Inferential Challenges in Machine Learning and Precision Medicine

• Activity Number: 603 - Statistical Inference for Precision Medicine and Subgroup Analysis
• Type: Invited
• Date/Time: Thursday, August 2, 2018 : 8:30 AM to 10:20 AM
• Sponsor: ENAR
• Author(s): Michael Kosorok*
• Companies: University of North Carolina at Chapel Hill
• Keywords: Dynamic treatment regimes; Individualized treatment rules; Machine learning; Precision medicine; Reinforcement learning; Statistical inference

Abstract

Precision medicine, the paradigm of improving clinical care through data driven approaches to tailoring treatment to the individual, is an important area of statistical and biomedical research. Individualized treatment rules (ITR's) formalize precision medicine as mappings from the space of patient covariates to the set of available treatments or, equivalently, as mappings which identify covariate-defined subgroups for which different treatments should be applied. ITR's are thus an important tool to improve patient outcomes through utilizing biomarkers to target treatment. Machine learning has become an increasingly utilized and evolving methodology for ITR discovery, but a number of inferential challenges arise in this setting, including non-regularity of the estimators. We discuss these issues and outline some helpful recent advances as well as open problems.