Inclusive, Differentially Private Federated Learning for Clinical Data
This work addresses privacy and performance challenges in federated learning for clinical AI, making it more viable for real-world healthcare applications, though it is incremental as it builds on existing differential privacy and federated learning approaches.
The paper tackled the problem of privacy and performance degradation in federated learning for clinical data by proposing a compliance-aware framework that adaptively adjusts differential privacy noise based on client compliance scores, resulting in accuracy improvements of up to 15% over traditional methods.
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.