The primary cause of death globally is heart disease. Millions of individuals throughout the world are impacted by this severe health issue. Enhancing early detection and preventive strategies can be achieved by utilizing machine learning to forecast cardiac disease. This study involved developing a machine learning model to predict heart disease risk by using medical data. Custom selection uses a process to analyze reported data when performing a sample evaluation using competitive and performance metrics such as sensitivity, specificity, accuracy, and F1 scores. Our study aims to develop a predictive model to detect heart disease. According to a comparative study of these models, random forest and decision tree are more accurate in predicting heart disease, with 100% accuracy.