Research / Labs

Ipek Ensari Lab

Our lab conducts studies on mobile health (mHealth) technologies and machine learning methods for complex patient-generated data toward improving chronic disease characterization and patient self-management. Our research is grounded in women’s reproductive health conditions (e.g., endometriosis, chronic pelvic pain disorders; CPPDs) and populations at increased risk for health disparities (e.g., sexual and gender minorities; SGM). To this end, we investigate: 1) Integration of mobile self-tracking and wearable data to augment electronic health records (EHRs) for improving clinical decision making and patient self-management, 2) Use of direct patient input for elucidating conditions that are poorly understood and not well documented in electronic health records, and 3) development of patient-centered mHealth measures and intervention tools that combine multifarious data streams.

Our lab conducts studies on mobile health (mHealth) technologies and machine learning methods for complex patient-generated data toward improving chronic disease characterization and patient self-management. Our research is grounded in women’s reproductive health conditions (e.g., endometriosis, chronic pelvic pain disorders; CPPDs) and populations at increased risk for health disparities (e.g., sexual and gender minorities; SGM). To this end, we investigate: 1) Integration of mobile self-tracking and wearable data to augment electronic health records (EHRs) for improving clinical decision making and patient self-management, 2) Use of direct patient input for elucidating conditions that are poorly understood and not well documented in electronic health records, and 3) development of patient-centered mHealth measures and intervention tools that combine multifarious data streams.

Our team is currently focusing on three exciting research projects that aim to improve the way we approach measurement of chronic symptoms and disease management in women's health: 

  1. We are using functional data methods and distributed lag models on patient-generated health data to create and evaluate patient-reported outcome measures for chronic symptoms such as pain and quality of life in a mobile health (mHealth) setting.  

  2. Leveraging data from electronic health records (EHRs) and self-tracked mobile data from mHealth apps, we are identifying phenotypes and endotypes within women's reproductive disorders and other heterogeneous diseases.   

  3. We are designing and evaluating reinforcement learning based mHealth-delivered behavioral recommender systems for chronic symptom self-management  

Team

Eugenia Alleva