Direct and Indirect Treatment Effects in the Presence of Semi-Competing Risks

TL;DR

This paper develops methods to decompose treatment effects into direct and indirect components in semi-competing risks scenarios, accounting for the complex censoring structure and providing asymptotic properties for estimators.

Contribution

It introduces two strategies for effect decomposition under mediation analysis in randomized trials with semi-competing risks, highlighting different assumptions for identifiability.

Findings

Asymptotic properties of estimators are established.

Simulation studies demonstrate differences between the two decomposition methods.

Real-data applications illustrate practical relevance.

Abstract

Semi-competing risks refer to the phenomenon that the terminal event (such as death) can censor the non-terminal event (such as disease progression) but not vice versa. The treatment effect on the terminal event can be delivered either directly following the treatment or indirectly through the non-terminal event. We consider two strategies to decompose the total effect into a direct effect and an indirect effect under the framework of mediation analysis in completely randomized experiments by adjusting the prevalence and hazard of non-terminal events, respectively. They require slightly different assumptions on cross-world quantities to achieve identifiability. We establish asymptotic properties for the estimated counterfactual cumulative incidences and decomposed treatment effects. We illustrate the subtle difference between these two decompositions through simulation studies and two real-data applications.