Abstract
PURPOSE: This study aimed to develop and validate a clinical prediction model for intensive care unit-acquired weakness (ICU-AW) in sepsis patients, in order aid the early identification of high-risk patients and enable targeted intervention measures. PATIENTS AND METHODS: This prospective observational study was a single-center study conducted in a tertiary hospital in Shenzhen, China. Eligible inpatients diagnosed with sepsis between January 2023 and June 2024 were enrolled. The least absolute shrinkage and selection operator (LASSO) regression model was used to optimize the feature selection for the risk prediction model for ICU-AW in sepsis patients. Multivariable logistic regression analysis was applied to build a predicting model that incorporated the features selected in the LASSO regression model. Receiver operating characteristic (ROC) and calibration curves, and decision curve analysis (DCA) were applied to assess the model. RESULTS: A total of 344 patients were included in the present study. Among these patients, 257 and 87 patients were assigned to the modeling and validation groups, respectively. Six independent predictors were identified: age, multiple organ dysfunction syndrome (MODS), use of neuromuscular blocking agents (NMBAs), duration of mechanical ventilation, duration of sedation, and Acute Physiology and Chronic Health Evaluation II (APACHE II) score. The nomogram revealed good performance, with an area under the ROC curve (AUC) of 0.905 (95% CI: 0.871-0.940) for the modeling group and 0.861 (95% CI: 0.784-0.939) for the validation group. The calibration curves indicated a good agreement between the predicted and observed outcomes. The DCA demonstrated a broad benefit threshold and good clinical effectiveness. CONCLUSION: The risk prediction model constructed in the present study demonstrated good predictive performance, providing a valuable reference for clinical practitioners to identify the risk of ICU-AW in patients with sepsis and implement prompt intervention.