Rigorous Bivariate Synthesis of Benefit-Risk Profiles for Direct Oral Anticoagulants in Atrial Fibrillation
Abstract
Selection of anticoagulant therapy relies on a balance between ischemic stroke prevention (the benefit) and (the risk) of major bleeding.[1] This analysis highlights a bivariate random effect meta-analysis of the four key Phase III trials. Making a comparison of Direct Oral Anticoagulant (DOACs) versus warfarin drawing on the four key Phase III trials:RE-LY, ROCKET-AF, ARISTOTLE, and ENGAGE AF-TIMI 48. This is done by incorporating modern small sample adjustments and conformal prediction intervals, in order to provide a strengthened framework for evidence based decision making under uncertainty.
References
1. Hartung, J., & Knapp, G. (2001). A refined method for the meta-analysis of controlled clinical trials with binary outcome.2Statistics in Medicine, 20(24), 3875-3889.
2. Riley, R. D., et al. (2017). Multivariate and network meta-analysis of multiple outcomes and multiple treatments: rationale, concepts, and examples.3 BMJ, 358, j3932.
3. Viechtbauer, W. (2005). Bias and efficiency of meta-analytic variance estimators in the random-effects model.4 Journal of Educational and Behavioral Statistics, 30(3), 261-293.
4. Vovk, V., Gammerman, A., & Shafer, G. (2005). Algorithmic Learning in a Random World.5 Springer Science & Business Media.
Downloads
Published
Versions
- 2026-06-15 (4)
- 2026-06-15 (3)
- 2026-06-15 (2)
- 2026-04-12 (1)
Issue
Section
License
Copyright (c) 2025 Oluwatomi Olukoya, Khaing Mar Lwin, Ata Ul Hayee Sohail

This work is licensed under a Creative Commons Attribution 4.0 International License.
Articles in Synthēsis are published under the Creative Commons Attribution 4.0 International (CC BY 4.0) licence. Authors retain copyright.