Susan Murphy, Professor of Statistics
Harvard University

Abstract:
There are a variety of formidable challenges to reinforcement learning and control for use in designing digital health interventions for individuals with chronic disorders. Challenges include settings in which most treatments delivered by a smart device have immediate nonnegative (hopefully positive) effects but the largest longer term effects tend to be negative due to user burden. Furthermore the resulting data must be amenable to conducting a variety of statistical analyses, including causal inference as well as for use in monitoring analyses. Other challenges include an immature domain science concerning the system dynamics yet the need to incorporate some domain science due to low signal to noise ratio as well as non-stationary and sparse data. Here we describe how we confront these challenges including our use of low variance proxies for the delay effects to the reward (e.g. immediate response) in an online “bandit” learning algorithm for use in personalizing mobile health interventions.

Bio:
Dr. Susan A. Murphy is a Radcliffe Alumnae Professor at the Radcliffe Institute and a professor of statistics and computer science at the Harvard John A. Paulson School of Engineering and Applied Sciences. A 2013 recipient of a MacArthur Fellowship, she was previously the H. E. Robbins Distinguished University Professor of Statistics, a research professor at the Institute for Social Research, and a professor of psychiatry, all at the University of Michigan.

Dr. Murphy earned her BS from Louisiana State University and her PhD from the University of North Carolina at Chapel Hill. Her research focuses on analytic methods to design and evaluate medical treatments that adapt to individuals, including some that use mobile devices to deliver tailored interventions for drug addicts, smokers, and heart disease patients, among others. She is a member of the National Academy of Medicine and of the National Academy of Sciences.