Objective: The purpose of the study was to explore the application effect of the risk classification nursing model in the prevention of pressure injury in critically ill patients in the ICU. Methods: A total of 186 critically ill patients admitted to the ICU of our hospital from January 2024 to December 2024 were randomly divided into the control group and the observation group according to the time of admission, with 93 cases in each group. Conventional pressure injury prevention nursing measures were used in the control group, while risk classification nursing model was adopted in the observation group. The incidence, staging, time of occurrence, length of hospital stay and nursing satisfaction of pressure injury were compared between the two groups. Results: The results showed that the incidence of pressure injury in the observation group was 5.38%, significantly lower than 15.05% in the control group (p < 0.05); The proportion of stage I pressure injury in the observation group was higher than that in the control group, and the proportion of stage II and above was lower than that in the control group (p < 0.05); The occurrence time of pressure injury in the observation group was later than that in the control group, and the length of hospital stay was shorter than that in the control group (p < 0.05); The nursing satisfaction score of the observation group was higher than that of the control group (p < 0.05). Conclusion: The risk classification nursing model can effectively reduce the incidence of pressure injury in critically ill patients in the ICU, delay the occurrence time, shorten the length of hospital stay, and improve nursing satisfaction. It is worthy of clinical promotion and application.