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

Abstract

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.

Keywords: Chronic obstructive pulmonary disease; ICU delirium; Intensive care unit; MIMIC-IV database; Nomogram.

Fig. 1

Variable Selection Plot Based on LASSO Regression. (A): Coefficient Distribution Plot; (B): 10-Fold Cross-Validation Statistics Plot in LASSO Regression. The regularization parameter (lambda) for LASSO regression was determined using the minimum criterion (lambda.min, left dashed line) and the 1-SE criterion (lambda.1se, right dashed line). In this study, the 1-SE criterion was selected, resulting in 14 non-zero coefficients for variable selection

Fig. 2

Nomogram Prediction Model for Delirium Occurrence in Older Patients with COPD in the ICU. CCI: Charlson Comorbidity Index; GCS: Glasgow Coma Scale; SOFA: Sequential Organ Failure Assessment; BUN: Blood Urea Nitrogen; In accordance with standard clinical documentation practices, the 24-hour urine output is displayed in mL, which is the conventional unit of measurement

Fig. 3

ROC curves of the Nomogram prediction model in the validation cohort (A) and the training cohort (B). 95% CI: 95% confidence interval; AUC: area under the curve

Fig. 4

Calibration curve plots of the Nomogram prediction model in the validation group (A) and the training group (B)

Fig. 5

DCA and CIC of the Nomogram prediction model in the validation group (A, C) and the training group (B, D)