Active Learning for Developing Personalized Treatment

• Activity Number: 105
• Type: Invited
• Date/Time: Monday, July 30, 2012 : 8:30 AM to 10:20 AM
• Sponsor: Section on Statistical Learning and Data Mining
• Author(s): Kun Deng*+ and Joelle Pineau and Susan Murphy
• Companies: University of Michigan and McGill University and University of Michigan
• Keywords: machine learning ; active learning ; personalized medicine ; bandit model ; reinforcement learning ; biomarker profile

Abstract

The personalization of treatment via biomarkers and other risk categories has drawn increasing interest among clinical scientists. Personalized treatment strategies can be learned using data from clinical trials, but such trials are very costly to run. We explore the use of active learning techniques to design more efficient trials, addressing issues such as whom to recruit, at what point in the trial, and which treatment to assign, throughout the duration of the trial. We propose a novel minimax bandit model and discuss the computational challenges and issues pertaining to this approach. We evaluate our active learning policies using both simulated data, and data modeled after a clinical trial for treating depressed individuals, and contrast our methods with other plausible active learning policies.