Informing sequential clinical decision-making through reinforcement learning: an empirical study

Publication Abstract

Shortreed, Susan M., Eric Laber, Daniel J. Lizotte, T. Scott Stroup, Joelle Pineau , and Susan A. Murphy. 2011. "Informing sequential clinical decision-making through reinforcement learning: an empirical study." Machine Learning, 84(1-2): 109-136.

This paper highlights the role that reinforcement learning can play in the optimization of treatment policies for chronic illnesses. Before applying any off-the-shelf reinforcement learning methods in this setting, we must first tackle a number of challenges. We outline some of these challenges and present methods for overcoming them. First, we describe a multiple imputation approach to overcome the problem of missing data. Second, we discuss the use of function approximation in the context of a highly variable observation set. Finally, we discuss approaches to summarizing the evidence in the data for recommending a particular action and quantifying the uncertainty around the Q-function of the recommended policy. We present the results of applying these methods to real clinical trial data of patients with schizophrenia.

10.1007/s10994-010-5229-0

PMCID: PMC3143507. (Pub Med Central)

Country of focus: United States of America.

Browse | Search | Books | Next

PSC In The News

RSS Feed icon

Mitchell notes challenge of long term epigenetic human study design around pregnancy risks

Morenoff details How COVID-19 is Impacting Detroit Residents

More News

Highlights

Bloome wins a 2020 William Julius Wilson Early Career Award from Inequality, Poverty, and Mobility section of the ASA

Pfeffer recognized with William Julius Wilson Early Career Award from Inequality, Poverty, and Mobility section of the ASA

More Highlights


Connect with PSC follow PSC on Twitter Like PSC on Facebook