Enhancing the Performance of Heart Disease Prediction Models with Ensemble Learning

Heart disease is one of the main causes of death worldwide; rendering early and accurate detection is crucial for efficient care. The research presented here suggests a clinical and demographic data-driven machine learning strategy for predicting the existence of heart disease in patients. Several classification techniques, including logistic regression, decision trees, K-nearest neighbors, and support vector machines, were implemented within the ensemble framework by using a publicly accessible dataset of patient information. Metrics like accuracy, precision, recall, and F1 score have been employed to evaluate the performance of the proposed model. The suggested ensemble model’s highest accuracy of 94.95% demonstrated its promise as an important tool for heart disease early diagnosis and therapy.