From challenges and pitfalls to recommendations and opportunities: Implementing federated learning in healthcare

Li, Ming; Xu, Pengcheng; Hu, Junjie; Tang, Zeyu; Yang, Guang

doi:10.1016/j.media.2025.103497

reviewMedical Image AnalysisFeb 14, 2025HYBRID OA

From challenges and pitfalls to recommendations and opportunities: Implementing federated learning in healthcare

MLMing Li PXPengcheng Xu JHJunjie Hu ZTZeyu Tang GYGuang Yang

NIHR Imperial Biomedical Research Centre · Imperial College London · +3 more institutions

PubMed

Indexed incrossrefpubmed

Abstract

Federated learning holds great potential for enabling large-scale healthcare research and collaboration across multiple centers while ensuring data privacy and security are not compromised. Although numerous recent studies suggest or utilize federated learning based methods in healthcare, it remains unclear which ones have potential clinical utility. This review paper considers and analyzes the most recent studies up to May 2024 that describe federated learning based methods in healthcare. After a thorough review, we find that the vast majority are not appropriate for clinical use due to their methodological flaws and/or underlying biases which include but are not limited to privacy concerns, generalization…

Citation impact

67

total citations

FWCI: 99.14
Percentile: 100%
References: 221

Citations per year

Authors

5

Topics & keywords

Topics

Keywords

Health care
Computer science
Data science
Knowledge management
Artificial intelligence
Human–computer interaction
Political science

No related works found for this paper.