Construction and validation of sleep disorder Nomogram prediction model in patients with liver cirrhosis

LU Yawei; ZHANG Hui; XU Jing; ZHONG Lei; XIANG Xiaoting

doi:10.12102/j.issn.1009-6493.2025.05.003

Abstract：Objective:To investigate the risk factors of sleep disorders in patients with liver cirrhosis,and construct a risk prediction model of sleep disorders in patients with liver cirrhosis,and provide an effective and convenient sleep disorder screening tool for clinical staff.Methods:A total of 300 patients with cirrhosis admitted to the department of hepatology of a tertiary grade A hospital in Anhui province from March 2023 to September 2023 were selected.Logistic regression analysis was used to explore the influencing factors of sleep disorders in patients with cirrhosis,and the risk prediction model of sleep disorders in patients with cirrhosis was constructed.Receiver operating characteristic(ROC)curve,Hosmer-Lemeshow test,correction curve and DCA were used to evaluate the performance of the model.Results:Logistic regression analysis showed that malnutrition,pain,depression,C-reactive protein and globulin were the influencing factors of sleep disorders in patients with cirrhosis.The area under ROC curve(AUC)of the model was 0.773(95%CI 0.720-0.826).H-L goodness of fit test(χ2=1.443,P=0.486)and calibration curve showed that the prediction probability and observation probability had high consistency.The DCA curve showed that the net benefit can be obtained by using the model.Conclusion:Nutrition,pain,depression,C-reactive protein and globulin are the influencing factors of sleep disorders in patients with cirrhosis.The risk prediction model based on the above variables has good predictive efficacy,and can be used as a tool for early clinical prediction of sleep disorders in patients with cirrhosis.