A Novel Approach for Heart Disease Prediction Using Ensemble Machine Learning Techniques

Heart disorders remain a leading cause of global mortality, driven by various factors such as genetics, elevated cholesterol, hypertension, diabetes, tobacco use, and unhealthy lifestyles. Early detection and continuous monitoring are crucial to reducing fatalities, but challenges persist due to limited medical consultations and daily monitoring constraints. In this work, we introduce the Cascading Heart Disease Identifier (CHDI) approach, representing a novel advancement in predictive modeling. Utilizing ensemble learning principles, CHDI concatenates multiple classifiers, leveraging output information from preceding classifiers to enhance subsequent predictions. Our methodology incorporates a diverse range of machine learning techniques, including voting ensemble classifiers to construct prediction models. The purpose of our study is to evaluate how well health indicators can predict cardiac disease.The CHDI Algorithm exemplifies how machine learning can significantly contribute to early disease detection, thus fostering improved healthcare outcomes. The CHDI model’s predictive performance has been greatly improved by reaching a higher accuracy of 93.4