Faculty, Staff and Student Publications
Language
English
Publication Date
2-5-2025
Journal
Nature Communications
DOI
10.1038/s41467-025-56510-9
PMID
39910076
PMCID
PMC11799213
PubMedCentral® Posted Date
2-5-2025
PubMedCentral® Full Text Version
Post-print
Abstract
Quality improvement, clinical research, and patient care can be supported by medical predictive analytics. Predictive models can be improved by integrating more patient records from different healthcare centers (horizontal) or integrating parts of information of a patient from different centers (vertical). We introduce Distributed Cross-Learning for Equitable Federated models (D-CLEF), which incorporates horizontally- or vertically-partitioned data without disseminating patient-level records, to protect patients' privacy. We compared D-CLEF with centralized/siloed/federated learning in horizontal or vertical scenarios. Using data of more than 15,000 patients with COVID-19 from five University of California (UC) Health medical centers, surgical data from UC San Diego, and heart disease data from Edinburgh, UK, D-CLEF performed close to the centralized solution, outperforming the siloed ones, and equivalent to the federated learning counterparts, but with increased synchronization time. Here, we show that D-CLEF presents a promising accelerator for healthcare systems to collaborate without submitting their patient data outside their own systems.
Keywords
Humans, California, COVID-19, SARS-CoV-2, Hospitals, Privacy, Electronic Health Records, Confidentiality, Experimental models of disease, Outcomes research
Published Open-Access
yes
Recommended Citation
Kuo, Tsung-Ting; Gabriel, Rodney A; Koola, Jejo; et al., "Distributed Cross-Learning for Equitable Federated Models – Privacy-Preserving Prediction on Data From Five California Hospitals" (2025). Faculty, Staff and Student Publications. 950.
https://digitalcommons.library.tmc.edu/uthshis_docs/950