Learning Cost-Effective and Interpretable Regimes for Treatment Recommendation
This work addresses the need for automated, interpretable decision-making in domains like healthcare, offering a practical solution for treatment recommendations, though it is incremental as it builds on existing methods like MDP and UCT.
The authors tackled the problem of automating cost-effective and interpretable treatment recommendations by learning decision lists that map patient characteristics to treatments, achieving improved outcomes and reduced costs in experiments on real-world asthma patient data.
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.