Joint Seminar: The Departments of Biostatistics and Statistics present: Michael Kosorok, Personalize Medicine, Clinical Trials and Machine Learning
Personalized medicine means different things to different people, but it is clearly an active and important area of current research interest. In this talk we discuss some of the recent work in this area and highlight the role of clinical trials, including both traditional designs as well as newer designs, including Sequential Multiple Assignment Randomize Trials (SMARTs) and other novel designs. Several specific clinical examples will be discussed in detail. We also discuss the use of machine learning to help identify treatment regimens which adapt to patient features, including biomarkers. One interesting new tool, outcome weighted learning, is discussed in some detail and a few results will be presented as well as a discussion of several relevant open questions.