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.
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.
Study Type
OBSERVATIONAL
Enrollment
583
Wenzhou Medical College
Wenzhou, Zhejiang, China
Living status
The routine therapy of patients were same, including absolute bed rest, energy supplements and vitamins, intravenous drop infusion albumin, maintenance water, electrolyte and acid-base equilibrium, and prevention and treatment complications, etc. The start date of the follow-up was the date of the diagnosis of ACHBLF. In this study, patients receiving liver transplantation within 3 months were considered as death. All patients with ACHBLF were followed up for at least 3 months and the outcome (death or survival) of corresponding patient was recorded.
Time frame: Up to 08 months
Calculating MELD-based Scoring Systems
MELD score (R = 9.57 × ln (creatinine (mg/dL)) + 3.78×ln (bilirubin (mg/dL)) + 11.2×ln (INR) + 6.43) was used to measure the mortality risk in patients with end-stage liver disease. Given the lack of donors, MELD was used as organ allocation tool to increase graft success rate and patient survival rates, which was generally accepted. Recently, some adjustments were added to the original MELD formula to overcome limitations of MELD score. Published data suggested that MELD-Na (R = MELD + 1.59 × (135 - serum sodium (mmol/L))) might improve the prognostic accuracy \[5\]. Furthermore, several other scoring systems such as MELDNa (R = MELD - serum sodium (mmol/L) - (0.025 × MELD × (140 - serum sodium (mmol/L))) + 140), MESO (R = (MELD/serum sodium (mmol/L)) × 100), iMELD (R = MELD + (age(year) × 0.3) - (0.7 × serum sodium (mmol/L)) + 100)), etc had been described for predicting the mortality of end-stage liver disease accurately.
Time frame: Up to 02 months
Construction of ANN
ANN can mimic a biological neural system both structurally and functionally. It consists of a set of highly complex, interconnected processing units (neurons) linked with weighted connections, and include an input layer, an output layer and one or more hidden layers. The input layer contains neurons which receive the data available for the analysis (e.g. various clinical, demographic or laboratory data) and the output layer contains neurons which export different predictive outcomes (e.g. clinical diagnosis or prognosis). The hidden layers are used to allow complex relations between the input and output neurons to evolve.In this study, we built ANN by using a graphical neural network development tool NeuroSolution V5.05 (Neurodimension, Florida, United State).
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.
Time frame: Up to 01 months
Statistical Analysis
Statistical analysis was performed using SPSS 13.0 software and MedCalc 10.0 software. The Kolmogorov-Smirnov test was applied to determine whether sample data were likely to be derived from a normal distribution population. Continuous variables were expressed by mean ± standard deviation and compared using Wilcoxon signed rank test or Mann-Whitney U test when necessary. Categorical variables were described by proportions or count and compared using proportions Chi-square test or the Fisher's exact test when necessary. Performances of the ANN prediction in the training cohort and in the validation cohort were tested using ROC analysis, in which AUROC was used to compare the performance of ANN and MELD-based scoring series using the Hanley and McNeil method. A value of P \< 0.05 was considered statistically significant.
Time frame: Up to 02 months
Laboratory Tests
Liver function tests, complete blood count and coagulation tests were performed within the first 24h after admission. The liver function tests included alanine aminotranferase, aspartate aminotranferase, total bilirubin (TBil), albumin, serum sodium, alpha-fetoprotein (AFP) and creatinine. Complete blood count was made up of platelet and hemoglobin (Hb). Coagulation tests contained prothrombin activity (PTA) and international normalized ratio (INR). Additionally, hepatitis B e antigen (HBeAg) was detected by conventional serological assays. Serum HBV DNA was measured by quantitative polymerase chain reaction(PCR) assay (Roche Amplicor, limit of detectability of 100 IU/ml) after admission.
Time frame: Up to 07 months