Copyright
©The Author(s) 2025. Published by Baishideng Publishing Group Inc. All rights reserved.
World J Gastroenterol. Nov 7, 2025; 31(41): 111361
Published online Nov 7, 2025. doi: 10.3748/wjg.v31.i41.111361
Published online Nov 7, 2025. doi: 10.3748/wjg.v31.i41.111361
Development of a deep learning model for guiding treatment decisions of acute variceal bleeding in patients with cirrhosis
Yi Xiang, Xiao-Long Qi, Liver Disease Center of Integrated Traditional Chinese and Western Medicine, Department of Radiology, Zhongda Hospital, Medical School, Southeast University, Nurturing Center of Jiangsu Province for State Laboratory of AI Imaging and Interventional Radiology (Southeast University), Nanjing 210009, Jiangsu Province, China
Yi Xiang, Xiao-Long Qi, Basic Medicine Research and Innovation Center of Ministry of Education, Zhongda Hospital, Southeast University, State Key Laboratory of Digital Medical Engineering, Nanjing 210009, Jiangsu Province, China
Yi Xiang, The First Affiliated Hospital, Gannan Medical University, Ganzhou 341000, Jiangxi Province, China
Na Yang, Bin Liu, The Engineering Research Center of Intelligent Theranostics Technology and Instruments, Ministry of Education, School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing 211166, Jiangsu Province, China
Na Yang, Tian-Lei Zheng, Shi Geng, Lei Zhao, Artificial Intelligence Unit, Department of Medical Equipment Management, Affiliated Hospital of Xuzhou Medical University, Xuzhou 221006, Jiangsu Province, China
Tian-Lei Zheng, School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, Jiangsu Province, China
Yi-Fei Huang, Xing Wang, Bin Wu, Department of Gastroenterology, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou 510630, Guangdong Province, China
Tian-Yu Liu, Department of Gastroenterology, Suining Central Hospital, Suining 629000, Sichuan Province, China
De-Qiang Ma, Department of Infectious Diseases, Hubei Provincial Clinical Research Center for Precise Diagnosis and Treatment of Liver Cancer, Taihe Hospital, Hubei University of Medicine, Shiyan 442000, Hubei Province, China
Sheng-Juan Hu, People’s Hospital of Ningxia Hui Autonomous Region (Ningxia Medical University Affiliated People’s Hospital of Autonomous Region), Yinchuan 750004, Ningxia Hui Autonomous Region, China
Wen-Hui Zhang, Department of Digestive System, Beijing Daxing District People’s Hospital, Beijing 102600, China
Wen-Hui Zhang, Diagnosis and Treatment Center, The Fifth Medical Center of PLA General Hospital, Beijing 100039, China
Hui-Ling Xiang, Department of Gastroenterology and Hepatology, Tianjin Third Central Hospital, Tianjin Key Laboratory of Extracorporeal Life Support for Critical Diseases, Institute of Hepatobiliary Disease, Tianjin 300170, China
Li-Yao Zhang, CHESS Center, The Sixth People’s Hospital of Shenyang, Shenyang 110006, Liaoning Province, China
Li-Li Yuan, Department of Gastroenterology, Shanxi Bethune Hospital, Taiyuan 030032, Shanxi Province, China
Tong Dang, Inner Mongolia Institute of Digestive Diseases, The Second Affiliated Hospital of Baotou Medical College, Inner Mongolia University of science and technology, Baotou 014010, Inner Mongolia Autonomous Region, China
Guo Zhang, The People’s Hospital, Nanning 530021, Guangxi Zhuang Autonomous Region, China
Li-Jun Peng, Department of Gastroenterology, Linyi People’s Hospital, Linyi 276003, Shan
Min Gao, Department of Gastroenterology, Sir Run Run Shaw Hospital, School of Medicine, Zhejiang University, Hangzhou 310016, Zhejiang Province, China
Dong-Li Xia, Zhen-Bei Liu, Department of Gastroenterology, Chongqing University Fuling Hospital, Chongqing 408000, China
Jia Li, Department of Gastroenterology and Hepatology, Tianjin Second People’s Hospital, Tianjin 300192, China
Ying Song, Department of Gastroenterology, Xi’an GaoXin Hospital, Xi’an 710075, Shaanxi Province, China
Xi-Qiao Zhou, Department of Gastroenterology, First Affiliated Hospital of Nanjing Medical University, Nanjing 210029, Jiangsu Province, China
Xing-Si Qi, Department of Gastroenterology, The Affiliated Hospital of Qingdao University, Qingdao 266003, Shandong Province, China
Jing Zeng, Department of Emergency, Huizhou Third People’s Hospital, Guangzhou Medical University, Huizhou 516000, Guangdong Province, China
