Machine Learning and Deep Learning in Predicting Coronary Heart Disease

Abstract

Coronary heart disease is the leading cause of morbidity and mortality worldwide. Current diagnostic tools for this disease are not well suited to monitoring response to treatment. In this article, machine learning model k-nearest neighbor (k-NN) and deep learning model artificial neural network (ANN) were used and compared to evaluate the risk of coronary heart disease. The Framingham dataset was used to apply the techniques mentioned above. In addition, the Hotdecking missing data filing method was also taken into consideration to prepare the dataset before applying machine learning and deep learning techniques. At the end of the data analysis, 85.50% accuracy was obtained for k-NN and 85.85% accuracy for ANN. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.