Learning While Treating: Challenges in Deploying Learning Algorithms for Real-Time Health Optimization

Thursday, April 3, 2025 – 1:00 pm CT

About the Webinar:

In the treatment of individuals with chronic health conditions, a critical task is the design of sequential treatments to determine when and in which context to deliver treatments. We operationalize this task through the construction of decision rules that take as input the individual's current context and output a recommended treatment. Prior data may be available on a similar population that could be used to inform the construction of initial decision rules. There is increasing interest in personalization of these rules in real time as individuals experience the sequences of treatment. Here we discuss our work on designing and deploying online learning algorithms for use in personalizing mobile health interventions. We will put this work in the general context of continual optimization, discussing post-study inferential methods to inform future studies.

About the Presenter:

Walter Dempsey is an Assistant Professor of Biostatistics and Assistant Research Professor at the Institute for Social Research. His research focuses on statistical methods for digital and mobile health. His current work involves three complementary research themes: (1) experimental design and data analytic methods to inform multi-stage decision making in health; (2) statistical modeling of complex longitudinal and survival data; and (3) statistical modeling of complex relational structures such as interaction networks. In the coming years, he will continue to design and apply novel statistical methodologies to make sense of complex longitudinal, survival, and relational datasets. This work will inform decision making in health by aiding in intervention evaluation and development. Prior to joining, he was a postdoctoral fellow in the Department of Statistics at Harvard University where he worked within the Statistical Reinforcement Learning Lab under the supervision of Susan Murphy. He received his PhD in Statistics at the University of Chicago under the supervision of Peter McCullagh. More about Walter Dempsey.