Introduction: Acute Myocardial Infarction (AMI) is one of the most common cause of mortality causes in Iran. The aim of this study was to provide a model for predicting the survival of patients with AMI in Imam Reza hospital in Mashhad.Methods: We recruited 607 patient aged>25 years, admitted to the CCU of Imam Reza hospital in Mashhad. This was a 5-year retrospective study in which patients had been followed during 2007 to 2012. The main outcome of the study was death due to AMI. The effect of independent predictors on survival was examined in a multivariate Cox regression model.Result: Using multivariate Cox regression analysis, variables remaining in the final model including: age (HR: 1.04, P=0.000), male gender (HR: 0.71, P=0.03), diabetes (HR: 1.93, P=0.000), history of ischemic heart disease (HR: 1.35, P=0.04), acute transmural myocardial infarction of unspecified site (HR: 3.23 P=0.007), and type of intervention and diagnostic procedures. By multiplying the significant variables into the regression coefficient, a risk score was calculated. Applying cut offs at percentiles of 25 and 75, three risk groups were identified. In low and high-risk groups, 5-year survival rate was 91% and 20% respectively.Conclusion: Identification of additional risk factors and providing a new approach to high-risk group may lead to increase in survival of these patients.