Uncovering Treatment Effect Heterogeneity in Pragmatic Gerontology Trials

TL;DR

This paper introduces a Bayesian machine learning approach within a causal framework to identify heterogeneity in treatment effects among older adults in gerontology trials, especially when outcomes are truncated by death.

Contribution

It extends principal stratification with BART to flexibly estimate subgroup-specific effects, revealing treatment heterogeneity hidden in average effects.

Findings

Some subgroups benefit from telecare despite null average effect

The method uncovers heterogeneity in treatment response among older adults

Personalized intervention strategies can be informed by these insights

Abstract

Detecting heterogeneity in treatment response enriches the interpretation of gerontologic trials. In aging research, estimating the effect of the intervention on clinically meaningful outcomes faces analytical challenges when it is truncated by death. For example, in the Whole Systems Demonstrator trial, a large cluster-randomized study evaluating telecare among older adults, the overall effect of the intervention on quality of life was found to be null. However, this marginal intervention estimate obscures potential heterogeneity of individuals responding to the intervention, particularly among those who survive to the end of follow-up. To explore this heterogeneity, we adopt a causal framework grounded in principal stratification, targeting the Survivor Average Causal Effect (SACE)-the treatment effect among "always-survivors," or those who would survive regardless of treatment assignment. We extend this framework using Bayesian Additive Regression Trees (BART), a nonparametric machine learning method, to flexibly model both latent principal strata and stratum-specific potential outcomes. This enables the estimation of the Conditional SACE (CSACE), allowing us to uncover variation in treatment effects across subgroups defined by baseline characteristics. Our analysis reveals that despite the null average effect, some subgroups experience distinct quality of life benefits (or lack thereof) from telecare, highlighting opportunities for more personalized intervention strategies. This study demonstrates how embedding machine learning methods, such as BART, within a principled causal inference framework can offer deeper insights into trial data with complex features including truncation by death and clustering-key considerations in analyzing pragmatic gerontology trials.