Cardiovascular Health in AI: A Comprehensive Overview to Acute Myocardial Infarction Prediction

Considering cardiovascular difficulties as the primary cause of worldwide mortality, authors examined learning models for predicting acute myocardial infarction (AMI) with the highest possible rate of accuracy, precision and other performance metrics. Prediction of the acute myocardial infarction is developed using Machine Learning (ML) algorithms such as: Multilayer perceptron (MLP), Support Vector Machine (SVM), XGBoost, and Naive Bayes (NB). Accuracy higher than 80% is expected for correct predictions of infarction. The models of examined studies are mostly tested in the Python programming language. The importance of this research lies in its commitment to achieving scientific and experimental validation by considering all the essential factors necessary for a rigorous and credible scientific paper. By employing exploratory data analysis (EDA) on input parameters, various models are constructed, and the best feasible prediction models for AMI are presented, which may be further enhanced by integrating more specific risk variables.