Analysis Of Correlation Between Liver Function Evaluation Model And The Prognosis Of Patients With Decompensated Cirrhosis And Esophagogastric Varices Bleeding Undergoing TIPS Procedures

Part 1 A study on the application of artificial intelligence to validate and compare ALBI grade to predict 1-year rebleeding rates after early TIPSPurpose To validate and compare the prognostic performance of the albumin-bilirubin(ALBI)grade,platelet-albumin-bilirubin(PALBI)grade,Child-Pugh grade,and Model for End-Stage Liver Disease(MELD)score in predicting the 1-year variceal rebleeding probability using artificial intelligence for patients with cirrhosis and esophagogastric varices bleeding(EGVB)undergoing early transjugular intrahepatic portosystemic shunt(E-TIPS)procedures.Materials and Methods This dual-center retrospective study included two cohorts,with patients enrolled between January 2016 and September 2018 in the training cohort and January 2017 and September 2018 in the validation cohort.In the training cohort,risk factors associated with the 1-year variceal rebleeding probability were identified using univariate and multivariate logistic analyses.ALBI-,PALBI-,Child-Pugh-,and MELD-based nomograms and an artificial neural network(ANN)model were established and validated internally in the training cohort and externally in the validation cohort,which included patients with variceal bleeding who were treated with preventive TIPS.Results A total of 259 patients were included.The median follow-up periods were 24.1 and 18.9 months,and the 1-year variceal rebleeding rates were 12.3%(14/114)and 10.3%(15/145)in the training and validation cohorts,respectively.In the training cohort,all four variables were identified as independent risk factors.Four nomograms were then established and showed comparable prognostic performances after internal(C-index:0.879,0.829,0.874,and 0.798,P>0.05)and external(C-index:0.720,0.719,0.718,and 0.703,P>0.05)validation.The ANN demonstrated that Child-Pugh grade has the most significant effect,and it is worth noting that the importance gap between ALBI and Child-Pugh grades is small.Conclusions There were no significant differences in these four liver function evaluation models in predicting the possibility of the 1-year variceal rebleeding for patients undergoing early TIPS.Considering of objectivity and usability,ALBI grade has the potential to be used as an clinical tool for the prediction of rebleeding in patients with EGVB.Part 2 Research on establishing a prediction model of early overt hepatic encephalopathy after TIPS based on liver stiffnessObjective To investigate the feasibility of using artificial intelligence to establish a predictive model of early overt hepatic encephalopathy(OHE)after TIPS based on liver stiffness.Materials and Methods Patients with EGVB treated with 8mm Viatorr stents TIPS from June 2017 to October 2019 were retrospectively analyzed in a single center.Univariate and multivariate logistic analyses were used to identify risk factors that may be associated with early OHE after TIPS.Nomograms and an artificial neural network(ANN)model were established based on independent risk factors and validated internally in the training cohort.Results A total of 83 patients were included with an average follow-up period of 13.0 months,and the 3-months OHE rates was 20.5%(17/83)in the training cohort,Age(<65,≥65),Liver stiffness,Portal vein flow velocity 3 days after procedure were identified as independent risk factors.Nomogram was then established based on these three variables and showed higher accuracy after internal validation(ROC=0.8681,95%CI=0.7926,0.9435).Artificial neural networks shows that age and liver stiffness play a more important role in predicting early OHE after TIPS.Conclusions Preliminary confirmation that establishing an early OHE prediction model based on liver stiffness is feasible and valid.It has individualized guiding significance for the primary prevention of postoperative HE,early nutrition intervention and self-health management of patients after TIPS.