109 FLINT HALL
80 Newell Drive
Gainesville, FL 32611
Speaker: Dr. Brian Denton, Industrial & Operations Engineering at University of Michigan
Title: Robust Markov Decision Processes for Medical Treatment Optimization
Abstract: Medical treatment decisions, such as glycemic control for patients with type 2 diabetes, involve difficult tradeoffs between the risks and the benefits of treatment. The diversity of treatment options that patients can choose over time and the uncertainty in future health outcomes result in a difficult sequential decision-making problem that plays out over the course of a patient’s lifetime. In this seminar, I will first discuss the development of a Markov chain-based glycemic control model, based on longitudinal patient data, for comparing the effectiveness and cost of different treatment regimens for individuals newly diagnosed with type 2 diabetes. Next, I will discuss an approach to evaluate the sensitivity of model outcomes with respect to uncertainty in transition probabilities of the underlying Markov chain. Finally, I will present a robust Markov decision process model (RMDP) that is applicable in many contexts where the goal is to optimize medical treatment decisions. I will discuss some properties of this model, describe computationally efficient solution methods, and illustrate the application of this model to glycemic control.
Biography: Brian Denton is a Professor in the Department of Industrial and Operations Engineering at the University of Michigan, in Ann Arbor, MI. He is also a Professor in the Department of Urology and a member of the Cancer Center at the University of Michigan. Previously he was an Associate Professor in the Department of Industrial & Systems Engineering at NC State University, a Senior Associate Consultant at Mayo Clinic, and a Senior Engineer at IBM. He is past president of the INFORMS Health Applications Section and he served as Secretary on the INFORMS Board of Directors from 2012 to 2015. He is also Past President of INFORMS. He has served on several editorial boards including the INFORMS Journal on Optimization, IISE Transactions, M&SOM, Interfaces, Operations Research, and Medical Decision Making. His current research interests are in the optimization of decision making under uncertainty with applications to chronic diseases including cancer, cardiovascular disease and diabetes. He completed his Ph.D. in Management Science at McMaster University, his M.Sc. in Physics at York University, and his B.Sc. in Chemistry and Physics at McMaster University in Hamilton, Ontario, Canada.
Industrial & Systems Engineering