Learning Cost-Effective and Interpretable Regimes for Treatment Recommendation

TL;DR

This paper introduces a method to learn cost-effective, interpretable treatment decision lists that maximize outcomes and minimize costs, using a novel MDP-based approach with UCT for efficient search, validated on asthma treatment data.

Contribution

It presents a new framework for learning decision lists that balance outcomes and costs, employing a Markov Decision Process and UCT-based search for improved interpretability and efficiency.

Findings

Effective in optimizing treatment outcomes and costs

Demonstrated success on real-world asthma data

Outperforms baseline methods in interpretability and efficiency

Abstract

Decision makers, such as doctors and judges, make crucial decisions such as recommending treatments to patients, and granting bails to defendants on a daily basis. Such decisions typically involve weighting the potential benefits of taking an action against the costs involved. In this work, we aim to automate this task of learning {cost-effective, interpretable and actionable treatment regimes. We formulate this as a problem of learning a decision list -- a sequence of if-then-else rules -- which maps characteristics of subjects (eg., diagnostic test results of patients) to treatments. We propose a novel objective to construct a decision list which maximizes outcomes for the population, and minimizes overall costs. We model the problem of learning such a list as a Markov Decision Process (MDP) and employ a variant of the Upper Confidence Bound for Trees (UCT) strategy which leverages customized checks for pruning the search space effectively. Experimental results on real world observational data capturing treatment recommendations for asthma patients demonstrate the effectiveness of our approach.