A nomogram for predicting delirium in the ICU among older patients with chronic obstructive pulmonary disease.

BACKGROUND

Delirium is common among critically ill older patients with chronic obstructive pulmonary disease (COPD). This study aims to develop a nomogram model to predict the risk of ICU delirium in older patients with COPD.

METHODS

This study included 1,912 older COPD patients admitted to the ICU from the MIMIC-IV database. The patients were randomly divided into training and validation sets in a 7:3 ratio. LASSO regression, univariable and multivariable logistic regression were used to select the best predictive factors based on demographic, clinical, laboratory, and treatment data at ICU admission. A nomogram model was then constructed. The model's accuracy was evaluated using calibration curves. Its predictive performance and clinical utility were assessed using the area under the receiver operating characteristic curve (AUC), decision curve analysis (DCA), and clinical impact curves (CIC).

RESULTS

A total of 638 patients (33.4%) developed ICU delirium, with a median age of 76.00 (IQR: 71.00-83.00) years. Ten independent factors were identified for the nomogram model, including cerebrovascular disease (OR: 1.91; 95% CI, 1.38-2.64), Charlson Comorbidity Index (OR: 1.08; 95% CI, 1.02-1.13), Glasgow Coma Scale (OR: 0.82; 95% CI, 0.77-0.87), SOFA score (OR: 1.15; 95% CI, 1.07-1.22), heart rate (OR: 1.01; 95% CI, 1.01-1.02), body temperature (OR: 1.60; 95% CI, 1.14-2.24), blood urea nitrogen (OR: 1.01; 95% CI, 1.00-1.02), 24-hour urine output (OR: 1.02; 95% CI, 1.01-1.02), fentanyl (OR: 1.94; 95% CI, 1.47-2.55), and oxygen flow (OR: 1.04; 95% CI, 1.02-1.07). The model achieved an AUC of 0.86 (95% CI, 0.83-0.90) in the training set and 0.86 (95% CI, 0.84-0.88) in the validation set. The calibration curve showed good agreement between predicted and observed values (P > 0.05). DCA and CIC results indicated the model's strong predictive value and clinical applicability.

CONCLUSIONS

This study developed an intuitive and simple nomogram model to predict the risk of ICU delirium in older patients with COPD. The model can help clinicians quickly identifying high-risk delirium patients upon ICU admission, thereby optimizing early intervention and treatment strategies.