Semi- and non-parametric approaches to individualized treatment regimes in the presence of causal mediation

2026-06-19

AI Summary

This study addresses the limitation of conventional individualized treatment rules, which rely solely on total causal effects and thus lack path-specific interpretability in settings involving multiple mediators. The authors propose, for the first time, a framework for estimating conditional mediation effects using Bayesian semiparametric and nonparametric methods to construct individualized treatment rules tailored to specific causal pathways. By doing so, the approach enhances both the flexibility and interpretability of treatment decisions. The method’s efficacy and practical utility are demonstrated through an application to the allocation of hepatitis C–positive donor kidneys, where it successfully identifies path-specific optimal treatment strategies, thereby validating its real-world applicability.

Abstract

Individualized treatment rules (ITRs) map an individual patient's characteristics to their recommended treatment value. Typically, the optimal ITR is defined as the rule which maximizes a mean counterfactual outcome; the resulting ITR maximizes the effect of treatment along all causal pathways to the outcome, including indirect pathways through mediating variables. Although maximizing the total effect is often sufficient, explicitly incorporating causal mediation in an ITR analysis has several potential benefits such as enhanced interpretability, and additional flexibility in targeting specific causal pathways. For this purpose, we introduce novel Bayesian semiparametric and nonparametric estimators for conditional mediation effects in the presence of multiple mediators and show how they can be used to estimate optimal ITRs. We demonstrate the proposed methodology via an application to optimal kidney allocation with hepatitis C positive donors.

Problem

• individualized treatment regimes
• causal mediation
• conditional mediation effects
• multiple mediators
• counterfactual outcome

Innovation

• Bayesian semiparametric
• nonparametric estimation
• causal mediation
• individualized treatment regimes
• conditional mediation effects