Abstract
INTRODUCTION: The study aimed to develop and validate a nomogram for predicting sepsis-associated encephalopathy (SAE) in elderly patients with sepsis admitted to the intensive care unit (ICU). METHODS: We conducted a retrospective study at the First Affiliated Hospital of Wenzhou Medical University. The least absolute shrinkage and selection operator (LASSO) regression was employed to identify characteristic predictors for SAE, and a nomogram was subsequently developed. The nomogram's performance was evaluated using receiver operating characteristic (ROC) curves, the concordance index (C-index), calibration curves, the Brier score, and decision curve analysis (DCA) to assess discrimination, calibration, and clinical utility. Internal validation was performed using the bootstrap resampling method. RESULTS: A total of 231 elderly sepsis patients were included in the study, among whom 66 were diagnosed with SAE. The study identified invasive mechanical ventilation (IMV), platelet count, white blood cell (WBC) count, glucose levels, lactate levels, and calcium levels as significant risk factors for SAE. The nomogram demonstrated an area under the curve (AUC) of 0.861, outperforming other predictive factors. The corrected C-index, determined through 500 bootstrap validations, was 0.842. Additionally, the calibration curve indicated strong agreement between predicted outcomes and actual observations. The Brier score of the prediction model was 0.139. Finally, DCA revealed that the nomogram had high clinical applicability. CONCLUSION: The prediction nomogram and online website demonstrated strong predictive performance for the occurrence of SAE in elderly patients with sepsis, which made the evaluation process of SAE more convenient and efficient.