Unlocking multi-institutional insights into disease progression with PEAL as a lossless, one-shot federated learning solution
Yicheng Shen, Ji Soo Kim, Chongliang Luo, Scott L. Zeger, Robyn T. Domsic, Ami A. Shah, Jiayi Tong · 2026
Read Unlocking multi-institutional insights into disease progression with PEAL as a lossless, one-shot federated learning solution by Yicheng Shen, Ji Soo Kim, Chongliang Luo, Scott L. Zeger, Robyn T. Domsic, Ami A. Shah, Jiayi Tong (2026) 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/PMC13639078.txt.
Description
Yicheng Shen and six colleagues introduce PEAL in 2026, a federated learning method for studying how diseases progress across hospitals without moving patient records. Privacy rules, transfer costs, and differences between sites make pooled health record analysis hard.
PEAL fits standard longitudinal models from a single round of summary statistics, yet returns results identical to pooling the raw data. Simulations confirmed its accuracy, and the team applied it to systemic sclerosis patients at two United States scleroderma centers, recovering sensible disease trajectories. The method offers research networks a private, efficient way to study rare diseases over time.
Catalog record
| CREATOR | Yicheng Shen, Ji Soo Kim, Chongliang Luo, Scott L. Zeger, Robyn T. Domsic, Ami A. Shah, Jiayi Tong |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 78307 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |