Development of a nomogram to predict subsyndromal delirium in patients with cancer admitted to the intensive care unit

BACKGROUND: Subsyndromal delirium (SSD) is a prevalent condition that significantly affects the prognosis of patients with cancer admitted to the intensive care unit (ICU). However, a validated nomogram to predict the risk of SSD in this vulnerable population remains lacking. METHODS: This study included 258 middle-aged and older patients with cancer admitted to the ICU postoperatively. Logistic regression analysis was conducted to determine risk factors for SSD. These factors were integrated into a nomogram model for prediction. The area under the receiver operating characteristic curve (AUC), calibration plot, and decision curve analysis were used to assess the model's performance. The research adhered to TRIPOD guidelines. RESULTS: A total of 58 patients (22.48%) developed SSD. Multivariate logistic regression identified sex, marital status, American Society of Anesthesiologists grade, hypotension, mechanical ventilation (hours), admission source, and serum potassium as independent risk factors for SSD in middle-aged and older patients with cancer in the ICU. The nomogram constructed from these variables achieved an AUC of 0.837 (95% confidence interval, 0.778-0.897). Internal validation demonstrated strong calibration and high clinical use of the model. CONCLUSION: Middle-aged and older patients with cancer are at increased risk of developing SSD after postoperative transfer to the ICU. The nomogram developed in this study provides an effective tool for clinicians to identify high-risk patients at an early stage.