Quantitative Issues in Cancer Research Working Seminar

Patrick Emedom-Nnamdi
Doctoral Student, Department of Biostatistics, Harvard University

“Nonparametric Q-Value Function Approximation: An Application to Postoperative Spine Disease Recovery”

ABSTRACT: Improving patient recovery after a post-operative event continues to be a concern for many medical providers. In general, different treatment recommendations concerning postoperative mobilization can lead to variations in patient recovery. In order to provide guidance for physicians, we construct a data-driven approach to discover post-operative recovery strategies based on patient mobilization that leverages digital phenotyping. In this talk, I will present our approach toward estimating recovery strategies for postoperative spine disease patients using an interpretable, nonparametric Q-value function approximator.