Prediction of ischemic heart disease in patients with diabetes mellitus: Machine learning study on population data

Objective: The main symptom of ischemic heart disease (IHD) is chest pain and diabetic patients are likely to not perceive chest pain due to neuropathy. Therefore, the prediction of IHD in patients with diabetes mellitus is crucial. In this study, we aimed to predict IHD in patients with diabetes mellitus using various machine learning techniques. Additionally, we aimed to interpret the machine learning model. Materials and Methods: We used eXtreme Gradient Boosting (XGBoost), logistic regression, Multi-Layer Perceptron (MLP), random forest, decision tree and K-Nearest Neighbors (KNN) algorithms to predict IHD in patients with diabetes mellitus. Additionally, we used the SHapley Additive exPlanations (SHAP) method to interpret our machine learning model. Results: According to performance analysis, the XGBoost model had a superior performance with 0.814 area under the curve (AUC) on the training set and 0.795 AUC on the test set. The Brier score of the XGBoost model was 0.153. SHAP analysis results showed that the presence of hypertension has the highest contribution to the presence of IHD in patients with diabetes mellitus. Conclusion: Machine learning has the potential to provide decision support to clinicians in the identification of IHD in patients with diabetes mellitus.