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): 116105
Published online Apr 21, 2026. doi: 10.3748/wjg.v32.i15.116105
Published online Apr 21, 2026. doi: 10.3748/wjg.v32.i15.116105
Deep learning-enhanced prediction of small intestinal bleeding points using long short-term memory networks
Hsin-Yu Kuo, Department of Internal Medicine, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan 701, Taiwan
Kun-Hua Lee, Department of Trauma, Changhua Christian Hospital, Changhua 50006, Taiwan
Chu-Kuang Chou, Division of Gastroenterology and Hepatology, Department of Internal Medicine, Ditmanson Medical Foundation Chia-Yi Christian Hospital, Chiayi 60002, Taiwan
Arvind Mukundan, Department of Computer Science Engineering, School of Engineering and Technology, Sanjivani University, Kopargaon, Maharastra 423603, India
Arvind Mukundan, Department of Mechanical Engineering, Advanced Institute of Manufac
Riya Karmakar, Department of Integrated B.Tech, School of Engineering and Technology, Sanjivani University, Kopargaon, Maharastra 423603, India
Riya Karmakar, Thong-Lin Wang, Hsiang-Chen Wang, Department of Mechanical Engineering, National Chung Cheng University, Chiayi 62102, Taiwan
Tsung-Hsien Chen, Department of Internal Medicine, Ditmanson Medical Foundation Chiayi Christian Hospital, Chiayi 60002, Taiwan
Ping-Hung Liu, Division of General Surgery, Kaohsiung Armed Forces General Hospital, Kaohsiung 80284, Taiwan
Co-corresponding authors: Ping-Hung Liu and Hsiang-Chen Wang.
Author contributions: Mukundan A, Lee KH, Wang TL and Wang HC designed the research; Lee KH and Kuo HY performed data curation; Lee KH and Karmakar R performed formal analysis; Lee KH acquired funding; Kuo HY, Mukundan A, Chen TH and Wang HC performed the investigation; Karmakar R, Mukundan A, Kuo HY, Wang TL, Chou CK, Liu PH and Wang HC contributed to methodology; Kuo HY contributed to project administration; Karmakar R provided resources; Karmakar R, Mukundan A, Wang TL, Chen TH and Chou CK developed the software; Liu PH, Chou CK, Chen TH and Wang HC supervised the study; Kuo HY, Karmakar R, Chen TH and Wang HC validated the results; Chou CK and Wang HC contributed to visualization; Chen TH, Kuo HY, Mukundan A and Chou CK wrote the original draft; Liu PH and Wang HC wrote, reviewed and edited the manuscript. All authors have read and agreed to the published version of the manuscript.
Supported by the National Science and Technology Council of the Republic of China, No. NSTC 113-2221-E-194-011-MY3 and No. NSTC 114-2314-B-006-095-MY3; National Cheng Kung University Hospital, No. NCKUH-11404023; and the Dalin Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation-National Chung Cheng University Joint Research Program and Kaohsiung Armed Forces General Hospital Research Program, Research Center on Artificial Intelligence and Sustainability, National Chung Cheng University, Taiwan under the “Generative Digital Twin System Design for Sustainable Smart City Development in Taiwan”, No. KAFGH_D_115045.
Institutional review board statement: The study was conducted according to the guidelines of the Declaration of Helsinki and approved by the Institutional Review Board of National Cheng Kung University Hospital (No. A-ER-111-145). National Cheng Kung University Hospital waived the informed consent to publish.
Informed consent statement: Written informed consent was waived in this study because of the retrospective, anonymized nature of the study design.
Conflict-of-interest statement: All authors declare that they have no conflict of interest.
STROBE statement: The authors have read the STROBE Statement—checklist of items, and the manuscript was prepared and revised according to the STROBE Statement—checklist of items.
Data sharing statement: The datasets generated and/or analyzed during the current study are not publicly available due to restrictions regarding patient privacy and ethical considerations. However, the de-identified data are available from the corresponding author on reasonable request.
Corresponding author: Hsiang-Chen Wang, Professor, Department of Mechanical Engineering, National Chung Cheng University, No. 168 University Road, Chiayi 62102, Taiwan.
Received: November 3, 2025
Revised: December 14, 2025
Accepted: January 27, 2026
Published online: April 21, 2026
Processing time: 164 Days and 3.3 Hours
Revised: December 14, 2025
Accepted: January 27, 2026
Published online: April 21, 2026
Processing time: 164 Days and 3.3 Hours
Core Tip
Core Tip: This study proposes a practical deep learning pipeline that combines convolutional neural networks for spatial feature extraction with long short-term memory networks for temporal modeling to detect small intestinal bleeding in capsule endoscopy videos. Using datasets from a clinical cohort and the Kvasir-Capsule collection, we show that models trained with richer multiclass labels yield more informative features for sequential prediction, enabling higher long short-term memory accuracy and lower temporal error than binary setups. The approach delivers consistent frame-by-frame detection performance with clinically feasible processing speed, highlights the value of leveraging temporal dependencies beyond single-frame analysis, and outlines a path toward interpretable, efficient triage in capsule endoscopy workflows.