Eleven quick tips for Biomedical Federated Learning
PLOS Computational Biology · 21.08.2026 · 22 (8) · e1014530
DOI: 10.1371/journal.pcbi.1014530 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 21.08.2026. Verfasst von Kyle Ellrott und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, Oregon Health & Sciences University, Portland, United States of America. Hauptthemen laut MEDLINE: Federated Learning, Computational Biology, Machine Learning. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NCI NIH HHS, NHGRI NIH HHS, NIH.
Abstract (Originalsprache)
Modern statistical and machine learning techniques are effective at describing, testing hypotheses and making predictions from complex data. This effectiveness is strongly influenced by the volume and heterogeneity of available data. In many fields, including much of biomedicine, large centralized datasets are not available because of cost, privacy, regulatory or other restrictions. In these cases, smaller datasets are distributed across a large number of independent sites. Medical record data is a classic example of this challenge: the total number of patients may be large, but their records are distributed across many health systems and cannot easily be centralized. Federated learning (FL) is a machine learning paradigm that enables training and validation of a shared model in settings of decentralized data. FL can improve model accuracy and generalizability by increasing sample size, but has trade-offs ranging from operational complexity to data-privacy risks to the potential to introduce unexpected imbalances in model accuracy. We outline ten tips for successfully and sustainably implementing FL for Biomedical applications, ensuring both ethical data governance and improved model performance in sensitive domains.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Biomedical Engineering, Oregon Health & Sciences University, Portland, United States of America.
- Division of Oncological Sciences, Knight Cancer Institute, Portland, United States of America.
- Health Futures, Microsoft Research, Redmond, Washington, United States of America.
- Healthcare and Life Sciences, TTEC Digital, Austin, Texas, United States of America.
- Faculty of Health Sciences, Simon Fraser University, Vancouver, British Columbia, Canada.
- Department of Molecular and Medical Genetics, Oregon Health & Sciences University, Portland, United States of America.
ORCID-Profile: Kyle Ellrott, Paul C Boutros
Förderung
- NCI NIH HHS
- NHGRI NIH HHS
- NIH
- Ministry of Research, Innovation and Digitization under Romania’s National Recovery and Resilience Plan
Zitieren
APA
Ellrott, K., Malladi, V. S., Bélisle-Pipon, J. C., Demir, E., Bensoussan, Y., Mangul, S., Bui, A. A. T., & Boutros, P. C. (2026). Eleven quick tips for Biomedical Federated Learning. PLOS Computational Biology, 22(8), e1014530. https://doi.org/10.1371/journal.pcbi.1014530
Vancouver
Ellrott K, Malladi VS, Bélisle-Pipon JC, Demir E, Bensoussan Y, Mangul S, et al. Eleven quick tips for Biomedical Federated Learning. PLOS Computational Biology. 2026;22(8):e1014530. doi:10.1371/journal.pcbi.1014530
BibTeX
@article{Ellrott2026,
author = {Ellrott, Kyle and Malladi, Venkat S and Bélisle-Pipon, Jean-Christophe and Demir, Emek and Bensoussan, Yael and Mangul, Serghei and Bui, Alex A T and Boutros, Paul C},
title = {Eleven quick tips for Biomedical Federated Learning},
journal = {PLOS Computational Biology},
year = {2026},
volume = {22},
number = {8},
pages = {e1014530},
doi = {10.1371/journal.pcbi.1014530}
}
EUVIMED