Developing a Nomogram to Predict the Risk of Delirium in ICU Patients: A Retrospective Cohort Study

Delirium is a prevalent and severe neuropsychiatric syndrome commonly observed among critically ill patients in the intensive care unit (ICU). Despite its substantial clinical impact, effective tools for predicting delirium risk remain limited. This study aimed to develop and validate a nomogram to predict the risk of delirium in ICU patients, integrating clinical, demographic and laboratory parameters for individualized risk assessment.

A retrospective cohort study was conducted involving 964 ICU patients admitted between January 2020 and December 2023. Comprehensive clinical data were collected, and delirium was assessed using the Confusion Assessment Method for the ICU (CAM-ICU). Predictive variables were identified using Least Absolute Shrinkage and Selection Operator (LASSO) regression, followed by multivariate logistic regression analysis. A nomogram was constructed based on significant predictors and validated using calibration curves, receiver operating characteristic (ROC) curves, and decision curve analysis (DCA).

Among the 964 ICU patients, 186 (19.3%) developed delirium. Eight predictors were identified as independent risk factors for delirium, including drug abuse, alcohol abuse, male sex, maximum potassium (potassium_max), minimum chloride (chloride_min), length of hospital stay, maximum blood urea nitrogen (BUN_max), and minimum hematocrit (hematocrit_min). The nomogram demonstrated good discrimination with an area under the ROC curve (AUC) of 0.732 (95% CI: 0.690-0.773) and satisfactory calibration. DCA confirmed the clinical utility of the model, showing a net benefit across a wide range of risk thresholds.

This study developed a robust and clinically applicable nomogram for predicting ICU delirium risk, integrating key clinical and laboratory variables. The nomogram can aid ICU clinicians in implementing timely preventive interventions to improve patient outcomes.