医疗联邦因果推断用于效果估计:方法、挑战与应用
Federated causal inference for effect estimation in healthcare: methods, challenges, and applications
npj Artificial Intelligence 发表综述,回顾不集中化患者数据前提下的联邦因果推断方法,涵盖二元、连续及生存时间终点。文章通过 estimand、分布式计算协议和隐私机制三个维度比较策略,指出混杂、异质性及隐私效用权衡等未解决挑战,支持对联邦因果方法进行严谨评估。
- Review
- Open access
- Published: 17 October 2026
- Haoyang Li ORCID: orcid.org/0000-0003-3544-55631,
- Zheqi Lyu1,
- Meihan Wei1,
- Simai Cheng1,
- Wenhan Zheng ORCID: orcid.org/0009-0007-5092-76041,
- Fuying Ding1,
- Jie Xu2,
- Kyra Gan3,
- Max Sunog4,
- Colin Magdamo5,
- Mark W. Albers ORCID: orcid.org/0000-0001-7855-34554,5,
- Fei Wang1 &
- …
- Chengxi Zang1
npj Artificial Intelligence (2026) Cite this article
We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply.
Abstract
Federated causal inference enables treatment-effect estimation across healthcare systems without centralizing patient-level data. We review methods for binary, continuous, and time-to-event outcomes through three lenses: estimand, distributed-computation protocol, and privacy mechanism. We compare major strategies, clarify when federated analyses can approximate pooled results, and highlight unresolved challenges in confounding, heterogeneity, survival estimands, privacy–utility trade-offs, validation, and software. This framework supports rigorous evaluation of federated causal methods in healthcare.
Funding
C.Z. would like to acknowledge the support from NIH award 1R01HD120978. F.W. would like to acknowledge the support from NSF award 2212175 and NIH awards RF1AG072449, RF1AG084178, R01AG080991, R01AG080624, R01AG076448, R01AG076234. M.W.A. would like to acknowledge the support from NIH award R01AG058063. J.X. would like to acknowledge the support from NIH/NHLBI award 1R01HL169277.
Author information
Authors and Affiliations
Department of Population Health Sciences, Weill Cornell Medicine, New York, NY, USA
Haoyang Li, Zheqi Lyu, Meihan Wei, Simai Cheng, Wenhan Zheng, Fuying Ding, Fei Wang & Chengxi Zang
Department of Health Outcomes & Biomedical Informatics, University of Florida, Gainesville, FL, USA
Jie Xu
Cornell Tech, Cornell University, New York, NY, USA
Kyra Gan
Massachusetts General Hospital, Boston, MA, USA
Max Sunog & Mark W. Albers
Harvard Medical School, Boston, MA, USA
Colin Magdamo & Mark W. Albers
Authors
- Haoyang Li
- Zheqi Lyu
- Meihan Wei
- Simai Cheng
- Wenhan Zheng
- Fuying Ding
- Jie Xu
- Kyra Gan
- Max Sunog
- Colin Magdamo
- Mark W. Albers
- Fei Wang
- Chengxi Zang
Corresponding author
Correspondence to Chengxi Zang.
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Li, H., Lyu, Z., Wei, M. et al. Federated causal inference for effect estimation in healthcare: methods, challenges, and applications. npj Artif. Intell. (2026). https://doi.org/10.1038/s44387-026-00168-1
Received: 31 January 2026
Accepted: 28 September 2026
Published: 17 October 2026
DOI: https://doi.org/10.1038/s44387-026-00168-1
来源:Nature 健康护理主题 · nature.com