Predictive nomogram for coronary heart disease in patients with type 2 diabetes mellitus

OBJECTIVE: This study aimed to identify risk factors for coronary heart disease (CHD) in patients with type 2 diabetes mellitus (T2DM), build a clinical prediction model, and draw a nomogram. STUDY DESIGN AND METHODS: Coronary angiography was performed for 1,808 diabetic patients who were recruited at the department of cardiology in The Second Affiliated Hospital of Nanchang University from June 2020 to June 2022. After applying exclusion criteria, 560 patients were finally enrolled in this study and randomly divided into training cohorts (n = 392) and validation cohorts (n = 168). The least absolute shrinkage and selection operator (LASSO) is used to filter features in the training dataset. Finally, we use logical regression to establish a prediction model for the selected features and draw a nomogram. RESULTS: The discrimination, calibration, and clinical usefulness of the prediction model were evaluated using the c-index, receiver operating characteristic (ROC) curve, calibration chart, and decision curve. The effects of gender, diabetes duration, non-high-density lipoprotein cholesterol, apolipoprotein A1, lipoprotein (a), homocysteine, atherogenic index of plasma (AIP), nerve conduction velocity, and carotid plaque merit further study. The C-index was 0.803 (0.759–0.847) in the training cohort and 0.775 (0.705–0.845) in the validation cohort. In the ROC curve, the Area Under Curve (AUC) of the training set is 0.802, and the AUC of the validation set is 0.753. The calibration curve showed no overfitting of the model. The decision curve analysis (DCA) demonstrated that the nomogram is effective in clinical practice. CONCLUSION: Based on clinical information, we established a prediction model for CHD in patients with T2DM.