Abstract
OBJECTIVE: This study aimed to assess the clinical utility and prognostic value of a panel of serum cytokines for predicting major adverse cardiovascular events (MACE) in patients with acute myocardial infarction (AMI) after percutaneous coronary intervention (PCI). METHODS: We enrolled 232 AMI patients who underwent PCI. Based on the occurrence of MACE during follow-up, patients were categorized into a poor prognosis group (n=127) and a good prognosis group (n=105). Serum levels of interleukin IL-1β, IL-6, IL-8, IL-10, and tumor necrosis factor-alpha (TNF-α) were measured. Spearman correlation analysis was employed to evaluate the relationships between cytokine levels and MACE risk. Nine distinct machine learning models, incorporating all identified independent risk factors for MACE, were developed and evaluated. RESULTS: Levels of high-sensitivity C-reactive protein (hs-CRP), IL-6, IL-8, and TNF-α were significantly elevated in patients who developed MACE compared to those who did not. IL-6 emerged as a relatively strong predictor of MACE, with an area under the curve (AUC) of 0.82 (95% CI: 0.77-0.87). The IL-6/IL-10 ratio also demonstrated predictive value for MACE (AUC=0.74, 95% CI: 0.69-0.80). Furthermore, significant differences were observed between initial presentation and readmission levels for the IL-8/IL-10 and TNF-α/IL-10 ratios in patients readmitted for AMI following MACE. Among the nine machine learning models constructed, the XGBoost and Logistic Regression models, which incorporated all independent risk factors, demonstrated robust performance, both AUC values exceeded 0.8. CONCLUSION: AMI patients with elevated serum cytokine levels exhibited a lower 1-year survival rate. Serum cytokine profiles show significant predictive value for MACE following PCI in AMI patients.