Abstract:Objective To analyze the factors related to the severity of coronary artery disease (CAD) in type 2 diabetes mellitus (T2DM) patients, with the aim of providing a reference for the risk assessment of them. Methods Clinical data of 322 T2DM patients combined with CAD admitted to Jinan City People's Hospital from January 2019 to May 2023 were retrospectively analyzed. They were divided into the mild group (Gensini score≤54, n=177) and the moderate to severe group (Gensini score＞54, n=145) based on the Gensini score. The clinical data of age, gender, and blood indexes between the two groups were compared. Least absolute shrinkage and selection operator (LASSO) and logistic regression analysis were used to screen for factors correlated with the severity of CAD in T2DM patients. The prediction model was established, the model calibration curve and the receiver operating characteristic curve (ROC) were drawn, and the area under the curve (AUC) was calculated to evaluate its accuracy. Results Age, total cholesterol, fasting blood glucose, remnant cholesterol and lipoprotein (a) levels were higher in the moderate to severe CAD in the mild group (P＜0.05).For patients with moderate to severe coronary artery lesions in T2DM, the multivariate logistic regression analysis showed that age, residual cholesterol and serum lipoprotein (a) levels were independent risk factors (P＜0.05). LASSO regression showed age (Z=3.251, P=0.001), residual cholesterol (Z=2.565, P=0.010) and serum lipoprotein (a) levels (Z=7.989, P＜0.001) were independent predictor of T2MD patients with moderate to serve CAD, 〖JP+1〗and the column chart prediction model constructed from the above factors had good accuracy (AUC=0.826). Conclusion Age, remnant cholesterol and lipoprotein (a) levels can effectively predict the severity of CAD in T2DM patients, and have good accuracy.