Model Evaluation of Various Supervised Machine Learning Algorithm for Heart Disease Prediction

Machine Learning (ML) is a type of Artificial Intelligence (Al) that allows the machine to learn from data and become more accurate in predicting outcomes without human intervention. The fundamental idea of machine learning is to mimic the way our brain works. In a variety of application domains, including medicine and healthcare, ML techniques have demonstrated strong prediction abilities. This study evaluated and compared several popular supervised machine learning techniques for predicting heart diseases using medical records from the UCI Machine learning repository. The performance of different models, including Support Vector Machines (SVM), K-Nearest Neighbor (KNN), and Logistic Regression models, is examined in this paper. The performance of these algorithms was analyzed based on the (Area Under ROC Curve) AUC score. AUC is an evaluation metric that helps us validate our machine learning algorithm how good it is, and the decision is made to implement if the AUC score is more significant than 0.5. The trial result verifies that the Logistic regression algorithm has achieved the highest AUC score of 0.87 compared to other ML algorithms.