Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data.
Sheller MJ, Edwards B, Reina GA, Martin J, Pati S, Kotrotsou A, Milchenko M, Xu W, Marcus D, Colen RR, Bakas S. · 2020
Read Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data. by Sheller MJ, Edwards B, Reina GA, Martin J, Pati S, Kotrotsou A, Milchenko M, Xu W, Marcus D, Colen RR, Bakas S. (2020) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/europmc-pmc7387485.txt.
Description
Sheller and co-authors demonstrate federated learning for medicine in Scientific Reports. Deep learning needs large, diverse datasets, but hospitals cannot freely pool patient data for privacy and ownership reasons. Federated learning instead sends the model to each hospital, trains locally, and merges only the learned updates.
Across 10 institutions, federated models reached 99 percent of the quality achieved by centralizing the data. The team also tested how models generalize to hospitals outside the federation, and how uneven data splits affect learning. The approach promises collaboration without surrendering records. Readers get a proof of concept for a privacy-preserving way to build medical AI at scale.
Catalog record
| CREATOR | Sheller MJ, Edwards B, Reina GA, Martin J, Pati S, Kotrotsou A, Milchenko M, Xu W, Marcus D, Colen RR, Bakas S. |
|---|---|
| YEAR | 2020 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 53 KB |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |