A Robust Framework for Secure Cardiovascular Risk Prediction: An Architectural Case Study of Differentially Private Federated Learning

arXiv cs.LG / 3/17/2026

📰 NewsDeveloper Stack & InfrastructureModels & Research

共有:

Key Points

FedCVR is a privacy-preserving federated learning framework for cardiovascular risk prediction across multiple clinical institutions.
Instead of proposing a new optimizer, the work conducts a systems engineering analysis to quantify the trade-offs of server-side adaptive optimization under utility-prioritized differential privacy.
The study shows that adding server-side momentum as a temporal denoiser yields a stable F1-score of 0.84 and an AUC of 0.96 in a high-fidelity synthetic environment calibrated to Framingham and Cleveland data.
The findings indicate that server-side adaptivity is a structural prerequisite for recovering clinical utility under realistic privacy budgets and offer an engineering blueprint for secure multi-institution collaboration.

Abstract

Accurate cardiovascular risk prediction is crucial for preventive healthcare; however, the development of robust Artificial Intelligence (AI) models is hindered by the fragmentation of clinical data across institutions due to stringent privacy regulations. This paper presents a comprehensive architectural case study validating the engineering robustness of FedCVR, a privacy-preserving Federated Learning framework applied to heterogeneous clinical networks. Rather than proposing a new theoretical optimizer, this work focuses on a systems engineering analysis to quantify the operational trade-offs of server-side adaptive optimization under utility-prioritized Differential Privacy (DP). By conducting a rigorous stress test in a high-fidelity synthetic environment calibrated against real-world datasets (Framingham, Cleveland), we systematically evaluate the system's resilience to statistical noise. The validation results demonstrate that integrating server-side momentum as a temporal denoiser allows the architecture to achieve a stable F1-score of 0.84 and an Area Under the Curve (AUC) of 0.96, statistically outperforming standard stateless baselines. Our findings confirm that server-side adaptivity is a structural prerequisite for recovering clinical utility under realistic privacy budgets, providing a validated engineering blueprint for secure multi-institutional collaboration.