Linear Federated Learning for Outcome Prediction With Application to Hepatocellular Carcinoma Radiotherapy
LFL maintained or improved predictive performance over single-institution models for survival and hepatic toxicity in patients with HCC treated with EBRT while preserving model interpretability and patient privacy. These findings support LFL's role in multi-institutional collaborations.
Authors
- Ibrahim M. Chamseddine (ORCID: https://orcid.org/0000-0002-7005-8692)
- Keyur D Shah (ORCID: https://orcid.org/0000-0002-0886-655X)
- Eugene J. Koay (ORCID: https://orcid.org/0000-0001-7675-3461)
- Harald Paganetti (ORCID: https://orcid.org/0000-0002-6257-2413)
- Theodore Sunki Hong (ORCID: https://orcid.org/0000-0001-8481-6581)
- Jennifer Yon-Li Wo (ORCID: https://orcid.org/0000-0001-9872-5912)
- Pablo Yepes
- Christian V. Guthier
- Jim Roberts
Institutions
- The University of Texas MD Anderson Cancer Center (US)
- Harvard University (US)
- Emory University (US)
- Mass General Brigham (US)
- Rice University (US)
Publication Details
- Journal
- JCO Clinical Cancer Informatics
- Published
- 2025-06-30
- DOI
- https://doi.org/10.1200/cci-25-00074
- Primary Topic
- Economic and Financial Impacts of Cancer
- Type
- article
- Field-Weighted Citation Impact
- 0.00