Predictive Modeling for Self-Tracking Apps: A Case Study in Menstrual Health
Noemie Elhadad
September 8, 2021, Wednesday, 3:00 PM - 4:00 PM EDT
Mobile health apps provide a rich source of self-tracked health observations that hold the promise to characterize underlying physiological state and disease trajectories, as well as to support users in self-managing their health. But these data streams are also notoriously unreliable since they hinge on user adherence to the app. In this talk, I will focus on menstrual trackers, a highly popular type of self-tracking technology, and will present our ongoing work on characterizing variability in menstrual cycle within and across individuals and building models that predict next cycle date all the while accounting for skipped tracking data.
Dr. Noemie Elhadad is an Associate Professor of Biomedical Informatics, affiliated with Computer Science and the Data Science Institute at Columbia University. She obtained her PhD in 2006 in Computer Science, focusing on multi-document, patient-specific text summarization of the clinical literature. She was on the Computer Science faculty at The City College of New York and the CUNY graduate center starting in 2006 before joining the Department of Biomedical Informatics at Columbia in 2007. Dr. Elhadad was Chair of the Health Analytics Center at the Columbia Data Science Institute from 2013 to 2016. She is the Graduate Program Director at DBMI. Dr. Elhadad's research interests are at the intersection of machine learning, natural language processing, and medicine. She investigates ways in which observational clinical data (e.g., electronic health records) and patient-generated data (e.g., online health community discussions, mobile health data) can enhance access to relevant information for clinicians, patients, and health researchers alike and can ultimately impact healthcare and health of patients.