A causal meta-analysis framework for clinical trials with unequal randomization ratios
Research Synthesis Methods · 2026-07 · 17 (4) · 770-781
DOI: 10.1017/rsm.2025.10069 ↗Kurz gefasst
Metaanalyse in der Zeitschrift Research Synthesis Methods, online erschienen am 05.03.2026. Verfasst von Dazheng Zhang und 4 weiteren Autor:innen. Beteiligte Einrichtung: The Center for Health AI and Synthesis of Evidence (CHASE), https://ror.org/00b30xv10University of Pennsylvania, Philadelphia, PA, USA. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIH HHS, National Institutes of Health.
Abstract (Originalsprache)
Meta-analysis synthesizes evidence from multiple randomized clinical trials and informs evidence-based practices across various medical domains. Recently, causally interpretable meta-analysis has been proposed and applied to treatment evaluations for target populations, requiring individual participant data (IPD). Standard meta-analysis assumes transportability or exchangeability of a (conditional) relative effect (such as relative risk or odds ratio), which may be violated when the relative effects are correlated with the baseline risks across clinical trials. In addition, the weighted average of some study-specific effect measures such as the (log) odds ratios or the (log) hazard ratios is non-collapsible and does not correspond to any target population. Furthermore, when the randomization ratios between treated versus untreated arms vary across trials, confounding bias may occur. To address these challenges, we propose a causal meta-analysis (CMA) framework using only aggregated data, enabling causally interpretable and accurate estimation for different target populations. The CMA adjusts its weights for treatment effect across various target populations, including the average treatment effect (ATE), the ATE on the treated (ATT) population, the ATE on the control (ATC) population, and the ATE in the overlap (ATO) population. Mathematically, we discover the connection between traditional meta-analysis estimators and CMAs. For example, the Mantel–Haenszel weighted meta-analysis is equivalent to the CMA with ATO.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- The Center for Health AI and Synthesis of Evidence (CHASE), https://ror.org/00b30xv10University of Pennsylvania, Philadelphia, PA, USA.
- Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine, https://ror.org/00b30xv10The University of Pennsylvania, Philadelphia, PA, USA.
- The Graduate Group in Applied Mathematics and Computational Science, School of Arts and Sciences, https://ror.org/00b30xv10University of Pennsylvania, Philadelphia, PA, USA.
- Statistical Research and Data Science Center, https://ror.org/01xdqrp08Pfizer Inc., USA.
- Division of Biostatistics and Health Data Sciences, University of Minnesota Twin Cities, Minneapolis, MN, USA.
- Leonard Davis Institute of Health Economics, Philadelphia, PA, USA.
ORCID-Profile: Haitao Chu
Förderung
- NIH HHS
- National Institutes of Health
Zitieren
APA
Zhang, D., Zhang, B., Li, L., Chu, H., & Chen, Y. (2026). A causal meta-analysis framework for clinical trials with unequal randomization ratios. Research Synthesis Methods, 17(4), 770-781. https://doi.org/10.1017/rsm.2025.10069
Vancouver
Zhang D, Zhang B, Li L, Chu H, Chen Y. A causal meta-analysis framework for clinical trials with unequal randomization ratios. Research Synthesis Methods. 2026;17(4):770-781. doi:10.1017/rsm.2025.10069
BibTeX
@article{Zhang2026,
author = {Zhang, Dazheng and Zhang, Bingyu and Li, Lu and Chu, Haitao and Chen, Yong},
title = {A causal meta-analysis framework for clinical trials with unequal randomization ratios},
journal = {Research Synthesis Methods},
year = {2026},
volume = {17},
number = {4},
pages = {770--781},
doi = {10.1017/rsm.2025.10069}
}
EUVIMED