Construction Of A Predictive Model For In-hospital Mortality In Patients With Acute ST-segment Elevation Myocardial Infarction

Background and Objective:The treatment strategies for acute ST segment elevation myocardial infarction(STEMI)are constantly improving,and the risk scoring models previously established based on Western patients may not be fully applicable to the medical environment in China.Therefore,this study aims to develop a prediction model for in-hospital mortality among patients suffering from STEMI using data from China Chest Pain Center(CCPC).Methods:Our study was a multicenter retrospective analysis of STEMI patients undergoing coronary intervention,and the endpoint event was in-hospital mortality.Total data was split into 70% training set and 30% validation set.LASSO and multivariate logistic regression analyses were performed to identify the best predictors of in-hospital mortality.Based above the results,we incorporated the selected predictors into the Nomogram.The performance of the model was assessed by discrimination,calibration,and clinical utility.Results:A total of 81,548 participants were included in the final analysis,4,404 deaths occurred.The independent predictors of in-hospital mortality were age,heart rate,systolic blood pressure,left ventricular ejection fraction,Killip class,hospital level,chronic kidney disease,In-hospital heart failure,left main coronary artery disease,and postoperative thrombolysis in myocardial infarction(TIMI)grade.This predictive model show a great discrimination(training set: AUC=0.801,95%CI :0.791-0.801;validation set: AUC=0.795,95% CI: 0.781-0.809).The calibration curve and decision curve analysis unequivocally indicate that the Nomogram exhibits outstanding predictive accuracy and provides significant clinical utility.Conclusion:The Nomogram developed in this study can accurately predict in-hospital mortality in STEMI patients in China.It may assist physicians in risk assessment and clinical decision-making,thereby improving patients prognosis.