Copyright: ©Author(s) 2026. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial (CC BY-NC 4.0) license. No commercial re-use. See permissions. Published by Baishideng Publishing Group Inc.
World J Gastroenterol. Apr 21, 2026; 32(15): 116679
Published online Apr 21, 2026. doi: 10.3748/wjg.v32.i15.116679
Published online Apr 21, 2026. doi: 10.3748/wjg.v32.i15.116679
Deep learning-based multimodal model for predicting on-treatment histological outcomes in chronic hepatitis B-associated advanced liver fibrosis
Wei Han, Quan-Wei He, Yong-Ping Yang, Liver Disease Research Center, Hainan Hospital of Chinese PLA General Hospital, Sanya 572013, Hainan Province, China
Wei Han, Ding-Yuan Cheng, Si-Hao Wang, Shu-Juan Gong, Yong-Ping Yang, Medical School of Chinese PLA, Chinese PLA General Hospital, Beijing 100853, China
Wei Han, Yan Chen, Yong-Ping Yang, Faculty of Liver Disease of Chinese PLA General Hospital, The Fifth Medical of Chinese PLA General Hospital, Beijing 100039, China
Co-first authors: Wei Han and Ding-Yuan Cheng.
Co-corresponding authors: Yan Chen and Yong-Ping Yang.
Author contributions: Han W and Cheng DY performed the study, trained the deep learning models, carried out the analyses, and drafted the original manuscript, contributed equally as co-first authors; He QW, Wang SH, and Gong SJ collected the data and performed part of analysis; Yang YP and Chen Y contributed to the design of the study, and critically reviewed and revised the manuscript, contributed equally as co-corresponding authors; all authors have read and approve the final manuscript.
Supported by State Key Projects Specialized on Infectious Disease, Chinese Ministry of Science and Technology, No. 2013ZX10005002; and Beijing Key Research Project of Special Clinical Application, No. Z221100007422002.
Institutional review board statement: This study was approved the Institutional Review Board of The 302nd Hospital of the Chinese PLA, No. 2013145D.
Informed consent statement: All study participants, or their legal guardian, provided informed written consent prior to study enrollment.
Conflict-of-interest statement: All the authors report no relevant conflicts of interest for this article.
Data sharing statement: The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.
Corresponding author: Yong-Ping Yang, Liver Disease Research Center, Hainan Hospital of Chinese PLA General Hospital, Haitang Bay, Sanya 572013, Hainan Province, China.
Received: November 18, 2025
Revised: December 20, 2025
Accepted: January 28, 2026
Published online: April 21, 2026
Processing time: 148 Days and 20.2 Hours
Revised: December 20, 2025
Accepted: January 28, 2026
Published online: April 21, 2026
Processing time: 148 Days and 20.2 Hours
Core Tip
Core Tip: This study presents a multimodal model that integrates pathological slide staining with clinical features to predict the probability of histological reversal following standard antiviral therapy in patients with advanced chronic hepatitis B-related fibrosis. The model demonstrates robust predictive accuracy in both internal validation and external test sets. This methodology supports patient risk stratification and informs the development of personalized, optimized treatment strategies.