Xiao-Yan Tan, Department of Gastroenterology, Maoming People’s Hospital, Maoming 525000, Guangdong Province, China
Ming-Ming Deng, Department of Gastroenterology, The Affiliated Hospital of Southwest Medical University, Luzhou 646000, Sichuan Province, China
Hai-Ming Fang, Department of Gastroenterology and Hepatology, The Second Hospital of Anhui Medical University, Hefei 230601, Anhui Province, China
Sheng-Lin Qi, Department of Hepatology, Dalian Sixth People’s Hospital, Dalian 116031, Liaoning Province, China
Song He, Department of Gastroenterology, The Second Affiliated Hospital of Chongqing Medical University, Chongqing 400010, China
Yong-Feng He, Department of Gastroenterology, Endoscopic Center, Ankang Central Hospital, Ankang 725000, Shaanxi Province, China
Bin Ye, Department of Gastroenterology, Lishui Hospital of Zhejiang University, The Fifth Affiliated Hospital of Wenzhou Medical University, Lishui Central Hospital, Lishui 323000, Zhejiang Province, China
Wei Wu, Department of Gastroenterology, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, Zhejiang Province, China
Jiang-Bo Shao, Department of Liver Disease, The Third People’s Hospital of Zhenjiang, Zhenjiang 212000, Jiangsu Province, China
Wei Wei, Department of Gastroenterology, Affiliated Jinhua Hospital, Zhejiang University School of Medicine, Jinhua 321000, Zhejiang Province, China
Jian-Ping Hu, Department of Gastroenterology, First People’s Hospital of Yinchuan City, Yinchuan 750001, Ningxia Hui Autonomous Region, China
Xin Yong, Department of Gastroenterology, General Hospital of Western Theater Command, Chengdu 610000, Sichuan Province, China
Chao-Hui He, Department of Gastroenterology and Endoscopy, The Fifth affiliated Zhuhai Hospital of Zunyi Medical University, Zhuhai 519000, Guangdong Province, China
Jin-Lun Bao, Department of Gastroenterology, Shannan People’s Hospital, Shannan 856000, Tibet Autonomous Region, China
Yue-Ning Zhang, Center of Hepatology and Gastroenterology, Beijing You’an Hospital, Capital Medical University, Beijing 100069, China
Rui Ji, Department of Gastroenterology, The First Hospital of Lanzhou University, Lanzhou 730000, Gansu Province, China
Yang Bo, Department of Hepatobiliary Surgery, People’s Hospital of Ningxia Hui Autonomous Region, Yinchuan 750000, Ningxia Hui Autonomous Region, China
Wei Yan, Department of Gastroenterology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Tech
Hong-Jiang Li, Department of Hepatology, Baoding People’s Hospital, Baoding 071000, Hebei Province, China
Sheng-Li Li, Clinical Research Institute, The Affiliated Hospital of Xuzhou Medical University, Xuzhou 221006, Jiangsu Province, China
Co-first authors: Yi Xiang and Na Yang.
Co-corresponding authors: Bin Liu and Xiao-Long Qi.
Author contributions: Qi XL and Liu B accept full responsibility for the conduct of the study and had full access to the data and control of the decision to publish; Xiang Y conceived the overall study and drafted the manuscript; Yang N led the development of the artificial intelligence model; Zheng TL validated the artificial intelligence model; Huang YF and Liu TY performed the statistical analysis; Ma DQ and Zhang WH created the figures; Xiang HL, Zhang LY, Yuan LL, and Wang X collected endoscopic treatment cohort data; Liu TY, Dang T, Zhang G, Hu SJ, Wu B, and Peng LJ collected transjugular intrahepatic portosystemic shunt treatment cohort data; Gao M, Xia DL, Liu ZB, Li J, Song Y, Zhou XQ, and Qi XS conducted follow-up on enrolled patients; Ma DQ, Zeng J, Tan XY, Deng MM, and Fang HM organized and archived baseline patient data and follow-up information; Qi SL and He S managed ethical review processes; He YF, Ye B, Wu W, Shao JB, and Wei W facilitated project progress; Hu JP, Yong X, He CH, and Bao JL wrote the methods and materials section; Zhang YN, Ji R, Bo Y, and Yan W prepared patients for surgery; Li HJ and Li SL assisted in revising the manuscript draft; Geng S and Zhao L supported the artificial intelligence model’s platform setup and algorithm implementation; Liu B was responsible for the overall project; Qi XL conceived the study and acquired case data from various hospitals.
