Development and validation of an in-hospital major adverse cardiovascular events risk model for young patients with acute coronary syndrome: a retrospective cohort study

Abstract

Background: The incidence of acute coronary syndrome (ACS) among young individuals is increasing, making it a leading cause of mortality in this population. This study aimed to develop and validate a risk prediction model for in-hospital major adverse cardiovascular events (MACE) in young ACS patients. Methods: A retrospective analysis was performed to predict in-hospital MACE. Patients were divided into a training set (n = 342) and a testing set (n = 171). Screening variables were optimized using least absolute shrinkage and selection operator (LASSO) regression and univariable logistic regression analysis. A predictive nomogram model was developed through multivariate logistic regression. The model’s discrimination and calibration were assessed using the receiver operating characteristic (ROC) curve, calibration plots, and Hosmer-Lemeshow goodness-of-fit tests. Clinical utility was evaluated using decision curve analysis (DCA). Results: White blood cell count, Killip classification, lymphocyte count, heart rate, triglycerides, and Gensini score were identified as significant predictors. The constructed nomogram demonstrated strong predictive performance. The area under the ROC curve (AUC) was 0.9242 (95% confidence interval [CI]: [0.8841–0.9643]) for the training set and 0.8346 (95% CI [0.742–0.9272]) for the testing set, with respective cut-off values of 0.107 and 0.119. Calibration was confirmed with Hosmer-Lemeshow statistics of 12.454 (p = 0.2558) in the training set and 7.16 (p = 0.7102) in the testing set. DCA showed threshold probabilities ranging from 0% to 100% in the training set and 0% to 90% in the testing set. Conclusions: The proposed nomogram model demonstrated robust discrimination and calibration, offering a valuable tool for predicting the risk of in-hospital MACE in young ACS patients.