence of background interference on bone age evaluation, improve the accuracy of bone age evaluation, provide important reference value for bone age determination, and can aid in the prevention of adolescent growth and development diseases.

Gao Yunyuan, Zhu Tao, Xu Xiaohua

2020-Sep-28

Attention mechanism, Bone age assessment, Deep learning, Segmentation

In Social cognitive and affective neuroscience ; h5-index 61.0

Tovar Dale T, Chavez Robert S

2020-Sep-28

dMRI, fMRI, meta-analysis, unsupervised learning

In Journal of medical Internet research ; h5-index 88.0

BACKGROUND : Deep learning models have attracted significant interest from health care researchers during the last few decades. There have been many studies that apply deep learning to medical applications and achieve promising results. However, there are three limitations to the existing models: (1) most clinicians are unable to interpret the results from the existing models, (2) existing models cannot incorporate complicated medical domain knowledge (eg, a disease causes another disease), and (3) most existing models lack visual exploration and interaction. Both the electronic health record (EHR) data set and the deep model results are complex and abstract, which impedes clinicians from exploring and communicating with the model directly.

OBJECTIVE : The objective of this study is to develop an interpretable and accurate risk prediction model as well as an interactive clinical prediction system to support EHR data exploration, knowledge graph demonstration, and model interpretation.

METHODS : A domain-knowledge-guided recurrent neural network (DG-RNN) model is proposed to predict clinical risks. The model takes medical event sequences as input and incorporates medical domain knowledge by attending to a subgraph of the whole medical knowledge graph. A global pooling operation and a fully connected layer are used to output the clinical outcomes. The middle results and the parameters of the fully connected layer are helpful in identifying which medical events cause clinical risks. DG-Viz is also designed to support EHR data exploration, knowledge graph demonstration, and model interpretation.

RESULTS : We conducted both risk prediction experiments and a case study on a real-world data set. A total of 554 patients with heart failure and 1662 control patients without heart failure were selected from the data set. The experimental results show that the proposed DG-RNN outperforms the state-of-the-art approaches by approximately 1.5%. The case study demonstrates how our medical physician collaborator can effectively explore the data and interpret the prediction results using DG-Viz.

CONCLUSIONS : In this study, we present DG-Viz, an interactive clinical prediction system, which brings together the power of deep learning (ie, a DG-RNN-based model) and visual analytics to predict clinical risks and visually interpret the EHR prediction results. Experimental results and a case study on heart failure risk prediction tasks demonstrate the effectiveness and usefulness of the DG-Viz system. This study will pave the way for interactive, interpretable, and accurate clinical risk predictions.

Li Rui, Yin Changchang, Yang Samuel, Qian Buyue, Zhang Ping

2020-Sep-28

electronic health records, interpretable deep learning, knowledge graph, visual analytics

In Journal of computational biology : a journal of computational molecular cell biology

Syed Khajamoinuddin, Sleeman William, Soni Payal, Hagan Michael, Palta Jatinder, Kapoor Rishabh, Ghosh Preetam

2020-Sep-25

SEER, SVM, androgen deprivation therapy, localized prostate cancer, radiation therapy, random forests

In Chaos, solitons, and fractals

Harrou Fouzi, Dairi Abdelkader, Kadri Farid, Sun Ying

2020-Oct

Deep learning, ED demands, Emergency departments, Forecasting, Patient flows

In Materials today. Proceedings

Somasekar J, Pavan Kumar Visulaization P, Sharma Avinash, Ramesh G

2020-Sep-22

COVID-19, Chest X-Ray Images, Classification, Diagnosis, Machine Learning, medical image analysis

In Analytical chemistry

Olaetxea Ion, Valero Ana, Lopez Eneko, Lafuente Héctor, Izeta Ander, Jaunarena Ibon, Seifert Andreas

2020-Sep-28

In Communications biology

Peng Weng Kung, Ng Tian-Tsong, Loh Tze Ping

2020-Sep-28

In Scientific reports ; h5-index 158.0

Babanezhad Meisam, Nakhjiri Ali Taghvaie, Marjani Azam, Shirazian Saeed

2020-Sep-28

In Journal of proteome research

Yang Yi, Horvatovich Péter, Qiao Liang

2020-Sep-28

In Dementia and neurocognitive disorders

BACKGROUND AND PURPOSE : This study uses an artificial-intelligence model (recurrent neural network) for evaluating the following hypothesis: social determinants of disease association in a middle-aged or old population are different across gender and age groups. Here, the disease association indicates an association among cerebrovascular disease, hearing loss and cognitive impairment.

METHODS : Data came from the Korean Longitudinal Study of Ageing (2014-2016), with 6,060 participants aged 53 years or more, that is, 2,556 men, 3,504 women, 3,640 aged 70 years or less (70-), 2,420 aged 71 years or more (71+). The disease association was divided into 8 categories: 1 category for having no disease, 3 categories for having 1, 3 categories for having 2, and 1 category for having 3. Variable importance, the effect of a variable on model performance, was used for finding important social determinants of the disease association in a particular gender/age group, and evaluating the hypothesis above.

RESULTS : Based on variable importance from the recurrent neural network, important social determinants of the disease association were different across gender and age groups: 1) leisure activity for men; 2) parents alive, income and economic activity for women; 3) children alive, education and family activity for 70-; and 4) brothers/sisters cohabiting, religious activity and leisure activity for 70+.

CONCLUSIONS : The findings of this study support the hypothesis, suggesting the development of new guidelines reflecting different social determinants of the disease association across gender and age groups.

Lee Kwang Sig, Park Kun Woo

2020-Sep

Age, Cerebrovascular Disease, Cognitive Impairment, Gender, Hearing Loss, Social Determinant

In Applied microbiology and biotechnology

Hesami Mohsen, Jones Andrew Maxwell Phineas

2020-Sep-28

Androgenesis, Computational approach, Data-driven model, Embryogenesis, In vitro culture, Machine learning algorithm, Organogenesis, Plant biotechnology, Rhizogenesis, Shoot proliferation

In Journal of the American Medical Informatics Association : JAMIA

OBJECTIVE : To improve patient safety and clinical outcomes by reducing the risk of prescribing errors, we tested the accuracy of a hybrid clinical decision support system in prioritizing prescription checks.

MATERIALS AND METHODS : Data from electronic health records were collated over a period of 18 months. Inferred scores at a patient level (probability of a patient's set of active orders to require a pharmacist review) were calculated using a hybrid approach (machine learning and a rule-based expert system). A clinical pharmacist analyzed randomly selected prescription orders over a 2-week period to corroborate our findings. Predicted scores were compared with the pharmacist's review using the area under the receiving-operating characteristic curve and area under the precision-recall curve. These metrics were compared with existing tools: computerized alerts generated by a clinical decision support (CDS) system and a literature-based multicriteria query prioritization technique. Data from 10 716 individual patients (133 179 prescription orders) were used to train the algorithm on the basis of 25 features in a development dataset.

RESULTS : While the pharmacist analyzed 412 individual patients (3364 prescription orders) in an independent validation dataset, the areas under the receiving-operating characteristic and precision-recall curves of our digital system were 0.81 and 0.75, respectively, thus demonstrating greater accuracy than the CDS system (0.65 and 0.56, respectively) and multicriteria query techniques (0.68 and 0.56, respectively).

DISCUSSION : Our innovative digital tool was notably more accurate than existing techniques (CDS system and multicriteria query) at intercepting potential prescription errors.

CONCLUSIONS : By primarily targeting high-risk patients, this novel hybrid decision support system improved the accuracy and reliability of prescription checks in a hospital setting.

Corny Jennifer, Rajkumar Asok, Martin Olivier, Dode Xavier, Lajonchère Jean-Patrick, Billuart Olivier, Bézie Yvonnick, Buronfosse Anne

2020-Sep-27

clinical, clinical pharmacy information systems, decision support systems, electronic prescribing, medication errors, supervised machine learning

In Integrative biology : quantitative biosciences from nano to macro

Masso Majid

2020-Sep-28

computational mutagenesis, homology-directed DNA repair, machine learning, prediction, structure–function relationships, variants

In The Lancet. Digital health

Background : The COVID-19 pandemic has affected millions of individuals and caused hundreds of thousands of deaths worldwide. Predicting mortality among patients with COVID-19 who present with a spectrum of complications is very difficult, hindering the prognostication and management of the disease. We aimed to develop an accurate prediction model of COVID-19 mortality using unbiased computational methods, and identify the clinical features most predictive of this outcome.

Methods : In this prediction model development and validation study, we applied machine learning techniques to clinical data from a large cohort of patients with COVID-19 treated at the Mount Sinai Health System in New York City, NY, USA, to predict mortality. We analysed patient-level data captured in the Mount Sinai Data Warehouse database for individuals with a confirmed diagnosis of COVID-19 who had a health system encounter between March 9 and April 6, 2020. For initial analyses, we used patient data from March 9 to April 5, and randomly assigned (80:20) the patients to the development dataset or test dataset 1 (retrospective). Patient data for those with encounters on April 6, 2020, were used in test dataset 2 (prospective). We designed prediction models based on clinical features and patient characteristics during health system encounters to predict mortality using the development dataset. We assessed the resultant models in terms of the area under the receiver operating characteristic curve (AUC) score in the test datasets.

Findings : Using the development dataset (n=3841) and a systematic machine learning framework, we developed a COVID-19 mortality prediction model that showed high accuracy (AUC=0·91) when applied to test datasets of retrospective (n=961) and prospective (n=249) patients. This model was based on three clinical features: patient's age, minimum oxygen saturation over the course of their medical encounter, and type of patient encounter (inpatient vs outpatient and telehealth visits).

Interpretation : An accurate and parsimonious COVID-19 mortality prediction model based on three features might have utility in clinical settings to guide the management and prognostication of patients affected by this disease. External validation of this prediction model in other populations is needed.

Funding : National Institutes of Health.

Yadaw Arjun S, Li Yan-Chak, Bose Sonali, Iyengar Ravi, Bunyavanich Supinda, Pandey Gaurav

2020-Oct

In The Lancet. Digital health

Background : Prompt identification of patients suspected to have COVID-19 is crucial for disease control. We aimed to develop a deep learning algorithm on the basis of chest CT for rapid triaging in fever clinics.

Methods : We trained a U-Net-based model on unenhanced chest CT scans obtained from 2447 patients admitted to Tongji Hospital (Wuhan, China) between Feb 1, 2020, and March 3, 2020 (1647 patients with RT-PCR-confirmed COVID-19 and 800 patients without COVID-19) to segment lung opacities and alert cases with COVID-19 imaging manifestations. The ability of artificial intelligence (AI) to triage patients suspected to have COVID-19 was assessed in a large external validation set, which included 2120 retrospectively collected consecutive cases from three fever clinics inside and outside the epidemic centre of Wuhan (Tianyou Hospital [Wuhan, China; area of high COVID-19 prevalence], Xianning Central Hospital [Xianning, China; area of medium COVID-19 prevalence], and The Second Xiangya Hospital [Changsha, China; area of low COVID-19 prevalence]) between Jan 22, 2020, and Feb 14, 2020. To validate the sensitivity of the algorithm in a larger sample of patients with COVID-19, we also included 761 chest CT scans from 722 patients with RT-PCR-confirmed COVID-19 treated in a makeshift hospital (Guanggu Fangcang Hospital, Wuhan, China) between Feb 21, 2020, and March 6, 2020. Additionally, the accuracy of AI was compared with a radiologist panel for the identification of lesion burden increase on pairs of CT scans obtained from 100 patients with COVID-19.

Findings : In the external validation set, using radiological reports as the reference standard, AI-aided triage achieved an area under the curve of 0·953 (95% CI 0·949-0·959), with a sensitivity of 0·923 (95% CI 0·914-0·932), specificity of 0·851 (0·842-0·860), a positive predictive value of 0·790 (0·777-0·803), and a negative predictive value of 0·948 (0·941-0·954). AI took a median of 0·55 min (IQR: 0·43-0·63) to flag a positive case, whereas radiologists took a median of 16·21 min (11·67-25·71) to draft a report and 23·06 min (15·67-39·20) to release a report. With regard to the identification of increases in lesion burden, AI achieved a sensitivity of 0·962 (95% CI 0·947-1·000) and a specificity of 0·875 (95 %CI 0·833-0·923). The agreement between AI and the radiologist panel was high (Cohen's kappa coefficient 0·839, 95% CI 0·718-0·940).

Interpretation : A deep learning algorithm for triaging patients with suspected COVID-19 at fever clinics was developed and externally validated. Given its high accuracy across populations with varied COVID-19 prevalence, integration of this system into the standard clinical workflow could expedite identification of chest CT scans with imaging indications of COVID-19.

Funding : Special Project for Emergency of the Science and Technology Department of Hubei Province, China.

Wang Minghuan, Xia Chen, Huang Lu, Xu Shabei, Qin Chuan, Liu Jun, Cao Ying, Yu Pengxin, Zhu Tingting, Zhu Hui, Wu Chaonan, Zhang Rongguo, Chen Xiangyu, Wang Jianming, Du Guang, Zhang Chen, Wang Shaokang, Chen Kuan, Liu Zheng, Xia Liming, Wang Wei

2020-Oct

In European journal of operational research

Reisach Ulrike

2020-Sep-22

Artificial intelligence, Behavioral OR, Decision-making, Education, Ethics in OR

In Frontiers in psychology ; h5-index 92.0

Papatzikis Efthymios, Zeba Fathima, Särkämö Teppo, Ramirez Rafael, Grau-Sánchez Jennifer, Tervaniemi Mari, Loewy Joanne

2020

COVID-19, music and neuroscience, music and neuroscience research protocols, music therapy, research crisis response

ArXiv Preprint

S. D. Lalitha, K. K. Thyagharajan

2020-09-29

In The Lancet. Digital health

Zhou Yadi, Wang Fei, Tang Jian, Nussinov Ruth, Cheng Feixiong

2020-Sep-18

In SN comprehensive clinical medicine

Gaur Uma, Majumder Md Anwarul Azim, Sa Bidyadhar, Sarkar Sankalan, Williams Arlene, Singh Keerti

2020-Sep-22

COVID-19 pandemic, Challenges, Online learning, Opportunities, Preclinical medical education, Remote learning

In Heliyon

Moreno Jenny Marcela, Sánchez Juan Manuel, Espitia Helbert Eduardo

2020-Sep

Artificial Neural Networks, Artificial intelligence, Climate variability, Climatology, Computer engineering, Control systems, Earth sciences, Environmental economics, Environmental science, Flood, Magdalena River, Neuro Fuzzy Systems, Support Vector Machine, Systems engineering

In NPJ digital medicine

Benjamens Stan, Dhunnoo Pranavsingh, Meskó Bertalan

2020

Health services, Outcomes research

In Data in brief

Ponciano Vasco, Pires Ivan Miguel, Ribeiro Fernando Reinaldo, Garcia Nuno M

2020-Oct

Accelerometer, Electrocardiography, Electroencephalography, Health, Magnetometer, Mobile devices, Sensors, Timed-up and go test

In Data in brief

Sánchez Luis, Vasile Massimiliano

2020-Oct

Collision risk assessment, Epistemic uncertainty, Evidence theory, Risk assessment, Space traffic management

In Data in brief

Fuchs K, Grundmann T, Haldimann M, Fleisch E

2020-Oct

Computer vision, Deep learning, GTIN, Object detection, Packaged products

In Data in brief

Ismail Asmida, Ahmad Siti Anom, Che Soh Azura, Hassan Mohd Khair, Harith Hazreen Haizi

2020-Oct

Deep learning, Image dataset, Indoor objects, Object classification, Object detection

In European journal of radiology open

Araki Tetsuro, Washko George R, Schiebler Mark L, O’Connor George T, Hatabu Hiroto

2020

CT, Framingham Heart Study, Interstitial lung abnormalities, Lung, Pleural plaques, Thymus

In Frontiers in veterinary science ; h5-index 25.0

Sikka Poonam, Nath Abhigyan, Paul Shyam Sundar, Andonissamy Jerome, Mishra Dwijesh Chandra, Rao Atmakuri Ramakrishna, Balhara Ashok Kumar, Chaturvedi Krishna Kumar, Yadav Keerti Kumar, Balhara Sunesh

2020

blood, buffalo, feed conversion efficiency, partial least square regression, prediction models

In Journal of medical imaging and radiation sciences

BACKGROUND AND PURPOSE : The use of AI in the process of CT image reconstruction may improve image quality of resultant images and therefore facilitate low-dose CT examinations.

METHODS : Articles in this review were gathered from multiple databases (Google Scholar, Ovid and Monash University Library Database). A total of 17 articles regarding AI use in CT image reconstruction was reviewed, including 1 white paper from GE Healthcare.

RESULTS : DLR algorithms performed better in terms of noise reduction abilities, and image quality preservation at low doses when compared to other reconstruction techniques.

CONCLUSION : Further research is required to discuss clinical application and diagnostic accuracy of DLR algorithms, but AI is a promising dose-reduction technique with future computational advances.

Zhang Ziyu, Seeram Euclid

2020-Sep-24

Convolutional neural networks, Deep learning, Dose reduction, Generative adversarial networks, Machine learning

In Applied soft computing

Ezzat Dalia, Hassanien Aboul Ella, Ella Hassan Aboul

2020-Sep-22

Convolutional neural networks, Deep learning, Gravitational search algorithm, Hyperparameters optimization, SARS-CoV-2, Transfer learning

ArXiv Preprint

Naoto Masuzawa, Yoshiro Kitamura, Keigo Nakamura, Satoshi Iizuka, Edgar Simo-Serra

2020-09-29

In Frontiers in cell and developmental biology

Objective : The objective of this study was to compare the novel artificial intelligence (A.I.)-driven lateral cephalometric (Late. Ceph.) analysis of 14 different dental characteristics (DC) among different types of cleft lip and palate (CLP) and non-cleft (NC) individuals.

Materials and Methods : A retrospective study was conducted on 123 individuals [31 = NC, 29 = BCLP (bilateral cleft lip and palate), 41 = UCLP (unilateral cleft lip and palate), 9 = UCLA (unilateral cleft lip and alveolus), and 13 = UCL (unilateral cleft lip)] with an average age of 14.77 years. Demographic details were gathered from the clinical records. A novel artificial intelligence-driven Webceph software has been used for the Late. Ceph. analysis. A total of 14 different types of angular and linear DC measurements were analyzed and compared among groups. Two-way ANOVA and multiple-comparison statistics tests were applied to see the differences between gender and among different types of CLP versus NC subjects.

