Search

This work develops a robust classifier for a COVID-19 pre-screening model from crowdsourced cough sound data. The crowdsourced cough recordings contain a variable number of coughs, with some input sound files more informative than the others. Accurate detection of COVID-19 from the sound datasets requires overcoming two main challenges (i) the variable number of coughs in each recording and (ii) the low number of COVID-positive cases compared to healthy coughs in the data. We use two open datasets of crowdsourced cough recordings and segment each cough recording into non-overlapping coughs. The segmentation enriches the original data without oversampling by splitting the original cough sound files into non-overlapping segments. Splitting the sound files enables us to increase the samples of the minority class (COVID-19) without changing the feature distribution of the COVID-19 samples resulted from applying oversampling techniques. Each cough sound segment is transformed into six image representations for further analyses. We conduct extensive experiments with shallow machine learning, Convolutional Neural Network (CNN), and pre-trained CNN models. The results of our models were compared to other recently published papers that apply machine learning to cough sound data for COVID-19 detection. Our method demonstrated a high performance using an ensemble model on the testing dataset with area under receiver operating characteristics curve = 0.77, precision = 0.80, recall = 0.71, F1 measure = 0.75, and Kappa = 0.53. The results show an improvement in the prediction accuracy of our COVID-19 pre-screening model compared to the other models. [ABSTRACT FROM AUTHOR]

Improvement of traffic signal control (TSC) efficiency has been found to lead to improved urban transportation and enhanced quality of life. Recently, the use of reinforcement learning (RL) in various areas of TSC has gained significant traction; thus, we conducted a systematic literature review as a systematic, comprehensive, and reproducible review to dissect all the existing research that applied RL in the network-level TSC domain, called as RL in NTSC or RL-NTSC for brevity. The review only targeted the network-level articles that tested the proposed methods in networks with two or more intersections. This review covers 160 peer-reviewed articles from 30 countries published from 1994 to March 2020. The goal of this study is to provide the research community with statistical and conceptual knowledge, summarize existence evidence, characterize RL applications in NTSC domains, explore all applied methods and major first events in the defined scope, and identify areas for further research based on the explored research problems in current research. We analyzed the extracted data from the included articles in the following seven categories: (i) publication and authors' data, (ii) method identification and analysis, (iii) environment attributes and traffic simulation, (iv) application domains of RL-NTSC, (v) major first events of RL-NTSC and authors' key statements, (vi) code availability, and (vii) evaluation. This paper provides a comprehensive view of the past 26 years of research on applying RL to NTSC. It also reveals the role of advancing deep learning methods in the revival of the research area, the rise of using non-commercial microscopic traffic simulators, a lack of interaction between traffic and transportation engineering practitioners and researchers, and a lack of proposal and creation of testbeds which can likely bring different communities together around common goals. • A review on Reinforcement Learning in the network-scale Traffic Signal Control area. • Presents a comprehensive systematic literature review of 160 included articles. • Consolidates and characterizes the existing research on the defined area. • Explores the methods, applications, domains, and first events in the defined scope. • Identifies past and present trends and directions for further research in the area. [ABSTRACT FROM AUTHOR]

Multiplex electrochemical biosensors have been used for eliminating the matrix effect in complex bodily fluids or enabling the detection of two or more bioanalytes, overall resulting in more sensitive assays and accurate diagnostics. Many electrochemical biosensors lack reliable and low-cost multiplexing to meet the requirements of point-of-care detection due to either limited functional biosensors for multi-electrode detection or incompatible readout systems. We developed a new dual electrochemical biosensing unit accompanied by a customized potentiostat to address the unmet need for point-of-care multi-electrode electrochemical biosensing. The two-working electrode system was developed using screen-printing of a carboxyl-rich nanomaterial containing ink, with both working electrodes offering active sites for recognition of bioanalytes. The low-cost bi-potentiostat system (∼$80) was developed and customized specifically to the bi-electrode design and used for rapid, repeatable, and accurate measurement of electrochemical impedance spectroscopy signals from the dual biosensor. This binary electrochemical data acquisition (Bi-ECDAQ) system accurately and selectively detected SARS-CoV-2 Nucleocapsid protein (N-protein) in both spiked samples and clinical nasopharyngeal swab samples of COVID-19 patients within 30 min. The two working electrodes offered the limit of detection of 116 fg/mL and 150 fg/mL, respectively, with the dynamic detection range of 1–10,000 pg/mL and the sensitivity range of 2744–2936 Ω mL/pg.mm2 for the detection of N-protein. The potentiostat performed comparable or better than commercial Autolab potentiostats while it is significantly lower cost. The open-source Bi-ECDAQ presents a customizable and flexible approach towards addressing the need for rapid and accurate point-of-care electrochemical biosensors for the rapid detection of various diseases. [Display omitted] • Introduced a dual-biosensor offering the potential of electrochemical multiplexing. • Developed a custom-made readout platform, comparable to commercial potentiostats. • Rapid and accurate impedimetry signal acquisition from the two working electrode immunosensor. • Independent performance of each working electrode in the detection of COVID-19 biomarker. • Validated for recognizing U.K variant (B.1.1.7) of COVID-19 clinical nasopharyngeal sample. [ABSTRACT FROM AUTHOR]

Objective: The purpose of this study is to summarize the results from 3 experimental studies into the use of artificial intelligence to classify and segment colour fundus images with choroidal nevi., Study Design: This study is based on a secondary analysis of colour fundus images taken of patients receiving usual clinical care from the Alberta Ocular Brachytherapy Program., Methods: High-resolution colour fundus images were labeled by experienced ocular oncologists. In experimental study 1, four pre-trained models (ResNet 50, VGG-19, VGG-16, and AlexNet) were evaluated for their ability to classify images based on the presence of choroidal nevi. In experimental study 2, the performance of 3 patch-based models to classify images based on the presence of choroidal nevi were compared. In experimental study 3, four convolutional neural network models were developed to segment the images. In experimental studies 1 and 2, performance was measured using accuracy, precision, recall, F1 score, and AUC. In experimental study 3, IoU and Dice measures were used to evaluate performance., Results: A total of 591 labelled colour fundus images were used for analysis. In experimental study 1, VGG-16 showed the best accuracy, AUC, and recall, but lower precision in classifying images. In experimental study 2, the patched approached enhanced with artifact and contrast outperformed the others in classifying images. In experimental study 3, a voting-based Ensemble model excelled in segmenting the part of images with nevi., Conclusions: It is feasible to train AI models to identify choroidal nevi in colour fundus images., (Copyright © 2024 Canadian Ophthalmological Society. Published by Elsevier Inc. All rights reserved.)

The increasing availability of electronic health records and administrative data and the adoption of computer-based technologies in healthcare have significantly focused on medical informatics. Sepsis is a time-critical condition with high mortality, yet it is often not identified in a timely fashion. The early detection and diagnosis of sepsis can increase the likelihood of survival and improve long-term outcomes for patients. In this paper, we use SHapley Additive exPlanations (SHAP) analysis to explore the variables most highly associated with developing sepsis in patients and evaluating different supervised learning models for classification. To develop our predictive models, we used the data collected after the first and the fifth hour of admission and evaluated the contribution of different features to the prediction results for both time intervals. The results of our study show that, while there is a high level of missing data during the early stages of admission, this data can be effectively utilized for the early prediction of sepsis. We also found a high level of inconsistency between the contributing features at different stages of admission, which should be considered when developing machine learning models.