5/13/21 | 4:15pm | Online only

Susan Murphy

Professor
Harvard

Abstract: In digital health there is much interest in using reinforcement learning (RL) to personalize sequences of intervention decisions to each user. These sequential decision making problems involve decisions concerning whether to deliver an intervention and if so what kind of intervention to deliver given the user's current context (location, recent responsivity to treatments, mood,...). To decide whether the RL algorithm should be one of multiple intervention components that might be included in an "optimized" digital intervention, we need to assess if the algorithm is indeed personalizing the decisions to the users. In this talk we discuss some of our first efforts in this direction with HeartSteps, a digital intervention designed to improve physical activity by users with hypertension.

Bio: Susan Murphy is Professor of Statistics at Harvard University, Radcliffe Alumnae Professor at the Radcliffe Institute, Harvard University, and Professor of Computer Science at the Harvard John A. Paulson School of Engineering and Applied Sciences. Her lab works on clinical trial designs and online learning algorithms for developing personalized digital health interventions. She developed the micro-randomized trial for use in constructing mobile health interventions; this trial design is in use across a broad range of health related areas. She is a 2013 MacArthur Fellow, a member of the National Academy of Sciences and the National Academy of Medicine, both of the US National Academies.