FedCVD++: Communication-Efficient Federated Learning for Cardiovascular Risk Prediction with Parametric and Non-Parametric Model Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gaber, Abdelrhman, Abd-Eltawab, Hassan, Elgallab, John, Abuzied, Youssif, Mpanya, Dineo, Celik, Turgay, Kumar, Swarun, ElBatt, Tamer
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917041047339008
author Gaber, Abdelrhman
Abd-Eltawab, Hassan
Elgallab, John
Abuzied, Youssif
Mpanya, Dineo
Celik, Turgay
Kumar, Swarun
ElBatt, Tamer
author_facet Gaber, Abdelrhman
Abd-Eltawab, Hassan
Elgallab, John
Abuzied, Youssif
Mpanya, Dineo
Celik, Turgay
Kumar, Swarun
ElBatt, Tamer
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_22963
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FedCVD++: Communication-Efficient Federated Learning for Cardiovascular Risk Prediction with Parametric and Non-Parametric Model Optimization
Gaber, Abdelrhman
Abd-Eltawab, Hassan
Elgallab, John
Abuzied, Youssif
Mpanya, Dineo
Celik, Turgay
Kumar, Swarun
ElBatt, Tamer
Machine Learning
Other Quantitative Biology
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.
title FedCVD++: Communication-Efficient Federated Learning for Cardiovascular Risk Prediction with Parametric and Non-Parametric Model Optimization
topic Machine Learning
Other Quantitative Biology
url https://arxiv.org/abs/2507.22963