Evaluation of Machine Learning Model’s Accuracy for Heart Attack Prediction

Abstract

Machine learning is a type of artificial intelligence that allows applications to become more accurate at predicting results without being explicitly programmed to do so. Machine learning techniques such as Decision tree, K-Nearest Neighbors (KNN), Naïve Bayes, Support Vector Machine (SVM), Logistic Regression, Multi layer perceptron etc, are used to predict the heart attack. These studies offers an analysis of the existing machine learning algorithm and provides a comprehensive overview of the previous research and evaluate the accuracy of the machine learning modals. Both low and high-risk patients for a heat attack were evaluated for the study. The results indicate that methods Logistic Regression and Support Vector Machine algorithms outperform other traditional classifiers in terms of prediction accuracy and generalization.