Results : Of the 14 DC tested, no significant gender disparities were found (p > 0.05). In relation to different types of CLP versus NC subjects, 8 over 14 DC were statistically significant (p < 001 to p = 0.03). Six other DC variables show insignificant (p > 0.05) noteworthy alterations in relation to type of CLP.

Conclusion : Based on the results, type of CLP revealed significantly altered DC compared to NC. Among different types of CLP, BCLP exhibited a maximum alteration in different DC.

Alam Mohammad Khursheed, Alfawzan Ahmed Ali

2020

bilateral cleft lip and palate, dental characteristics, incisal display, non-syndromic cleft lip and palate, overbite, overjet, unilateral cleft lip and palate

In Frontiers in cell and developmental biology

Perera Nadeesha, Dehmer Matthias, Emmert-Streib Frank

2020

artificial intelligence, deep learning, information extraction, named entity recognition, natural language processing, relation detection, text analytics, text mining

In Frontiers in bioengineering and biotechnology

Ward Andrew C, Dubey Prachi, Basnett Pooja, Lika Granit, Newman Gwenyth, Corrigan Damion K, Russell Christopher, Kim Jongrae, Chakrabarty Samit, Connolly Patricia, Roy Ipsita

2020

Polyhydroxyalkanoates, Pseudomonas aeruginosa, artificial intelligence, biopolymer, electrochemical, graphene, pyocyanin, wound dressing

In Frontiers in bioengineering and biotechnology

Bodzas Alexandra, Kodytek Pavel, Zidek Jan

2020

acute leukemia, automated leukemia detection, blood smear image analysis, cell segmentation, image processing, leukemic cell identification, machine learning

In Frontiers in bioengineering and biotechnology

Koelewijn Anne D, Ijspeert Auke J

2020

balance control, neuromusculoskeletal simulation, perturbed standing, proprioception, reflexes

In Frontiers in pediatrics

Fotiadou Eleni, Vullings Rik

2020

convolutional neural networks, encoder-decoder network, fetal ECG denoising, fetal ECG enhancement, fetal electrocardiography

In Frontiers in oncology

Objective : Shear-wave elastography (SWE) can improve the diagnostic specificity of the B-model ultrasonography (US) in breast cancer. However, whether deep learning-based radiomics signatures based on the B-mode US (B-US-RS) or SWE (SWE-RS) could further improve the diagnostic performance remains to be investigated. We aimed to develop the B-US-RS and SWE-RS and determine their performances in classifying breast masses.

Materials and Methods : This retrospective study included 291 women (mean age ± standard deviation, 40.9 ± 12.3 years) from two centers who had US-visible solid breast masses and underwent biopsy and/or surgical resection between June 2015 and July 2017. B-mode US and SWE images of the 198 masses in 198 patients (training cohort) from center 1 were segmented, respectively, to construct B-US-RS and SWE-RS using the least absolute shrinkage and selection operator regression and tested in an independent validation cohort of 65 masses in 65 patients from center 1 and in an external validation cohort of 28 masses in 28 patients from center 2. The performances of B-US-RS and SWE-RS were assessed using receiver operating characteristic (ROC) analysis and compared with that of radiologist assessment [Breast Imaging Reporting and Data System (BI-RADS)] and quantitative SWE parameters [maximum elasticity (E_max), mean elasticity (E_mean), elasticity ratio (E_ratio), and elastic modulus standard deviation (E_SD)] by using the McNemar test.

Results : The single best-performing quantitative SWE parameter, E_max, had a higher specificity than BI-RADS assessment in the training and independent validation cohorts (P < 0.001 for both). The areas under the ROC curves (AUCs) of B-US-RS and SWE-RS both were 0.99 (95% CI = 0.99-1.00) in the training cohort, 1.00 (95% CI = 1.00-1.00) in the independent validation cohort, and 1.00 (95% CI = 1.00-1.00) in the external validation cohort. The specificities of B-US-RS and SWE-RS were higher than that of E_max in the training (P < 0.001 for both) and independent validation cohorts (P = 0.02 for both).

Conclusion : The B-US-RS and SWE-RS outperformed the quantitative SWE parameters and BI-RADS assessment for classifying breast masses. The integration of the deep learning-based radiomics approach would help improve the classification ability of B-mode US and SWE for breast masses.

Zhang Xiang, Liang Ming, Yang Zehong, Zheng Chushan, Wu Jiayi, Ou Bing, Li Haojiang, Wu Xiaoyan, Luo Baoming, Shen Jun

2020

breast neoplasms, deep learning, radiomics, shear-wave elastography, ultrasonography

In Journal of epilepsy research

An Sora, Kang Chaewon, Lee Hyang Woon

2020-Jun

Artificial intelligence, Epilepsy, Patient-specific modeling, Precision medicine, Seizures

In Materials today. Proceedings

Somasekar J, Pavan Kumar Visulaization P, Sharma Avinash, Ramesh G

2020-Sep-22

COVID-19, Chest X-Ray Images, Classification, Diagnosis, Machine Learning, medical image analysis

In PeerJ

Shen Justin, Valagolam Davesh, McCalla Serena

2020

Air pollution, Carbon monoxide, Nitrogen dioxide, Particulate matter, Prediction model, Prophet forecasting model, Seoul, South Korea, Sulfur dioxide, Tropospheric ozone

In The British journal of nutrition

Gamboa-Delgado Edna Magaly, Amaya-Castellanos Claudia Isabel, Bahamonde Antonio

2020-Sep-28

Child Care, Health Behavior, Health Education, Nutrition, Obesity

In Neuropsychiatric disease and treatment

Background : The outbreak of the 2019 novel coronavirus disease (COVID-19) not only caused physical abnormalities, but also caused psychological distress, especially for undergraduate students who are facing the pressure of academic study and work. We aimed to explore the prevalence rate of probable anxiety and probable insomnia and to find the risk factors among a longitudinal study of undergraduate students using the approach of machine learning.

Methods : The baseline data (T1) were collected from freshmen who underwent psychological evaluation at two months after entering the university. At T2 stage (February 10th to 13th, 2020), we used a convenience cluster sampling to assess psychological state (probable anxiety was assessed by general anxiety disorder-7 and probable insomnia was assessed by insomnia severity index-7) based on a web survey. We integrated information attained at T1 stage to predict probable anxiety and probable insomnia at T2 stage using a machine learning algorithm (XGBoost).

Results : Finally, we included 2009 students (response rate: 80.36%). The prevalence rate of probable anxiety and probable insomnia was 12.49% and 16.87%, respectively. The XGBoost algorithm predicted 1954 out of 2009 students (translated into 97.3% accuracy) and 1932 out of 2009 students (translated into 96.2% accuracy) who suffered anxiety and insomnia symptoms, respectively. The most relevant variables in predicting probable anxiety included romantic relationship, suicidal ideation, sleep symptoms, and a history of anxiety symptoms. The most relevant variables in predicting probable insomnia included aggression, psychotic experiences, suicidal ideation, and romantic relationship.

Conclusion : Risks for probable anxiety and probable insomnia among undergraduate students can be identified at an individual level by baseline data. Thus, timely psychological intervention for anxiety and insomnia symptoms among undergraduate students is needed considering the above factors.

Ge Fenfen, Zhang Di, Wu Lianhai, Mu Hongwei

2020

COVID-19, anxiety, cohort, insomnia, machine learning

ArXiv Preprint

Chen Li, Yixin Li, Changhao Sun, Hao Chen, Hong Zhang

2020-09-29

In Arrhythmia & electrophysiology review

Muthalaly Rahul G, Evans Robert M

2020-Aug

Machine learning, ablation, artificial intelligence, big data, cardiac devices, neural network, surface electrocardiography

In Frontiers in plant science

Lin Zhe, Guo Wenxuan

2020

TensorFlow, computer vision, convolutional neural networks, deep learning, image segmentation, python, sorghum panicle, unmanned aerial systems

In Frontiers in plant science

Khan Faraz Ahmad, Voß Ute, Pound Michael P, French Andrew P

2020

annotation, deep learning, machine learning, phenotyping, plant analysis procedures, software

In Frontiers in plant science

de Souza Rafael Soares Correa, Armanhi Jaderson Silveira Leite, Arruda Paulo

2020

inoculants, metagenomics, plant growth-promoting (PGP), plant microbiome, synthetic microbial community (SynCom)

In Frontiers in immunology ; h5-index 100.0

Chen Siteng, Zhang Ning, Wang Tao, Zhang Encheng, Wang Xiang, Zheng Junhua

2020

PD-L1, machine learning, metastatic urothelial carcinoma, nomogram, response

In Frontiers in immunology ; h5-index 100.0

Springer Ido, Besser Hanan, Tickotsky-Moskovitz Nili, Dvorkin Shirit, Louzoun Yoram

2020

TCR repertoire analysis, autoencoder (AE), deep learning, epitope specificity, evaluation methods, long short-term memory (LSTM), machine learning

In Frontiers in endocrinology ; h5-index 55.0

Zhou Jiamin, Damasceno Pablo F, Chachad Ravi, Cheung Justin R, Ballatori Alexander, Lotz Jeffrey C, Lazar Ann A, Link Thomas M, Fields Aaron J, Krug Roland

2020

biomarkers, bone marrow fat, deep learning, magnetic resonance imaging, segmentation, spine imaging

In Frontiers in neurology

Alaka Shakiru A, Menon Bijoy K, Brobbey Anita, Williamson Tyler, Goyal Mayank, Demchuk Andrew M, Hill Michael D, Sajobi Tolulope T

2020

acute ischemic stroke, clinical risk prediction, discrimination calibration, functional outcome, machine learning

In Frontiers in psychology ; h5-index 92.0

Papatzikis Efthymios, Zeba Fathima, Särkämö Teppo, Ramirez Rafael, Grau-Sánchez Jennifer, Tervaniemi Mari, Loewy Joanne

2020

COVID-19, music and neuroscience, music and neuroscience research protocols, music therapy, research crisis response

In Frontiers in neurorobotics

Zeng Yi, Zhao Yuxuan, Zhang Tielin, Zhao Dongcheng, Zhao Feifei, Lu Enmeng

2020

brain inspired model, connection maturation, false-belief task, inhibitory control, self-experience, theory of mind

ArXiv Preprint

Sana Yasin, Syed Asad Hussain, Sinem Aslan, Imran Raza, Muhammad Muzammel, Alice Othmani

2020-09-28

bioRxiv Preprint

Mirabelli, C.; Wotring, J. W.; Zhang, C. J.; McCarty, S. M.; Fursmidt, R.; Frum, T.; Kadambi, N. S.; Amin, A. T.; O’Meara, T. R.; Pretto-Kernahan, C. D.; Spence, J. R.; Huang, J.; Alysandratos, K. D.; Kotton, D. N.; Handelman, S. K.; Wobus, C. E.; Weatherwax, K. J.; Mashour, G. A.; O’Meara, M. J.; Sexton, J. Z.

2020-09-28

ArXiv Preprint

Halla Sigurthorsdottir, Jérôme Van Zaen, Ricard Delgado-Gonzalo, Mathieu Lemay

2020-09-28

In Orphanet journal of rare diseases

BACKGROUND : Rare Diseases (RDs), which are defined as diseases affecting no more than 5 out of 10,000 people, are often severe, chronic and life-threatening. A main problem is the delay in diagnosing RDs. Clinical decision support systems (CDSSs) for RDs are software systems to support clinicians in the diagnosis of patients with RDs. Due to their clinical importance, we conducted a scoping review to determine which CDSSs are available to support the diagnosis of RDs patients, whether the CDSSs are available to be used by clinicians and which functionalities and data are used to provide decision support.

METHODS : We searched PubMed for CDSSs in RDs published between December 16, 2008 and December 16, 2018. Only English articles, original peer reviewed journals and conference papers describing a clinical prototype or a routine use of CDSSs were included. For data charting, we used the data items "Objective and background of the publication/project", "System or project name", "Functionality", "Type of clinical data", "Rare Diseases covered", "Development status", "System availability", "Data entry and integration", "Last software update" and "Clinical usage".

RESULTS : The search identified 636 articles. After title and abstracting screening, as well as assessing the eligibility criteria for full-text screening, 22 articles describing 19 different CDSSs were identified. Three types of CDSSs were classified: "Analysis or comparison of genetic and phenotypic data," "machine learning" and "information retrieval". Twelve of nineteen CDSSs use phenotypic and genetic data, followed by clinical data, literature databases and patient questionnaires. Fourteen of nineteen CDSSs are fully developed systems and therefore publicly available. Data can be entered or uploaded manually in six CDSSs, whereas for four CDSSs no information for data integration was available. Only seven CDSSs allow further ways of data integration. thirteen CDSS do not provide information about clinical usage.

CONCLUSIONS : Different CDSS for various purposes are available, yet clinicians have to determine which is best for their patient. To allow a more precise usage, future research has to focus on CDSSs RDs data integration, clinical usage and updating clinical knowledge. It remains interesting which of the CDSSs will be used and maintained in the future.

Schaaf Jannik, Sedlmayr Martin, Schaefer Johanna, Storf Holger

2020-Sep-24

Clinical decision support systems, Computer-assisted diagnosis, Rare diseases

In Health & place

Nagata Shohei, Nakaya Tomoki, Hanibuchi Tomoya, Amagasa Shiho, Kikuchi Hiroyuki, Inoue Shigeru

2020-Sep-22

Deep learning, Google street view, Neighborhood walkability, Semantic segmentation, Walking behavior

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

Hussain Shaista, Anees Ayesha, Das Ankit, Nguyen Binh P, Marzuki Mardiana, Lin Shuping, Wright Graham, Singhal Amit

2020-Sep-20

Deep learning, Drug discovery, Generative modeling, High-content imaging

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

Hwang Young Jun, Kim Gun Ho, Sung Eui Suk, Nam Kyoung Won

2020-Sep-25

Infusion pump, convolutional neural network, monitoring, patient safety, real-time

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

Wu Bijiao, Wang Dingheng, Zhao Guangshe, Deng Lei, Li Guoqi

2020-Sep-19

Balanced structure, Hierarchical Tucker, Hybrid tensor decomposition, Neural network compression, Tensor-train

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

Salazar González Jose L, Zaccaro Carlos, Álvarez-García Juan A, Soria Morillo Luis M, Sancho Caparrini Fernando

2020-Sep-17

Convolutional neural network, Data augmentation, Deep learning, Feature Pyramid Network, Synthetic data, Weapon detection

In Tissue & cell

Mackay Benita S, Praeger Matthew, Grant-Jacob James A, Kanczler Janos, Eason Robert W, Oreffo Richard O C, Mills Ben

2020-Sep-15

Deep learning, modeling technique, stem cell behavior, topographical cues

In Computer methods and programs in biomedicine

BACKGROUND AND OBJECTIVE : Neurodegenerative diseases like Parkinson's disease often take several years before they can be diagnosed reliably based on clinical grounds. Imaging techniques such as MRI are used to detect anatomical (structural) pathological changes. However, these kinds of changes are usually seen only late in the development. The measurement of functional brain activity by means of [¹⁸F]fluorodeoxyglucose positron emission tomography (FDG-PET) can provide useful information, but its interpretation is more difficult. The scaled sub-profile model principal component analysis (SSM/PCA) was shown to provide more useful information than other statistical techniques. Our objective is to improve the performance further by combining SSM/PCA and prototype-based generalized matrix learning vector quantization (GMLVQ).

METHODS : We apply a combination of SSM/PCA and GMLVQ as a classifier. In order to demonstrate the combination's validity, we analyze FDG-PET data of Parkinson's disease (PD) patients collected at three different neuroimaging centers in Europe. We determine the diagnostic performance by performing a ten times repeated ten fold cross validation. Additionally, discriminant visualizations of the data are included. The prototypes and relevance of GMLVQ are transformed back to the original voxel space by exploiting the linearity of SSM/PCA. The resulting prototypes and relevance profiles have then been assessed by three neurologists.

RESULTS : One important finding is that discriminative visualization can help to identify disease-related properties as well as differences which are due to center-specific factors. Secondly, the neurologist assessed the interpretability of the method and confirmed that prototypes are similar to known activity profiles of PD patients.

CONCLUSION : We have shown that the presented combination of SSM/PCA and GMLVQ can provide useful means to assess and better understand characteristic differences in FDG-PET data from PD patients and HCs. Based on the assessments by medical experts and the results of our computational analysis we conclude that the first steps towards a diagnostic support system have been taken successfully.

van Veen Rick, Gurvits Vita, Kogan Rosalie V, Meles Sanne K, de Vries Gert-Jan, Renken Remco J, Rodriguez-Oroz Maria C, Rodriguez-Rojas Rafael, Arnaldi Dario, Raffa Stefano, de Jong Bauke M, Leenders Klaus L, Biehl Michael

2020-Aug-22

Parkinson’s disease (PD), Scaled sub-profile scaling model principal component analysis (SSM/PCA), [(18)F]Fluorodeoxyglucose positron emission tomography (FDG-PET), generalized matrix learning vector quantization (GMLVQ)

In Journal of critical care ; h5-index 48.0

Carra Giorgia, Salluh Jorge I F, da Silva Ramos Fernando José, Meyfroidt Geert

2020-Sep-09

Big data, Data mining, Intensive care unit, Machine learning, Predictive modeling

In The spine journal : official journal of the North American Spine Society

BACKGROUND CONTEXT : The introduction and integration of robot technology into modern spine surgery provides surgeons with millimeter accuracy for pedicle screw placement. Coupled with computer-based navigation platforms, robot-assisted spine surgery utilizes augmented reality to potentially improve the safety profile of instrumentation.

PURPOSE : In this study, the authors seek to determine the safety and efficacy of robotic-assisted pedicle screw placement compared to conventional free-hand (FH) technique.

STUDY DESIGN/SETTING : We conducted a systematic review of the electronic databases using different MeSH terms from 1980 to 2020.

OUTCOME MEASURES : The present study measures pedicle screw accuracy, complication rates, proximal-facet joint violation, intra-operative radiation time, radiation dosage, and length of surgery.

