Download PDF
Open Access
CC BY 4.0 · Endoscopy
DOI: 10.1055/a-2721-6552
Original article

A rural-to-center artificial intelligence model for diagnosing Helicobacter pylori infection and premalignant gastric conditions using endoscopy images captured in routine practice

Authors

  • Tsung-Hsien Chiang

    1   Department of Integrated Diagnostics and Therapeutics, National Taiwan University Hospital, Taipei City, Taiwan (Ringgold ID: RIN38006)
    2   Department of Internal Medicine, College of Medicine, National Taiwan University, Taipei City, Taiwan

  • Yen-Ning Hsu

    3   Center of Intelligent Healthcare, National Taiwan University Hospital, Taipei City, Taiwan (Ringgold ID: RIN38006)

  • Min-Han Chen

    3   Center of Intelligent Healthcare, National Taiwan University Hospital, Taipei City, Taiwan (Ringgold ID: RIN38006)

  • Yi-Ru Chen

    2   Department of Internal Medicine, College of Medicine, National Taiwan University, Taipei City, Taiwan

  • Hsiu-Chi Cheng

    4   Department of Internal Medicine, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan City, Taiwan
    5   Institute of Clinical Medicine, College of Medicine, National Cheng Kung University, Tainan City, Taiwan
    6   Institute of Molecular Medicine, College of Medicine, National Cheng Kung University, Tainan City, Taiwan

  • Mei-Jin Chen

    7   Nangan Township, Bureau of Public Health, Matsu Islands, Lienchiang County, Taiwan

  • Fu-Jen Lee

    8   Department of Internal Medicine, Fu Jen Catholic University Hospital, New Taipei City, Taiwan (Ringgold ID: RIN485856)

  • Chi-Yang Chang

    8   Department of Internal Medicine, Fu Jen Catholic University Hospital, New Taipei City, Taiwan (Ringgold ID: RIN485856)
    9   School of Medicine, ollege of Medicine, Fu Jen Catholic University, New Taipei City, Taiwan

  • Chun-Chao Chang

    10   Division of Gastroenterology and Hepatology, Department of Internal Medicine, Taipei Medical University Hospital, Taipei City, Taiwan
    11   Division of Gastroenterology and Hepatology, Department of Internal Medicine, School of Medicine, College of Medicine, Taipei Medical University, Taipei City, Taiwan
    12   Taipei Medical University Research Center for Digestive Medicine, Taipei Medical University, Taipei City, Taiwan

  • Ming-Jong Bair

    13   Division of Gastroenterology, Department of Internal Medicine, Taitung Mackey Memorial Hospital, Taitung, Taiwan
    14   Mackay Medical College, New Taipei City, Taiwan

  • Jyh-Ming Liou

    2   Department of Internal Medicine, College of Medicine, National Taiwan University, Taipei City, Taiwan
    15   Department of Medicine, National Taiwan University Cancer Center, Taipei City, Taiwan

  • Chiuan-Jung Chen

    16   Information Technology Office, National Taiwan University Hospital, Taipei City, Taiwan (Ringgold ID: RIN38006)

  • Yen-Chung Chen

    17   Department of Pathology, National Yang Ming Chiao Tung University Hospital, Yilan City, Taiwan (Ringgold ID: RIN218818)

  • Hung Chiang

    18   Taipei Institute of Pathology, Taipei City, Taiwan

  • Chia-Tung Shun

    19   Department of Pathology, College of Medicine, National Taiwan University, Taipei City, Taiwan

  • Jui-Hsuan Liu

    20   Lienchiang County Hospital, Nangan Township, Lienchiang County, Matsu Islands, Taiwan, Matsu Islands, Taiwan

  • Han-Mo Chiu

    2   Department of Internal Medicine, College of Medicine, National Taiwan University, Taipei City, Taiwan

  • Ming-Shiang Wu

    2   Department of Internal Medicine, College of Medicine, National Taiwan University, Taipei City, Taiwan

  • Jiun-Yu Yu

    21   Department and Graduate Institute of Business Administration, National Taiwan University, Taipei City, Taiwan (Ringgold ID: RIN33561)

