Inclusive, Differentially Private Federated Learning for Clinical Data

TL;DR

This paper introduces a compliance-aware federated learning framework that adaptively adjusts differential privacy noise based on client compliance, improving model accuracy and inclusivity in clinical data applications.

Contribution

It proposes a novel adaptive noise mechanism and a compliance scoring tool to enhance privacy, security, and participation fairness in federated learning for healthcare.

Findings

Up to 15% accuracy improvement when including less compliant clinics

Enhanced privacy and security through compliance-aware noise adjustment

Promotes equitable participation across diverse clinical settings

Abstract

Federated Learning (FL) offers a promising approach for training clinical AI models without centralizing sensitive patient data. However, its real-world adoption is hindered by challenges related to privacy, resource constraints, and compliance. Existing Differential Privacy (DP) approaches often apply uniform noise, which disproportionately degrades model performance, even among well-compliant institutions. In this work, we propose a novel compliance-aware FL framework that enhances DP by adaptively adjusting noise based on quantifiable client compliance scores. Additionally, we introduce a compliance scoring tool based on key healthcare and security standards to promote secure, inclusive, and equitable participation across diverse clinical settings. Extensive experiments on public datasets demonstrate that integrating under-resourced, less compliant clinics with highly regulated institutions yields accuracy improvements of up to 15% over traditional FL. This work advances FL by balancing privacy, compliance, and performance, making it a viable solution for real-world clinical workflows in global healthcare.