On Heterogeneous Treatment Effects in Heterogeneous Causal Graphs

TL;DR

This paper introduces a novel framework for modeling and estimating heterogeneous causal effects within complex graphical models, addressing challenges in healthcare research related to heterogeneity and comorbidity.

Contribution

It generalizes causal graphical models to include confounder interactions and mediators, providing theoretical forms and an interactive structural learning method for HCEs.

Findings

Theoretical characterization of HCEs at the individual level.

Development of an interactive structural learning algorithm.

Empirical validation through simulations and psychiatric disorder analysis.

Abstract

Heterogeneity and comorbidity are two interwoven challenges associated with various healthcare problems that greatly hampered research on developing effective treatment and understanding of the underlying neurobiological mechanism. Very few studies have been conducted to investigate heterogeneous causal effects (HCEs) in graphical contexts due to the lack of statistical methods. To characterize this heterogeneity, we first conceptualize heterogeneous causal graphs (HCGs) by generalizing the causal graphical model with confounder-based interactions and multiple mediators. Such confounders with an interaction with the treatment are known as moderators. This allows us to flexibly produce HCGs given different moderators and explicitly characterize HCEs from the treatment or potential mediators on the outcome. We establish the theoretical forms of HCEs and derive their properties at the individual level in both linear and nonlinear models. An interactive structural learning is developed to estimate the complex HCGs and HCEs with confidence intervals provided. Our method is empirically justified by extensive simulations and its practical usefulness is illustrated by exploring causality among psychiatric disorders for trauma survivors.