Construction and verification of risk nomogram prediction model for subdelirium syndrome after cardiopulmonary bypass
Cai Guoqi
Wu Qiansheng
Abstract：Objective To identify risk factors for subsyndromal delirium (SSD) in cardiovascular surgery patients undergoing cardiopulmonary bypass (CPB),and develop a nomogram-based risk prediction model to facilitate early recognition of SSD. Methods 368 patients undergoing cardiovascular surgery with CPB were included. Independent risk factors for SSD were identified through univariate and multivariate logistic regression analyses. A risk prediction model was established,and a nomogram was constructed. The model's predictive performance was validated using bootstrapping. Results SSD occurred in 48.6％ of patients. Univariate analysis revealed that age,surgical duration,cardiac function classification,American Society of Anesthesiologists (ASA) classification,mechanical ventilation time,CPB duration,postoperative complications,and volume of blood product transfusion were significantly associated with SSD. Multivariate analysis identified age,ASA classification,surgical duration,mechanical ventilation duration,and platelet transfusion volume as independent risk factors. The prediction curve in the prediction model of SSD risk was basically consistent with the observed curve,with AUC=0.795. Conclusion The incidence of SSD after CPB is high,and the nomogram prediction model has good accuracy and discrimination,which can be used to identify high-risk SSD patients as early as possible.
Keywords：Subsyndromal deliriumCardiopulmonary bypassRisk predictionNomogramICU
Publication Date：2024-12-28
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：6( 478-483 )