Hybrid Federated and Split Learning for Privacy Preserving Clinical Prediction and Treatment Optimization
🤖 AI Summary
This work addresses the challenge of cross-institutional clinical collaboration under stringent privacy regulations that restrict sharing of raw patient data. The authors propose a hybrid architecture integrating federated and split learning, wherein feature extraction modules reside on client devices while the prediction head is hosted on a coordinating server. At the split layer, they introduce a tunable privacy–utility trade-off mechanism, lightweight defenses—including activation clipping and Gaussian noise injection—and privacy auditing capabilities. This design explicitly delineates collaboration boundaries and enables fine-grained privacy control. Experiments across three non-IID clinical datasets demonstrate that the proposed method consistently outperforms existing approaches in terms of predictive performance, decision-ranking capability under resource constraints, resilience against privacy leakage, and communication efficiency.
Application Category
📝 Abstract
Collaborative clinical decision support is often constrained by governance and privacy rules that prevent pooling patient-level records across institutions. We present a hybrid privacy-preserving framework that combines Federated Learning (FL) and Split Learning (SL) to support decision-oriented healthcare modeling without raw-data sharing. The approach keeps feature-extraction trunks on clients while hosting prediction heads on a coordinating server, enabling shared representation learning and exposing an explicit collaboration boundary where privacy controls can be applied. Rather than assuming distributed training is inherently private, we audit leakage empirically using membership inference on cut-layer representations and study lightweight defenses based on activation clipping and additive Gaussian noise. We evaluate across three public clinical datasets under non-IID client partitions using a unified pipeline and assess performance jointly along four deployment-relevant axes: factual predictive utility, uplift-based ranking under capacity constraints, audited privacy leakage, and communication overhead. Results show that hybrid FL-SL variants achieve competitive predictive performance and decision-facing prioritization behavior relative to standalone FL or SL, while providing a tunable privacy-utility trade-off that can reduce audited leakage without requiring raw-data sharing. Overall, the work positions hybrid FL-SL as a practical design space for privacy-preserving healthcare decision support where utility, leakage risk, and deployment cost must be balanced explicitly.
Problem
Research questions and friction points this paper is trying to address.
privacy-preserving
clinical prediction
treatment optimization
federated learning
split learning
Innovation
Methods, ideas, or system contributions that make the work stand out.
Hybrid Federated Learning
Split Learning
Privacy-Preserving Healthcare
Membership Inference Attack
Non-IID Clinical Data
🔎 Similar Papers
No similar papers found.
