COLA-GLM: collaborative one-shot and lossless algorithms of generalized linear models for decentralized observational healthcare data

COLA-GLM: collaborative one-shot and lossless algorithms of generalized linear models for decentralized observational healthcare data

Abstract Clinical insights from real-world data often require aggregating information from institutions to ensure sufficient sample sizes and generalizability. However, patient privacy concerns only limit the sharing of patient-level data, and traditional federated learning algorithms, relying on ex...

Full description

Saved in:
Bibliographic Details
Main Authors: Qiong Wu, Jenna M. Reps, Lu Li, Bingyu Zhang, Yiwen Lu, Jiayi Tong, Dazheng Zhang, Thomas Lumley, Milou T. Brand, Mui Van Zandt, Thomas Falconer, Xing He, Yu Huang, Haoyang Li, Chao Yan, Guojun Tang, Andrew E. Williams, Fei Wang, Jiang Bian, Bradley Malin, George Hripcsak, Martijn J. Schuemie, Yun Lu, Steve Drew, Jiayu Zhou, David A. Asch, Yong Chen
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:npj Digital Medicine
Online Access:https://doi.org/10.1038/s41746-025-01781-1
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Abstract Clinical insights from real-world data often require aggregating information from institutions to ensure sufficient sample sizes and generalizability. However, patient privacy concerns only limit the sharing of patient-level data, and traditional federated learning algorithms, relying on extensive back-and-forth communications, can be inefficient to implement. We introduce the Collaborative One-shot Lossless Algorithm for Generalized Linear Models (COLA-GLM), a novel federated learning algorithm that supports diverse outcome types via generalized linear models and achieves results identical to a pooled patient-level data analysis (lossless) with only a single round of aggregated data exchange (one-shot). To further protect aggregated institutional data, we developed a secure extension, secure-COLA-GLM, utilizing homomorphic encryption. We demonstrated the effectiveness and lossless property of COLA-GLM through applications to an international influenza cohort and a decentralized U.S. COVID-19 mortality study. COLA-GLM and secure-COLA-GLM offer a scalable, efficient solution for decentralized collaborative learning involving multiple data partners and diverse security requirements.
ISSN:2398-6352

Similar Items