RESULTS : A total of 1,525 patients (7,379 pedicle screws) from 19 studies with 777 patients (51.0% with 3,684 pedicle screws) in the robotic-assisted group were included. Perfect pedicle screw accuracy, as categorized by Gerztbein-Robbin Grade A, was significantly superior with robotic-assisted surgery compared to FH-technique (OR: 1.68, 95%CI:1.20-2.35; p=0.003). Similarly, clinically acceptable pedicle screw accuracy (Grade A+B) was significantly higher with robotic-assisted surgery versus FH-technique (OR: 1.54, 95%CI:1.01-2.37; p=0.05). Furthermore, the complication rates and proximal-facet joint violation were 69% (OR: 0.31, 95%CI:0.20-0.48; p<0.00001) and 92% less likely (OR: 0.08, 95%CI:0.03-0.20; p<0.00001) with robotic-assisted surgery versus FH-group. Robotic-assisted pedicle screw implantation significantly reduced intra-operative radiation time (MD: -5.30,95%CI:-6.83-3.76; p<0.00001) and radiation dosage (MD: -3.70, 95%CI:-4.80-2.60; p<0.00001) compared to the conventional FH-group. However, the length of surgery was significantly higher with robotic-assisted surgery (MD: 22.70, 95%CI:6.57-38.83; p=0.006) compared to the FH-group.

CONCLUSION : This meta-analysis corroborates the accuracy of robot-assisted pedicle screw placement.

Fatima Nida, Massaad Elie, Hadzipasic Muhamed, Shankar Ganesh M, Shin John H

2020-Sep-22

artificial intelligence, augmented reality, efficacy, pedicle screw, robotics, safety, spine fusion

In Resuscitation ; h5-index 66.0

BACKGROUND : Submersion time is a strong predictor for death in drowning, already 10 minutes after submersion, survival is poor. Traditional search efforts are time-consuming and demand a large number of rescuers and resources. We aim to investigate the feasibility and effectiveness of using drones combined with an online machine learning (ML) model for automated recognition of simulated drowning victims.

METHODS : This feasibility study used photos taken by a drone hovering at 40 m altitude over an estimated 3000 m² surf area with individuals simulating drowning. Photos from 2 ocean beaches in the south of Sweden were used to a) train an online ML model b) test the model for recognition of a drowning victim.

RESULTS : The model was tested for recognition on n = 100 photos with one victim and n = 100 photos with no victims. In drone photos containing one victim (n = 100) the ML model sensitivity for drowning victim recognition was 91% (95%CI 84.9%- 96.2%) with a median probability score that the finding was human of 66% (IQR 52-71). In photos with no victim (n = 100) the ML model specificity was 90% (95%CI: 83.9%- 95.6%). False positives were present in 17.5% of all n = 200 photos but could all be ruled out manually as false objects.

CONCLUSIONS : The use of a drone and a ML model was feasible and showed satisfying effectiveness in identifying a submerged static human simulating drowning in open water and favorable environmental conditions. The ML algorithm and methodology should be further optimized, again tested and validated in a real-life clinical study.

Claesson A, Schierbeck S, Hollenberg J, Forsberg S, Nordberg P, Ringh M, Olausson M, Jansson A, Nord A

2020-Sep-22

Drone, Drowning, Machine-learning, OHCA

In Biotechnology advances

Arya Sagar S, Rookes James, Cahill David, Lenka Sangram K

2020-Sep-22

Artificial gene cluster, Computational modeling, Metabolic engineering, Plant cell suspension culture, Plant gene clusters, Plant specialized metabolites

In Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology

Maspero Matteo, Bentvelzen Laura G, Savenije Mark Hf, Guerreiro Filipa, Seravalli Enrica, Janssens Geert O, van den Berg Cornelis At, Philippens Marielle Ep

2020-Sep-22

Artificial intelligence, Brain tumors, Deep learning, Image-to-image translation, Machine learning., Pediatric oncology, Radiotherapy, Synthetic CT

In Current biology : CB

Ossmy Ori, Adolph Karen E

2020-Sep-22

artificial intelligence, behavioral flexibility, computer vision, cruising, infants, limb coordination, locomotion, machine learning, motor development, problem solving

In Expert opinion on therapeutic targets

INTRODUCTION : A myriad of cellular pathophysiological responses are mediated by polymodal ion channels that respond to chemical and physical stimuli such as thermoTRP channels. Intriguingly, these channels are pivotal therapeutic targets with limited clinical pharmacology. In silico methods offer an unprecedented opportunity for discovering new lead compounds targeting thermoTRP channels with improved pharmacological activity and therapeutic index.

AREAS COVERED : This article reviews the progress on thermoTRP channel pharmacology because of (i) advances in solving their atomic structure using cryo-electron microscopy and, (ii) progress on computational techniques including homology modeling, molecular docking, virtual screening, molecular dynamics, ADME/Tox and artificial intelligence. Together, they have increased the number of lead compounds with clinical potential to treat a variety of pathologies. We used original and review articles from Pubmed (1997-2020), as well as the clinicaltrials.gov database, containing the terms thermoTRP, artificial intelligence, docking, and molecular dynamics.

EXPERT OPINION : The atomic structure of thermoTRP channels along with computational methods constitute a realistic first line strategy for designing drug candidates with improved pharmacology and clinical translation. In silico approaches can also help predict potential side-effects that can limit clinical development of drug candidates. Together, they should provide drug candidates with upgraded therapeutic properties.

Fernández-Ballester Gregorio, Fernández-Carvajal Asia, Ferrer-Montiel Antonio

2020-Sep-24

ADME, artificial intelligence, docking, ion channel, molecular dynamics, thermoTRP channels, virtual screening

In Cancer cell ; h5-index 124.0

Li Jun, Chen Hu, Wang Yumeng, Chen Mei-Ju May, Liang Han

2020-Sep-23

In Clinical physiology and functional imaging

INTRODUCTION : Lymph node metastases are a key prognostic factor in prostate cancer (PCa), but detecting lymph node lesions from PET/CT images is a subjective process resulting in inter-reader variability. Artificial intelligence (AI)-based methods can provide an objective image analysis. We aimed at developing and validating an AI-based tool for detection of lymph node lesions.

METHODS : A group of 399 patients with biopsy-proven PCa who had undergone ¹⁸ F-choline PET/CT for staging prior to treatment were used to train (n=319) and test (n=80) the AI-based tool. The tool consisted of convolutional neural networks using complete PET/CT scans as inputs. In the test set, the AI-based lymph node detections were compared to those of two independent readers. The association with PCa-specific survival was investigated.

RESULTS : The AI-based tool detected more lymph node lesions than Reader B (98 vs 87/117; p=0.045) using Reader A as reference. AI-based tool and Reader A showed similar performance (90 vs 87/111; p=0.63) using Reader B as reference. The number of lymph node lesions detected by the AI-based tool, PSA, and curative treatment were significantly associated with PCa-specific survival.

CONCLUSION : This study shows the feasibility of using an AI-based tool for automated and objective interpretation of PET/CT images that can provide assessments of lymph node lesions comparable with that of experienced readers, and prognostic information in PCa patients.

Borrelli Pablo, Larsson Måns, Ulén Johannes, Enqvist Olof, Trägårdh Elin, Hvid Poulsen Mads, Mortensen Mike Allan, Kjölhede Henrik, Høilund-Carlsen Poul Flemming, Edenbrandt Lars

2020-Sep-25

Artificial intelligence, Fluorocholine, Lymph node metastases, PCa, PET

In The FEBS journal

Partel Gabriele, Wählby Carolina

2020-Sep-25

RNA profiling, Spatial transcriptomics, gene expression, graph representation learning, tissue analysis

In Bioinformatics (Oxford, England)

MOTIVATION : The gene expression regulatory network in yeast controls the selective implementation of the information contained in the genome sequence. We seek to understand how, in different physiological states, the network reconfigures itself to produce a different proteome.

RESULTS : This article analyses this reconfiguration, focusing on changes in the local structure of the network. In particular, we define, extract and compare the 1-neighbourhoods of each transcription factor, where a 1-neighbourhood of a node in a network is the minimal subgraph of the network containing all nodes connected to the central node by an edge. We report the similarities and differences in the topologies and connectivities of these neighbourhoods in five physiological states for which data are available: cell cycle, DNA damage, stress response, diauxic shift, and sporulation. Based on our analysis, it seems apt to regard the components of the regulatory network as 'software', and the responses to changes in state, 'reprogramming'.

Lesk Arthur M, Konagurthu Arun S

2020-Sep-25

In Bioinformatics (Oxford, England)

MOTIVATION : With the rapid increase of biomedical articles, large-scale automatic Medical Subject Headings (MeSH) indexing has become increasingly important. FullMeSH, the only method for large-scale MeSH indexing with full text, suffers from three major drawbacks: FullMeSH 1) uses Learning To Rank (LTR), which is time-consuming, 2) can capture some pre-defined sections only in full text, and 3) ignores the whole MEDLINE database.

RESULTS : We propose a computationally lighter, full-text and deep learning based MeSH indexing method, BERTMeSH, which is flexible for section organization in full text. BERTMeSH has two technologies: 1) the state-of-the-art pre-trained deep contextual representation, BERT (Bidirectional Encoder Representations from Transformers), which makes BERTMeSH capture deep semantics of full text. 2) a transfer learning strategy for using both full text in PubMed Central (PMC) and title and abstract (only and no full text) in MEDLINE, to take advantages of both. In our experiments, BERTMeSH was pre-trained with 3 million MEDLINE citations and trained on approximately 1.5 million full text in PMC. BERTMeSH outperformed various cutting edge baselines. For example, for 20K test articles of PMC, BERTMeSH achieved a Micro F-measure of 69.2%, which was 6.3% higher than FullMeSH with the difference being statistically significant. Also prediction of 20K test articles needed 5 minutes by BERTMeSH, while it took more than 10 hours by FullMeSH, proving the computational efficiency of BERTMeSH.

SUPPLEMENTARY INFORMATION : Supplementary data are available at Bioinformatics online.

You Ronghui, Liu Yuxuan, Mamitsuka Hiroshi, Zhu Shanfeng

2020-Sep-25

In Nucleic acids research ; h5-index 217.0

Ding Nana, Yuan Zhenqi, Zhang Xiaojuan, Chen Jing, Zhou Shenghu, Deng Yu

2020-Sep-25

In Bioinformatics (Oxford, England)

MOTIVATION : Recent advances in high-throughput long-read sequencers, such as PacBio and Oxford Nanopore sequencers, produce longer reads with more errors than short-read sequencers. In addition to the high error rates of reads, non-uniformity of errors leads to difficulties in various downstream analyses using long reads. Many useful simulators, which characterize long read error patterns and simulate them, have been developed. However, there is still room for improvement in the simulation of the non-uniformity of errors.

RESULTS : To capture characteristics of errors in reads for long read sequencers, here, we introduce a generative model for quality scores, in which a hidden Markov Model with a latest model selection method, called Factorized information criteria, is utilized. We evaluated our developed simulator from various points, indicating that our simulator successfully simulates reads that are consistent with real reads.

AVAILABILITY : The source codes of PBSIM2 are freely available from https://github.com/yukiteruono/pbsim2.

SUPPLEMENTARY INFORMATION : Supplementary data are available at Bioinformatics online.

Ono Yukiteru, Asai Kiyoshi, Hamada Michiaki

2020-Sep-25

In PloS one ; h5-index 176.0

Barth Michael, Güllich Arne, Raschner Christian, Emrich Eike

2020

In PloS one ; h5-index 176.0

Weninger Leon, Na Chuh-Hyoun, Jütten Kerstin, Merhof Dorit

2020

In PloS one ; h5-index 176.0

Xue Jia, Chen Junxiang, Chen Chen, Zheng Chengda, Li Sijia, Zhu Tingshao

2020

In The American journal of psychiatry

OBJECTIVE : Dissociative experiences commonly occur in response to trauma, and while their presence strongly affects treatment approaches in posttraumatic spectrum disorders, their etiology remains poorly understood and their phenomenology incompletely characterized. Methods to reliably assess the severity of dissociation symptoms, without relying solely on self-report, would have tremendous clinical utility. Brain-based measures have the potential to augment symptom reports, although it remains unclear whether brain-based measures of dissociation are sufficiently sensitive and robust to enable individual-level estimation of dissociation severity based on brain function. The authors sought to test the robustness and sensitivity of a brain-based measure of dissociation severity.

METHODS : An intrinsic network connectivity analysis was applied to functional MRI scans obtained from 65 women with histories of childhood abuse and current posttraumatic stress disorder (PTSD). The authors tested for continuous measures of trauma-related dissociation using the Multidimensional Inventory of Dissociation. Connectivity estimates were derived with a novel machine learning technique using individually defined homologous functional regions for each participant.

RESULTS : The models achieved moderate ability to estimate dissociation, after controlling for childhood trauma and PTSD severity. Connections that contributed the most to the estimation mainly involved the default mode and frontoparietal control networks. By contrast, all models performed at chance levels when using a conventional group-based network parcellation.

CONCLUSIONS : Trauma-related dissociative symptoms, distinct from PTSD and childhood trauma, can be estimated on the basis of network connectivity. Furthermore, between-network brain connectivity may provide an unbiased estimate of symptom severity, paving the way for more objective, clinically useful biomarkers of dissociation and advancing our understanding of its neural mechanisms.

Lebois Lauren A M, Li Meiling, Baker Justin T, Wolff Jonathan D, Wang Danhong, Lambros Ashley M, Grinspoon Elizabeth, Winternitz Sherry, Ren Jianxun, Gönenç Atilla, Gruber Staci A, Ressler Kerry J, Liu Hesheng, Kaufman Milissa L

2020-Sep-25

In PloS one ; h5-index 176.0

Pelka Obioma, Friedrich Christoph M, Nensa Felix, Mönninghoff Christoph, Bloch Louise, Jöckel Karl-Heinz, Schramm Sara, Sanchez Hoffmann Sarah, Winkler Angela, Weimar Christian, Jokisch Martha

2020

In PLoS computational biology

Raphel Fabien, De Korte Tessa, Lombardi Damiano, Braam Stefan, Gerbeau Jean-Frederic

2020-Sep-25

In Applied optics

Kolenov D, Davidse D, Le Cam J, Pereira S F

2020-Sep-20

In Journal of computer assisted tomography

PURPOSE : To assess whether a machine-learning model based on texture features extracted from multiparametric magnetic resonance imaging could yield an accurate diagnosis in differentiating pilocytic astrocytoma from cystic oligodendrogliomas.

MATERIALS AND METHODS : The preoperative images from multisequences were used for tumor segmentation. Radiomic features were extracted and selected for machine-learning models. Semantic features and selected radiomic features from training data set were built, and the performance of each model was evaluated by receiver operating characteristic curve and accuracy from isolated testing data set.

RESULTS : In terms of different sequences, the best classifier was built by radiomic features extracted from enhanced T1WI-based classifier. The best model in our study turned out to be the gradient boosted trees classifier with an area under curve value of 0.99.

CONCLUSION : Our study showed that gradient boosted trees based on texture features extracted from enhanced T1WI could become an additional tool for improving diagnostic accuracy to differentiate pilocytic astrocytoma from cystic oligodendroglioma.

Zhao Yajing, Lu Yiping, Li Xuanxuan, Zheng Yingyan, Yin Bo

2020-Sep-23

In Physics in medicine and biology

Arabi Hossein, Zaidi Habib

2020-Sep-25

In Journal of medical Internet research ; h5-index 88.0

BACKGROUND : Coronavirus Disease 2019 (COVID-19) is a rapidly emerging respiratory disease caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Due to the rapid human-to-human transmission of SARS-CoV-2, many healthcare systems are at risk of exceeding their healthcare capacities, in particular in terms of SARS-CoV-2 tests, hospital and intensive care unit (ICU) beds and mechanical ventilators. Predictive algorithms could potentially ease the strain on healthcare systems by identifying those who are most likely to receive a positive SARS-CoV-2 test, be hospitalised or admitted to the ICU.

OBJECTIVE : To develop, study and evaluate clinical predictive models that estimate, using machine learning and based on routinely collected clinical data, which patients are likely to receive a positive SARS-CoV-2 test, require hospitalisation or intensive care.

METHODS : Using a systematic approach to model development and optimisation, we train and compare various types of machine learning models, including logistic regression, neural networks, support vector machines, random forests, and gradient boosting. To evaluate the developed models, we perform a retrospective evaluation on demographic, clinical and blood analysis data from a cohort of 5644 patients. In addition, we determine which clinical features are predictive to what degree for each of the aforementioned clinical tasks using causal explanations.

RESULTS : Our experimental results indicate that our predictive models identify (i) patients that test positive for SARS-CoV-2 a priori at a sensitivity of 75% (95% confidence interval [CI]: 67%, 81%) and a specificity of 49% (95% CI: 46%, 51%), (ii) SARS-CoV-2 positive patients that require hospitalisation with 0.92 area under the receiver operator characteristic curve [AUC] (95% CI: 0.81, 0.98), and (iii) SARS-CoV-2 positive patients that require critical care with 0.98 AUC (95% CI: 0.95, 1.00).

CONCLUSIONS : Our results indicate that predictive models trained on routinely collected clinical data could be used to predict clinical pathways for COVID-19, and therefore help inform care and prioritise resources.

CLINICALTRIAL :

Schwab Patrick, Schütte DuMont August, Dietz Benedikt, Bauer Stefan

2020-Sep-14

In IEEE/ACM transactions on computational biology and bioinformatics

Quan Lijun, Sun Xiaoyu, Wu Jian, Mei Jie, Huang Liqun, He Ruji, Nie Liangpeng, Chen Yu, Lyu Qiang

2020-Sep-25

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

Li Haofeng, Zeng Yirui, Li Guanbin, Lin Liang, Yu Yizhou

2020-Sep-25

In IEEE transactions on bio-medical engineering

OBJECTIVE : The utilization of hyperspectral imaging (HSI) in real-time tumor segmentation during a surgery have recently received much attention, but it remains a very challenging task.

METHODS : In this work, we propose semantic segmentation methods and compare them with other relevant deep learning algorithms for tongue tumor segmentation. To the best of our knowledge, this is the first work using deep learning semantic segmentation for tumor detection in HSI data using channel selection and accounting for more spatial tissue context and global comparison between the prediction map and the annotation per sample.

