Abstract
BACKGROUND: This study aims to investigate the impact of clinical and electrocardiographic parameters on the prognosis of patients with acute ST-segment elevation myocardial infarction (STEMI) and develop a personalized nomogram model for predicting the risk of poor prognosis, thereby providing a reference tool for clinical risk assessment. METHODS: A total of 321 patients with STEMI admitted between January 2023 and November 2024 were enrolled in this study. Clinical data and electrocardiographic parameters, including left ventricular ejection fraction (LVEF), semaphorin 4D (Sema4D), QT dispersion (QTd), QRS duration, and corrected QT interval, were collected. Univariate analysis was performed to identify variables with significant differences, and a logistic regression model was constructed to predict prognosis. To optimize variable selection and avoid multicollinearity, least absolute shrinkage and selection operator regression was also applied. The discriminative ability of the model was evaluated using receiver operating characteristic curve analysis, and its predictive accuracy was assessed through calibration curves and a nomogram. RESULTS: LVEF, Sema4D, QTd, QRS duration, and corrected QT interval were identified as independent prognostic factors in STEMI patients. Among them, LVEF served as a protective factor, whereas Sema4D and QTd showed particularly strong associations with poor prognosis. Least absolute shrinkage and selection operator regression further confirmed the independent predictive value of these variables, enhancing the robustness of the model. The area under the receiver operating characteristic curve of the prediction model was 0.87, indicating excellent discrimination and good calibration. The model demonstrated high predictive accuracy and holds clinical utility for identifying patients at risk of poor outcomes following STEMI. CONCLUSION: The prognostic model developed in this study integrates multiple key predictors of STEMI outcomes, demonstrating strong discriminative and predictive performance. It may serve as a valuable tool for clinical risk stratification and individualized treatment planning.