Treatment Policy Learning in Multiobjective Settings with Fully Observed Outcomes
Name
3394486.3403245.pdf
Description
Published version
Size
1.8 MB
Format
Adobe PDF
Checksum (MD5)
3837b6a080f4dcb01c3c586f7d7850b1
Author(s)
Boominathan, Soorajnath
Oberst, Michael
Zhou, Helen
Kanjilal, Sanjat
Sontag, David
Date Issued
August 2020
Journal
Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Publisher
ACM
Citation
Boominathan, Soorajnath, Oberst, Michael, Zhou, Helen, Kanjilal, Sanjat and Sontag, David. 2020. "Treatment Policy Learning in Multiobjective Settings with Fully Observed Outcomes." Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.
Version
Final published version
Abstract
© 2020 Owner/Author. 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.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Institute for Medical Engineering & Science
Terms of Use
Creative Commons Attribution 4.0 International license
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3394486.3403245
