Cardiovascular Disease Detection Using Hybrid Ensemble Models

Abstract

Cardiovascular Diseases (CVDs) remain one of the primary causes of mortality worldwide, emphasizing the need for timely and accurate diagnostic approaches to reduce associated risks. This study explores the application of advanced Deep Learning (DL) and Machine Learning (ML) techniques to improve diagnostic accuracy. Unlike conventional ML methods that rely extensively on manual feature engineering, DL approaches enable automatic feature extraction, making them highly effective for analyzing complex datasets. Using the Heart Disease Dataset, the study addresses class imbalance through Adaptive Synthetic (ADASYN) Oversampling and introduces a novel ensemble-based detection framework. Extensive evaluation demonstrates that the Voting Classifier performs better than individual models. The findings highlight the effectiveness of ensemble techniques in managing diverse data conditions and achieving high diagnostic performance, thereby demonstrating their potential to significantly enhance CVD diagnosis.