Heart disease is a globally pervasive health issue, with early detection and precise prognosis being imperative for improving patient outcomes and abating healthcare costs. One promising approach to predicting heart disease is through the use of machine learning models that analyse patient data. The application of machine learning models has exhibited tremendous potential in predicts heart disease by analysing patient data. In this manuscript, we scrutinize the performance of different machine learning models in predict the heart disease using a heart disease dataset. Machine learning offers a more innovative and precise approach by leveraging large amounts of patient data to predict the possibility of developing heart disease in new patients. We carry out a comprehensive comparison of various models, including decision trees, logistic regression, random forests, support vector machines, and so on, in terms of their accuracy, precision, recall, F1-score, and area under the ROC curve. Our findings divulge that the NAVIE BAYE’S model attains the highest accuracy of 92.46% in predicting heart disease.