Informing Sequential Clinical Decision-Making Through Reinforcement Learning: An Empirical Study
Abstract
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.
Cite
Text
Shortreed et al. "Informing Sequential Clinical Decision-Making Through Reinforcement Learning: An Empirical Study." Machine Learning, 2011. doi:10.1007/S10994-010-5229-0Markdown
[Shortreed et al. "Informing Sequential Clinical Decision-Making Through Reinforcement Learning: An Empirical Study." Machine Learning, 2011.](https://mlanthology.org/mlj/2011/shortreed2011mlj-informing/) doi:10.1007/S10994-010-5229-0BibTeX
@article{shortreed2011mlj-informing,
title = {{Informing Sequential Clinical Decision-Making Through Reinforcement Learning: An Empirical Study}},
author = {Shortreed, Susan M. and Laber, Eric B. and Lizotte, Daniel J. and Stroup, T. Scott and Pineau, Joelle and Murphy, Susan A.},
journal = {Machine Learning},
year = {2011},
pages = {109-136},
doi = {10.1007/S10994-010-5229-0},
volume = {84},
url = {https://mlanthology.org/mlj/2011/shortreed2011mlj-informing/}
}