A Tree-based Model Averaging Approach for Personalized Treatment Effect Estimation from Heterogeneous Data Sources
This addresses the problem of limited sample sizes and privacy constraints in healthcare settings for researchers and practitioners, offering an incremental improvement over existing methods.
The paper tackles the challenge of accurately estimating personalized treatment effects at a single site with limited data by proposing a tree-based model averaging approach that leverages models from other heterogeneous sites without sharing subject-level data, demonstrating improved accuracy in a real-world study on oxygen therapy effects on hospital survival rates.
Accurately estimating personalized treatment effects within a study site (e.g., a hospital) has been challenging due to limited sample size. Furthermore, privacy considerations and lack of resources prevent a site from leveraging subject-level data from other sites. We propose a tree-based model averaging approach to improve the estimation accuracy of conditional average treatment effects (CATE) at a target site by leveraging models derived from other potentially heterogeneous sites, without them sharing subject-level data. To our best knowledge, there is no established model averaging approach for distributed data with a focus on improving the estimation of treatment effects. Specifically, under distributed data networks, our framework provides an interpretable tree-based ensemble of CATE estimators that joins models across study sites, while actively modeling the heterogeneity in data sources through site partitioning. The performance of this approach is demonstrated by a real-world study of the causal effects of oxygen therapy on hospital survival rate and backed up by comprehensive simulation results.