Construction and verification of prediction model of living space restriction in patients with acute exacerbation of chronic obstructive pulmonary disease

WU Yan; LIU Huiying; YU Hua

doi:10.12104/j.issn.1674-4748.2025.02.003

Abstract：Objective:To explore the related factors of living space restriction in patients with acute exacerbation of chronic obstructive pulmonary disease(AECOPD),and establish a risk prediction model for verification.Methods:A total of 189 patients with AECOPD admitted to the hospital from January 2023 to February 2024 were retrospectively selected by convenience sampling method as research objects,and were divided into living space restricted group(n=86)and non-living space restricted group(n=103)according to whether living space restricted was found.The influencing factors of living space restricted were analyzed,and a predictive risk model was constructed.And 81 AECOPD patients admitted to the hospital from March 2024 to August were selected as the verification group for verification.Results:Binary Logistic regression analysis results showed that,Age≥60 years,＞2 acute exacerbations in the past 1 year,introversion personality type,no social involvement,long duration of chronic obstructive pulmonary disease(COPD),and high levels of chronic obstructive pulmonary disease assessment test(CAT score),C-reactive protein(CRP),and lymphocyte ratio(NLR)were independent of patients with AECOPD who presented with limited living space Risk factors(all P＜0.05).The Hosmer-Lemeshow goodness of fit test showed that x2=6.383,P＞0.05,which proved that the model had good goodness of fit and good prediction efficiency.The area under the curve(AUC)was 0.915[95％CI(0.875,0.955),P＜0.001],the sensitivity was 84.90％,the specificity was 88.30％,and the maximum approximate entry index was 0.732.Decision curve analysis(DCA)shows that the overall trend of correction curve is basically consistent with the ideal curve,which indicates that the model has good goodness of fit and good prediction efficiency.Conclusion:The living space restriction in patients with AECOPD is affected by multiple factors.The risk prediction model constructed has good consistency and differentiation,which can provide reference value for clinical risk assessment.