PDF icon Download PDF
Open Access
CC BY 4.0 · Endosc Int Open
DOI: 10.1055/a-2695-0556
Original article

Impact of interaction between an artificial intelligence endoscopic support system and endoscopists on diagnosis of gastric neoplastic lesions

Hiroya Mizutani
1   Department of Gastroenterology Graduate School of Medicine, The University of Tokyo, Bunkyo-ku, Japan (Ringgold ID: RIN13143)
2   Department of Next-Generation Endoscopic Computer Vision Graduate School of Medicine, The University of Tokyo, Bunkyo-ku, Japan (Ringgold ID: RIN13143)
,
Yosuke Tsuji
1   Department of Gastroenterology Graduate School of Medicine, The University of Tokyo, Bunkyo-ku, Japan (Ringgold ID: RIN13143)
2   Department of Next-Generation Endoscopic Computer Vision Graduate School of Medicine, The University of Tokyo, Bunkyo-ku, Japan (Ringgold ID: RIN13143)
,
Dai Kubota
1   Department of Gastroenterology Graduate School of Medicine, The University of Tokyo, Bunkyo-ku, Japan (Ringgold ID: RIN13143)
2   Department of Next-Generation Endoscopic Computer Vision Graduate School of Medicine, The University of Tokyo, Bunkyo-ku, Japan (Ringgold ID: RIN13143)
,
Hiroyuki Hisada
1   Department of Gastroenterology Graduate School of Medicine, The University of Tokyo, Bunkyo-ku, Japan (Ringgold ID: RIN13143)
,
Yuko Miura
1   Department of Gastroenterology Graduate School of Medicine, The University of Tokyo, Bunkyo-ku, Japan (Ringgold ID: RIN13143)
,
Daisuke Ohki
1   Department of Gastroenterology Graduate School of Medicine, The University of Tokyo, Bunkyo-ku, Japan (Ringgold ID: RIN13143)
,
Chihiro Takeuchi 
1   Department of Gastroenterology Graduate School of Medicine, The University of Tokyo, Bunkyo-ku, Japan (Ringgold ID: RIN13143)
,
Naomi Kakushima
1   Department of Gastroenterology Graduate School of Medicine, The University of Tokyo, Bunkyo-ku, Japan (Ringgold ID: RIN13143)
,
Nobutake Yamamichi
1   Department of Gastroenterology Graduate School of Medicine, The University of Tokyo, Bunkyo-ku, Japan (Ringgold ID: RIN13143)
,
Ryosuke Kikuchi
3   AI Medical Service Inc., Tokyo, Japan
,
Mitsuaki Ishioka
4   Department of Gastroenterology, The Cancer Institute Hospital Of JFCR, Koto-ku, Japan (Ringgold ID: RIN117105)
5   Nihonbashi Ningyocho Gastroenterology and Endoscopy Clinic, Tokyo, Japan
,
Atsuo Yamada
1   Department of Gastroenterology Graduate School of Medicine, The University of Tokyo, Bunkyo-ku, Japan (Ringgold ID: RIN13143)
6   Ochanomizu Surugadai Clinic, Tokyo, Japan
,
Shinya Kodashima
7   Department of Medicine Graduate School of Medicine, Teikyo University School of Medicine, Tokyo, Japan
,
Tomohiro Tada
3   AI Medical Service Inc., Tokyo, Japan
8   Department of Surgical Oncology Graduate School of Medicine, The University of Tokyo, Bunkyo-ku, Japan (Ringgold ID: RIN13143)
9   Department of Gastroenterology and Proctology, Tada Tomohiro Institute of Gastroenterology and Proctology, Saitama, Japan
,
Mitsuhiro Fujishiro
1   Department of Gastroenterology Graduate School of Medicine, The University of Tokyo, Bunkyo-ku, Japan (Ringgold ID: RIN13143)
› Author Affiliations
Supported by: AI Medical Service Inc. Clinical Trial: Registration number (trial ID): jRCT1030210697, Trial registry: Japan Medical Association Clinical Trial Registry (http://www.jmacct.med.or.jp/), Type of Study: retrospective, open-label, comparative validation study
› Further Information
Also available ateRef
 PDF Download
Preview

Background and study aims: Artificial intelligence (AI) is expected to enhance the ability of endoscopists to detect gastric neoplastic lesions; however, its effectiveness among highly skilled Japanese expert endoscopists has not been validated. We developed a novel AI-assisted diagnostic tool for detection of gastric neoplastic lesions and evaluated its utility by comparing the diagnostic performance of endoscopists with and without AI assistance. Patients and methods: Diagnostic performance of gastric neoplastic lesions without and with AI assistance was compared among 14 expert endoscopists and 12 non-expert endoscopists using an evaluation dataset consisting of 150 images containing neoplastic lesions and 350 images without lesions. A general linear mixed model was applied for comparative analysis. The primary outcome was to demonstrate superiority of sensitivity and non-inferiority of specificity among expert endoscopists using AI compared with those without AI. The significance level for sensitivity was set at 2.5% and the non-inferiority margin for specificity was defined as a log odds ratio of -0.25. Results: Our AI demonstrated superiority in sensitivity (66.4% without AI vs. 83.5% with AI; odds ratio [OR] 2.562, 97.5% confidence interval [CI] 2.069-3.172) and non-inferiority in specificity (90.8% without AI vs. 92.9% with AI; OR 1.326, 95% CI 1.122-1.565) among expert endoscopists. Conclusions: AI contributed to improved diagnostic performance even among Japanese expert endoscopists in detecting gastric neoplastic lesions. These findings suggest that the AI system may have potential to support consistently high diagnostic performance across varying levels of endoscopic expertise.



Publication History

Received: 05 February 2025

Accepted after revision: 31 July 2025

Accepted Manuscript online:
03 September 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

Bibliographical Record
Hiroya Mizutani, Yosuke Tsuji, Dai Kubota, Hiroyuki Hisada, Yuko Miura, Daisuke Ohki, Chihiro Takeuchi, Naomi Kakushima, Nobutake Yamamichi, Ryosuke Kikuchi, Mitsuaki Ishioka, Atsuo Yamada, Shinya Kodashima, Tomohiro Tada, Mitsuhiro Fujishiro. Impact of interaction between an artificial intelligence endoscopic support system and endoscopists on diagnosis of gastric neoplastic lesions. Endosc Int Open ; 0: a26950556.
DOI: 10.1055/a-2695-0556