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

doi:10.1093/jamia/ocac188

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

J Am Med Inform Assoc. 2022 Dec 13;30(1):54-63. doi: 10.1093/jamia/ocac188.

Authors

Le Peng¹, Gaoxiang Luo¹, Andrew Walker¹, Zachary Zaiman², Emma K Jones³, Hemant Gupta⁴, Kristopher Kersten⁵, John L Burns⁶, Christopher A Harle⁷, Tanja Magoc⁸, Benjamin Shickel^{9

10}, Scott D Steenburg¹¹, Tyler Loftus^{10

12}, Genevieve B Melton^{3

4

13

14}, Judy Wawira Gichoya¹⁵, Ju Sun¹, Christopher J Tignanelli^{3

13

14}

Affiliations

¹ Department of Computer Science and Engineering, University of Minnesota, Minneapolis, Minnesota, USA.
² Department of Computer Science, Emory University, Atlanta, Georgia, USA.
³ Department of Surgery, University of Minnesota, Minneapolis, Minnesota, USA.
⁴ Fairview Health Services, Minneapolis, Minnesota, USA.
⁵ Nvidia Corporation, Santa Clara, California, USA.
⁶ The School of Medicine, Indiana University, Indianapolis, Indiana, USA.
⁷ Department of Health Outcomes and Biomedical Informatics, University of Florida, Gainesville, Florida, USA.
⁸ University of Florida College of Medicine, Gainesville, Florida, USA.
⁹ Department of Medicine, University of Florida, Gainesville, Florida, USA.
¹⁰ Intelligent Critical Care Center, University of Florida, Gainesville, Florida, USA.
¹¹ Department of Radiology and Imaging Sciences, Indiana University School of Medicine, Indianapolis, Indiana, USA.
¹² Department of Surgery, University of Florida, Gainesville, Florida, USA.
¹³ Center for Learning Health System Sciences, University of Minnesota, Minneapolis, Minnesota, USA.
¹⁴ Institute for Health Informatics, University of Minnesota, Minneapolis, Minnesota, USA.
¹⁵ Department of Radiology, Emory University, Atlanta, Georgia, USA.

Abstract

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.

Keywords: COVID-19; artificial intelligence; computer vision; federated learning.

Publication types

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.

MeSH terms

COVID-19 Testing*
COVID-19*
Europe
Hospitals
Humans
Learning
United States

Abstract

Publication types

MeSH terms

Grants and funding