Abstract: OBJECTIVE To explore the screening methods of risk for nosocomial infection based on diagnosis related groups (DRGs) death risk classification and observe their application. METHODS A total of 86 920 patients who were discharged from the Affiliated Hospital of Guizhou Medical University from Jan 1, 2021 to Aug 31,2021 were recruited as the research subjects. The DRGs-related information and prevalence of nosocomial infection were analyzed. Pearson correlation analysis was performed for the association between the DRG-based death risk classification and the incidence of nosocomial infection. The risk of nosocomial infection in the patients with different grades of death risk were evaluated by screening test evaluation indexes. RESULTS The patients were grouped based on DRG death risk, from the low risk group to the high risk group, the incidence of nosocomial infection showed an upward trend with the rise of grade(P＜0.05), and there was certain relationship(P＜0.05). The result of the screening test indicated that the sensitivity of all the death risk groups was less than 30%, the specificity was 97.89% in the high-risk group(97.89%), and the positive likelihood ratio was 7.37. Receiver operating characteristic (ROC) curve analysis showed that the area under curve (AUC) was 0.75 (95%CI:0.70-0.80). CONCLUSION The sensitivity of the DRGs-based death risk classification is low for the screening of risk for nosocomial infection, and there is less significance in evaluating the risk of nosocomial infection. The specificity and positive likelihood ratio of the high risk group are high, and it is necessary to conduct a survey of missed report of nosocomial infection so as to raise the efficiency of survey of missed report.