Machine Learning for Comorbidity Prediction: Diabetes and Cardiovascular Disease

This research focuses on the extent to which machine learning systems can help determine the risk of cardiovascular disease (CVD) based on diabetes status. So far, we have used extensive data to identify diabetics. After that, diagnosis of presence of CVD on separate diabetic-positive and diabetic-negative populations was done using Support Vector Classifier (SVC), Naive Bayes (NB), Decision Tree (DT), and Random Forest algorithms. The method above is to see how these models compared in prediction of different diabetes subgroups. We focused on assessing the applicability of these models to develop targeted risk assessment for CVD by examining the performance of each algorithm on the diabetic-positive and diabetic-negative groups.