RESULTS AND CONCLUSION : On a clinical data set with tongue squamous cell carcinoma, our best method obtains very strong results of average dice coefficient and area under the ROC-curve of 0.891 +/- 0.053 and 0.924 +/- 0.036, respectively on the original spatial image size. The results show that a very good performance can be achieved even with a limited amount of data. We demonstrate that important information regarding tumor decision is encoded in various channels, but some channel selection and filtering is beneficial over the full spectra. Moreover, we use both visual (VIS) and near-infrared (NIR) spectrum, rather than commonly used only VIS spectrum; although VIS spectrum is generally of higher significance, we demonstrate NIR spectrum is crucial for tumor capturing in some cases.

SIGNIFICANCE : The HSI technology augmented with accurate deep learning algorithms has a huge potential to be a promising alternative to digital pathology or a doctors' supportive tool in real-time surgeries.

Trajanovski Stojan, Shan Caifeng, Weijtmans Pim J C, Brouwer de Koning Susan G, Ruers Theo J M

2020-Sep-25

In Radiographics : a review publication of the Radiological Society of North America, Inc

Yu Alice C, Eng John

2020-Sep-25

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

Asher Jana, Resnick Dean, Brite Jennifer, Brackbill Robert, Cone James

2020-Sep-22

9/11 health, data matching, disaster epidemiology, epidemiology, interagency cooperation, probabilistic record linkage, record linkage

In PloS one ; h5-index 176.0

Xue Jia, Chen Junxiang, Chen Chen, Zheng Chengda, Li Sijia, Zhu Tingshao

2020

In The clinical respiratory journal

BACKGROUND : Erectile dysfunction (ED) with obstructive sleep apnea (OSA) is a relatively common issue for men. A number of clinical studies have demonstrated that continuous positive airway pressure (CPAP) therapy may effectively alleviate ED symptom from patients with OSA.

METHODS : PubMed, MEDLINE, EMBASE and Cochrane Library databases were utilized and searched for the relevant studies up to September 2, 2019. The International Index of Erectile Function 5 (IIEF-5) scoring system from the patients before and after receiving their CPAP therapy were collected according to the strict inclusion and exclusion criteria. REVMEN 5.3 software was applied for the meta-analysis.

RESULTS : A total of seven publications consisted of 206 ED patients with OSA were included in the study. ED patients with OSA received CPAP treatment were significantly improved based on the IIEF-5 scores [Weighted Mean Difference (WMD) = 1.14, 95% confidence interval (CI) = 0.89 - 1.38, z =9.09, p < 0.0001].Our research found that the high heterogeneity is mainly due to Zhang's research, because his patient's AHI is much higher than other patients. We removed Zhang's study, a moderate heterogeneity (I² = 54%, P = 0.05) was found in this study. Our research found that the high heterogeneity is mainly due to Zhang's research, because his patient's AHI is much higher than other patients.

CONCLUSION : The results suggest that continuous positive airway pressure therapy improve erectile dysfunction patients with obstructive sleep apnea. However, further evidence is needed due to the insufficient number of included patients and high heterogeneity.

Yang Zhihao, Du Guodong, Ma Lei, Lv Yunhui, Zhao Yang, Yau Tung On

2020-Sep-25

Continuous positive airway pressure, Meta-analysis, erectile dysfunction, obstructive sleep apnea

In Diabetes therapy : research, treatment and education of diabetes and related disorders

INTRODUCTION : The objective of this study was to examine changes in hemoglobin A1c (HbA1c), anti-diabetic medication use, insulin resistance, and other ambulatory glucose profile metrics between baseline and after 90 days of participation in the Twin Precision Nutrition (TPN) Program enabled by Digital Twin Technology.

METHODS : This was a retrospective study of patients with type 2 diabetes who participated in the TPN Program and had at least 3 months of follow-up. The TPN machine learning algorithm used daily continuous glucose monitor (CGM) and food intake data to provide guidelines that would enable individual patients to avoid foods that cause blood glucose spikes and to replace them with foods that do not produce spikes. Physicians with access to daily CGM data titrated medications and monitored patient conditions.

RESULTS : Of the 89 patients who initially enrolled in the TPN Program, 64 patients remained in the program and adhered to it for at least 90 days; all analyses were performed on these 64 patients. At the 90-day follow-up assessment, mean (± standard deviation) HbA1c had decreased from 8.8 ± 2.2% at baseline by 1.9 to 6.9 ± 1.1%, mean weight had decreased from 79.0 ± 16.2 kg at baseline to 74.2 ± 14.7 kg, and mean fasting blood glucose had fallen from 151.2 ± 45.0 mg/dl at baseline to 129.1 ± 36.7 mg/dl. Homeostatic model assessment of insulin resistance (HOMA-IR) had decreased by 56.9% from 7.4 ± 3.5 to 3.2 ± 2.8. At the 90-day follow-up assessment, all 12 patients who were on insulin had stopped taking this medication; 38 of the 56 patients taking metformin had stopped metformin; 26 of the 28 patients on dipeptidyl peptidase-4 (DPP-4) inhibitors discontinued DPP-4 inhibitors; all 13 patients on alpha-glucosidase inhibitors discontinued these inhibitors; all 34 patients on sulfonylureas were able to stop taking these medications; two patients stopped taking pioglitazone; all ten patients on sodium-glucose cotransporter-2 (SGLT2) inhibitors stopped taking SGLT2 inhibitors; and one patient stopped taking glucagon-like peptide-1 analogues.

CONCLUSION : The results provide evidence that daily precision nutrition guidance based on CGM, food intake data, and machine learning algorithms can benefit patients with type 2 diabetes. Adherence for 3 months to the TPN Program resulted in patients achieving a 1.9 percentage point decrease in HbA1c, a 6.1% drop in weight, a 56.9% reduction in HOMA-IR, a significant decline in glucose time below range, and, in most patients, the elimination of diabetes medication use.

Shamanna Paramesh, Saboo Banshi, Damodharan Suresh, Mohammed Jahangir, Mohamed Maluk, Poon Terrence, Kleinman Nathan, Thajudeen Mohamed

2020-Sep-25

Artificial intelligence, Continuous glucose monitoring, Diabetes medication elimination, Digital twin technology, HbA1c reduction, Precision nutrition, Type 2 diabetes

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

Li Peixuan, Zhao Huaici, Liu Pengfei, Cao Feidao

2020-Sep-25

Feature pyramid, Fetal head measurement, Fully convolutional networks, ROI pooling, Ultrasound image segmentation

In Journal of medical Internet research ; h5-index 88.0

BACKGROUND : Supervised machine learning (ML) is being featured in the health care literature with study results frequently reported using metrics such as accuracy, sensitivity, specificity, recall, or F1 score. Although each metric provides a different perspective on the performance, they remain to be overall measures for the whole sample, discounting the uniqueness of each case or patient. Intuitively, we know that all cases are not equal, but the present evaluative approaches do not take case difficulty into account.

OBJECTIVE : A more case-based, comprehensive approach is warranted to assess supervised ML outcomes and forms the rationale for this study. This study aims to demonstrate how the item response theory (IRT) can be used to stratify the data based on how difficult each case is to classify, independent of the outcome measure of interest (eg, accuracy). This stratification allows the evaluation of ML classifiers to take the form of a distribution rather than a single scalar value.

METHODS : Two large, public intensive care unit data sets, Medical Information Mart for Intensive Care III and electronic intensive care unit, were used to showcase this method in predicting mortality. For each data set, a balanced sample (n=8078 and n=21,940, respectively) and an imbalanced sample (n=12,117 and n=32,910, respectively) were drawn. A 2-parameter logistic model was used to provide scores for each case. Several ML algorithms were used in the demonstration to classify cases based on their health-related features: logistic regression, linear discriminant analysis, K-nearest neighbors, decision tree, naive Bayes, and a neural network. Generalized linear mixed model analyses were used to assess the effects of case difficulty strata, ML algorithm, and the interaction between them in predicting accuracy.

RESULTS : The results showed significant effects (P<.001) for case difficulty strata, ML algorithm, and their interaction in predicting accuracy and illustrated that all classifiers performed better with easier-to-classify cases and that overall the neural network performed best. Significant interactions suggest that cases that fall in the most arduous strata should be handled by logistic regression, linear discriminant analysis, decision tree, or neural network but not by naive Bayes or K-nearest neighbors. Conventional metrics for ML classification have been reported for methodological comparison.

CONCLUSIONS : This demonstration shows that using the IRT is a viable method for understanding the data that are provided to ML algorithms, independent of outcome measures, and highlights how well classifiers differentiate cases of varying difficulty. This method explains which features are indicative of healthy states and why. It enables end users to tailor the classifier that is appropriate to the difficulty level of the patient for personalized medicine.

Kline Adrienne, Kline Theresa, Shakeri Hossein Abad Zahra, Lee Joon

2020-Sep-25

item response theory, machine learning, mortality, statistical model

In Journal of interpersonal violence

Amusa Lateef B, Bengesai Annah V, Khan Hafiz T A

2020-Sep-25

South Africa, decision tree, intimate partner violence, machine learning

In Cellular microbiology

Saito-Nakano Yumiko, Wahyuni Ratna, Nakada-Tsukui Kumiko, Tomii Kentaro, Nozaki Tomoyoshi

2020-Sep-25

Cytoskeleton, Entamoeba histolytica, Lysosome, Pathogenesis, Phagocytosis, Rab7D, Trogocytosis, Vesicular traffic

In Molecular systems biology

Lopez Romain, Gayoso Adam, Yosef Nir

2020-Sep

deep generative models, molecular biology, neural networks

In Yonsei medical journal

Bae Sohi, Choi Yoon Seong, Sohn Beomseok, Ahn Sung Soo, Lee Seung Koo, Yang Jaemoon, Kim Jinna

2020-Oct

Radiomics, lymphoma, magnetic resonance imaging, oropharynx, squamous cell carcinoma

In Pediatric allergy and immunology : official publication of the European Society of Pediatric Allergy and Immunology

BACKGROUND : We sought to evaluate whether elective Caesarean section is associated with subsequent hospitalization for bronchiolitis.

METHODS : This is a retrospective cohort study which used the electronic medical record database of Clalit Health Services, the largest healthcare fund in Israel, serving over 4.5 million members and over half of the total population. The primary outcome was bronchiolitis admission in the first two years of life. We performed logistic regression analyses to identify independent associations. We repeated the analysis using boosted decision tree machine learning techniques to confirm our findings.

RESULTS : There were 124,553 infants enrolled between 2008-2010 and 5,168 (4.1%) were hospitalized for bronchiolitis in the first two years of life. In logistic regression models stratified by seasons, elective Caesarean section birth was associated with 15% increased odds (95% CI: 1.02-1.30) for infants born in the fall season, 28% increased odds (95% CI: 1.11, 1.47) in the winter, 35% increased odds (95% CI: 1.12-1.62) in the spring, and 37% increased odds (95% CI: 1.18-1.60) in the summer. In the boosted gradient decision tree analysis, the area under the curve for risk of bronchiolitis admission was 0.663 (95% CI: 0.652, 0.674) with timing of birth as the most important feature.

CONCLUSION : Elective Caesarean section, a potentially modifiable risk factor, is associated with increased odds of hospitalization for bronchiolitis in the first two years of life. These data should be considered when scheduling elective Caesarean sections especially for infants born in spring and summer months.

Douglas Lindsey C, Leventer-Roberts Maya, Levinkron Ohad, Wilson Karen M

2020-Sep-24

Bronchiolitis, Caesarean section, Risk Factors

In Statistics in medicine

Sun Tao, Wei Yue, Chen Wei, Ding Ying

2020-Sep-24

AMD progression, GWAS, deep learning, predictor importance, survival prediction

In Biomedicines

Oriuchi Noboru, Sugawara Shigeyasu, Shiga Tohru

2020-Sep-22

FDG-PET/CT, artificial intelligence, cancer stem cell, immunotherapy, radiomics, theranostics, therapeutic evaluation, tumor microenvironment

In Journal of medical Internet research ; h5-index 88.0

BACKGROUND : Coronavirus Disease 2019 (COVID-19) is a rapidly emerging respiratory disease caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Due to the rapid human-to-human transmission of SARS-CoV-2, many healthcare systems are at risk of exceeding their healthcare capacities, in particular in terms of SARS-CoV-2 tests, hospital and intensive care unit (ICU) beds and mechanical ventilators. Predictive algorithms could potentially ease the strain on healthcare systems by identifying those who are most likely to receive a positive SARS-CoV-2 test, be hospitalised or admitted to the ICU.

OBJECTIVE : To develop, study and evaluate clinical predictive models that estimate, using machine learning and based on routinely collected clinical data, which patients are likely to receive a positive SARS-CoV-2 test, require hospitalisation or intensive care.

METHODS : Using a systematic approach to model development and optimisation, we train and compare various types of machine learning models, including logistic regression, neural networks, support vector machines, random forests, and gradient boosting. To evaluate the developed models, we perform a retrospective evaluation on demographic, clinical and blood analysis data from a cohort of 5644 patients. In addition, we determine which clinical features are predictive to what degree for each of the aforementioned clinical tasks using causal explanations.

RESULTS : Our experimental results indicate that our predictive models identify (i) patients that test positive for SARS-CoV-2 a priori at a sensitivity of 75% (95% confidence interval [CI]: 67%, 81%) and a specificity of 49% (95% CI: 46%, 51%), (ii) SARS-CoV-2 positive patients that require hospitalisation with 0.92 area under the receiver operator characteristic curve [AUC] (95% CI: 0.81, 0.98), and (iii) SARS-CoV-2 positive patients that require critical care with 0.98 AUC (95% CI: 0.95, 1.00).

CONCLUSIONS : Our results indicate that predictive models trained on routinely collected clinical data could be used to predict clinical pathways for COVID-19, and therefore help inform care and prioritise resources.

CLINICALTRIAL :

Schwab Patrick, Schütte DuMont August, Dietz Benedikt, Bauer Stefan

2020-Sep-14

In The British journal of dermatology

Wan B, Ganier C, Du-Harpur X, Harun N, Watt F M, Patalay R, Lynch M D

2020-Sep-24

In Journal of surgical oncology ; h5-index 45.0

Melstrom Laleh G, Rodin Andrei S, Rossi Lorenzo A, Fu Paul, Fong Yuman, Sun Virginia

2020-Sep-24

artificial intelligence, biometrics, machine learning in surgery, patient-reported outcomes, telehealth

In Medical physics ; h5-index 59.0

PURPOSE : Recently, brain tumor segmentation has made important progress. How-ever, the quality of manual labels plays an important role in the performance, while in practice, it could vary greatly and in turn could substantially mislead the learning process and decrease the accuracy. We need to design a mechanism to combine label correction and sample reweighting to improve the effectiveness of brain tumor segmentation.

METHODS : We propose a novel sample reweighting and label refinement method, and a novel 3D generative adversarial network (GAN) is introduced to combine these two models into an united framework.

RESULTS : Extensive experiments on the BraTS19 dataset have demonstrated that our approach obtains competitive results when compared with other state-of-the-art approaches when handling the false labels in brain tumor segmentation.

CONCLUSIONS : The 3D GAN-based approach is an effective approach to handle false label masks by simultaneously applying label correction and sample reweighting. Our method is robust to variations in tumor shape and background clutter.

Cheng Guohua, Ji Hongli, He Linyang

2020-Sep-24

brain tumor segmentation, deep learning, generative adversarial network, volume segmentation

In Neuroinformatics

Zhang Hua, Mo Jiajie, Jiang Han, Li Zhuyun, Hu Wenhan, Zhang Chao, Wang Yao, Wang Xiu, Liu Chang, Zhao Baotian, Zhang Jianguo, Zhang Kai

2020-Sep-25

Deep learning, Delineation, Grade classification, Meningiomas, PSPNet

In Emergency radiology

Gopireddy Dheeraj Reddy, Mahmoud Hagar, Baig Saif, Le Rebecca, Bhosale Priya, Lall Chandana

2020-Sep-25

Emergency, Kidney, Magnetic resonance imaging, Renal hemorrhage

In European radiology ; h5-index 62.0

OBJECTIVES : To develop and evaluate a deep learning algorithm for fully automated detection of primary sclerosing cholangitis (PSC)-compatible cholangiographic changes on three-dimensional magnetic resonance cholangiopancreatography (3D-MRCP) images.

METHODS : The datasets of 428 patients (n = 205 with confirmed diagnosis of PSC; n = 223 non-PSC patients) referred for MRI including MRCP were included in this retrospective IRB-approved study. Datasets were randomly assigned to a training (n = 386) and a validation group (n = 42). For each case, 20 uniformly distributed axial MRCP rotations and a subsequent maximum intensity projection (MIP) were calculated, resulting in a training database of 7720 images and a validation database of 840 images. Then, a pre-trained Inception ResNet was implemented which was conclusively fine-tuned (learning rate 10^-3).

RESULTS : Applying an ensemble strategy (by binning of the 20 axial projections), the mean absolute error (MAE) of the developed deep learning algorithm for detection of PSC-compatible cholangiographic changes was lowered from 21 to 7.1%. Sensitivity, specificity, positive predictive (PPV), and negative predictive value (NPV) for detection of these changes were 95.0%, 90.9%, 90.5%, and 95.2% respectively.

CONCLUSIONS : The results of this study demonstrate the feasibility of transfer learning in combination with extensive image augmentation to detect PSC-compatible cholangiographic changes on 3D-MRCP images with a high sensitivity and a low MAE. Further validation with more and multicentric data is now desirable, as it is known that neural networks tend to overfit the characteristics of the dataset.

KEY POINTS : • The described machine learning algorithm is able to detect PSC-compatible cholangiographic changes on 3D-MRCP images with high accuracy. • The generation of 2D projections from 3D datasets enabled the implementation of an ensemble strategy to boost inference performance.

Ringe Kristina I, Vo Chieu Van Dai, Wacker Frank, Lenzen Henrike, Manns Michael P, Hundt Christian, Schmidt Bertil, Winther Hinrich B

2020-Sep-24

Cholangiography, Deep learning, Machine learning, Sclerosing cholangitis

In Eye and vision (London, England)

Purpose : To develop an automated classification system using a machine learning classifier to distinguish clinically unaffected eyes in patients with keratoconus from a normal control population based on a combination of Scheimpflug camera images and ultra-high-resolution optical coherence tomography (UHR-OCT) imaging data.

