Zheng Ming-Hua, Seto Wai-Kay, Shi Ke-Qing, Wong Danny Ka-Ho, Fung James, Hung Ivan Fan-Ngai, Fong Daniel Yee-Tak, Yuen John Chi-Hang, Tong Teresa, Lai Ching-Lung, Yuen Man-Fung
Department of Infection and Liver Diseases, Liver Research Center, the First Affiliated Hospital of Wenzhou Medical University, Wenzhou, Zhejiang, China; Department of Medicine, the University of Hong Kong, Queen Mary Hospital, Hong Kong, China.
Department of Medicine, the University of Hong Kong, Queen Mary Hospital, Hong Kong, China; State Key Laboratory for Liver Research, the University of Hong Kong, Queen Mary Hospital, Hong Kong, China.
PLoS One. 2014 Jun 10;9(6):e99422. doi: 10.1371/journal.pone.0099422. eCollection 2014.
BACKGROUND & AIMS: Hepatitis B surface antigen (HBsAg) seroclearance and seroconversion are regarded as favorable outcomes of chronic hepatitis B (CHB). This study aimed to develop artificial neural networks (ANNs) that could accurately predict HBsAg seroclearance or seroconversion on the basis of available serum variables.
Data from 203 untreated, HBeAg-negative CHB patients with spontaneous HBsAg seroclearance (63 with HBsAg seroconversion), and 203 age- and sex-matched HBeAg-negative controls were analyzed. ANNs and logistic regression models (LRMs) were built and tested according to HBsAg seroclearance and seroconversion. Predictive accuracy was assessed with area under the receiver operating characteristic curve (AUROC).
Serum quantitative HBsAg (qHBsAg) and HBV DNA levels, qHBsAg and HBV DNA reduction were related to HBsAg seroclearance (P<0.001) and were used for ANN/LRM-HBsAg seroclearance building, whereas, qHBsAg reduction was not associated with ANN-HBsAg seroconversion (P = 0.197) and LRM-HBsAg seroconversion was solely based on qHBsAg (P = 0.01). For HBsAg seroclearance, AUROCs of ANN were 0.96, 0.93 and 0.95 for the training, testing and genotype B subgroups respectively. They were significantly higher than those of LRM, qHBsAg and HBV DNA (all P<0.05). Although the performance of ANN-HBsAg seroconversion (AUROC 0.757) was inferior to that for HBsAg seroclearance, it tended to be better than those of LRM, qHBsAg and HBV DNA.
ANN identifies spontaneous HBsAg seroclearance in HBeAg-negative CHB patients with better accuracy, on the basis of easily available serum data. More useful predictors for HBsAg seroconversion are still needed to be explored in the future.
乙肝表面抗原（HBsAg）血清学清除和血清学转换被视为慢性乙型肝炎（CHB）的良好转归。本研究旨在开发人工神经网络（ANN），以便能够根据可用的血清变量准确预测HBsAg血清学清除或血清学转换。
分析了203例未经治疗、HBeAg阴性的CHB患者（其中63例发生HBsAg血清学转换）自发HBsAg血清学清除的数据，以及203例年龄和性别匹配的HBeAg阴性对照的数据。根据HBsAg血清学清除和血清学转换构建并测试了人工神经网络和逻辑回归模型（LRM）。通过受试者工作特征曲线下面积（AUROC）评估预测准确性。
血清定量HBsAg（qHBsAg）和HBV DNA水平、qHBsAg和HBV DNA下降与HBsAg血清学清除相关（P<0.001），并用于构建人工神经网络/逻辑回归模型-HBsAg血清学清除，而qHBsAg下降与人工神经网络-HBsAg血清学转换无关（P = 0.197），逻辑回归模型-HBsAg血清学转换仅基于qHBsAg（P = 0.01）。对于HBsAg血清学清除，人工神经网络在训练、测试和B基因型亚组中的AUROC分别为0.96、0.93和0.95。它们显著高于逻辑回归模型、qHBsAg和HBV DNA的AUROC（均P<0.05）。虽然人工神经网络-HBsAg血清学转换的性能（AUROC 0.757）不如HBsAg血清学清除，但它往往优于逻辑回归模型、qHBsAg和HBV DNA。
人工神经网络能够根据容易获得的血清数据，更准确地识别HBeAg阴性CHB患者的自发HBsAg血清学清除。未来仍需要探索更有用的HBsAg血清学转换预测指标。
