Construction of a predictive model for in-hospital mortality in patients with acute myocardial infarction complicated with cardiogenic shock.

Background and objective: Acute myocardial infarction (AMI) complicated by cardiogenic shock (CS) carries a substantial risk of morbidity and mortality. However, a validated clinical prediction model for in-hospital mortality in these patients is still lacking. This study seeks to develop and validate a mortality risk prediction tool to assist clinicians in early identification of high-risk patients and guide personalized therapeutic interventions. Methods: We conducted a retrospective analysis of clinical data from 1,419 patients diagnosed with AMI. Of these, 150 patients with AMI complicated by CS were enrolled. Participants were randomly assigned to a training group (70%) or a testing group (30%). Following logistic regression analysis, variables were selected using LASSO regression. Seven candidate predictors were selected for inclusion in the final nomogram model. Model performance was assessed through the area under the receiver operating characteristic curve (AUC), decision curve analysis (DCA), and calibration curves. Results: A total of 150 patients with AMI complicated by CS were included in the study. In-hospital mortality occurred in 41 patients (27.33%). Eleven variables, including age, smokers, and left ventricular ejection fraction (LVEF), were identified as potential predictors of in-hospital mortality. The final nomogram incorporated the following independent predictors: age, LVEF, creatine kinase-MB (CK-MB), high-sensitivity C-reactive protein (Hs-CRP), β-blocker use, angiotensin-converting enzyme inhibitor/angiotensin receptor blocker (ACEI/ARB) use, and statin use. During internal validation, the nomogram demonstrated AUC values of 0.941 in the training sets and 0.981 in the testing sets. Both calibration curves and DCA showed excellent agreement between predicted probabilities and observed outcomes. Conclusion: This study developed and internally validated a clinically applicable prediction model and nomogram for assessing the risk of in-hospital mortality among patients with AMI complicated by CS. The results offer readily applicable insights to guide clinical practitioners in implementing timely, personalized patient management strategies.