Practical exploration of constructing a predictive model for acute upper gastrointestinal bleeding in patients with liver cirrhosis based on the albumin bilirubin index
Objective:To explore the predictive value of albumin-bilirubin(ALBI)index for acute upper gastrointestinal bleeding in patients with liver cirrhosis,and to establish relevant predictive models.Methods:Choose between December 2019 and December 2022 were complicated with acute upper gastrointestinal bleeding in patients with cirrhosis as the research object,collect patients clinical data,using ROC curve to assess the predictive value of ALBI index,and calculate the optimal cutoff value.Univariate and multivariate Logistic regression were used to analyze the influencing factors of patients with liver cirrhosis complicated with acute upper gastrointestinal bleeding,and a nomogram model was established accordingly.Results:The area under the ROC curve predicted by ALBI index for cirrhosis patients with acute upper gastrointestinal bleeding was 0.764(95%CI:0.693-0.835).Long course of disease,ascites,Ca<2.2 mmol/L,PT≥ 16 s,PLT<100 x 109/L and ALBI index-1.87 were independent risk factors for acute upper gastrointestinal bleeding in patients with liver cirrhosis(P<0.05).Based on this,a nomogram model was established to predict the risk of acute upper gastrointestinal bleeding in patients with liver cirrhosis.The model validation results showed that the C-index was 0.854,the calibration curve approached the ideal curve,and the AUC of the ROC curve was 0.851(95%CI:0.823-0.879).Within the prediction range of 5%to 96%,the model had a net benefit.Conclusion:ALBI index has high predictive value for liver cirrhosis patients with acute upper gastrointestinal bleeding,and the column chart model constructed based on ALBI index can effectively predict the risk of liver cirrhosis patients with acute upper gastrointestinal bleeding.