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
. 2012 Sep 1;107(449):1106-1118.
doi: 10.1080/01621459.2012.695674.

Estimating Individualized Treatment Rules Using Outcome Weighted Learning

Yingqi Zhao  1 , Donglin Zeng, A John Rush, Michael R Kosorok
Affiliations

Estimating Individualized Treatment Rules Using Outcome Weighted Learning

Yingqi Zhao et al. J Am Stat Assoc. .

Abstract

There is increasing interest in discovering individualized treatment rules for patients who have heterogeneous responses to treatment. In particular, one aims to find an optimal individualized treatment rule which is a deterministic function of patient specific characteristics maximizing expected clinical outcome. In this paper, we first show that estimating such an optimal treatment rule is equivalent to a classification problem where each subject is weighted proportional to his or her clinical outcome. We then propose an outcome weighted learning approach based on the support vector machine framework. We show that the resulting estimator of the treatment rule is consistent. We further obtain a finite sample bound for the difference between the expected outcome using the estimated individualized treatment rule and that of the optimal treatment rule. The performance of the proposed approach is demonstrated via simulation studies and an analysis of chronic depression data.

Keywords: Bayes Classifier; Cross Validation; Dynamic Treatment Regime; Individualized Treatment Rule; RKHS; Risk Bound; Weighted Support Vector Machine.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Contour Plots of Value Function for Example 1 with λn ∈ (0, 10) and σn ∈ (0, 10)
Figure 2
Figure 2
MSE for Value Functions of Individualized Treatment Rules
Figure 3
Figure 3
MSE for Misclassification Rates of Individualized Treatment Rules
See this image and copyright information in PMC

References

    1. Bartlett PL, Bousquet O, Mendelson S. Local Rademacher Complexities. The Annals of Statistics. 2005;33(4):1497–1537.
    1. Bartlett PL, Jordan MI, McAuliffe JD. Convexity, Classification, and Risk Bounds. J of American Statistical Association. 2006;101(473):138–156.
    1. Blanchard G, Bousquet O, Massart P. Statistical Performance of Support Vector Machines. Annals of Statistics. 2008;36:489–531.
    1. Bradley PS, Mangasarian OL. Feature Selection via Concave Minimization and Support Vector Machines. Proc. 15th International Conf. on Machine Learning; San Francisco, CA, USA: Morgan Kaufmann Publishers Inc; 1998.
    1. Buzdar AU. Role of Biologic Therapy and Chemotherapy in Hormone Receptor and HER2-Positive Breast Cancer. Annals of Oncology. 2009;20:993–999. - PubMed

LinkOut - more resources