Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Jan:22:167.

Estimation and Optimization of Composite Outcomes

Daniel J Luckett  1 , Eric B Laber  2 , Siyeon Kim  3 , Michael R Kosorok  4
Affiliations

Estimation and Optimization of Composite Outcomes

Daniel J Luckett et al. J Mach Learn Res. 2021 Jan.

Abstract

There is tremendous interest in precision medicine as a means to improve patient outcomes by tailoring treatment to individual characteristics. An individualized treatment rule formalizes precision medicine as a map from patient information to a recommended treatment. A treatment rule is defined to be optimal if it maximizes the mean of a scalar outcome in a population of interest, e.g., symptom reduction. However, clinical and intervention scientists often seek to balance multiple and possibly competing outcomes, e.g., symptom reduction and the risk of an adverse event. One approach to precision medicine in this setting is to elicit a composite outcome which balances all competing outcomes; unfortunately, eliciting a composite outcome directly from patients is difficult without a high-quality instrument, and an expert-derived composite outcome may not account for heterogeneity in patient preferences. We propose a new paradigm for the study of precision medicine using observational data that relies solely on the assumption that clinicians are approximately (i.e., imperfectly) making decisions to maximize individual patient utility. Estimated composite outcomes are subsequently used to construct an estimator of an individualized treatment rule which maximizes the mean of patient-specific composite outcomes. The estimated composite outcomes and estimated optimal individualized treatment rule provide new insights into patient preference heterogeneity, clinician behavior, and the value of precision medicine in a given domain. We derive inference procedures for the proposed estimators under mild conditions and demonstrate their finite sample performance through a suite of simulation experiments and an illustrative application to data from a study of bipolar depression.

Keywords: Individualized treatment rules; Inverse reinforcement learning; Precision medicine; Utility functions.

PubMed Disclaimer

Figures

Figure 1:
Figure 1:
Box plots of log SUM-D by substance abuse and treatment.
Figure 2:
Figure 2:
Box plots of log SUM-M by substance abuse and treatment.
See this image and copyright information in PMC

References

    1. Abbeel Pieter and Ng Andrew Y. Apprenticeship learning via inverse reinforcement learning. In Proceedings of the Twenty-first International Conference on Machine Learning. ACM, 2004.
    1. Benkeser David, Mertens Andrew, Colford John M, Hubbard Alan, Arnold Benjamin F, Stein Aryeh, and van der Laan Mark J. A machine learning-based approach for estimating and testing associations with multivariate outcomes. The international journal of biostatistics, 1(ahead-of-print), 2020. - PubMed
    1. Blatt D, Murphy SA, and Zhu J. A-learning for approximate planning. Ann Arbor, 1001: 48109–2122, 2004.
    1. Butler Emily L, Laber Eric B, Davis Sonia M, and Kosorok Michael R. Incorporating patient preferences into estimation of optimal individualized treatment rules. Biometrics, 74(1): 18–26, 2018. - PMC - PubMed
    1. Carlsson Fredrik and Martinsson Peter. Design techniques for stated preference methods in health economics. Health economics, 12(4):281–294, 2003. - PubMed

LinkOut - more resources