Frontiers in Medicine (Mar 2025)
Development and validation of a predictive model for acute exacerbation in chronic obstructive pulmonary disease patients with comorbid insomnia
Abstract
AimTo develop and validate a risk prediction model for estimating the likelihood of insomnia in patients with acute exacerbations of chronic obstructive pulmonary disease (AECOPD).MethodsThis prospective study enrolled 253 patients with AECOPD treated at the Department of Respiratory and Critical Care Medicine, Chaohu Hospital Affiliated with Anhui Medical University, between September 2022 and April 2024. Patients were randomly assigned to a training set and a testing set in a 7:3 ratio. Least Absolute Shrinkage and Selection Operator (LASSO) regression analysis was conducted in the training set to identify factors associated with insomnia in patients with AECOPD. A nomogram was constructed based on four identified variables to visualize the prediction model. Model validation involved the Hosmer-Lemeshow test, and its performance was assessed through receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). Model interpretability was further enhanced using SHapley Additive exPlanations (SHAP).ResultsPSQI grade, marital status (widowed), white blood cell (WBC) count, and eosinophil percentage (EOS%) were identified as significant predictors of insomnia in patients with AECOPD. The nomogram based on these predictors exhibited excellent predictive performance, with areas under the ROC curve (AUCs) of 0.987 and 0.933 for the training and testing sets, respectively. The calibration curves and Hosmer-Lemeshow test demonstrated strong agreement between predicted and observed outcomes, while DCA confirmed the model’s superior clinical utility.ConclusionThis study established a risk prediction model based on four variables to estimate the probability of insomnia in patients with AECOPD. The model exhibited excellent predictive accuracy and clinical applicability, offering valuable guidance for early identification and management of insomnia in this population.
Keywords
