Abstract: Objective: To explore the influencing factors of hypoactive delirium in ICU patients and establish a prediction model,providing a reference basis for clinical nurses to correctly identify hypoactive delirium. Methods: From March 2023 to July 2024,patients admitted to the department of critical care medicine of The First Affiliated Hospital of Anhui Medical University were selected as the research subjects.The ICU confusion assessment method and the Richmond resting-sedation score were used to evaluate delirium in the patients.The influencing factors of patients with hypoactive delirium were analyzed using the general information questionnaire,acute physiology and chronic health evaluation Ⅱ(APACHE Ⅱ score),and Barthel index (BI),and the goodness of fit and predictive effect of the model were verified through the ROC curve. Results: A total of 197 research subjects were included.Among them,99 patients developed delirium,with an incidence rate of 50.25%.Among them,65 cases (65.66%) were the hypoactive type,11 cases (11.11%) were the increased activity type,and 23 cases (23.23%) were the mixed type.The patients with hypoactive delirium and those without delirium were compared in terms of age,types of concurrent chronic diseases,sleep disorders,hyponatremia,sepsis,mechanical ventilation,emergency surgery,restraint,catheterization,urea nitrogen,PaCO₂,C-reactive protein,APACHEⅡscore,BI score.The differences were all statistically significant (P<0.05 to P<0.01).The results of logistic regression analysis showed that hyponatremia,mechanical ventilation,emergency surgery,C-reactive protein,APACHE Ⅱ score,and BI score were independent predictors of hypoactive delirium in ICU patients (P<0.05 to P<0.01).The model fit was evaluated by the ROC curve.The area under the curve was 0.972,95%CI was 0.948-0.996,the sensitivity was 98.5%,the specificity was 88.8%.The Hosmer-Lemeshow test results showed that the model fit was relatively high (P=0.81). Conclusions: The incidence of delirium in ICU patients is relatively high,mainly in the form of hypoactive delirium.The prediction model of hypoactive delirium suggests that attention should be paid to patients with hyponatremia,mechanical ventilation,a history of emergency surgery,elevated C-reactive protein,a higher APACHE Ⅱ score,and a lower ability of daily living.The prediction model can screen patients for early hypoactive delirium.