Methods : A total of 121 eyes from 121 participants were classified by 2 cornea experts into 3 groups: normal (50 eyes), with keratoconus (38 eyes) or with subclinical keratoconus (33 eyes). All eyes were imaged with a Scheimpflug camera and UHR-OCT. Corneal morphological features were extracted from the imaging data. A neural network was used to train a model based on these features to distinguish the eyes with subclinical keratoconus from normal eyes. Fisher's score was used to rank the differentiable power of each feature. The receiver operating characteristic (ROC) curves were calculated to obtain the area under the ROC curves (AUCs).

Results : The developed classification model used to combine all features from the Scheimpflug camera and UHR-OCT dramatically improved the differentiable power to discriminate between normal eyes and eyes with subclinical keratoconus (AUC = 0.93). The variation in the thickness profile within each individual in the corneal epithelium extracted from UHR-OCT imaging ranked the highest in differentiating eyes with subclinical keratoconus from normal eyes.

Conclusion : The automated classification system using machine learning based on the combination of Scheimpflug camera data and UHR-OCT imaging data showed excellent performance in discriminating eyes with subclinical keratoconus from normal eyes. The epithelial features extracted from the OCT images were the most valuable in the discrimination process. This classification system has the potential to improve the differentiable power of subclinical keratoconus and the efficiency of keratoconus screening.

Shi Ce, Wang Mengyi, Zhu Tiantian, Zhang Ying, Ye Yufeng, Jiang Jun, Chen Sisi, Lu Fan, Shen Meixiao

2020

Combined-devices, Machine learning, Scheimpflug camera, Subclinical keratoconus, Ultra-high resolution optical coherence tomography

In Frontiers in surgery

Chang Michael, Canseco Jose A, Nicholson Kristen J, Patel Neil, Vaccaro Alexander R

2020

artificial intelligence, deep learning, machine learning, orthopedic surgery, spine surgery

In Frontiers in medicine

Ge Huiqing, Pan Qing, Zhou Yong, Xu Peifeng, Zhang Lingwei, Zhang Junli, Yi Jun, Yang Changming, Zhou Yuhan, Liu Limin, Zhang Zhongheng

2020

COVID-19, asynchonized, asynchrony, lung mechanics, mechanical ventilation, prone positioning

In Frontiers in medicine

Dimitriou Neofytos, Arandjelović Ognjen, Caie Peter D

2020

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

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

Tartaglione Enzo, Barbano Carlo Alberto, Berzovini Claudio, Calandri Marco, Grangetto Marco

2020-Sep-22

COVID-19, chest X-ray, classification, deep learning

In Frontiers in medicine

Ge Huiqing, Pan Qing, Zhou Yong, Xu Peifeng, Zhang Lingwei, Zhang Junli, Yi Jun, Yang Changming, Zhou Yuhan, Liu Limin, Zhang Zhongheng

2020

COVID-19, asynchonized, asynchrony, lung mechanics, mechanical ventilation, prone positioning

In Frontiers in medicine

Calabrese Leonard H, Calabrese Cassandra, Lenfant Tiphaine, Kirchner Elizabeth, Strand Vibeke

2020

PML, TNF inhibitors, infection, natalizumab, targeted therapies, tuberculosis, vaccine

In PeerJ

Background : Numerous studies have utilized machine-learning techniques to predict the early onset of type 2 diabetes mellitus. However, fewer studies have been conducted to predict an appropriate diagnosis code for the type 2 diabetes mellitus condition. Further, ensemble techniques such as bagging and boosting have likewise been utilized to an even lesser extent. The present study aims to identify appropriate diagnosis codes for type 2 diabetes mellitus patients by means of building a multi-class prediction model which is both parsimonious and possessing minimum features. In addition, the importance of features for predicting diagnose code is provided.

Methods : This study included 149 patients who have contracted type 2 diabetes mellitus. The sample was collected from a large hospital in Taiwan from November, 2017 to May, 2018. Machine learning algorithms including instance-based, decision trees, deep neural network, and ensemble algorithms were all used to build the predictive models utilized in this study. Average accuracy, area under receiver operating characteristic curve, Matthew correlation coefficient, macro-precision, recall, weighted average of precision and recall, and model process time were subsequently used to assess the performance of the built models. Information gain and gain ratio were used in order to demonstrate feature importance.

Results : The results showed that most algorithms, except for deep neural network, performed well in terms of all performance indices regardless of either the training or testing dataset that were used. Ten features and their importance to determine the diagnosis code of type 2 diabetes mellitus were identified. Our proposed predictive model can be further developed into a clinical diagnosis support system or integrated into existing healthcare information systems. Both methods of application can effectively support physicians whenever they are diagnosing type 2 diabetes mellitus patients in order to foster better patient-care planning.

Kuo Kuang-Ming, Talley Paul, Kao YuHsi, Huang Chi Hsien

2020

Diagnosis, Machine-learning techniques, Predictive models, Type 2 diabetes mellitus

In Translational vision science & technology

Purpose : To develop deep learning (DL) models to predict best-corrected visual acuity (BCVA) from optical coherence tomography (OCT) images from patients with neovascular age-related macular degeneration (nAMD).

Methods : Retrospective analysis of OCT images and associated BCVA measurements from the phase 3 HARBOR trial (NCT00891735). DL regression models were developed to predict BCVA at the concurrent visit and 12 months from baseline using OCT images. Binary classification models were developed to predict BCVA of Snellen equivalent of <20/40, <20/60, and ≤20/200 at the concurrent visit and 12 months from baseline.

Results : The regression model to predict BCVA at the concurrent visit had R² = 0.67 (root-mean-square error [RMSE] = 8.60) in study eyes and R² = 0.84 (RMSE = 9.01) in fellow eyes. The best classification model to predict BCVA at the concurrent visit had an area under the receiver operating characteristic curve (AUC) of 0.92 in study eyes and 0.98 in fellow eyes. The regression model to predict BCVA at month 12 using baseline OCT had R² = 0.33 (RMSE = 14.16) in study eyes and R² = 0.75 (RMSE = 11.27) in fellow eyes. The best classification model to predict BCVA at month 12 had AUC = 0.84 in study eyes and AUC = 0.96 in fellow eyes.

Conclusions : DL shows promise in predicting BCVA from OCTs in nAMD. Further research should elucidate the utility of models in clinical settings.

Translational Relevance : DL models predicting BCVA could be used to enhance understanding of structure-function relationships and develop more efficient clinical trials.

Kawczynski Michael G, Bengtsson Thomas, Dai Jian, Hopkins J Jill, Gao Simon S, Willis Jeffrey R

2020-Sep

deep learning, neovascular age-related macular degeneration, ocular imaging, public health ophthalmology, tele-ophthalmology

In Turkish journal of orthodontics

Objective : To compare the accuracy of cephalometric analyses made with fully automated tracings, computerized tracing, and app-aided tracings with equivalent hand-traced measurements, and to evaluate the tracing time for each cephalometric analysis method.

Methods : Pre-treatment lateral cephalometric radiographs of 40 patients were randomly selected. Eight angular and 4 linear parameters were measured by 1 operator using 3 methods: computerized tracing with software Dolphin Imaging 13.01(Dolphin Imaging and Management Solutions, Chatsworth, Calif, USA), app-aided tracing using the CephNinja 3.51 app (Cyncronus LLC, WA, USA), and web-based fully automated tracing with CephX (ORCA Dental AI, Las Vegas, NV). Correction of CephX landmarks was also made. Manual tracings were performed by 3 operators. Remeasurement of 15 radiographs was carried out to determine the intra-examiner and inter-examiner (manual tracings) correlation coefficient (ICC). Inter-group comparisons were made with one-way analysis of variance. The Tukey test was used for post hoc testing.

Results : Overall, greater variability was found with CephX compared with the other methods. Differences in GoGn-SN (°), I-NA (°), I-NB (°), I-NA (mm), and I-NB (mm) were statistically (p<0.05) and clinically significant using CephX, whereas CephNinja and Dolphin were comparable to manual tracings. Correction of CephX landmarks gave similar results to CephNinja and Dolphin. All the ICCs exceeded 0.85, except for I-NA (°), I-NB (°), and I-NB (mm), which were traced with CephX. The shortest analyzing time was obtained with CephX.

Conclusion : Fully automatic analysis with CephX needs to be more reliable. However, CephX analysis with manual correction is promising for use in clinical practice because it is comparable to CephNinja and Dolphin, and the analyzing time is significantly shorter.

Meriç Pamir, Naoumova Julia

2020-Sep

Apps, artificial intelligence, automated identification, automatic tracing, cephalometric, computerized tracing, web-based

In Therapeutic advances in chronic disease

Background : We aimed to determine the role of non-mydriatic fundus examination and artificial intelligence (AI) in screening diabetic retinopathy (DR) in patients with diabetes in the Metabolic Disease Management Center (MMC) in Tianjin, China.

Methods : Adult patients with type 2 diabetes mellitus who were first treated by MMC in Tianjin First Central Hospital and Tianjin 4th Center Hospital were divided into two groups according to the time that MMC was equipped with the non-mydriatic ophthalmoscope and AI system and could complete fundus examination independently (the former was the control group, the latter was the observation group). The observation indices were as follows: the incidence of DR, the fundus screening rate of the two groups, and fundus screening of diabetic patients with different course of disease.

Results : A total of 5039 patients were enrolled in this study. The incidence rate of DR was 18.6%, 29.8%, and 49.6% in patients with diabetes duration of ⩽1 year, 1-5 years, and >5 years, respectively. The screening rate of fundus in the observation group was significantly higher compared with the control group (81.3% versus 28.4%, χ² = 1430.918, p < 0.001). The DR screening rate of the observation group was also significantly higher compared with the control group in patients with diabetes duration of ⩽1 year (77.3% versus 20.6%; χ² = 797.534, p < 0.001), 1-5 years (82.5% versus 31.0%; χ² = 197.124, p < 0.001) and ⩾5 years (86.9% versus 37.1%; χ² = 475.609, p < 0.001).

Conclusions : In the case of limited medical resources, MMC can carry out one-stop examination, treatment, and management of DR through non-mydratic fundus examination and AI assistance, thus incorporating the DR screening process into the endocrine clinic, so as to facilitate early diagnosis.

Hao Zhaohu, Cui Shanshan, Zhu Yanjuan, Shao Hailin, Huang Xiao, Jiang Xia, Xu Rong, Chang Baocheng, Li Huanming

2020

artificial intelligence, diabetic retinopathy, fundus screening, non-mydratic fundus examination

In Frontiers in genetics ; h5-index 62.0

Bresolin Tiago, Dórea João R R

2020

beef cattle, dairy cattle, mid-infrared, near-infrared, novel phenotypes, spectral information

In Frontiers in plant science

Oña Chuquimarca Samara, Ayala-Ruano Sebastián, Goossens Jonas, Pauwels Laurens, Goossens Alain, Leon-Reyes Antonio, Ángel Méndez Miguel

2020

JAZ, MYC, computer, hotspots, machine learning, modeling, plant defense

In Frontiers in psychology ; h5-index 92.0

Levy Jessica, Mussack Dominic, Brunner Martin, Keller Ulrich, Cardoso-Leite Pedro, Fischbach Antoine

2020

longitudinal data, machine learning, model comparison, school effectiveness, value-added modeling

In Frontiers in psychiatry

Wiguna Tjhin, Wigantara Ngurah Agung, Ismail Raden Irawati, Kaligis Fransiska, Minayati Kusuma, Bahana Raymond, Dirgantoro Bayu

2020

Indonesia, attention-deficit/hyperactivity disorder, diagnostic tool, digital game, machine learning, neuropsychological test, virtual reality

In Frontiers in pharmacology

Shayakhmetov Rim, Kuznetsov Maksim, Zhebrak Alexander, Kadurin Artur, Nikolenko Sergey, Aliper Alexander, Polykovskiy Daniil

2020

adversarial autoencoders, conditional generation, deep learning, drug discovery, gene expression, generative models, representation learning

In Diagnostics (Basel, Switzerland)

Lee Kwang-Sig, Ahn Ki Hoon

2020-Sep-22

artificial intelligence, early diagnosis, preterm birth

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

Tartaglione Enzo, Barbano Carlo Alberto, Berzovini Claudio, Calandri Marco, Grangetto Marco

2020-Sep-22

COVID-19, chest X-ray, classification, deep learning

In Frontiers in integrative neuroscience

Objective : Transcranial magnetic stimulation (TMS), a non-invasive procedure, stimulates the cortex evaluating the central motor pathways. The response is called motor evoked potential (MEP). Polyphasia results when the response crosses the baseline more than twice (zero crossing). Recent research shows MEP polyphasia in patients with generalized genetic epilepsy (GGE) and their first-degree relatives compared with controls. Juvenile Myoclonic Epilepsy (JME), a GGE type, is not well studied regarding polyphasia. In our study, we assessed polyphasia appearance probability with TMS in JME patients, their healthy first-degree relatives and controls. Two genetic approaches were applied to uncover genetic association with polyphasia.

Methods : 20 JME patients, 23 first-degree relatives and 30 controls underwent TMS, obtaining 10-15 MEPs per participant. We evaluated MEP mean number of phases, proportion of MEP trials displaying polyphasia for each subject and variability between groups. Participants underwent whole exome sequencing (WES) via trio-based analysis and two-case scenario. Extensive bioinformatics analysis was applied.

Results : We identified increased polyphasia in patients (85%) and relatives (70%) compared to controls (47%) and significantly higher mean number of zero crossings (i.e., occurrence of phases) (patients 1.49, relatives 1.46, controls 1.22; p < 0.05). Trio-based analysis revealed a candidate polymorphism, p.Glu270del,in SYT14 (Synaptotagmin 14), in JME patients and their relatives presenting polyphasia. Sanger sequencing analysis in remaining participants showed no significant association. In two-case scenario, a machine learning approach was applied in variants identified from odds ratio analysis and risk prediction scores were obtained for polyphasia. The results revealed 61 variants of which none was associated with polyphasia. Risk prediction scores indeed showed lower probability for non-polyphasic subjects on having polyphasia and higher probability for polyphasic subjects on having polyphasia.

Conclusion : Polyphasia was present in JME patients and relatives in contrast to controls. Although no known clinical symptoms are linked to polyphasia this neurophysiological phenomenon is likely due to common cerebral electrophysiological abnormality. We did not discover direct association between genetic variants obtained and polyphasia. It is likely these genetic traits alone cannot provoke polyphasia, however, this predisposition combined with disturbed brain-electrical activity and tendency to generate seizures may increase the risk of developing polyphasia, mainly in patients and relatives.

Stefani Stefani, Kousiappa Ioanna, Nicolaou Nicoletta, Papathanasiou Eleftherios S, Oulas Anastasis, Fanis Pavlos, Neocleous Vassos, Phylactou Leonidas A, Spyrou George M, Papacostas Savvas S

2020

genetics, juvenile myoclonic epilepsy, neurophysiology, polymorphism, polyphasia, transcranial magnetic stimulation, whole exome sequencing

In Frontiers in neural circuits

Miguel-Blanco Aitor, Manoonpong Poramate

2020

central pattern generator, forward model, legged robot control, lesion-induced plasticity, neural circuits, serotonin, synaptic plasticity, walking machines

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

Kim Seokhwi, Bae Won Jung, Ahn Ji Mi, Heo Jin-Hyung, Kim Kyoung-Mee, Choi Kyeong Woon, Sung Chang Ohk, Lee Dakeun

2020-Sep-24

In Scientific reports ; h5-index 158.0

Starke Sebastian, Leger Stefan, Zwanenburg Alex, Leger Karoline, Lohaus Fabian, Linge Annett, Schreiber Andreas, Kalinauskaite Goda, Tinhofer Inge, Guberina Nika, Guberina Maja, Balermpas Panagiotis, von der Grün Jens, Ganswindt Ute, Belka Claus, Peeken Jan C, Combs Stephanie E, Boeke Simon, Zips Daniel, Richter Christian, Troost Esther G C, Krause Mechthild, Baumann Michael, Löck Steffen

2020-Sep-24

In Scientific reports ; h5-index 158.0

Shim Eungjune, Kim Joon Yub, Yoon Jong Pil, Ki Se-Young, Lho Taewoo, Kim Youngjun, Chung Seok Won

2020-Sep-24

In Nature communications ; h5-index 260.0

Yu Sunkyu, Piao Xianji, Park Namkyoo

2020-09-24

In Nature communications ; h5-index 260.0

Fu Fan, Wei Jianyong, Zhang Miao, Yu Fan, Xiao Yueting, Rong Dongdong, Shan Yi, Li Yan, Zhao Cheng, Liao Fangzhou, Yang Zhenghan, Li Yuehua, Chen Yingmin, Wang Ximing, Lu Jie

2020-09-24

In Genome research ; h5-index 99.0

Hammelman Jennifer, Krismer Konstantin, Banerjee Budhaditya, Gifford David K, Sherwood Richard I

2020-Sep-24

In Injury ; h5-index 49.0

Klontzas Michail E, Papadakis Georgios Z, Marias Kostas, Karantanas Apostolos H

2020-Sep-16

Artificial intelligence, Deep learning, Hybrid positron-emission Tomography/MR imaging, Magnetic resonance imaging, Musculoskeletal system/injuries, Neural networks

In Artificial intelligence in medicine ; h5-index 34.0

Li Yuan, Chen Pingjun, Li Zhiyuan, Su Hai, Yang Lin, Zhong Dingrong

2020-Aug

Deep learning, Frozen section, Rule-based protocol, Thyroid nodule, Whole slide image

In International journal of molecular sciences ; h5-index 102.0

Scimeca Manuel, Urbano Nicoletta, Bonfiglio Rita, Montanaro Manuela, Bonanno Elena, Schillaci Orazio, Mauriello Alessandro

2020-Sep-22

SARS-CoV-2, artificial intelligence, imaging diagnostic, pandemic, pathology

In International journal of molecular sciences ; h5-index 102.0

Scimeca Manuel, Urbano Nicoletta, Bonfiglio Rita, Montanaro Manuela, Bonanno Elena, Schillaci Orazio, Mauriello Alessandro

2020-Sep-22

SARS-CoV-2, artificial intelligence, imaging diagnostic, pandemic, pathology

In Artificial intelligence in medicine ; h5-index 34.0

Reyes Oscar, Pérez Eduardo, Luque Raúl M, Castaño Justo, Ventura Sebastián

2020-Aug

Alternative Splicing, Classification methods, Explaining classifier’s predictions, Feature weighting methods, Transcript-based analysis

In Artificial intelligence in medicine ; h5-index 34.0

Stylianou Nikolaos, Razis Gerasimos, Goulis Dimitrios G, Vlahavas Ioannis

2020-Aug

Evidence Based Medicine, Machine learning, Natural Language Processing, Neural networks, PICO

In Artificial intelligence in medicine ; h5-index 34.0

Gao Long, Zhang Lei, Liu Chang, Wu Shandong

2020-Aug

Data imbalance, Deep learning, Image complexity, Medical image classification

In Artificial intelligence in medicine ; h5-index 34.0

OBJECTIVE : In this paper, we proposed new methods for feature extraction in machine learning-based classification of atrial fibrillation from ECG signal.

