Heart Disease Prediction with Machine Learning Models: Superior Performance of Support Vector Machines

Abstract

Heart disease results from long-term damage or inflammation affecting the heart and blood vessels, and it can impact individuals regardless of age, gender, or social background. Recent studies highlight approaches in identifying and predicting the risk of this condition. Such models estimate the probability of heart disease in percentage terms, enabling early detection and intervention. In this work, the dataset was processed using Python, and two primary algorithms Random Forest and Support Vector Machine (SVM) were applied for classification. While both methods produced promising outcomes, the SVM model achieved the highest performance, recording an accuracy of 95%. These results demonstrate the capability of machine learning techniques in enhancing the reliability of heart disease prediction.