Evaluation of federated learning variations for COVID-19 diagnosis using chest radiographs from 42 US and European hospitals

Le Peng, Gaoxiang Luo, Andrew Walker, Zachary Zaiman, Emma K. Jones, Hemant Gupta, Kristopher Kersten, John L. Burns, Christopher A. Harle, Tanja Magoc, Benjamin Shickel, Scott D. Steenburg, Tyler Loftus, Genevieve B. Melton, Judy Wawira Gichoya, Ju Sun, Christopher J. Tignanelli

Research output: Contribution to journalArticlepeer-review

8 Scopus citations


Objective: Federated learning (FL) allows multiple distributed data holders to collaboratively learn a shared model without data sharing. However, individual health system data are heterogeneous. "Personalized"FL variations have been developed to counter data heterogeneity, but few have been evaluated using real-world healthcare data. The purpose of this study is to investigate the performance of a single-site versus a 3-client federated model using a previously described Coronavirus Disease 19 (COVID-19) diagnostic model. Additionally, to investigate the effect of system heterogeneity, we evaluate the performance of 4 FL variations. Materials and methods: We leverage a FL healthcare collaborative including data from 5 international healthcare systems (US and Europe) encompassing 42 hospitals. We implemented a COVID-19 computer vision diagnosis system using the Federated Averaging (FedAvg) algorithm implemented on Clara Train SDK 4.0. To study the effect of data heterogeneity, training data was pooled from 3 systems locally and federation was simulated. We compared a centralized/pooled model, versus FedAvg, and 3 personalized FL variations (FedProx, FedBN, and FedAMP). Results: We observed comparable model performance with respect to internal validation (local model: AUROC 0.94 vs FedAvg: 0.95, P =. 5) and improved model generalizability with the FedAvg model (P <. 05). When investigating the effects of model heterogeneity, we observed poor performance with FedAvg on internal validation as compared to personalized FL algorithms. FedAvg did have improved generalizability compared to personalized FL algorithms. On average, FedBN had the best rank performance on internal and external validation. Conclusion: FedAvg can significantly improve the generalization of the model compared to other personalization FL algorithms; however, at the cost of poor internal validity. Personalized FL may offer an opportunity to develop both internal and externally validated algorithms.

Original languageEnglish (US)
Pages (from-to)54-63
Number of pages10
JournalJournal of the American Medical Informatics Association
Issue number1
StatePublished - Jan 1 2023

Bibliographical note

Publisher Copyright:
© The Author(s) 2022. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com.


  • COVID-19
  • artificial intelligence
  • computer vision
  • federated learning

PubMed: MeSH publication types

  • Journal Article
  • Research Support, U.S. Gov't, P.H.S.
  • Research Support, N.I.H., Extramural
  • Research Support, U.S. Gov't, Non-P.H.S.


Dive into the research topics of 'Evaluation of federated learning variations for COVID-19 diagnosis using chest radiographs from 42 US and European hospitals'. Together they form a unique fingerprint.

Cite this