METHODS : Our proposed methods improved conventional 1-dimensional local binary pattern method in two ways. First, we proposed a dynamic threshold LBP code generation method for use with 1-dimensional signals, enabling the generated LBP codes to have a more detailed representation of the signal morphological pattern. Second, we introduced a variable step value into the LBP code generation algorithm to better cope with a high sampling frequency input signal without a downsampling process. The proposed methods do not employ computationally expensive processes such as filtering, wavelet transform, up/downsampling, or beat detection, and can be implemented using only simple addition, division, and compare operations.

RESULTS : Combining these two approaches, our proposed variable step dynamic threshold local binary pattern method achieved 99.11% sensitivity and 99.29% specificity when used as a feature generation algorithm in support vector machine classification of atrial fibrillation from MIT-BIH Atrial Fibrillation Database dataset. When applied on signals from MIT-BIH Arrhythmia Database, our proposed method achieved similarly good 99.38% sensitivity and 98.97% specificity.

CONCLUSION : Our proposed methods achieved one of the best results among published works in atrial fibrillation classification using the same dataset while using less computationally expensive calculations, without significant performance degradation when applied on signals from multiple databases with different sampling frequencies.

Yazid Muhammad, Abdur Rahman Mahrus

2020-Aug

AFDB, Atrial fibrillation, Dynamic threshold, Local binary pattern, MITDB, Variable step

In Artificial intelligence in medicine ; h5-index 34.0

Van Woensel William, Roy Patrice C, Abidi Syed Sibte Raza, Abidi Samina Raza

2020-Aug

Activities of daily living, Ambient assisted living, Ambient sensors, Data fusion, Indoor localization, Machine learning, Self-management, Semantic web, Virtual care, eHealth platform

In Artificial intelligence in medicine ; h5-index 34.0

Dagliati Arianna, Geifman Nophar, Peek Niels, Holmes John H, Sacchi Lucia, Bellazzi Riccardo, Sajjadi Seyed Erfan, Tucker Allan

2020-Aug

Electronic phenotyping, Longitudinal studies, Type 2 diabetes, Unsupervised machine learning

In Artificial intelligence in medicine ; h5-index 34.0

Sánchez-Peralta Luisa F, Bote-Curiel Luis, Picón Artzai, Sánchez-Margallo Francisco M, Pagador J Blas

2020-Aug

Colorectal cancer, Deep learning, Detection, Localization, Segmentation

In Artificial intelligence in medicine ; h5-index 34.0

Miao Fen, Wen Bo, Hu Zhejing, Fortino Giancarlo, Wang Xi-Ping, Liu Zeng-Ding, Tang Min, Li Ye

2020-Aug

Blood pressure, ECG, Long short-term memory, Residual network

In Chinese medical sciences journal = Chung-kuo i hsueh k'o hsueh tsa chih

Wang Zheng, Zhao Qing Hua, Yang Jing Lin, Zhou Feng

2020-Sep-30

In Diagnostic pathology ; h5-index 35.0

Fassler Danielle J, Abousamra Shahira, Gupta Rajarsi, Chen Chao, Zhao Maozheng, Paredes David, Batool Syeda Areeha, Knudsen Beatrice S, Escobar-Hoyos Luisa, Shroyer Kenneth R, Samaras Dimitris, Kurc Tahsin, Saltz Joel

2020-Sep-24

In Scientific data

Jiang Hou, Lu Ning, Qin Jun, Yao Ling

2020-09-23

In Science robotics

Stork Johannes A

2020-Sep-23

In Biomedical journal

Häfner Sophia Julia

2020-Aug-27

COVID-19, Contact tracing, Pseudovirus system, Repurposing drugs, SARS-CoV-2

In BMC biology

BACKGROUND : Access to quantitative information is crucial to obtain a deeper understanding of biological systems. In addition to being low-throughput, traditional image-based analysis is mostly limited to error-prone qualitative or semi-quantitative assessment of phenotypes, particularly for complex subcellular morphologies. The PVD neuron in Caenorhabditis elegans, which is responsible for harsh touch and thermosensation, undergoes structural degeneration as nematodes age characterized by the appearance of dendritic protrusions. Analysis of these neurodegenerative patterns is labor-intensive and limited to qualitative assessment.

RESULTS : In this work, we apply deep learning to perform quantitative image-based analysis of complex neurodegeneration patterns exhibited by the PVD neuron in C. elegans. We apply a convolutional neural network algorithm (Mask R-CNN) to identify neurodegenerative subcellular protrusions that appear after cold-shock or as a result of aging. A multiparametric phenotypic profile captures the unique morphological changes induced by each perturbation. We identify that acute cold-shock-induced neurodegeneration is reversible and depends on rearing temperature and, importantly, that aging and cold-shock induce distinct neuronal beading patterns.

CONCLUSION : The results of this work indicate that implementing deep learning for challenging image segmentation of PVD neurodegeneration enables quantitatively tracking subtle morphological changes in an unbiased manner. This analysis revealed that distinct patterns of morphological alteration are induced by aging and cold-shock, suggesting different mechanisms at play. This approach can be used to identify the molecular components involved in orchestrating neurodegeneration and to characterize the effect of other stressors on PVD degeneration.

Saberi-Bosari Sahand, Flores Kevin B, San-Miguel Adriana

2020-Sep-23

Aging, C. elegans, Convolutional neural networks, Deep learning, Machine learning, Neurodegeneration, Neuronal beading, Phenotyping

In European journal of radiology ; h5-index 47.0

PURPOSE : Diagnosing desmoid-type fibromatosis (DTF) requires an invasive tissue biopsy with β-catenin staining and CTNNB1 mutational analysis, and is challenging due to its rarity. The aim of this study was to evaluate radiomics for distinguishing DTF from soft tissue sarcomas (STS), and in DTF, for predicting the CTNNB1 mutation types.

METHODS : Patients with histologically confirmed extremity STS (non-DTF) or DTF and at least a pretreatment T1-weighted (T1w) MRI scan were retrospectively included. Tumors were semi-automatically annotated on the T1w scans, from which 411 features were extracted. Prediction models were created using a combination of various machine learning approaches. Evaluation was performed through a 100x random-split cross-validation. The model for DTF vs. non-DTF was compared to classification by two radiologists on a location matched subset.

RESULTS : The data included 203 patients (72 DTF, 131 STS). The T1w radiomics model showed a mean AUC of 0.79 on the full dataset. Addition of T2w or T1w post-contrast scans did not improve the performance. On the location matched cohort, the T1w model had a mean AUC of 0.88 while the radiologists had an AUC of 0.80 and 0.88, respectively. For the prediction of the CTNNB1 mutation types (S45 F, T41A and wild-type), the T1w model showed an AUC of 0.61, 0.56, and 0.74.

CONCLUSIONS : Our radiomics model was able to distinguish DTF from STS with high accuracy similar to two radiologists, but was not able to predict the CTNNB1 mutation status.

Timbergen Milea J M, Starmans Martijn P A, Padmos Guillaume A, Grünhagen Dirk J, van Leenders Geert J L H, Hanff D F, Verhoef Cornelis, Niessen Wiro J, Sleijfer Stefan, Klein Stefan, Visser Jacob J

2020-Sep-08

Aggressive, Beta catenin, Fibromatosis, Machine learning, Magnetic resonance imaging, Radiomics

In Quarterly journal of experimental psychology (2006)

Khemlani Sangeet, Johnson-Laird P N

2020-Sep-23

Inconsistency, bridging inferences, causal reasoning, domino effects, mental models, minimalism

In Journal of psychiatric research ; h5-index 59.0

BACKGROUND : Behavioral observations support clinical in-depth phenotyping but phenotyping and pattern recognition are affected by training background. As Attention Deficit Hyperactivity Disorder, Restless Legs syndrome/Willis Ekbom disease and medication induced activation syndromes (including increased irritability and/or akathisia), present with hyperactive-behaviors with hyper-arousability and/or hypermotor-restlessness (H-behaviors), we first developed a non-interpretative, neutral pictogram-guided phenotyping language (PG-PL) for describing body-segment movements during sitting (Data in Brief).

METHODOLOGY & RESULTS : The PG-PL was applied for annotating 12 1-min sitting-videos (inter-observer agreements >85%->97%) and these manual annotations were used as a ground truth to develop an automated algorithm using OpenPose, which locates skeletal landmarks in 2D video. We evaluated the algorithm's performance against the ground truth by computing the area under the receiver operator curve (>0.79 for the legs, arms, and feet, but 0.65 for the head). While our pixel displacement algorithm performed well for the legs, arms, and feet, it predicted head motion less well, indicating the need for further investigations.

CONCLUSION : This first automated analysis algorithm allows to start the discussion about distinct phenotypical characteristics of H-behaviors during structured behavioral observations and may support differential diagnostic considerations via in-depth phenotyping of sitting behaviors and, in consequence, of better treatment concepts.

Beyzaei Nadia, Bao Seraph, Bu Yanyun, Hung Linus, Hussaina Hebah, Maher Khaola Safia, Chan Melvin, Garn Heinrich, Kloesch Gerhard, Kohn Bernhard, Kuzeljevic Boris, McWilliams Scout, Spruyt Karen, Tse Emmanuel, Machiel Van der Loos Hendrik F, Kuo Calvin, Ipsiroglu Osman S

2020-Aug-29

Adverse drug reactions, Misdiagnosis, Movement disorders, Over-medication, Sleep-related movement disorders

In NeuroImage ; h5-index 117.0

Schramm Georg, Rigie David, Vahle Thomas, Rezaei Ahmadreza, Laere Koen van, Shepherd Timothy, Nuyts Johan, Boada Fernando

2020-Sep-21

Image reconstruction, Machine learning, Magnetic Resonance Imaging, Molecular Imaging, Quantification

In Ageing research reviews ; h5-index 66.0

Fang Evandro F, Xie Chenglong, Schenkel Joseph A, Wu Chenkai, Long Qian, Cui Honghua, Aman Yahyah, Frank Johannes, Liao Jing, Zou Huachun, Wang Ninie Y, Wu Jing, Liu Xiaoting, Li Tao, Fang Yuan, Niu Zhangming, Yang Guang, Hong Jiangshui, Wang Qian, Chen Guobing, Li Jun, Chen Hou-Zao, Kang Lin, Su Huanxing, Gilmour Brian C, Zhu Xinqiang, Jiang Hong, He Na, Tao Jun, Leng Sean Xiao, Tong Tanjun, Woo Jean

2020-Sep-21

Ageing policy, Dementia, Inflammageing, Oral ageing, Sexually transmitted diseases, Square dancing

In Methods (San Diego, Calif.)

Tian Tian, Min Martin Renqiang, Wei Zhi

2020-Sep-21

Deep learning, Imputation, ScRNA-seq

In Cell systems

Strokach Alexey, Becerra David, Corbi-Verge Carles, Perez-Riba Albert, Kim Philip M

2020-Sep-15

constraint satisfaction problem, deep learning, graph neural networks, inverse protein folding, protein design, protein optimization

In Neuron ; h5-index 148.0

Yang Guangyu Robert, Wang Xiao-Jing

2020-Sep-23

In DNA research : an international journal for rapid publication of reports on genes and genomes

Lee Jong-Hun, Saito Yutaka, Park Sung-Joon, Nakai Kenta

2020-Sep-24

Hidden Markov model, Neuro-epigenetics, Non-CpG methylation

In Journal of the National Cancer Institute

BACKGROUND : Magnetic resonance imaging (MRI) images are crucial unstructured data for prognostic evaluation in nasopharyngeal carcinoma (NPC). We developed and validated a prognostic system based on the MRI features and clinical data of locoregionally advanced NPC (LA-NPC) patients to distinguish low-risk patients with LA-NPC, for whom concurrent chemoradiotherapy (CCRT) is sufficient.

METHODS : This multicenter, retrospective study included 3444 patients with LA-NPC from January 1, 2010, to January 31, 2017. A three-dimensional convolutional neural network was used to learn the image features from pretreatment MRI images. An eXtreme Gradient Boosting model was trained with the MRI features and clinical data to assign an overall score to each patient. Comprehensive evaluations were implemented to assess the performance of the predictive system. We applied the overall score to distinguish high-risk patients from low-risk patients. The clinical benefit of induction chemotherapy (IC) was analyzed in each risk group by survival curves.

RESULTS : We constructed a prognostic system displaying a concordance index of 0.776 (95% CI = 0.746-0.806) for the internal validation cohort and 0.757 (95% CI = 0.695-0.819), 0.719 (95% CI = 0.650-0.789) and 0.746 (95% CI = 0.699-0.793) for the three external validation cohorts, which presented a statistically significant improvement compared to the conventional tumor-node-metastasis (TNM) staging system. In the high-risk group, patients who received IC plus CCRT had better outcomes than patients who received CCRT alone, while there was no statistically significant difference in the low-risk group.

CONCLUSIONS : The proposed framework can capture more complex and heterogeneous information to predict the prognosis of patients with LA-NPC and potentially contribute to clinical decision making.

Qiang Mengyun, Li Chaofeng, Sun Yuyao, Sun Ying, Ke Liangru, Xie Chuanmiao, Zhang Tao, Zou Yujian, Qiu Wenze, Gao Mingyong, Li Yingxue, Li Xiang, Zhan Zejiang, Liu Kuiyuan, Chen Xi, Liang Chixiong, Chen Qiuyan, Mai Haiqiang, Xie Guotong, Guo Xiang, Lv Xing

2020-Sep-24

In PloS one ; h5-index 176.0

Redfern Joseph, Sidorov Kirill, Rosin Paul L, Corcoran Padraig, Moore Simon C, Marshall David

2020

In PloS one ; h5-index 176.0

MOTIVATION : Calculating the magnitude of treatment effects or of differences between two groups is a common task in quantitative science. Standard effect size measures based on differences, such as the commonly used Cohen's, fail to capture the treatment-related effects on the data if the effects were not reflected by the central tendency. The present work aims at (i) developing a non-parametric alternative to Cohen's d, which (ii) circumvents some of its numerical limitations and (iii) involves obvious changes in the data that do not affect the group means and are therefore not captured by Cohen's d.

RESULTS : We propose "Impact" as a novel non-parametric measure of effect size obtained as the sum of two separate components and includes (i) a difference-based effect size measure implemented as the change in the central tendency of the group-specific data normalized to pooled variability and (ii) a data distribution shape-based effect size measure implemented as the difference in probability density of the group-specific data. Results obtained on artificial and empirical data showed that "Impact"is superior to Cohen's d by its additional second component in detecting clearly visible effects not reflected in central tendencies. The proposed effect size measure is invariant to the scaling of the data, reflects changes in the central tendency in cases where differences in the shape of probability distributions between subgroups are negligible, but captures changes in probability distributions as effects and is numerically stable even if the variances of the data set or its subgroups disappear.

CONCLUSIONS : The proposed effect size measure shares the ability to observe such an effect with machine learning algorithms. Therefore, the proposed effect size measure is particularly well suited for data science and artificial intelligence-based knowledge discovery from big and heterogeneous data.

Lötsch Jörn, Ultsch Alfred

2020

In Cancers

Chandramouli Sacheth, Leo Patrick, Lee George, Elliott Robin, Davis Christine, Zhu Guangjing, Fu Pingfu, Epstein Jonathan I, Veltri Robert, Madabhushi Anant

2020-Sep-21

active surveillance, machine learning, pathology, prostate cancer

In PloS one ; h5-index 176.0

Nori Vijay S, Hane Christopher A, Sun Yezhou, Crown William H, Bleicher Paul A

2020

In PLoS neglected tropical diseases ; h5-index 79.0

Zhao Naizhuo, Charland Katia, Carabali Mabel, Nsoesie Elaine O, Maheu-Giroux Mathieu, Rees Erin, Yuan Mengru, Garcia Balaguera Cesar, Jaramillo Ramirez Gloria, Zinszer Kate

2020-Sep-24

In PLoS neglected tropical diseases ; h5-index 79.0

Qian Wei, Viennet Elvina, Glass Kathryn, Harley David

2020-Sep-24

In PLoS computational biology

Mukherjee Rajib, Beykal Burcu, Szafran Adam T, Onel Melis, Stossi Fabio, Mancini Maureen G, Lloyd Dillon, Wright Fred A, Zhou Lan, Mancini Michael A, Pistikopoulos Efstratios N

2020-Sep-24

In The Journal of clinical investigation ; h5-index 129.0

BACKGROUND : Viral load surrogate endpoints transformed development of HIV and hepatitis C therapeutics. Surrogate endpoints for cytomegalovirus (CMV)-related morbidity and mortality could advance development of antiviral treatments. While observational data support using CMV viral load (VL) as a trial endpoint, randomized controlled trials (RCT) demonstrating direct associations between virologic markers and clinical endpoints are lacking.

METHODS : We performed CMV DNA polymerase chain reaction (PCR) on frozen serum samples from the only placebo-controlled RCT of ganciclovir for early treatment of CMV after hematopoietic cell transplantation (HCT). We used established criteria to assess VL kinetics as surrogates for CMV disease or death by weeks 8, 24, and 48 after randomization and quantified antiviral effects captured by each marker. We used ensemble-based machine learning to assess the predictive ability of VL kinetics and performed this analysis on a ganciclovir prophylaxis RCT for validation.

RESULTS : VL suppression with ganciclovir reduced cumulative incidence of CMV disease and death for 20 years after HCT. Mean VL, peak VL, and change in VL during the first five weeks of treatment fulfilled the Prentice definition for surrogacy, capturing > 95% of ganciclovir's effect, and yielded highly sensitive and specific predictions by week 48. In the prophylaxis trial, viral shedding rate satisfied the Prentice definition for CMV disease by week 24.

