Hybrid Multi-Model Fuzzy Ensemble Approach for Cardiovascular Diseases Detection

Abstract

Timely detection of cardiovascular diseases (CVDs) is crucial to reducing mortality rates. Recent advances in artificial intelligence (AI) and machine learning (ML) models for CVD detection often suffer from low model performance and hence lower accuracy and practicality of early CVD detection. In this study, we propose a novel hybrid ensemble learning framework that combines multiple ML algorithms and a fuzzy expert system to improve CVD diagnosis and prediction accuracy. We evaluate our proposed method on two standard datasets, namely the UCI Cleveland and Framingham, and compare it with four popular ensemble algorithms, namely Random Forest, Gradient Boosting, eXtreme Gradient Boosting, and Adaptive Boosting. Our results demonstrate that the proposed ensemble learning framework achieves higher accuracies of 91.2% (UCI Cleveland) and 91.7% (Framingham), surpassing existing algorithms by 3.3% and 8.8%, respectively.