Penalized robust learning for optimal treatment regimes with heterogeneous individualized treatment effects

The growing popularity of personalized medicine motivates people to explore individualized treatment regimes according to heterogeneous characteristics of the patients. For the large-scale data analysis, however, the data are collected at different times and different locations, i.e. subjects are us...

Full description

Saved in:
Bibliographic Details
Published in:Journal of applied statistics 2024-04, Vol.51 (6), p.1151-1170
Main Authors: Li, Canhui, Li, Weirong, Zhu, Wensheng
Format: Article
Language:English
Subjects:
Coefficients
Columns (structural)
Data analysis
double penalty
heterogeneity
homogeneity
Individualized treatment regime
Learning
residual
Robustness
sparsity
Statistical methods
Subgroups
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The growing popularity of personalized medicine motivates people to explore individualized treatment regimes according to heterogeneous characteristics of the patients. For the large-scale data analysis, however, the data are collected at different times and different locations, i.e. subjects are usually from a heterogeneous population, which causes that the optimal treatment regimes also vary for patients across different subgroups. In this paper, we mainly focus on the estimation of optimal treatment regimes for subjects come from a heterogeneous population with high-dimensional data. We first remove the main effects of the covariates for each subgroup to eliminate non-ignorable residual confounding. Based on the centralized outcome, we propose a penalized robust learning that estimates the coefficient matrix of the interactions between covariates and treatment by penalizing pairwise differences of the coefficients of any two subgroups for the same covariate, which can automatically identify the latent complex structure of the coefficient matrix with heterogeneous and homogeneous columns. At the same time, the penalized robust learning can also select the important variables that truly contribute to the individualized treatment decisions with commonly used sparsity structure penalty. Extensive simulation studies show that our proposed method outperforms current popular methods, and it is further illustrated in the real analysis of the Tamoxifen breast cancer data.
ISSN:0266-4763
1360-0532
DOI:10.1080/02664763.2023.2180167