A model to predict 3-month mortality risk of acute-on-chronic hepatitis B liver failure using artificial neural network.

Model for end-stage liver disease (MELD) scoring was initiated using traditional statistical technique by assuming a linear relationship between clinical features, but most phenomena in a clinical situation are not linearly related. The aim of this study was to predict 3-month mortality risk of acute-on-chronic hepatitis B liver failure (ACHBLF) on an individual patient level using an artificial neural network (ANN) system. The ANN model was built using data from 402 consecutive patients with ACHBLF. It was trained to predict 3-month mortality by the data of 280 patients and validated by the remaining 122 patients. The area under the curve of receiver operating characteristic (AUROC) was calculated for ANN and MELD-based scoring systems. The following variables age (P < 0.001), prothrombin activity (P < 0.001), serum sodium (P < 0.001), total bilirubin (P = 0.015), hepatitis B e antigen positivity rate (P < 0.001) and haemoglobin (P < 0.001) were significantly related to the prognosis of ACHBLF and were selected to build the ANN. The ANN performed significantly better than MELD-based scoring systems both in the training cohort (AUROC = 0.869 vs 0.667, 0.591, 0.643, 0.571 and 0.577; P < 0.001, respectively) and in the validation cohort (AUROC = 0.765 vs 0.599, 0.563, 0.601, 0.521 and 0.540; P ≤ 0.006, respectively). Thus, the ANN model was shown to be more accurate in predicting 3-month mortality of ACHBLF than MELD-based scoring systems.

The tumour necrosis factor-α-238A allele increases the risk of chronic HBV infection in European populations.

Tumour necrosis factor-α (TNF-α) plays a pivotal role in viral clearance and host immune response to hepatitis B virus (HBV) infection, of which the production capacity in individuals is demonstrated to be influenced by a single nucleotide polymorphism within the promoter region of TNF-α genes. However, there have been conflicting results reported in previous studies on TNF-α-238 and TNF-α-863 gene promoter polymorphisms in chronic HBV infection. To derive a more precise estimation of their relationship, we searched Pubmed (January, 1966-August, 2010) and China Biological Medicine Database (January, 1978-August, 2010) and carried out a meta-analysis involving nineteen studies that included 5245 chronic HBV infection cases and 3181 controls describing G238A genotypes, and eleven studies totalling 3576 cases and 2044 controls describing C863A genotypes. The overall meta-analysis did not suggest significant associations of TNF-α-238 and TNF-α-863 gene promoter polymorphisms with chronic HBV infection. However, in subgroup analysis by ethnicity, it indicated that TNF-α-238A allele carriers (GA + AA) in European populations had an increased risk of developing chronic HBV infection (OR = 2.22, 95% CI: 1.07-4.58, P = 0.032; OR = 4.46, 95% CI: 1.75-11.38, P = 0.002, respectively), when compared with spontaneous recovered and healthy populations, respectively. However, no significant associations were found in Asian populations in all genetic models. So, we draw the conclusion that the TNF-α-238A allele may increase the risk of chronic HBV infection in European populations.

Tumour necrosis factor-α-857T allele reduces the risk of hepatitis B virus infection in an Asian population.

Tumour necrosis factor-α (TNF-α) plays a pivotal role in hepatitis B virus (HBV) clearance and host immune response determining the chronicity of HBV infection. However, studies of the association between TNF-α-857 polymorphism and chronic HBV infection have reported conflicting results. So a meta-analysis was carried out to draw a more precise conclusion. Pubmed (January, 1966-March, 2011) and the China Biological Medicine Database (January, 1978-March, 2011) were searched using the keywords TNF-α gene polymorphism in combination with HBV infection without language restriction. Fourteen studies including 4929 chronic HBV infection cases and 2702 controls describing the C857T genotype were included in the meta-analysis. All fourteen studies focussed on an Asian population. The overall meta-analysis suggested that TNF-α-857T allele reduced the risk of chronic HBV infection in the Asian population (OR = 0.82, 95% CI: 0.71-0.95, P = 0.008) when compared with a spontaneously recovered population. In the sensitivity analyses of the groups obeying Hardy-Weinberg equilibrium (HWE), without the largest study population and without the smallest study population, a similar association was revealed (OR = 0.81, 95% CI: 0.68-0.98, P = 0.043; OR = 0.77, 95% CI: 0.68-0.87, P = 0.0001; OR = 0.81, 95% CI: 0.70-0.95, P = 0.009, respectively). However, when compared with a healthy population, no significant association was found in the Asian population in all groups. So, we draw the conclusion that the TNF-α-857T allele reduces the risk of chronic HBV infection in this Asian population.