Author

Description

This is a general survey of the latest developments in predicting heart attacks by applying machine learning and deep learning. Combined effects of hyperglycemia, dyslipidemia, inflammation, and endothelial dysfunction increase myocardial infarction risk and accelerate atherosclerosis of these high-risk metabolic populations. This survey is a systematic review of conventional clinical risk models, machine learning, deep learning, and explainable artificial intelligence (XAI) techniques used to predict cardiovascular risks. Important clinical, metabolic, demographic, and lifestyle characteristics of predictive modeling are discussed, as well as the pathophysiology. The analysis also reviews the issues associated with data quality, imbalance in classes, generalization, bias, and ethical and regulatory issues.

Keywords

Cardiovascular Disease, Deep Learning, Heart Attack Prediction, Machine Learning