Coronary Heart Disease Prognosis Using Machine-Learning Techniques on Patients With Type 2 Diabetes Mellitus

Abstract

Heart diseases and stroke are the number one cause of death and disability among people with type 2 diabetes (T2D). Clinicians and health authorities for many years have expressed interest in identifying individuals at increased risk of coronary heart disease (CHD). Our main objective is to develop a prognostic workflow of CHD in T2D patients using a Holter dataset. This workflow development will be based on machine learning techniques by testing a variety of classifiers and subsequent selection of the best performing system. It will also assess the impact of feature selection and bootstrapping techniques over these systems. Among a variety of classifiers such as Naive Bayes (NB), Random Forest (RF), Support Vector Machine (SVM), Alternating Decision Tree (ADT), Random Tree (RT) and K-Nearest Neighbour (KNN), the best performing classifier is NB. We achieved an area under receiver operating characteristics curve (AUC) of 68,06% and 74,33% for a prognosis of 3 and 4 years, respectively.

Developing a Clinical Decision Support System for Prediction Postoperative Coronary Artery Bypass Grafting Infection in Diabetic Patients

“…The use of machine learning algorithms is very sensitive and specific to the diagnosis of coronary artery disease [21,22]. Pimentel et al pointed out the important and effective role of machine learning algorithms in the early detection of coronary heart disease in patients with diabetes [23].…”