Online Program

Sequential Multiple Assignment Randomization Trials with EnRichment (SMARTer) Design

*Yuanjia Wang, Columbia University 
Fuda Hao, Eli Lilly and Company 
Donglin Zeng, University of North Carolina 

Keywords: Dynamic Treatment Regimes, Adaptive Treatment Sequence, Personalized Medicine, Individualized Health Care

The concept of personalized medicine has become increasingly influential in health care. However, individualized clinical decision-making is often complex due to differential patient treatment response and risk profile heterogeneity. Adding to the complication is that pharmacotherapy may exhibit distinct efficacy and safety profile for different patient populations. An optimal treatment for a patient that maximizes clinical benefit may also lead to greater concern of safety and adverse events. Thus, to guide individualized clinical decision-making and deliver optimal tailored treatments, maximizing clinical benefit should be considered in the context of controlling for the risk. In this work, we propose a machine learning approach to identify personalized optimal treatment strategy that maximizes clinical reward function under a constraint for the risk function. Algorithms, simulations, and theoretical properties will be presented. We apply our method to a randomized trial of type 2 diabetes patients to guide optimal use of the first-line insulin treatments based on individual patient characteristics while controlling for the number of hypoglycemia events.