Treatment Policy Learning in Multiobjective Settings with Fully Observed Outcomes

Abstract

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 any intermediate models of outcomes. Using a medical dataset of Urinary Tract Infection (UTI) patients, we show that all approaches are able to find policies that achieve strictly better performance on all outcomes than clinicians, while also trading off between different objectives as desired. We demonstrate additional benefits of the direct approach, including flexibly incorporating other goals such as deferral to physicians on simple cases.

Publication
Proceedings of the 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)
Sooraj Boominathan
Sooraj Boominathan
Master’s student
Michael Oberst
Michael Oberst
PhD Student

Michael’s research interests include developing learning algorithms for dealing with non-stationarity / dataset shift in predictive modelling, as well as robust learning of treatment policies from observational data.

Helen Zhou
Helen Zhou
Master’s student

PhD student, CMU

Sanjat Kanjilal
Sanjat Kanjilal
Clinical Fellow

Lecturer, Harvard Pilgrim Health Care Institute

David Sontag
David Sontag
Associate Professor of EECS

My research focuses on advancing machine learning and artificial intelligence, and using these to transform health care.

Related