Data-Powered Patient: Predicting Women's Flares Using Wearables w/ Ipek Ensari- nyhackr Dec Meetup

Visit https://www.nyhackr.org to learn more and follow https://x.com/nyhackr Talk Title- The Data-Powered Patient: Predicting Women's Chronic Disease Flares from Wearables Talk Description- Heart rate variability (HRV) is a well-known digital biomarker and is increasingly available in consumer wearables. However, extracting actionable predictions from HRV data, in particular for clinical use, remains challenging. Using specialized R packages, this presentation demonstrates how to model 24-hour periodic patterns in HRV metrics as non-linear circadian components to predict chronic disease flares. Grounded in real-life data from a NIH-funded longitudinal mHealth-based study of female chronic pelvic pain disorders, we will investigate how mixed-effects cosinor regression accommodates individual variation and complex interactions between circadian parameters and time-varying covariates (menstrual cycle, physical activity, sleep quality). These examples aim to illustrate how patient-generated data from everyday wearables can democratize access to predictive medicine by helping patient-users maximize the benefits of their data to gain predictive insights into their health status. Bio- Ipek Ensari is an Assistant Professor in the Windreich Department of Artificial Intelligence (AI) and Human Health at the Icahn School of Medicine at Mount Sinai, where she leads research at the intersection of digital health, AI, and women’s health. Her research focuses on digital phenotyping, disease forecasting, and AI-based just-in-time adaptive interventions for individuals with historically understudied female reproductive conditions such as endometriosis, fibroids, and menopausal transition. Dr. Ensari currently serves as the principal investigator of a NIH-funded project that investigates novel statistical models for developing and evaluating digital patient reported outcome measures for clinical benchmarking. By integrating novel mHealth data with more traditional data sources from electronic health records and biological markers, her research program aims to enable personalized disease and health forecasting that is actionable and interpretable.