Predicting major adverse cardiovascular events during hospitalization in patients with acute myocardial infarction after percutaneous coronary intervention: Development and validation of a nomogram

Abstract

Objectives: The risk of major adverse cardiovascular events (MACE) after percutaneous coronary intervention (PCI) is extremely high, and directly affects the early cardiac recovery and quality of life of patients. This study aimed to explore risk factors for MACE in patients with acute myocardial infarction (AMI) after PCI and to develop and validate a risk nomogram model.

Methodology: Clinical data of 396 AMI patients who underwent PCI in the Affiliated Hospital of Jiangnan University from July 2022 to July 2024 were retrospectively selected. Patients were divided into training (n=277) and validation (n=119) cohorts based on a 7:3 ratio. The data were analyzed using the Least Absolute Shrinkage and Selection Operator (LASSO) and logistic regression, and the results were transformed into a predictive nomogram. Receiver operating characteristic (ROC) curves were drawn to evaluate the efficacy of the nomogram model and calculate the area under the curve (AUC), as well as the calibration curve and clinical decision curve (DCA).

Results: The incidence of MACE was 21.2% (84/396). The identified significant predictors included no-reflow, thrombolysis in myocardial infarction (TIMI) grading, mean platelet volume and lymphocyte ratio (MPVLR), neutrophil to lymphocyte ratio (NLR), and levels of hypersensitive C-reactive protein (hs-CRP) and brain natriuretic peptide (BNP). The generated nomogram model demonstrated sufficient predictive accuracy, with AUC values of 0.961 (95% CI: 0.929-0.994) and 0.951 (95% CI: 0.894-1.000) for the training and validation cohorts, respectively. The calibration curve showed that the model’s predicted values are generally consistent with the actual values, indicating good calibration. DCA further confirmed that the predictive model has good clinical utility.

Conclusions: The risk prediction nomogram model developed in this study has good predictive performance and applicability for MACE during hospitalization.