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 14, 2026; 32(14): 115162
Published online Apr 14, 2026. doi: 10.3748/wjg.v32.i14.115162
Published online Apr 14, 2026. doi: 10.3748/wjg.v32.i14.115162
Predicting gastrointestinal bleeding and audio biomarkers based on machine learning analysis of bowel sounds
Lei Zhang, Cheng Su, School of Future Technology, Xi’an Jiaotong University, Xi’an 710049, Shaanxi Province, China
Meng-Yue Wang, Shi-Yu Wei, Chang Liu, Department of Hepatobiliary Surgery and Liver Transplantation, The Second Affiliated Hospital of Xi’an Jiaotong University, Xi’an 710000, Shaanxi Province, China
Sen-Yi Hu, Department of Biosciences, University of Liverpool, Liverpool L69 7ZX, United Kingdom
Xiao-Yang Ren, Ya-Ping Liu, Department of Gastroenterology, The First Affiliated Hospital of Xi’an Jiaotong University, Xi’an 710061, Shaanxi Province, China
Yong Wan, Department of Geriatric Surgery, The First Affiliated Hospital of Xi’an Jiaotong University, Xi’an 710061, Shaanxi Province, China
Co-corresponding authors: Chang Liu and Yong Wan.
Author contributions: Zhang L conceived the study, participated in study design, supervised data collection, and contributed to manuscript revision; Wang MY contributed substantially to the study design, data preprocessing, signal analysis, statistical modeling, and drafting of the manuscript, played a major role in result interpretation and figure preparation; Wei SY assisted in clinical data collection, bowel sound acquisition, and preliminary data cleaning; Su C participated in feature extraction, algorithm implementation, and model optimization; Hu SY assisted in patient recruitment, gastroscopy data verification, and clinical variable management; Ren XY supported the statistical analysis, participated in performance evaluation, and contributed to manuscript editing; Liu YP assisted in literature review, quality control of clinical records, and supplementary experiment verification; Liu C provided methodological guidance, supervised overall research progress, and critically reviewed the manuscript; Wan Y provided conceptual guidance, ensured clinical relevance, supervised the study, and finalized the manuscript. Liu C and Wan Y made equal contributions as co-corresponding authors. All authors approved the final version to publish.
Supported by Key Project of Shaanxi Provincial Natural Science Basic Research Program, No. 2024JC-ZDXM-49; and The Integration of Basic Shaanxi Wisdom Medical Common Technology Platform, No. 2023GXJS-01.
Institutional review board statement: This study was approved by the Institutional Review Board of the First Affiliated Hospital of Xi’an Jiaotong University, No. XJTU1AF2025 LSYY-633.
Informed consent statement: All participants were fully informed of the purpose, procedures, potential risks, and benefits of this study before enrollment. Written informed consent was obtained from each participant prior to data collection. Participants were assured that their involvement was voluntary and that they could withdraw from the study at any time without affecting their medical care.
Conflict-of-interest statement: All the authors report no relevant conflicts of interest for this article.
CONSORT 2010 statement: The authors have read the CONSORT 2010 Statement, and the manuscript was prepared and revised according to the CONSORT 2010 Statement.
Data sharing statement: The data generated in this study, after de-identification, are available from the corresponding author upon reasonable request. The data are intended for academic research purposes only, and requestors must comply with relevant ethical guidelines and privacy protection requirements.
Corresponding author: Yong Wan, MD, Department of Geriatric Surgery, The First Affiliated Hospital of Xi’an Jiaotong University, No. 277 West Yanta Road, Xi’an 710061, Shaanxi Province, China. docwanyong@xjtu.edu.cn
Received: October 14, 2025
Revised: December 15, 2025
Accepted: January 30, 2026
Published online: April 14, 2026
Processing time: 175 Days and 20.7 Hours
Revised: December 15, 2025
Accepted: January 30, 2026
Published online: April 14, 2026
Processing time: 175 Days and 20.7 Hours
Core Tip
Core Tip: This study develops a machine learning-based screening tool to identify upper gastrointestinal bleeding (UGIB) patients using multidimensional bowel sound (BS) features. It also explores pathological associations between UGIB-related BSs characteristics and blood biochemical indicators, leveraging feature importance evaluation and SHapley Additive exPlanations analysis to identify interpretable predictors. This study pioneers a noninvasive BS analysis tool for UGIB screening, leveraging multidimensional acoustic feature engineering and machine learning optimization.