Split Learning for Distributed Collaborative Training of Deep Learning Models in Health Informatics.

Autor:	Li Z; Vanderbilt University, Nashville, TN., Yan C; Vanderbilt University Medical Center, Nashville, TN., Zhang X; Vanderbilt University, Nashville, TN., Gharibi G; TripleBlind, Kansas City, MO., Yin Z; Vanderbilt University, Nashville, TN.; Vanderbilt University Medical Center, Nashville, TN., Jiang X; UTHealth, Houston, TX., Malin BA; Vanderbilt University, Nashville, TN.; Vanderbilt University Medical Center, Nashville, TN.
Jazyk:	angličtina
Zdroj:	AMIA ... Annual Symposium proceedings. AMIA Symposium [AMIA Annu Symp Proc] 2024 Jan 11; Vol. 2023, pp. 1047-1056. Date of Electronic Publication: 2024 Jan 11 (Print Publication: 2023).
Abstrakt:	Deep learning continues to rapidly evolve and is now demonstrating remarkable potential for numerous medical prediction tasks. However, realizing deep learning models that generalize across healthcare organizations is challenging. This is due, in part, to the inherent siloed nature of these organizations and patient privacy requirements. To address this problem, we illustrate how split learning can enable collaborative training of deep learning models across disparate and privately maintained health datasets, while keeping the original records and model parameters private. We introduce a new privacy-preserving distributed learning framework that offers a higher level of privacy compared to conventional federated learning. We use several biomedical imaging and electronic health record (EHR) datasets to show that deep learning models trained via split learning can achieve highly similar performance to their centralized and federated counterparts while greatly improving computational efficiency and reducing privacy risks. (©2023 AMIA - All rights reserved.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu