Treatment Policy Learning in Multiobjective Settings with Fully Observed Outcomes
This work addresses the challenge of optimizing treatment decisions in healthcare when multiple competing objectives exist, though it appears incremental as it builds on existing policy learning methods.
The paper tackled the problem of learning individualized treatment policies in medical settings where all potential outcomes are known but not available in real-time, and multiple objectives like effectiveness and side effects must be balanced. It presented and compared three approaches, showing that all achieved strictly better performance than clinicians on all outcomes in a UTI dataset, with the direct approach offering additional benefits like flexible goal incorporation.
In several medical decision-making problems, such as antibiotic prescription, laboratory testing can provide precise indications for how a patient will respond to different treatment options. This enables us to "fully observe" all potential treatment outcomes, but while present in historical data, these results are infeasible to produce in real-time at the point of the initial treatment decision. Moreover, treatment policies in these settings often need to trade off between multiple competing objectives, such as effectiveness of treatment and harmful side effects. We present, compare, and evaluate three approaches for learning individualized treatment policies in this setting: First, we consider two indirect approaches, which use predictive models of treatment response to construct policies optimal for different trade-offs between objectives. Second, we consider a direct approach that constructs such a set of policies without intermediate models of outcomes. Using a medical dataset of Urinary Tract Infection (UTI) patients, we show that all approaches learn policies that achieve strictly better performance on all outcomes than clinicians, while also trading off between different objectives. We demonstrate additional benefits of the direct approach, including flexibly incorporating other goals such as deferral to physicians on simple cases.