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

TL;DR

This paper presents a split learning framework that enables privacy-preserving, distributed training of deep learning models across healthcare organizations, achieving comparable performance to centralized models while enhancing privacy and efficiency.

Contribution

The paper introduces a novel split learning approach tailored for healthcare data, improving privacy and computational efficiency over federated learning.

Findings

Models trained via split learning achieve similar accuracy to centralized models.

Split learning significantly reduces privacy risks compared to federated learning.

The approach improves computational efficiency in distributed healthcare data training.

Abstract

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.