CONCLUSION : Our results support using CMV VL kinetics as surrogates for CMV disease, provide a framework for developing CMV preventative and therapeutic agents, and support reductions in viral load as the mechanism through which antivirals reduce CMV disease.

Duke Elizabeth R, Williamson Brian D, Borate Bhavesh, Golob Jonathan L, Wychera Chiara, Stevens-Ayers Terry, Huang Meei-Li, Cossrow Nicole, Wan Hong, Mast T Christopher, Marks Morgan A, Flowers Mary, Jerome Keith R, Corey Lawrence, Gilbert Peter B, Schiffer Joshua T, Boeckh Michael

2020-Sep-24

Clinical Trials, Drug therapy, Infectious disease, Stem cell transplantation

In JCI insight

Dangi Anil, Natesh Naveen R, Husain Irma, Ji Zhicheng, Barisoni Laura, Kwun Jean, Shen Xiling, Thorp Edward B, Luo Xunrong

2020-Sep-24

Bioinformatics, Immunology, Macrophages, Organ transplantation, Transplantation

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

Han Na, Wu Jigang, Fang Xiaozhao, Teng Shaohua, Zhou Guoxu, Xie Shengli, Li Xuelong

2020-Sep-24

In JCO clinical cancer informatics

PURPOSE : To examine the impact of a clinical decision support system (CDSS) on breast cancer treatment decisions and adherence to National Comprehensive Cancer Center (NCCN) guidelines.

PATIENTS AND METHODS : A cross-sectional observational study was conducted involving 1,977 patients at high risk for recurrent or metastatic breast cancer from the Chinese Society of Clinical Oncology. Ten oncologists provided blinded treatment recommendations for an average of 198 patients before and after viewing therapeutic options offered by the CDSS. Univariable and bivariable analyses of treatment changes were performed, and multivariable logistic regressions were estimated to examine the effects of physician experience (years), patient age, and receptor subtype/TNM stage.

RESULTS : Treatment decisions changed in 105 (5%) of 1,977 patients and were concentrated in those with hormone receptor (HR)-positive disease or stage IV disease in the first-line therapy setting (73% and 58%, respectively). Logistic regressions showed that decision changes were more likely in those with HR-positive cancer (odds ratio [OR], 1.58; P < .05) and less likely in those with stage IIA (OR, 0.29; P < .05) or IIIA cancer (OR, 0.08; P < .01). Reasons cited for changes included consideration of the CDSS therapeutic options (63% of patients), patient factors highlighted by the tool (23%), and the decision logic of the tool (13%). Patient age and oncologist experience were not associated with decision changes. Adherence to NCCN treatment guidelines increased slightly after using the CDSS (0.5%; P = .003).

CONCLUSION : Use of an artificial intelligence-based CDSS had a significant impact on treatment decisions and NCCN guideline adherence in HR-positive breast cancers. Although cases of stage IV disease in the first-line therapy setting were also more likely to be changed, the effect was not statistically significant (P = .22). Additional research on decision impact, patient-physician communication, learning, and clinical outcomes is needed to establish the overall value of the technology.

Xu Fengrui, Sepúlveda Martín-J, Jiang Zefei, Wang Haibo, Li Jianbin, Liu Zhenzhen, Yin Yongmei, Roebuck M Christopher, Shortliffe Edward H, Yan Min, Song Yuhua, Geng Cuizhi, Tang Jinhai, Purcell Jackson Gretchen, Preininger Anita M, Rhee Kyu

2020-Sep

In The journal of physical chemistry. A

Käser Silvan, Koner Debasish, Christensen Anders S, von Lilienfeld O Anatole, Meuwly Markus

2020-Sep-24

In The journal of physical chemistry. B

Tian Hao, Trozzi Francesco, Zoltowski Brian D, Tao Peng

2020-Sep-24

In Cancers

Jang Bum-Sup, Park Andrew J, Jeon Seung Hyuck, Kim Il Han, Lim Do Hoon, Park Shin-Hyung, Lee Ju Hye, Chang Ji Hyun, Cho Kwan Ho, Kim Jin Hee, Sunwoo Leonard, Choi Seung Hong, Kim In Ah

2020-Sep-21

glioblastoma, machine learning, pseudoprogression, radiotherapy

In Journal of thoracic imaging

PURPOSE : To evaluate the performance of a deep learning (DL) algorithm for the detection of COVID-19 on chest radiographs (CXR).

MATERIALS AND METHODS : In this retrospective study, a DL model was trained on 112,120 CXR images with 14 labeled classifiers (ChestX-ray14) and fine-tuned using initial CXR on hospital admission of 509 patients, who had undergone COVID-19 reverse transcriptase-polymerase chain reaction (RT-PCR). The test set consisted of a CXR on presentation of 248 individuals suspected of COVID-19 pneumonia between February 16 and March 3, 2020 from 4 centers (72 RT-PCR positives and 176 RT-PCR negatives). The CXR were independently reviewed by 3 radiologists and using the DL algorithm. Diagnostic performance was compared with radiologists' performance and was assessed by area under the receiver operating characteristics (AUC).

RESULTS : The median age of the subjects in the test set was 61 (interquartile range: 39 to 79) years (51% male). The DL algorithm achieved an AUC of 0.81, sensitivity of 0.85, and specificity of 0.72 in detecting COVID-19 using RT-PCR as the reference standard. On subgroup analyses, the model achieved an AUC of 0.79, sensitivity of 0.80, and specificity of 0.74 in detecting COVID-19 in patients presented with fever or respiratory systems and an AUC of 0.87, sensitivity of 0.85, and specificity of 0.81 in distinguishing COVID-19 from other forms of pneumonia. The algorithm significantly outperforms human readers (P<0.001 using DeLong test) with higher sensitivity (P=0.01 using McNemar test).

CONCLUSIONS : A DL algorithm (COV19NET) for the detection of COVID-19 on chest radiographs can potentially be an effective tool in triaging patients, particularly in resource-stretched health-care systems.

Chiu Wan Hang Keith, Vardhanabhuti Varut, Poplavskiy Dmytro, Yu Philip Leung Ho, Du Richard, Yap Alistair Yun Hee, Zhang Sailong, Fong Ambrose Ho-Tung, Chin Thomas Wing-Yan, Lee Jonan Chun Yin, Leung Siu Ting, Lo Christine Shing Yen, Lui Macy Mei-Sze, Fang Benjamin Xin Hao, Ng Ming-Yen, Kuo Michael D

2020-Sep-22

In Analytical chemistry

Russo Daniel P, Yan Xiliang, Shende Sunil, Huang Heng, Yan Bing, Zhu Hao

2020-Sep-24

In Der Ophthalmologe : Zeitschrift der Deutschen Ophthalmologischen Gesellschaft

BACKGROUND AND OBJECTIVE : In the last decades increasingly more systems of artificial intelligence have been established in medicine, which identify diseases or pathologies or discriminate them from complimentary diseases. Up to now the Corvis®ST (Corneal Visualization Scheimpflug Technology, Corvis®ST, Oculus, Wetzlar, Germany) yielded a binary index for classifying keratoconus but did not enable staging. The purpose of this study was to develop a prediction model, which mimics the topographic keratoconus classification index (TKC) of the Pentacam high resolution (HR, Oculus) with measurement parameters extracted from the Corvis®ST.

PATIENTS AND METHODS : In this study 60 measurements from normal subjects (TKC 0) and 379 eyes with keratoconus (TKC 1-4) were recruited. After measurement with the Pentacam HR (target parameter TKC) a measurement with the Corvis®ST device was performed. From this device 6 dynamic response parameters were extracted, which were included in the Corvis biomechanical index (CBI) provided by the Corvis®ST (ARTh, SP-A1, DA ratio 1 mm, DA ratio 2 mm, A1 velocity, max. deformation amplitude). In addition to the TKC as the target, the binarized TKC (1: TKC 1-4, 0: TKC 0) was modelled. The performance of the model was validated with accuracy as an indicator for correct classification made by the algorithm. Misclassifications in the modelling were penalized by the number of stages of deviation between the modelled and measured TKC values.

RESULTS : A total of 24 different models of supervised machine learning from 6 different families were tested. For modelling of the TKC stages 0-4, the algorithm based on a support vector machine (SVM) with linear kernel showed the best performance with an accuracy of 65.1% correct classifications. For modelling of binarized TKC, a decision tree with a coarse resolution showed a superior performance with an accuracy of 95.2% correct classifications followed by the SVM with linear or quadratic kernel and a nearest neighborhood classifier with cubic kernel (94.5% each).

CONCLUSION : This study aimed to show the principle of supervised machine learning applied to a set-up for the modelled classification of keratoconus staging. Preprocessed measurement data extracted from the Corvis®ST device were used to mimic the TKC provided by the Pentacam device with a series of different algorithms of machine learning.

Langenbucher Achim, Häfner Larissa, Eppig Timo, Seitz Berthold, Szentmáry Nóra, Flockerzi Elias

2020-Sep-24

Artificial intelligence, Corvis, Keratoconus, Scheimpflug corneal tomography, Supervised machine learning

In JAMA network open

Importance : The improvement of pulmonary nodule detection, which is a challenging task when using chest radiographs, may help to elevate the role of chest radiographs for the diagnosis of lung cancer.

Objective : To assess the performance of a deep learning-based nodule detection algorithm for the detection of lung cancer on chest radiographs from participants in the National Lung Screening Trial (NLST).

Design, Setting, and Participants : This diagnostic study used data from participants in the NLST ro assess the performance of a deep learning-based artificial intelligence (AI) algorithm for the detection of pulmonary nodules and lung cancer on chest radiographs using separate training (in-house) and validation (NLST) data sets. Baseline (T0) posteroanterior chest radiographs from 5485 participants (full T0 data set) were used to assess lung cancer detection performance, and a subset of 577 of these images (nodule data set) were used to assess nodule detection performance. Participants aged 55 to 74 years who currently or formerly (ie, quit within the past 15 years) smoked cigarettes for 30 pack-years or more were enrolled in the NLST at 23 US centers between August 2002 and April 2004. Information on lung cancer diagnoses was collected through December 31, 2009. Analyses were performed between August 20, 2019, and February 14, 2020.

Exposures : Abnormality scores produced by the AI algorithm.

Main Outcomes and Measures : The performance of an AI algorithm for the detection of lung nodules and lung cancer on radiographs, with lung cancer incidence and mortality as primary end points.

Results : A total of 5485 participants (mean [SD] age, 61.7 [5.0] years; 3030 men [55.2%]) were included, with a median follow-up duration of 6.5 years (interquartile range, 6.1-6.9 years). For the nodule data set, the sensitivity and specificity of the AI algorithm for the detection of pulmonary nodules were 86.2% (95% CI, 77.8%-94.6%) and 85.0% (95% CI, 81.9%-88.1%), respectively. For the detection of all cancers, the sensitivity was 75.0% (95% CI, 62.8%-87.2%), the specificity was 83.3% (95% CI, 82.3%-84.3%), the positive predictive value was 3.8% (95% CI, 2.6%-5.0%), and the negative predictive value was 99.8% (95% CI, 99.6%-99.9%). For the detection of malignant pulmonary nodules in all images of the full T0 data set, the sensitivity was 94.1% (95% CI, 86.2%-100.0%), the specificity was 83.3% (95% CI, 82.3%-84.3%), the positive predictive value was 3.4% (95% CI, 2.2%-4.5%), and the negative predictive value was 100.0% (95% CI, 99.9%-100.0%). In digital radiographs of the nodule data set, the AI algorithm had higher sensitivity (96.0% [95% CI, 88.3%-100.0%] vs 88.0% [95% CI, 75.3%-100.0%]; P = .32) and higher specificity (93.2% [95% CI, 89.9%-96.5%] vs 82.8% [95% CI, 77.8%-87.8%]; P = .001) for nodule detection compared with the NLST radiologists. For malignant pulmonary nodule detection on digital radiographs of the full T0 data set, the sensitivity of the AI algorithm was higher (100.0% [95% CI, 100.0%-100.0%] vs 94.1% [95% CI, 82.9%-100.0%]; P = .32) compared with the NLST radiologists, and the specificity (90.9% [95% CI, 89.6%-92.1%] vs 91.0% [95% CI, 89.7%-92.2%]; P = .91), positive predictive value (8.2% [95% CI, 4.4%-11.9%] vs 7.8% [95% CI, 4.1%-11.5%]; P = .65), and negative predictive value (100.0% [95% CI, 100.0%-100.0%] vs 99.9% [95% CI, 99.8%-100.0%]; P = .32) were similar to those of NLST radiologists.

Conclusions and Relevance : In this study, the AI algorithm performed better than NLST radiologists for the detection of pulmonary nodules on digital radiographs. When used as a second reader, the AI algorithm may help to detect lung cancer.

Yoo Hyunsuk, Kim Ki Hwan, Singh Ramandeep, Digumarthy Subba R, Kalra Mannudeep K

2020-Sep-01

In JAMA oncology ; h5-index 85.0

Importance : Machine learning (ML) algorithms can identify patients with cancer at risk of short-term mortality to inform treatment and advance care planning. However, no ML mortality risk prediction algorithm has been prospectively validated in oncology or compared with routinely used prognostic indices.

Objective : To validate an electronic health record-embedded ML algorithm that generated real-time predictions of 180-day mortality risk in a general oncology cohort.

Design, Setting, and Participants : This prognostic study comprised a prospective cohort of patients with outpatient oncology encounters between March 1, 2019, and April 30, 2019. An ML algorithm, trained on retrospective data from a subset of practices, predicted 180-day mortality risk between 4 and 8 days before a patient's encounter. Patient encounters took place in 18 medical or gynecologic oncology practices, including 1 tertiary practice and 17 general oncology practices, within a large US academic health care system. Patients aged 18 years or older with outpatient oncology or hematology and oncology encounters were included in the analysis. Patients were excluded if their appointment was scheduled after weekly predictions were generated and if they were only evaluated in benign hematology, palliative care, or rehabilitation practices.

Exposures : Gradient-boosting ML binary classifier.

Main Outcomes and Measures : The primary outcome was the patients' 180-day mortality from the index encounter. The primary performance metric was the area under the receiver operating characteristic curve (AUC).

Results : Among 24 582 patients, 1022 (4.2%) died within 180 days of their index encounter. Their median (interquartile range) age was 64.6 (53.6-73.2) years, 15 319 (62.3%) were women, 18 015 (76.0%) were White, and 10 658 (43.4%) were seen in the tertiary practice. The AUC was 0.89 (95% CI, 0.88-0.90) for the full cohort. The AUC varied across disease-specific groups within the tertiary practice (AUC ranging from 0.74 to 0.96) but was similar between the tertiary and general oncology practices. At a prespecified 40% mortality risk threshold used to differentiate high- vs low-risk patients, observed 180-day mortality was 45.2% (95% CI, 41.3%-49.1%) in the high-risk group vs 3.1% (95% CI, 2.9%-3.3%) in the low-risk group. Integrating the algorithm into the Eastern Cooperative Oncology Group and Elixhauser comorbidity index-based classifiers resulted in favorable reclassification (net reclassification index, 0.09 [95% CI, 0.04-0.14] and 0.23 [95% CI, 0.20-0.27], respectively).

Conclusions and Relevance : In this prognostic study, an ML algorithm was feasibly integrated into the electronic health record to generate real-time, accurate predictions of short-term mortality for patients with cancer and outperformed routinely used prognostic indices. This algorithm may be used to inform behavioral interventions and prompt earlier conversations about goals of care and end-of-life preferences among patients with cancer.

Manz Christopher R, Chen Jinbo, Liu Manqing, Chivers Corey, Regli Susan Harkness, Braun Jennifer, Draugelis Michael, Hanson C William, Shulman Lawrence N, Schuchter Lynn M, O’Connor Nina, Bekelman Justin E, Patel Mitesh S, Parikh Ravi B

2020-Sep-24

In Operative neurosurgery (Hagerstown, Md.)

BACKGROUND : Virtual reality spine simulators are emerging as potential educational tools to assess and train surgical procedures in safe environments. Analysis of validity is important in determining the educational utility of these systems.

OBJECTIVE : To assess face, content, and construct validity of a C4-C5 anterior cervical discectomy and fusion simulation on the Sim-Ortho virtual reality platform, developed by OSSimTechTM (Montreal, Canada) and the AO Foundation (Davos, Switzerland).

METHODS : Spine surgeons, spine fellows, along with neurosurgical and orthopedic residents, performed a simulated C4-C5 anterior cervical discectomy and fusion on the Sim-Ortho system. Participants were separated into 3 categories: post-residents (spine surgeons and spine fellows), senior residents, and junior residents. A Likert scale was used to assess face and content validity. Construct validity was evaluated by investigating differences between the 3 groups on metrics derived from simulator data. The Kruskal-Wallis test was employed to compare groups and a post-hoc Dunn's test with a Bonferroni correction was utilized to investigate differences between groups on significant metrics.

RESULTS : A total of 21 individuals were included: 9 post-residents, 5 senior residents, and 7 junior residents. The post-resident group rated face and content validity, median ≥4, for the overall procedure and at least 1 tool in each of the 4 steps. Significant differences (P < .05) were found between the post-resident group and senior and/or junior residents on at least 1 metric for each component of the simulation.

CONCLUSION : The C4-C5 anterior cervical discectomy and fusion simulation on the Sim-Ortho platform demonstrated face, content, and construct validity suggesting its utility as a formative educational tool.

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

2020-Sep-24

Anterior cervical discectomy and fusion, Neurosurgical simulation, Surgical education, Surgical simulation, Validation, Virtual reality

In Journal of thoracic imaging

PURPOSE : To evaluate the performance of a deep learning (DL) algorithm for the detection of COVID-19 on chest radiographs (CXR).

MATERIALS AND METHODS : In this retrospective study, a DL model was trained on 112,120 CXR images with 14 labeled classifiers (ChestX-ray14) and fine-tuned using initial CXR on hospital admission of 509 patients, who had undergone COVID-19 reverse transcriptase-polymerase chain reaction (RT-PCR). The test set consisted of a CXR on presentation of 248 individuals suspected of COVID-19 pneumonia between February 16 and March 3, 2020 from 4 centers (72 RT-PCR positives and 176 RT-PCR negatives). The CXR were independently reviewed by 3 radiologists and using the DL algorithm. Diagnostic performance was compared with radiologists' performance and was assessed by area under the receiver operating characteristics (AUC).

RESULTS : The median age of the subjects in the test set was 61 (interquartile range: 39 to 79) years (51% male). The DL algorithm achieved an AUC of 0.81, sensitivity of 0.85, and specificity of 0.72 in detecting COVID-19 using RT-PCR as the reference standard. On subgroup analyses, the model achieved an AUC of 0.79, sensitivity of 0.80, and specificity of 0.74 in detecting COVID-19 in patients presented with fever or respiratory systems and an AUC of 0.87, sensitivity of 0.85, and specificity of 0.81 in distinguishing COVID-19 from other forms of pneumonia. The algorithm significantly outperforms human readers (P<0.001 using DeLong test) with higher sensitivity (P=0.01 using McNemar test).

CONCLUSIONS : A DL algorithm (COV19NET) for the detection of COVID-19 on chest radiographs can potentially be an effective tool in triaging patients, particularly in resource-stretched health-care systems.

Chiu Wan Hang Keith, Vardhanabhuti Varut, Poplavskiy Dmytro, Yu Philip Leung Ho, Du Richard, Yap Alistair Yun Hee, Zhang Sailong, Fong Ambrose Ho-Tung, Chin Thomas Wing-Yan, Lee Jonan Chun Yin, Leung Siu Ting, Lo Christine Shing Yen, Lui Macy Mei-Sze, Fang Benjamin Xin Hao, Ng Ming-Yen, Kuo Michael D

2020-Sep-22

In Health informatics journal ; h5-index 25.0

Uddin Md Ashraf, Stranieri Andrew, Gondal Iqbal, Balasubramanian Venki

2020-Sep-24

Big Health data, Blockchain, classifier, deep learning, digital health record storage, electronic health record, machine learning, quality of performance, security and privacy, stream data

In Biomarkers in medicine

Wang Yao, Wang Yan, Guo Chunjie, Xie Xuping, Liang Sen, Zhang Ruochi, Pang Wei, Huang Lan

2020-Aug

cancer genotypes, deep learning, imaging phenotype, prediction and associations analysis, radiogenomics, radiomics

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

Misawa Masashi, Kudo Shin-Ei, Mori Yuichi, Maeda Yasuharu, Ogawa Yushi, Ichimasa Katsuro, Kudo Toyoki, Wakamura Kunihiko, Hayashi Takemasa, Miyachi Hideyuki, Baba Toshiyuki, Ishida Fumio, Itoh Hayato, Oda Masahiro, Mori Kensaku

2020-Sep-23

In Medical physics ; h5-index 59.0

PURPOSE : Optic pathway gliomas (OPG) are low-grade pilocytic astrocytomas accounting for 3-5% of pediatric intracranial tumors. Accurate and quantitative follow-up of OPG using MRI is crucial for therapeutic decision-making, yet is challenging due to the complex shape and heterogeneous tissue pattern which characterizes these tumors. The aim of this study was to implement automatic methods for segmentation and classification of OPG and its components, based on MRI.

METHODS : A total of 202 MRI scans from 29 patients with chiasmatic OPG scanned longitudinally were retrospectively collected and included in this study. Data included T₂ and post-contrast T₁ weighted images. The entire tumor volume and its components were manually annotated by a senior neuro-radiologist, and inter- and intra-rater variability of the entire tumor volume was assessed in a subset of scans. Automatic tumor segmentation was performed using deep-learning method with U-Net+ResNet architecture. A 5-fold cross-validation scheme was used to evaluate the automatic results relative to manual segmentation. Voxel based classification of the tumor into enhanced, non-enhanced and cystic components was performed using fuzzy c-means clustering.

RESULTS : The results of the automatic tumor segmentation were: mean dice score=0.736±0.025, precision=0.918±0.014, and recall=0.635±0.039 for the validation data, and dice score =0.761±0.011, precision=0.794±0.028, and recall=0.742±0.012 for the test data. The accuracy of the voxel based classification of tumor components was 0.94, with precision=0.89, 0.97, 0.85 and recall= 1.00, 0.79, 0.94 for the non-enhanced, enhanced and cystic components, respectively.

CONCLUSION : This study presents methods for automatic segmentation of chiasmatic OPG tumors and classification into the different components of the tumor, based on conventional MRI. Automatic quantitative longitudinal assessment of these tumors may improve radiological monitoring, facilitate early detection of disease progression and optimize therapy management.

Artzi Moran, Gershov Sapir, Ben-Sira Liat, Roth Jonathan, Kozyrev Danil, Shofty Ben, Gazit Tomer, Halag-Milo Tali, Constantini Shlomi, Ben Bashat Dafna

2020-Sep-23

Deep learning, Fuzzy c-means clustering, Optic pathway gliomas, Segmentation

In Cancers

Mohammadi Elyas, Benfeitas Rui, Turkez Hasan, Boren Jan, Nielsen Jens, Uhlen Mathias, Mardinoglu Adil

2020-Sep-21

drug repositioning, genomic screens, machine learning, systems medicine, systems pharmacology

In Experimental and therapeutic medicine

Trivizakis Eleftherios, Tsiknakis Nikos, Vassalou Evangelia E, Papadakis Georgios Z, Spandidos Demetrios A, Sarigiannis Dimosthenis, Tsatsakis Aristidis, Papanikolaou Nikolaos, Karantanas Apostolos H, Marias Kostas

2020-Nov

COVID-19, artificial intelligence, deep learning analysis, multi-institutional data

ArXiv Preprint

Weijian Li, Wei Zhu, E. Ray Dorsey, Jiebo Luo

2020-09-25

In Applied clinical informatics ; h5-index 22.0

BACKGROUND :  Care-management tools are typically utilized for chronic disease management. Sonoma County government agencies employed advanced health information technologies, artificial intelligence (AI), and interagency process improvements to help transform health and health care for socially disadvantaged groups and other displaced individuals.

OBJECTIVES :  The objective of this case report is to describe how an integrated data hub and care-management solution streamlined care coordination of government services during a time of community-wide crisis.

METHODS :  This innovative application of care-management tools created a bridge between social and clinical determinants of health and used a three-step approach-access, collaboration, and innovation. The program Accessing Coordinated Care to Empower Self Sufficiency Sonoma was established to identify and match the most vulnerable residents with services to improve their well-being. Sonoma County created an Interdepartmental Multidisciplinary Team to deploy coordinated cross-departmental services (e.g., health and human services, housing services, probation) to support individuals experiencing housing insecurity. Implementation of a data integration hub (DIH) and care management and coordination system (CMCS) enabled integration of siloed data and services into a unified view of citizen status, identification of clinical and social determinants of health from structured and unstructured sources, and algorithms to match clients across systems.

RESULTS :  The integrated toolset helped 77 at-risk individuals in crisis through coordinated care plans and access to services in a time of need. Two case examples illustrate the specific care and services provided individuals with complex needs after the 2017 Sonoma County wildfires.

CONCLUSION :  Unique application of a care-management solution transformed health and health care for individuals fleeing from their homes and socially disadvantaged groups displaced by the Sonoma County wildfires. Future directions include expanding the DIH and CMCS to neighboring counties to coordinate care regionally. Such solutions might enable innovative care-management solutions across a variety of public, private, and nonprofit services.

Snowdon Jane L, Robinson Barbie, Staats Carolyn, Wolsey Kenneth, Sands-Lincoln Megan, Strasheim Thomas, Brotman David, Keating Katie, Schnitter Elizabeth, Jackson Gretchen, Kassler William

2020-Aug

In Journal of gastrointestinal surgery : official journal of the Society for Surgery of the Alimentary Tract

BACKGROUND AND AIMS : Improving the rate of polyp detection is an important measure to prevent colorectal cancer (CRC). Real-time automatic polyp detection systems, through deep learning methods, can learn and perform specific endoscopic tasks previously performed by endoscopists. The purpose of this study was to explore whether a high-performance, real-time automatic polyp detection system could improve the polyp detection rate (PDR) in the actual clinical environment.

METHODS : The selected patients underwent same-day, back-to-back colonoscopies in a random order, with either traditional colonoscopy or artificial intelligence (AI)-assisted colonoscopy performed first by different experienced endoscopists (> 3000 colonoscopies). The primary outcome was the PDR. It was registered with clinicaltrials.gov . (NCT047126265).

RESULTS : In this study, we randomized 150 patients. The AI system significantly increased the PDR (34.0% vs 38.7%, p < 0.001). In addition, AI-assisted colonoscopy increased the detection of polyps smaller than 6 mm (69 vs 91, p < 0.001), but no difference was found with regard to larger lesions.

CONCLUSIONS : A real-time automatic polyp detection system can increase the PDR, primarily for diminutive polyps. However, a larger sample size is still needed in the follow-up study to further verify this conclusion.

TRIAL REGISTRATION : clinicaltrials.gov Identifier: NCT047126265.

Luo Yuchen, Zhang Yi, Liu Ming, Lai Yihong, Liu Panpan, Wang Zhen, Xing Tongyin, Huang Ying, Li Yue, Li Aiming, Wang Yadong, Luo Xiaobei, Liu Side, Han Zelong

2020-Sep-23

Artificial intelligence, Colonoscopy, Computer-aided diagnose

In Journal of cancer research and clinical oncology

PURPOSE : Ewing sarcoma (ES) is one of the most common malignant bone tumors in children and adolescents. The immune microenvironment plays an important role in the development of ES. Here, we developed an optimal signature for determining ES patient prognosis based on immune-related genes (IRGs).

METHODS : We analyzed the ES gene expression profile dataset, GSE17679, from the GEO database and extracted differential expressed IRGs (DEIRGs). Then, we conducted functional correlation and protein-protein interaction (PPI) analyses of the DEIRGs and used the machine learning algorithm-iterative Lasso Cox regression analysis to build an optimal DEIRG signature. In addition, we applied ES samples from the ICGC database to test the optimal gene signature. We performed univariate and multivariate Cox regressions on clinicopathological characteristics and optimal gene signature to evaluate whether signature is an important prognostic factor. Finally, we calculated the infiltration of 24 immune cells in ES using the ssGSEA algorithm, and analyzed the correlation between the DEIRGs in the optimal gene signature and immune cells.

RESULTS : A total of 249 DEIRGs were screened and an 11-gene signature with the strongest correlation with patient prognoses was analyzed using a machine learning algorithm. The 11-gene signature also had a high prognostic value in the ES external verification set. Univariate and multivariate Cox regression analyses showed that 11-gene signature is an independent prognostic factor. We found that macrophages and cytotoxic, CD8 T, NK, mast, B, NK CD56bright, TEM, TCM, and Th2 cells were significantly related to patient prognoses; the infiltration of cytotoxic and CD8 T cells in ES was significantly different. By correlating prognostic biomarkers with immune cell infiltration, we found that FABP4 and macrophages, and NDRG1 and Th2 cells had the strongest correlation.

CONCLUSION : Overall, the IRG-related 11-gene signature can be used as a reliable ES prognostic biomarker and can provide guidance for personalized ES therapy.

Ren En-Hui, Deng Ya-Jun, Yuan Wen-Hua, Wu Zuo-Long, Zhang Guang-Zhi, Xie Qi-Qi

2020-Sep-23

Ewing sarcoma, Immune cell infiltration, Iterative Lasso regression, Machine learning, Prognosis analysis

In Journal of the American Medical Informatics Association : JAMIA

OBJECTIVE : Machine learning models trained on electronic health records have achieved high prognostic accuracy in test datasets, but little is known about their embedding into clinical workflows. We implemented a random forest-based algorithm to identify hospitalized patients at high risk for delirium, and evaluated its performance in a clinical setting.

MATERIALS AND METHODS : Delirium was predicted at admission and recalculated on the evening of admission. The defined prediction outcome was a delirium coded for the recent hospital stay. During 7 months of prospective evaluation, 5530 predictions were analyzed. In addition, 119 predictions for internal medicine patients were compared with ratings of clinical experts in a blinded and nonblinded setting.

RESULTS : During clinical application, the algorithm achieved a sensitivity of 74.1% and a specificity of 82.2%. Discrimination on prospective data (area under the receiver-operating characteristic curve = 0.86) was as good as in the test dataset, but calibration was poor. The predictions correlated strongly with delirium risk perceived by experts in the blinded (r = 0.81) and nonblinded (r = 0.62) settings. A major advantage of our setting was the timely prediction without additional data entry.

DISCUSSION : The implemented machine learning algorithm achieved a stable performance predicting delirium in high agreement with expert ratings, but improvement of calibration is needed. Future research should evaluate the acceptance of implemented machine learning algorithms by health professionals.

CONCLUSIONS : Our study provides new insights into the implementation process of a machine learning algorithm into a clinical workflow and demonstrates its predictive power for delirium.

Jauk Stefanie, Kramer Diether, Großauer Birgit, Rienmüller Susanne, Avian Alexander, Berghold Andrea, Leodolter Werner, Schulz Stefan

2020-Sep-24

Machine learning, clinical decision support, delirium, electronic health records, prospective studies

In Journal of the American Medical Informatics Association : JAMIA

OBJECTIVE : The 2019 National Natural language processing (NLP) Clinical Challenges (n2c2)/Open Health NLP (OHNLP) shared task track 3, focused on medical concept normalization (MCN) in clinical records. This track aimed to assess the state of the art in identifying and matching salient medical concepts to a controlled vocabulary. In this paper, we describe the task, describe the data set used, compare the participating systems, present results, identify the strengths and limitations of the current state of the art, and identify directions for future research.

MATERIALS AND METHODS : Participating teams were provided with narrative discharge summaries in which text spans corresponding to medical concepts were identified. This paper refers to these text spans as mentions. Teams were tasked with normalizing these mentions to concepts, represented by concept unique identifiers, within the Unified Medical Language System. Submitted systems represented 4 broad categories of approaches: cascading dictionary matching, cosine distance, deep learning, and retrieve-and-rank systems. Disambiguation modules were common across all approaches.

RESULTS : A total of 33 teams participated in the MCN task. The best-performing team achieved an accuracy of 0.8526. The median and mean performances among all teams were 0.7733 and 0.7426, respectively.

CONCLUSIONS : Overall performance among the top 10 teams was high. However, several mention types were challenging for all teams. These included mentions requiring disambiguation of misspelled words, acronyms, abbreviations, and mentions with more than 1 possible semantic type. Also challenging were complex mentions of long, multi-word terms that may require new ways of extracting and representing mention meaning, the use of domain knowledge, parse trees, or hand-crafted rules.

Henry Sam, Wang Yanshan, Shen Feichen, Uzuner Ozlem

2020-Sep-24

clinical narratives, concept normalization, machine learning, natural language processing

In SIAM journal on mathematics of data science

Li Yuan, Mark Benjamin, Raskutti Garvesh, Willett Rebecca, Song Hyebin, Neiman David

2020

In Nature machine intelligence

Wang Sheng, Flynn Emily R, Altman Russ B

2020-Jul

In Journal of medical imaging (Bellingham, Wash.)

Xu Yangdi, Lee Lok Hin, Drukker Lior, Yaqub Mohammad, Papageorghiou Aris T, Noble Alison J

2020-Sep

cycle-consistent adversarial network, quantitative evaluation, realistic simulation, second-trimester scan, third-trimester scan, transventricular plane

In Cardiovascular diagnosis and therapy

Song Jae W, Wasserman Bruce A

2020-Aug

Black blood MR imaging, intracranial atherosclerosis, ischemic stroke, vessel wall MR imaging (VW-MR imaging)

In Cardiovascular diagnosis and therapy

Background : Statistically derived cardiovascular risk calculators (CVRC) that use conventional risk factors, generally underestimate or overestimate the risk of cardiovascular disease (CVD) or stroke events primarily due to lack of integration of plaque burden. This study investigates the role of machine learning (ML)-based CVD/stroke risk calculators (CVRC_ML) and compares against statistically derived CVRC (CVRC_Stat) based on (I) conventional factors or (II) combined conventional with plaque burden (integrated factors).

Methods : The proposed study is divided into 3 parts: (I) statistical calculator: initially, the 10-year CVD/stroke risk was computed using 13 types of CVRC_Stat (without and with plaque burden) and binary risk stratification of the patients was performed using the predefined thresholds and risk classes; (II) ML calculator: using the same risk factors (without and with plaque burden), as adopted in 13 different CVRC_Stat, the patients were again risk-stratified using CVRC_ML based on support vector machine (SVM) and finally; (III) both types of calculators were evaluated using AUC based on ROC analysis, which was computed using combination of predicted class and endpoint equivalent to CVD/stroke events.

Results : An Institutional Review Board approved 202 patients (156 males and 46 females) of Japanese ethnicity were recruited for this study with a mean age of 69±11 years. The AUC for 13 different types of CVRC_Stat calculators were: AECRS2.0 (AUC 0.83, P<0.001), QRISK3 (AUC 0.72, P<0.001), WHO (AUC 0.70, P<0.001), ASCVD (AUC 0.67, P<0.001), FRS_cardio (AUC 0.67, P<0.01), FRS_stroke (AUC 0.64, P<0.001), MSRC (AUC 0.63, P=0.03), UKPDS56 (AUC 0.63, P<0.001), NIPPON (AUC 0.63, P<0.001), PROCAM (AUC 0.59, P<0.001), RRS (AUC 0.57, P<0.001), UKPDS60 (AUC 0.53, P<0.001), and SCORE (AUC 0.45, P<0.001), while the AUC for the CVRC_ML with integrated risk factors (AUC 0.88, P<0.001), a 42% increase in performance. The overall risk-stratification accuracy for the CVRC_ML with integrated risk factors was 92.52% which was higher compared all the other CVRC_Stat.

Conclusions : ML-based CVD/stroke risk calculator provided a higher predictive ability of 10-year CVD/stroke compared to the 13 different types of statistically derived risk calculators including integrated model AECRS 2.0.

Jamthikar Ankush, Gupta Deep, Saba Luca, Khanna Narendra N, Araki Tadashi, Viskovic Klaudija, Mavrogeni Sophie, Laird John R, Pareek Gyan, Miner Martin, Sfikakis Petros P, Protogerou Athanasios, Viswanathan Vijay, Sharma Aditya, Nicolaides Andrew, Kitas George D, Suri Jasjit S