Aim To investigate the related influencing factors of major adverse cardiovascular events (MACE) in coronary heart disease (CHD) patients with type 2 diabetes mellitus (T2DM) based on prognostic nutritional index (PNI), and to construct a prediction model. Methods The clinical data of 391 patients with CHD combined with T2DM who were hospitalised in the Department of Cardiovascular Medicine of Hebei Provincial People's Hospital from January 2022 to January 2023 were collected and followed up for 1 year, and were divided into the MACE group (n＝99) and the non-MACE group (n＝292) according to the presence or absence of the occurrence of MACE, and were divided into the training set (n＝273) and the validation set (n＝118) in a ratio of 7∶3 by using the computer-generated random number method, and the patients in the training set were divided into the MACE (n＝67) group and the non-MACE group (n＝206) according to whether they had MACE or not. Lasso regression was used to screen the relevant influencing factors and to construct the prediction model of the column-line diagram, and the prediction model was validated by plotting receiver operating characteristic (ROC) curve, calibration curve, decision curve analysis (DCA), and clinical impact curve (CIC). Results Lasso regression showed that the use of angiotensin receptor neprilysin inhibitor (ARNI), fasting blood glucose (FBG), C-reactive protein (CRP), platelet to lymphocyte ratio (PLR), lipoprotein(a) (Lp(a), and PNI were the predictors of the occurrence of MACE in patients with CHD combined with T2DM. A column-line graph prediction model was constructed and validated based on the above predictors, and the area under the ROC curve (AUC) was 0.838(95%CI:0.778～0.898) in the training set and 0.872(95%CI:0.803～0.942) in the validation set, with a good discriminatory degree of the model, and the C-values of the calibration curves in the training set and the validation set were 0.838 and 0.872, respectively, with good fit. The results of the decision curve analysis and the clinical impact curve showed that the column-line graph prediction model had a higher net yield of MACE in patients with CHD combined with T2DM, with high clinical utility. Conclusion PNI is an influential factor in the occurrence of MACE in patients with CHD combined with T2DM, and the column-line graphical model constructed on the basis of predictors such as PNI is convenient for clinical use and has high predictive value in predicting the occurrence of MACE in patients with CHD combined with T2DM.