A Causal Machine Learning Framework for Treatment Personalization in Clinical Trials: Application to Ulcerative Colitis
This work addresses the challenge of ensuring that personalized treatment approaches in clinical trials lead to better patient outcomes, highlighting a critical gap between statistical detection and practical decision-making, with incremental methodological contributions.
The study tackled the problem of distinguishing between statistically detectable treatment effect heterogeneity and actual improvement in personalized treatment decisions in clinical trials, applying a causal machine learning framework to ulcerative colitis data. The result showed that endoscopic features, while associated with heterogeneity, did not improve remission rates and even worsened performance when used for treatment selection, whereas clinical variables like fecal calprotectin captured decision-relevant variation.
Randomized controlled trials estimate average treatment effects, but treatment response heterogeneity motivates personalized approaches. A critical question is whether statistically detectable heterogeneity translates into improved treatment decisions -- these are distinct questions that can yield contradictory answers. We present a modular causal machine learning framework that evaluates each question separately: permutation importance identifies which features predict heterogeneity, best linear predictor (BLP) testing assesses statistical significance, and doubly robust policy evaluation measures whether acting on the heterogeneity improves patient outcomes. We apply this framework to patient-level data from the UNIFI maintenance trial of ustekinumab in ulcerative colitis, comparing placebo, standard-dose ustekinumab every 12 weeks, and dose-intensified ustekinumab every 8 weeks, using cross-fitted X-learner models with baseline demographics, medication history, week-8 clinical scores, laboratory biomarkers, and video-derived endoscopic features. BLP testing identified strong associations between endoscopic features and treatment effect heterogeneity for ustekinumab versus placebo, yet doubly robust policy evaluation showed no improvement in expected remission from incorporating endoscopic features, and out-of-fold multi-arm evaluation showed worse performance. Diagnostic comparison of prognostic contribution against policy value revealed that endoscopic scores behaved as disease severity markers -- improving outcome prediction in untreated patients but adding noise to treatment selection -- while clinical variables (fecal calprotectin, age, CRP) captured the decision-relevant variation. These results demonstrate that causal machine learning applications to clinical trials should include policy-level evaluation alongside heterogeneity testing.