EUVIMEDEUVIMED entdecken
Klinische StudieOpen Access · CC BY 4.0

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

Tsung-Hsien Chiang, Yen-Ning Hsu, Min-Han Chen, Yi-Ru Chen, Hsiu-Chi Cheng, Mei-Jin Chen, Fu-Jen Lee, Chi-Yang Chang, Chun-Chao Chang, Ming-Jong Bair, Jyh-Ming Liou, Chiuan-Jung Chen und 11 weitere

Endoscopy · 2026-04 · 58 (04) · 343-354

DOI: 10.1055/a-2721-6552 ↗

Kurz gefasst

Klinische Studie in der Zeitschrift Endoscopy, online erschienen am 26.11.2025. Verfasst von Tsung-Hsien Chiang und 22 weiteren Autor:innen. Beteiligte Einrichtung: Department of Integrated Diagnostics and Therapeutics, National Taiwan University Hospital, Taipei City, Taiwan. Hauptthemen laut MEDLINE: Helicobacter Infections, Precancerous Conditions, Artificial Intelligence, Gastritis, Atrophic. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Taiwan University Hospital, National Science and Technology Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Helicobacter InfectionsPrecancerous ConditionsArtificial IntelligenceGastritis, AtrophicStomach NeoplasmsGastroscopyHumansHelicobacter pyloriMaleFemaleMiddle AgedBreath TestsAgedAdultTaiwanHospitals, RuralMetaplasiaGastric Mucosa

Autor:innen und Institutionen

  • Department of Integrated Diagnostics and Therapeutics, National Taiwan University Hospital, Taipei City, Taiwan.
  • Department of Internal Medicine, College of Medicine, National Taiwan University, Taipei City, Taiwan.
  • Center of Intelligent Healthcare, National Taiwan University Hospital, Taipei City, Taiwan.
  • Department of Internal Medicine, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan City, Taiwan.
  • Institute of Clinical Medicine, College of Medicine, National Cheng Kung University, Tainan City, Taiwan.
  • Institute of Molecular Medicine, College of Medicine, National Cheng Kung University, Tainan City, Taiwan.

ORCID-Profile: Yi-Chia Lee

Förderung

  • National Taiwan University Hospital
  • National Science and Technology Council

Zitieren

APA

Chiang, T. H., Hsu, Y. N., Chen, M. H., Chen, Y. R., Cheng, H. C., Chen, M. J., Lee, F. J., Chang, C. Y., Chang, C. C., Bair, M. J., Liou, J. M., Chen, C. J., Chen, Y. C., Chiang, H., Shun, C. T., Liu, J. H., Chiu, H. M., Wu, M. S., Yu, J. Y., …, & Chen, C. S. (2026). A rural-to-center artificial intelligence model for diagnosing Helicobacter pylori infection and premalignant gastric conditions using endoscopy images captured in routine practice. Endoscopy, 58(04), 343-354. https://doi.org/10.1055/a-2721-6552

Vancouver

Chiang TH, Hsu YN, Chen MH, Chen YR, Cheng HC, Chen MJ, et al. A rural-to-center artificial intelligence model for diagnosing Helicobacter pylori infection and premalignant gastric conditions using endoscopy images captured in routine practice. Endoscopy. 2026;58(04):343-354. doi:10.1055/a-2721-6552

BibTeX
@article{Chiang2026,
  author = {Chiang, Tsung-Hsien and Hsu, Yen-Ning and Chen, Min-Han and Chen, Yi-Ru and Cheng, Hsiu-Chi and Chen, Mei-Jin and Lee, Fu-Jen and Chang, Chi-Yang and Chang, Chun-Chao and Bair, Ming-Jong and Liou, Jyh-Ming and Chen, Chiuan-Jung and Chen, Yen-Chung and Chiang, Hung and Shun, Chia-Tung and Liu, Jui-Hsuan and Chiu, Han-Mo and Wu, Ming-Shiang and Yu, Jiun-Yu and Guo, Ruey-Shan and Lin, Jaw-Town and Lee, Yi-Chia and Chen, Chu-Song},
  title = {A rural-to-center artificial intelligence model for diagnosing Helicobacter pylori infection and premalignant gastric conditions using endoscopy images captured in routine practice},
  journal = {Endoscopy},
  year = {2026},
  volume = {58},
  number = {04},
  pages = {343--354},
  doi = {10.1055/a-2721-6552}
}
Kostenlos starten →