Predictive Model for CAD in Diabetic Patients using Machine Learning Models

Abstract

Machine Learning and Deep Learning methods are applied to diagnose diseases and give a better insight to understand them, whether it is through predictive modeling or reducing the dimensions of feature space. There was utilization of various ML and DL algorithms on Diabetes patients to produce binary classification on Coronary Artery Disease (CAD). Here a deduced relationship between various features with Coronary Artery Disease (CAD) was established. There was utilization of various data preprocessing techniques and created classifiers using Logistic Regression, Random Forest Classifier, Support Vector Machine, Naive Bayes and Artificial Neural Networks (ANN). The best classifier is chosen which gave the best results based on the calculation of sensitivity, specificity and accuracy which has been computed using Confusion Matrix. These results can help Diabetic Patients in early detection of Coronary Artery Disease (CAD) and ways to avoid developing it to acute levels.