{"ID":2888659,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.22963","arxiv_id":"2507.22963","title":"FedCVD++: Communication-Efficient Federated Learning for Cardiovascular Risk Prediction with Parametric and Non-Parametric Model Optimization","abstract":"Cardiovascular diseases (CVD) cause over 17 million deaths annually worldwide, highlighting the urgent need for privacy-preserving predictive systems. We introduce FedCVD++, an enhanced federated learning (FL) framework that integrates both parametric models (logistic regression, SVM, neural networks) and non-parametric models (Random Forest, XGBoost) for coronary heart disease risk prediction. To address key FL challenges, we propose: (1) tree-subset sampling that reduces Random Forest communication overhead by 70%, (2) XGBoost-based feature extraction enabling lightweight federated ensembles, and (3) federated SMOTE synchronization for resolving cross-institutional class imbalance. Evaluated on the Framingham dataset (4,238 records), FedCVD++ achieves state-of-the-art results: federated XGBoost (F1 = 0.80) surpasses its centralized counterpart (F1 = 0.78), and federated Random Forest (F1 = 0.81) matches non-federated performance. Additionally, our communication-efficient strategies reduce bandwidth consumption by 3.2X while preserving 95% accuracy. Compared to existing FL frameworks, FedCVD++ delivers up to 15% higher F1-scores and superior scalability for multi-institutional deployment. This work represents the first practical integration of non-parametric models into federated healthcare systems, providing a privacy-preserving solution validated under real-world clinical constraints.","short_abstract":"Cardiovascular diseases (CVD) cause over 17 million deaths annually worldwide, highlighting the urgent need for privacy-preserving predictive systems. We introduce FedCVD++, an enhanced federated learning (FL) framework that integrates both parametric models (logistic regression, SVM, neural networks) and non-parametri...","url_abs":"https://arxiv.org/abs/2507.22963","url_pdf":"https://arxiv.org/pdf/2507.22963v2","authors":"[\"Abdelrhman Gaber\",\"Hassan Abd-Eltawab\",\"John Elgallab\",\"Youssif Abuzied\",\"Dineo Mpanya\",\"Turgay Celik\",\"Swarun Kumar\",\"Tamer ElBatt\"]","published":"2025-07-30T06:17:33Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"q-bio.OT\"]","methods":"[]","has_code":false}