AUTHOR=Xiao Shucai , Dong Youzheng , Huang Bin , Jiang Xinghua 

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

JOURNAL=Frontiers in Cardiovascular Medicine

VOLUME=Volume 9 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/cardiovascular-medicine/articles/10.3389/fcvm.2022.1052547

DOI=10.3389/fcvm.2022.1052547

ISSN=2297-055X

ABSTRACT=Abstract
Objective: This study aimed to study risk factors for coronary heart disease (CHD) in type 2 diabetes mellitus (T2DM) patients, built a clinical prediction model and drew a nomogram.
Research Design and Methods: Coronary angiography was performed in 1808 diabetic patients who were recruited at department of cardiology in The Second Affiliated Hospital of Nanchang University from June 2020 to June 2022.After applying exclusion criteria, a total of 560 patients were enrolled in this study, and randomly divided into training (n = 392) and validation cohorts (n = 168) at a ratio of 3:1.The least absolute shrinkage and selection operator (LASSO) was used to select features in the training set, and then, logistic regression analysis was conducted to establish the prediction models and drew a nomogram.
Results: 
The application of C-index, Receiver Operating Characteristic (ROC) curve, calibration chart, and decision curve analyses were used to assess the discrimination, calibration, and clinical practicability of the predictive model. 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 are important considerations for 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. Through ROC analysis, the set area was 0.802 for the training set and 0.753 for the validation set. In the training, test, and validation sets. The calibration curve also demonstrated good consistence between the prediction and the observation. The decision curve analysis (DCA) demonstrated that the nomogram was clinically useful.
Conclusion:
We established a prediction model of CHD in T2DM patients based on collected clinical information and data analyses.