Supported by Key Research and Development Program of Jiangsu Province, No. BE2023767; Xuzhou Key Research and Development Program under Grant, No. KC23273; Affiliated Hospital of Xuzhou Medical University, No. 2022ZL26; and Construction Project of High-Level Hospital of Jiangsu Province, No. GSPSJ20240802.
Institutional review board statement: This study adhered to the ethical principles of the Declaration of Helsinki, and the study protocols were approved by the Ethics Committee of Zhongda Hospital, Southeast University.
Informed consent statement: Given the retrospective nature of this study, the requirement for informed consent was waived.
Conflict-of-interest statement: The authors declare that they have no conflict of interest.
STROBE statement: The authors have read the STROBE Statement—a checklist of items, and the manuscript was prepared and revised according to the STROBE Statement-a checklist of items.
Data sharing statement: The source codes of the artificial intelligence-acute variceal bleeding model and the complete dataset included in the study are available from the corresponding authors upon reasonable request. The online calculator for risk stratification of standard treatment failure in acute variceal bleeding patients is available on our server website at https://chess.nuist.edu.cn/index.
Open Access: This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: https://creativecommons.org/Licenses/by-nc/4.0/
Corresponding author: Xiao-Long Qi, MD, Professor, Liver Disease Center of Integrated Traditional Chinese and Western Medicine, Department of Radiology, Zhongda Hospital, Medical School, Southeast University, Nurturing Center of Jiangsu Province for State Laboratory of AI Imaging and Interventional Radiology (Southeast University), No. 87 Dingjiaqiao, Nanjing 210009, Jiangsu Province, China. qixiaolong@vip.163.com
Received: July 1, 2025
Revised: August 19, 2025
Accepted: September 28, 2025
Published online: November 7, 2025
Processing time: 131 Days and 1 Hours
Revised: August 19, 2025
Accepted: September 28, 2025
Published online: November 7, 2025
Processing time: 131 Days and 1 Hours
Abstract
BACKGROUND
Acute variceal bleeding (AVB) in patients with cirrhosis remains life-threatening; moreover, the current risk stratification methods have certain limitations. Rebleeding and mortality after AVB remain major challenges. Although preemptive transjugular intrahepatic portosystemic shunt (p-TIPS) can improve outcomes, not all patients benefit equally. Accurate risk stratification is needed to guide treatment decisions and identify those most likely to benefit from p-TIPS.
AIM
To develop an artificial intelligence (AI)-driven model to guide AVB treatment decisions, and identify candidates eligible for p-TIPS.
METHODS
Patients with cirrhosis and AVB, from two multicenter retrospective cohorts in China, who received endoscopic variceal ligation plus pharmacotherapy (n = 1227) or p-TIPS (n = 1863) were included. Baseline data within 24 hours of hospital admission were obtained. The AI-AVB model, based on the six-week failure and one-year mor
RESULTS
The AI-AVB model demonstrated superior predictive performance compared to traditional risk stratification methods. In the internal validation cohort, the model achieved an area under the curve (AUC) of 0.842 for predicting six-week treatment failure and 0.954 for one-year mortality. In the external validation cohort, the AUCs were 0.814 and 0.889, respectively. The model effectively identified patients at high risk of first-line treatment failure who may benefit from aggressive interventions such as p-TIPS. In contrast, advancing the treatment stra
CONCLUSION
The AI-AVB model can predict treatment outcomes, stratify the failure risk in cirrhotic patients with AVB, aid in clinical decisions, identify p-TIPS beneficiaries, and optimize personalized treatment strategies.
Keywords: Acute variceal bleeding; Liver cirrhosis; Deep learning; Risk stratification; Endoscopic therapy; Preemptive trans
Core Tip: A novel deep learning model was developed to predict treatment outcomes in patients with acute variceal bleeding, a life-threatening condition that is often observed in patients with cirrhosis. By analyzing clinical data collected within 24 hours of hospital admission, the artificial intelligence model can effectively identify high-risk patients who may benefit from more aggressive treatments, such as preemptive transjugular intrahepatic portosystemic shunt, while also helping avoid unwarranted invasive procedures for low-risk patients.