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

CREATORYicheng Shen, Ji Soo Kim, Chongliang Luo, Scott L. Zeger, Robyn T. Domsic, Ami A. Shah, Jiayi Tong
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE78307
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13639078

Browse the full library · About the Tower of Babel