Distributed cross-learning for equitable federated models - privacy-preserving prediction on data from five California hospitals
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 cen...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-025-56510-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823861819659255808 |
|---|---|
| author | Tsung-Ting Kuo Rodney A. Gabriel Jejo Koola Robert T. Schooley Lucila Ohno-Machado |
| author_facet | Tsung-Ting Kuo Rodney A. Gabriel Jejo Koola Robert T. Schooley Lucila Ohno-Machado |
| author_sort | Tsung-Ting Kuo |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-8b0161200fde4bb6954aedde3780188b |
| institution | Kabale University |
| issn | 2041-1723 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj-art-8b0161200fde4bb6954aedde3780188b2025-02-09T12:45:55ZengNature PortfolioNature Communications2041-17232025-02-0116111710.1038/s41467-025-56510-9Distributed cross-learning for equitable federated models - privacy-preserving prediction on data from five California hospitalsTsung-Ting Kuo0Rodney A. Gabriel1Jejo Koola2Robert T. Schooley3Lucila Ohno-Machado4Department of Biomedical Informatics and Data Science, School of Medicine, Yale UniversityDivision of Biomedical Informatics, Department of Medicine, University of California San Diego, La JollaDivision of Biomedical Informatics, Department of Medicine, University of California San Diego, La JollaDivision of Infectious Diseases and Global Public Health, Department of Medicine, University of California San Diego, La JollaDepartment of Biomedical Informatics and Data Science, School of Medicine, Yale UniversityAbstract 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.https://doi.org/10.1038/s41467-025-56510-9 |
| spellingShingle | Tsung-Ting Kuo Rodney A. Gabriel Jejo Koola Robert T. Schooley Lucila Ohno-Machado Distributed cross-learning for equitable federated models - privacy-preserving prediction on data from five California hospitals Nature Communications |
| title | Distributed cross-learning for equitable federated models - privacy-preserving prediction on data from five California hospitals |
| title_full | Distributed cross-learning for equitable federated models - privacy-preserving prediction on data from five California hospitals |
| title_fullStr | Distributed cross-learning for equitable federated models - privacy-preserving prediction on data from five California hospitals |
| title_full_unstemmed | Distributed cross-learning for equitable federated models - privacy-preserving prediction on data from five California hospitals |
| title_short | Distributed cross-learning for equitable federated models - privacy-preserving prediction on data from five California hospitals |
| title_sort | distributed cross learning for equitable federated models privacy preserving prediction on data from five california hospitals |
| url | https://doi.org/10.1038/s41467-025-56510-9 |
| work_keys_str_mv | AT tsungtingkuo distributedcrosslearningforequitablefederatedmodelsprivacypreservingpredictionondatafromfivecaliforniahospitals AT rodneyagabriel distributedcrosslearningforequitablefederatedmodelsprivacypreservingpredictionondatafromfivecaliforniahospitals AT jejokoola distributedcrosslearningforequitablefederatedmodelsprivacypreservingpredictionondatafromfivecaliforniahospitals AT roberttschooley distributedcrosslearningforequitablefederatedmodelsprivacypreservingpredictionondatafromfivecaliforniahospitals AT lucilaohnomachado distributedcrosslearningforequitablefederatedmodelsprivacypreservingpredictionondatafromfivecaliforniahospitals |