Development and validation of nomogram to predict long-term prognosis of critically ill patients with acute myocardial infarction

Background Acute myocardial infarction (AMI) is a common critical illness in the cardiovascular field, with poor prognosis. This study aimed to construct a nomogram to predict long-term survival of critically ill patients with AMI, which helps to assess severity, guide treatment, and improve prognosis. Methods and results The clinical data of patients with AMI was extracted from the database MIMIC-III v1.4. The Cox proportional hazards models were performed to identify the independently prognostic factors, and a nomogram for predicting long-term survival of AMI patients was developed based on the multifactor analysis, of which discriminative ability and accuracy was evaluated by concordance index (C-index) and calibration curve. Results A total of 1202 patients were included in the analysis, of which 841 were divided into the training set and 361 were the validation. Multivariate analysis shown that age, blood urea nitrogen, respiratory rate, SAPSII score, cardiogenic shock, cardiac arrhythmias, and respiratory failure served as the independently predictive factors, which were incorporated into the nomogram. Moreover, the nomogram shown favorable performance for predicting 4-year survival of AMI patients with the C-index of 0.788 [95% confidence interval (CI): 0.763 to 0.813] and 0.783 (95% CI: 0.748 to 0.818) in the training and validation set, respectively. Conclusion The nomogram we constructed here can accurately predict the long-term survival of patients with AMI.