Retrospective Study
Copyright ©The Author(s) 2025. Published by Baishideng Publishing Group Inc. All rights reserved.
World J Gastroenterol. Apr 7, 2025; 31(13): 104697
Published online Apr 7, 2025. doi: 10.3748/wjg.v31.i13.104697
Noninvasive prediction of esophagogastric varices in hepatitis B: An extreme gradient boosting model based on ultrasound and serology
Si-Yi Feng, Zong-Ren Ding, Jin Cheng, Hai-Bin Tu
Si-Yi Feng, Jin Cheng, Hai-Bin Tu, Department of Ultrasound, Mengchao Hepatobiliary Hospital of Fujian Medical University, Fuzhou 350025, Fujian Province, China
Zong-Ren Ding, Department of Hepatopancreatobiliary Surgery, Mengchao Hepatobiliary Hospital of Fujian Medical University, Fuzhou 350025, Fujian Province, China
Co-first authors: Si-Yi Feng and Zong-Ren Ding.
Author contributions: Feng SY conceived and designed the study, performed data analysis and interpretation, and wrote the first draft of the manuscript; Ding ZR participated in study design, assisted with data interpretation, and critically revised the manuscript for important intellectual content; Feng SY and Ding ZR contributed equally to this article, they are the co-first authors of this manuscript; Cheng J conducted data collection and analysis, contributed to the development of predictive models, and reviewed the manuscript; Tu HB supervised the project, provided critical feedback during manuscript preparation, and approved the final version for submission; Feng SY, Ding ZR, Cheng J, and Tu HB accepts responsibility for the integrity of the work and agrees to be accountable for all aspects of the research; and all authors have read and approved the final manuscript.
Supported by the Agency Natural Science Foundation of Fujian Province, China, No. 2022J011285 and No. 2023J011480.
Institutional review board statement: This study was approved by the Medical Ethics Committee of Mengchao Hepatobiliary Hospital, approval No. 2022_028_01.
Informed consent statement: All patients/participants provided their written informed consent to participate in this study.
Conflict-of-interest statement: All the authors report no relevant conflicts of interest for this article.
Data sharing statement: Technical appendix, statistical code, and dataset are available from the corresponding author at thb861126@163.com.
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: Hai-Bin Tu, Department of Ultrasound, Mengchao Hepatobiliary Hospital of Fujian Medical University, No. 66 Jintang Road, Jianxin Town, Cangshan District, Fuzhou 350025, Fujian Province, China. thb861126@163.com
Received: December 31, 2024
Revised: February 20, 2025
Accepted: March 11, 2025
Published online: April 7, 2025
Processing time: 94 Days and 4.4 Hours
Core Tip

Core Tip: We constructed a noninvasive predictive model using machine learning for esophagogastric varices in hepatitis B patients. An extreme gradient boosting model, based on ultrasound and serological markers, achieved high accuracy (area under the curve = 0.96) in predicting high-risk esophagogastric varices. Key predictive variables included albumin, prothrombin time, portal vein flow velocity and spleen stiffness. A web-based application was developed to facilitate clinical use, offering real-time risk assessment. This model provides a promising tool for targeted screening, potentially reducing the need for costly and risky endoscopic procedures in low-risk individuals.