Development and validation of a nomogram for predicting subsyndromal delirium in critically ill patients in the emergency department

This study aimed to develop and validate a nomogram for predicting subsyndromal delirium (SSD) risk in critically ill patients in the emergency department (ED). A retrospective cohort study was conducted on 712 patients admitted to the ED resuscitation room of Peking Union Medical College Hospital from January 2025 to August 2025. Patients were randomly divided into training (n = 525) and validation (n = 187) sets. Multivariate logistic regression analyses were performed to identify independent risk factors for SSD. A nomogram prediction model was constructed based on these factors and evaluated using receiver operating characteristic (ROC) curves, calibration plots, and decision curve analysis (DCA). Multivariate analysis identified six independent predictors of SSD: marital status (divorced: OR = 12.210, 95%CI 1.334-111.750), physical restraint (OR = 10.386, 95%CI 2.932-36.786), RASS score (OR = 4.090, 95%CI 2.029-8.243), APACHE II score (OR = 1.092, 95%CI 1.011-1.180), Barthel index (OR = 0.968, 95%CI 0.951-0.984), and PSQI score (OR = 1.239, 95%CI 1.123-1.368). The nomogram demonstrated excellent discrimination, with an AUC of 0.898. The calibration curve showed good agreement between predicted and actual probabilities. DCA indicated that the nomogram had significant clinical net benefit across a wide range of threshold probabilities. This study developed a novel nomogram that incorporates six readily available clinical variables. This tool effectively predicts the individual risk of SSD in ED critically ill patients, facilitating early identification and targeted preventive interventions to improve patient outcomes.