Nomogram Model for Predicting Risk of Postoperative Delirium in Adult Liver Transplant Patients: A Retrospective Study.

Background: Postoperative delirium is a common and serious complication following liver transplantation, early identification of high-risk patients is crucial for implementing preventive strategies and improving clinical outcomes. Objective: To develop and validate a prediction model for postoperative delirium (POD) in adult liver transplant patients using preoperative baseline characteristics, intraoperative factors and postoperative parameters available within 24 hours after surgery. The model aims to assess the risk of POD and provide early identification of high-risk patients. Methods: A retrospective analysis was conducted on liver transplant patients, classified based on the presence or absence of POD. Key risk factors were identified using univariate and multivariate logistic regression. The prediction model was established and validated, with performance evaluated using the area under the receiver operating characteristic curve (AUROC). The prediction model was visualized as a nomogram for practical application. Results: A total of 480 patients were included, with a POD incidence of 30.8%. Six key predictors were identified: age, APACHE score, albumin, AST, BUN, and blood ammonia. The final model achieved an AUROC of 0.757 (95% CI: 0.709-0.806), sensitivity of 66.2%, and specificity of 77.7%. The optimal classification threshold of the model is 0.341, that is, patients with a predicted probability exceeding 0.341 were classified as high-risk for delirium. Conclusion: The developed nomogram effectively predicts postoperative delirium risk in liver transplant patients, offering clinical utility for risk stratification and management.