  • Ruey-Shan Guo

    21   Department and Graduate Institute of Business Administration, National Taiwan University, Taipei City, Taiwan (Ringgold ID: RIN33561)

  • Jaw-Town Lin

    22   Division of Gastroenterology and Hepatology, Department of Internal Medicine, E-Da Hospital, Kaohsiung City, Taiwan

  • Yi-Chia Lee  ‡

    2   Department of Internal Medicine, College of Medicine, National Taiwan University, Taipei City, Taiwan
    23   Department of Medical Research, National Taiwan University Hospital, Taipei City, Taiwan

  • Chu-Song Chen‡

    24   Department of Computer Science and Information Engineering, National Taiwan University, Taipei City, Taiwan (Ringgold ID: RIN33561)

Supported by: National Taiwan University Hospital 114-E0009
Supported by: National Science and Technology Council 111-2314-B-002-136-MY3 and 114-2314-B-002-245-MY3

Clinical Trial:

Registration number (trial ID): NCT05762991, Trial registry: ClinicalTrials.gov (http://www.clinicaltrials.gov/), Type of Study: Prospective


Further Information
Also available at
  Permissions and Reprints


Graphical Abstract

Referred to by:

Artificial intelligence in endoscopy: a yet underused but promising tool in underserved settingsEndoscopy eFirst
DOI: 10.1055/a-2750-5476

Abstract

Background

Diagnosing Helicobacter pylori infection and premalignant gastric conditions typically requires 13C urea breath testing or histological assessment, which are often unavailable in remote areas. A rural-to-center artificial intelligence (AI) model was developed and implemented to automatically evaluate upper endoscopy images from routine clinical practice.

Methods

Endoscopic images were collected from a rural hospital on Matsu Islands and a tertiary center across Taiwan Strait. During model development (2020–2022), AI algorithms were trained, validated, and tested to exclude low-quality and non-gastric images, segment gastric regions, and enhance mucosal features for detecting H. pylori infection and premalignant conditions. During model implementation (2023–2024), endoscopic images from a rural hospital were transmitted to the medical center for AI analyses, with results promptly returned.

Results

In the development phase, diagnostic accuracies were 92.8% (95%CI 88.9%–96.6%) for H. pylori, 88.6% (95%CI 87.2%–90.0%) for atrophic gastritis, and 88.0% (95%CI 86.5%–89.5%) for intestinal metaplasia. In the implementation phase, 3518 rural residents underwent 13C urea breath testing or pepsinogen testing; 421 with positive results underwent endoscopy. No significant differences were observed between AI-predicted and clinically observed prevalence: H. pylori (13.9% vs. 12.9%; P = 0.55), atrophic gastritis (15.7% vs. 11.9%; P = 0.34), and intestinal metaplasia (27.6% vs. 22.4%; P = 0.32). Implementation-phase diagnostic accuracies were 91.3% (95%CI 88.0%–94.6%), 79.9% (95%CI 72.1%–86.3%), and 63.4% (95%CI 54.7%–71.6%), respectively.

Conclusions

AI enabled physicians in resource-limited settings to rapidly assess gastric health using routinely captured endoscopic images, bridging gaps in access and expertise.

Supplementary Material



Publication History

Received: 23 May 2025

Accepted after revision: 12 October 2025

Accepted Manuscript online:
13 October 2025

Article published online:
26 November 2025

© 2025. The Author(s). This is an open access article published by Thieme under the terms of the Creative Commons Attribution License, permitting unrestricted use, distribution, and reproduction so long as the original work is properly cited. (https://creativecommons.org/licenses/by/4.0/).

Georg Thieme Verlag KG
Oswald-Hesse-Straße 50, 70469 Stuttgart, Germany