Prediction of Coronary Heart Disease using Supervised Machine Learning Algorithms

Abstract

New technologies like Machine learning and Big data analytics have been proven to provide promising solutions to biomedical communities, healthcare problems, and patient care. They also help in early prediction of disease by accurate interpretation of medical data. Disease management strategies can further be improved by the detection of early signs of disease. This early prediction, moreover, can be helpful in controlling the symptoms of the disease as well as the proper treatment of disease. Machine learning approaches can be used in the prediction of chronic diseases, such as kidney and heart diseases, by developing the classification models. In this paper, we propose a preprocessing extensive approach to predict Coronary Heart Diseases (CHD). The approach involves replacing null values, resampling, standardization, normalization, classification, and prediction. This work aims to predict the risk of CHD using machine learning algorithms like Random Forest, Decision Trees, and K-Nearest Neighbours. Also, a comparative study among these algorithms on the basis of prediction accuracy is performed. Further, $K$ -fold Cross Validation is used to generate randomness in the data. These algorithms are experimented over “Framingham Heart Study” dataset, which is having 4240 records. In our experimental analysis, Random Forest, Decision Tree, and K-Nearest Neighbour achieved an accuracy of 96.8%, 92.7%, and 92.89% respectively. Therefore, by including our preprocessing steps, Random Forest classification gives more accurate results than other machine learning algorithms.