Study of the Model to Predict 3-month Mortality Risk of Acute-on-chronic Hepatitis B Liver Failure

Wenzhou Medical University

Status: Completed

Conditions: Acute-on-chronic Hepatitis B Liver Failure

Treatments: Other: Using training and testing groups to construct ANN based on laboratory tests

Study type: Observational

Funder types: Other

Identifiers

NCT01826760

wenzhouMC 023

Details and patient eligibility

About

This study was to predict 3-month mortality risk of acute-on-chronic hepatitis B liver failure (ACHBLF) on an individual patient level using artificial neural network (ANN) system. The area under the curve of receiver operating characteristic (AUROC) were calculated for ANN and MELD-based scoring systems to evaluate the performances of the ANN prediction.

Full description

Hepatitis B virus (HBV) is a major human pathogen which causes high morbidity and mortality worldwide. HBV is one of the leading causes for rapid deterioration of liver function, which is a serious condition termed as "acute-on-chronic liver failure (ACLF)" with high mortality. There is a high prevalence of HBV in Asian developing countries where acute-on-chronic hepatitis B liver failure (ACHBLF) accounts for more than 70% of ACLF and almost 120, 000 patients died of ACHBLF each year. The transplantation of liver is the basic and strong effective therapeutic option for ACHBLF patients. However, liver transplantation is difficult to be extensively applied due to the shortage of liver donors and other socioeconomic problems. Thus, an early predictive model, which is objective, reasonable and accurate, is necessary for severity discrimination and organ allocation to decrease the mortality of ACHBLF.

MELD-based scoring systems still failed to predict the mortality of a considerable proportion of patients and their predictive accuracy was not satisfying enough.

The ANN is a novel computer model inspired by the working of human brain. It can build nonlinear statistical models to deal with the complex biological systems. In the recent years, ANN models have been introduced in clinical medicine for clinical validations, including predicting the hepatocellular carcinoma patients' disease-free survival and preoperative tumor grade, predicting the mortality of patients with end-stage liver disease and identifying the risk of prostate carcinoma.

Enrollment: 583 patients

Sex: All

Ages: 19 to 87 years old

Volunteers: Accepts Healthy Volunteers

Inclusion criteria

• Acute hepatic insult manifesting as jaundice and coagulopathy
• Complicated within 4 weeks by ascites
• And/or encephalopathy in a patient with chronic HBV infection

Exclusion criteria

• Patients with evidence of non-B hepatitis virus
• alcohol abuse leads to liver failure
• autoimmune leads to liver failure
• oxic or other causes that might lead to liver failure
• past or current hepatocellular carcinoma
• liver transplantation
• serious diseases in other organ systems

Trial design

583 participants in 2 patient groups

acute-on-chronic hepatitis B liver failure, training group

Description:

ACHBLF was defined as an acute hepatic insult manifesting as jaundice and coagulopathy, complicated within 4 weeks by ascites and/or encephalopathy in a patient with chronic HBV infection according to consensus recommendations of the Asian Pacific Association for the Study of the Liver in 2009. ACHBLF patients were assigned to a training cohort and a validation cohort randomly. One of the major limitations of ANN is over-training, which can lead to good performance on training sets but poor performance on relatively independent validation sets. To avoid over-training during building ANN, a part of ACHBLF patients were again randomly selected from the training group to train the network and the remaining were used for cross-validation.

Treatment:

Other: Using training and testing groups to construct ANN based on laboratory tests

acute-on-chronic hepatitis B liver failure, testing group

Description:

ACHBLF was defined as an acute hepatic insult manifesting as jaundice and coagulopathy, complicated within 4 weeks by ascites and/or encephalopathy in a patient with chronic HBV infection according to consensus recommendations of the Asian Pacific Association for the Study of the Liver in 2009. To avoid over-training during building ANN, a part of ACHBLF patients were again randomly selected from the training group to train the network and the remaining were used for cross-validation.

Treatment:

Other: Using training and testing groups to construct ANN based on laboratory tests