Artificial neural network accurately predicts hepatitis B surface antigen seroclearance.

<h4>Background & aims</h4>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 seroconve...

Full description

Saved in:
Bibliographic Details
Main Authors: Ming-Hua Zheng, Wai-Kay Seto, Ke-Qing Shi, Danny Ka-Ho Wong, James Fung, Ivan Fan-Ngai Hung, Daniel Yee-Tak Fong, John Chi-Hang Yuen, Teresa Tong, Ching-Lung Lai, Man-Fung Yuen
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2014-01-01
Series:PLoS ONE
Online Access:https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0099422&type=printable
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850191309536493568
author Ming-Hua Zheng
Wai-Kay Seto
Ke-Qing Shi
Danny Ka-Ho Wong
James Fung
Ivan Fan-Ngai Hung
Daniel Yee-Tak Fong
John Chi-Hang Yuen
Teresa Tong
Ching-Lung Lai
Man-Fung Yuen
author_facet Ming-Hua Zheng
Wai-Kay Seto
Ke-Qing Shi
Danny Ka-Ho Wong
James Fung
Ivan Fan-Ngai Hung
Daniel Yee-Tak Fong
John Chi-Hang Yuen
Teresa Tong
Ching-Lung Lai
Man-Fung Yuen
author_sort Ming-Hua Zheng
collection DOAJ
description <h4>Background & aims</h4>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.<h4>Methods</h4>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).<h4>Results</h4>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.<h4>Conclusions</h4>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.
format Article
id doaj-art-101c2f6e867646469e73a4e00a35bc93
institution OA Journals
issn 1932-6203
language English
publishDate 2014-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-101c2f6e867646469e73a4e00a35bc932025-08-20T02:14:57ZengPublic Library of Science (PLoS)PLoS ONE1932-62032014-01-0196e9942210.1371/journal.pone.0099422Artificial neural network accurately predicts hepatitis B surface antigen seroclearance.Ming-Hua ZhengWai-Kay SetoKe-Qing ShiDanny Ka-Ho WongJames FungIvan Fan-Ngai HungDaniel Yee-Tak FongJohn Chi-Hang YuenTeresa TongChing-Lung LaiMan-Fung Yuen<h4>Background & aims</h4>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.<h4>Methods</h4>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).<h4>Results</h4>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.<h4>Conclusions</h4>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.https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0099422&type=printable
spellingShingle Ming-Hua Zheng
Wai-Kay Seto
Ke-Qing Shi
Danny Ka-Ho Wong
James Fung
Ivan Fan-Ngai Hung
Daniel Yee-Tak Fong
John Chi-Hang Yuen
Teresa Tong
Ching-Lung Lai
Man-Fung Yuen
Artificial neural network accurately predicts hepatitis B surface antigen seroclearance.
PLoS ONE
title Artificial neural network accurately predicts hepatitis B surface antigen seroclearance.
title_full Artificial neural network accurately predicts hepatitis B surface antigen seroclearance.
title_fullStr Artificial neural network accurately predicts hepatitis B surface antigen seroclearance.
title_full_unstemmed Artificial neural network accurately predicts hepatitis B surface antigen seroclearance.
title_short Artificial neural network accurately predicts hepatitis B surface antigen seroclearance.
title_sort artificial neural network accurately predicts hepatitis b surface antigen seroclearance
url https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0099422&type=printable
work_keys_str_mv AT minghuazheng artificialneuralnetworkaccuratelypredictshepatitisbsurfaceantigenseroclearance
AT waikayseto artificialneuralnetworkaccuratelypredictshepatitisbsurfaceantigenseroclearance
AT keqingshi artificialneuralnetworkaccuratelypredictshepatitisbsurfaceantigenseroclearance
AT dannykahowong artificialneuralnetworkaccuratelypredictshepatitisbsurfaceantigenseroclearance
AT jamesfung artificialneuralnetworkaccuratelypredictshepatitisbsurfaceantigenseroclearance
AT ivanfanngaihung artificialneuralnetworkaccuratelypredictshepatitisbsurfaceantigenseroclearance
AT danielyeetakfong artificialneuralnetworkaccuratelypredictshepatitisbsurfaceantigenseroclearance
AT johnchihangyuen artificialneuralnetworkaccuratelypredictshepatitisbsurfaceantigenseroclearance
AT teresatong artificialneuralnetworkaccuratelypredictshepatitisbsurfaceantigenseroclearance
AT chinglunglai artificialneuralnetworkaccuratelypredictshepatitisbsurfaceantigenseroclearance
AT manfungyuen artificialneuralnetworkaccuratelypredictshepatitisbsurfaceantigenseroclearance