Objective To evaluate the accuracy of different pressure injury risk assessment tools in predicting the risk of pressure injury in ICU patients, and to provide evidence for accurate screening of patients at risk of pressure injury in ICU. Methods PubMed, Cochrane Library, CINAHL, Embase, Web of Science, CNKI, VIP database, Wanfang database, and China Biomedical Literature Service System were electronically searched for literature about pressure injury risk assessment scales in ICU.After literature screening, quality appraisal, and data extraction, the ANOVA model was used to achieve the network Meta-analysis of the accuracy of diagnostic experiments based on the Bayesian method. Results A total of 28 articles with 11,221 patients were included, involving 12 pressure injury risk assessment tools.The results of the Meta-analysis showed that the superiority index of the Cubbin & Jackson Revised scale was the highest, with sensitivity ［0.72,95%CI(0.59,0.82)］ and specificity ［0.75,95%CI(0.63,0.84)］, followed by the EVARUCI scale, with sensitivity ［0.75,95%CI(0.54,0.90)］, specificity ［0.65,95%CI(0.42,0.83)］.The superiority index of Braden scale was the lowest, with sensitivity ［0.66,95%CI(0.62,0.71)］ and specificity ［0.58,95%CI(0.54,0.61)］. Conclusion The Cubbin & Jackson Revised scale and the EVARUCI scale have good diagnostic accuracy and can be used preferentially when clinical medical staff assesse the risk of pressure injury in ICU patients.