Development of a Nomogram Model to Predict the Risk of Postoperative Delirium in Cardiac Surgery Patients

Postoperative delirium (POD) is a common and severe complication following cardiac surgery, with an incidence of about 65% in older patients. This study aimed to develop a predictive model for POD in patients aged ≥ 18 years, to enhance early detection and intervention. A retrospective analysis was performed on the data collected from 825 patients who underwent cardiac surgery at Nanjing First Hospital (May 2021-July 2022). POD was diagnosed using the Confusion Assessment Method for the ICU (CAM-ICU). We used LASSO regression and multivariate logistic regression to identify key predictors for the nomogram. The incidence of POD was 23.6%, with significant predictors including head CT findings, hyperlactatemia before extubation, APACHE II score, ASA score, and length of hospital stay. The model demonstrated strong predictive ability (AUC: 0.922 training, 0.896 validation). A web-based calculator ( https://baozexiang.shinyapps.io/dynnomapp/ ) was developed to enhance clinical risk assessment and patient outcomes.