Development of a Risk Prediction Model for Major Adverse Cardiovascular Events After PCI in Patients with Coronary Heart Disease

OBJECTIVE: To identify predictors of major adverse cardiovascular events (MACE) after percutaneous coronary intervention (PCI) in coronary heart disease (CHD) patients and construct a risk prediction model to identify high-risk patients and optimize postoperative management. METHODS: A single-center retrospective study enrolled 500 CHD patients who underwent PCI at Hangzhou TCM Hospital between April 2021 and October 2022. Data on demographics, laboratory results, imaging parameters, and postoperative outcomes were collected. Variables were selected using LASSO regression, and a predictive model was built with the Cox proportional hazard model. Model performance was assessed with AUC, Brier score, sensitivity (TP), specificity (TN), positive predictive value (PPV), and negative predictive value (NPV), and visualized using a column-line plot. RESULTS: The 1-, 2-, and 3-year MACE rates were 32.8%, 37.0%, and 37.4%, respectively. Eleven independent predictors were identified, and the AUCs for 1-, 2-, and 3-year MACE predictions in the test set were 0.754 (95% CI: 0.661-0.847), 0.747 (0.630-0.864), and 0.771 (0.546-0.996), outperforming traditional scores. The model effectively stratified risk (log-rank P<0.05). Calibration curves showed high agreement between predicted and actual risks (Brier score<0.25), and decision curve analysis (DCA) indicated significant clinical benefit. CONCLUSION: This study provides robust evidence for the accurate management of post-PCI patients, enhancing predictive efficacy, risk stratification, and clinical applicability through multidimensional data integration, advanced variable selection, and visualization tools.