A Bayesian approach to the survivor average causal effect in cluster-randomized crossover trials

2025-05-27

AI Summary

In cluster-randomized crossover (CRXO) trials, patient mortality renders non-terminal outcomes (e.g., length of hospital stay) unobservable outside the survivor subpopulation, rendering the survivor average causal effect (SACE) non-identifiable under standard assumptions. This paper introduces the first principal stratification–Bayesian causal inference framework specifically designed for CRXO trials. It proposes a structural model and scientifically plausible assumptions that ensure SACE identifiability, integrating structural equation modeling with Markov chain Monte Carlo (MCMC) estimation. The method demonstrates robust performance in small-sample simulations. Applied to a real-world CRXO study comparing proton pump inhibitors versus H₂-receptor antagonists on hospital stay among mechanically ventilated patients, it yields credible posterior estimates of the SACE. The key innovation lies in the systematic integration of principal stratification with Bayesian inference for CRXO designs—resolving the longstanding challenge of identifying causal effects on non-terminal outcomes under death truncation.

Technology Category

• Reasoning under Uncertainty: Causality
• Machine Learning: Causal Learning
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Security and Privacy: Large-scale security measurements
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

In cluster-randomized crossover (CRXO) trials, groups of individuals are randomly assigned to two or more sequences of alternating treatments. Since clusters act as their own control, the CRXO design is typically more statistically efficient than the usual parallel-arm trial. CRXO trials are increasingly popular in many areas of health research where the number of available clusters is limited. Further, in trials among severely ill patients, researchers often want to assess the effect of treatments on secondary non-terminal outcomes, but frequently in these studies, there are patients who do not survive to have these measurements fully recorded. In this paper, we provide a causal inference framework and treatment effect estimation methods for addressing truncation by death in the setting of CRXO trials. We target the survivor average causal effect (SACE) estimand, a well-defined subgroup treatment effect obtained via principal stratification. We propose novel structural and standard modeling assumptions to enable SACE identification followed by estimation within a Bayesian paradigm. We evaluate the small-sample performance of our proposed Bayesian approach for the estimation of the SACE in CRXO trial settings via simulation studies. We apply our methods to a previously conducted two-period cross-sectional CRXO study examining the impact of proton pump inhibitors compared to histamine-2 receptor blockers on length of hospitalization among adults requiring invasive mechanical ventilation.

Problem

• Estimating treatment effects in cluster-randomized crossover trials with patient mortality
• Addressing truncation by death in secondary non-terminal outcome measurements
• Developing Bayesian methods for survivor average causal effect estimation

Innovation

• Bayesian approach for survivor average causal effect
• Structural and standard modeling assumptions
• Small-sample performance evaluation via simulation