Objective:To investigate the predictive factors of prognosis in patients with septic cardiomyopathy and building pre-diction model.Methods:A retrospective study was conducted on 156 patients with purulent pericarditis,and they were divided into a model set and a validation set in a 7∶3 ratio.The patients in the model set were divided into survival and death groups according to dif-ferent outcomes.The influence factors on the prognosis of the model set patients were evaluated by multivariate Cox regression analysis,and a ROC curve and decision curve analysis(DCA)were used to validate the model using R software.Results:Multiple COX regres-sion analysis indicated that lactic acid,D-dimer,interleukin-6,APACHE-Ⅱscore and SOFA score were independent risk factors for 28 deaths in hospital with septic cardiomyopathy.ROC curve analysis results showed that the predictive value curve area(AUC)of the model set was 0.90,and the AUC of the validation set was 0.83,indicated that the model has good value in the prognosis of patients with septic cardiomyopathy.The results of the clinical decision curve(DCA curve)suggested that the clinical benefit of the validation set and the model set in this model was superior to the"assume all patients die"(all)and"assume all patients die"(none)curves.Conclusion:The prediction model has a good fit to the actual and correction curves,approaching the ideal curve,and has certain clini-cal practical value for patients with septic cardiomyopathy.