סמינר שמיעה לתלמידי תואר שני ושלישי
Enhancing Case-Control Matching in Clinical Trials: A Wearable Data Framework for Improved Outcome Precision in Vaccine Studies
Recruiting participants for clinical trials is a resource-intensive process, where the quality of case-control matching directly influences the reliability and validity of trial outcomes. We developed a methodological framework to enhance case-control matching by analyzing continuous physiological data from wearable devices, such as smartwatches, with the goal of improving effect size estimation in clinical trials. Our approach incorporates a novel convolution-based method for imputing missing data in time series, combined with advanced matching algorithms to pair cases and controls based on physiological similarities. Simulation-based analyses were conducted to evaluate the potential improvements in outcome precision and reliability. We validated our framework using data from 5,000 individuals infected with COVID-19, applying it specifically to COVID-19 vaccination studies. Results suggest that in scenarios with low outcome risk and low vaccine efficacy, our approach may help reduce the required sample size while maintaining similar outcomes to those observed in larger trials. This framework represents a promising step forward in optimizing participant recruitment and enhancing outcome reliability in clinical research, particularly in vaccination studies.
Bio:
Edan Shahmoon, M.Sc. student at the department of Industrial Engineering in Tel Aviv University, specializing in Data Science. Edan holds a B.SC. Degree in Industrial Engineering from Tel Aviv University. His professional background includes roles as a Research Assistant at Berglas School of Economics, a DevOps engineer at Hewlett Packard Enterprise (HPE) and as a Data Scientist in the field of predictive maintenance.
