Causal Machine Learning for Treatment Effect Heterogeneity: Interpretation, Benchmarking, Validation
American Journal of Epidemiology · 13.11.2026
DOI: 10.1093/aje/kwag294 ↗Kurz gefasst
Fachartikel in der Zeitschrift American Journal of Epidemiology, online erschienen am 13.11.2026. Verfasst von Philip Heesen und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neuroradiology, University Hospital Heidelberg, Heidelberg, Germany.
Abstract (Originalsprache)
Causal machine learning (ML) has emerged as a promising approach for predicting individualized treatment effects and advancing precision medicine, moving beyond the limitations of conventional one-variable-at-a-time subgroup analyses of randomized trials. A recent benchmarking study by Chen and colleagues evaluated several causal ML learners across two large trials and concluded that current methods do not yet demonstrate reliable performance for clinical application. While such applied methodological investigations are valuable, this conclusion warrants a more nuanced examination. Multiple independent research groups have successfully applied causal ML across respiratory medicine and critical care, identifying clinically meaningful treatment effect heterogeneity that prior subgroup analyses had not resolved, although these applications have methodological limitations and do not yet establish that the detected heterogeneity is robust across internal and external validation. We outline four sequential and iterative dimensions central to credible causal ML analyses: choice of learner, model training with cross-fitting, internal validation using calibration-for-benefit and rank-weighted metrics, and external validation aligned with the original causal question. With careful methodological execution, causal ML holds considerable promise for personalized treatment decisions and warrants continued development; dismissing the field prematurely risks overlooking a powerful tool for personalized treatment decisions.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Neuroradiology, University Hospital Heidelberg, Heidelberg, Germany.
- LMU Munich, Munich, Germany.
- Munich Center for Machine Learning, Munich, Germany.
- Division of Pharmacoepidemiology, Brigham and Women's Hospital, Boston, USA.
- Harvard T.H. Chan School of Public Health, Boston, USA.
ORCID-Profile: Rishi J Desai, Stefan Feuerriegel
Zitieren
APA
Heesen, P., Schröder, M., Desai, R. J., & Feuerriegel, S. (2026). Causal Machine Learning for Treatment Effect Heterogeneity: Interpretation, Benchmarking, Validation. American Journal of Epidemiology. https://doi.org/10.1093/aje/kwag294
Vancouver
Heesen P, Schröder M, Desai RJ, Feuerriegel S. Causal Machine Learning for Treatment Effect Heterogeneity: Interpretation, Benchmarking, Validation. American Journal of Epidemiology. 2026. doi:10.1093/aje/kwag294
BibTeX
@article{Heesen2026,
author = {Heesen, Philip and Schröder, Maresa and Desai, Rishi J and Feuerriegel, Stefan},
title = {Causal Machine Learning for Treatment Effect Heterogeneity: Interpretation, Benchmarking, Validation},
journal = {American Journal of Epidemiology},
year = {2026},
doi = {10.1093/aje/kwag294}
}
EUVIMED