Endoscopy 2025; 57(03): 210-217
DOI: 10.1055/a-2421-3194
Original article

Randomized controlled trial of an artificial intelligence diagnostic system for the detection of esophageal squamous cell carcinoma in clinical practice

1   Gastroenterology, Cancer Institute Hospital, Japanese Foundation For Cancer Research, Tokyo, Japan (Ringgold ID: RIN13609)
,
1   Gastroenterology, Cancer Institute Hospital, Japanese Foundation For Cancer Research, Tokyo, Japan (Ringgold ID: RIN13609)
,
Yusuke Kato
2   AI Medical Service, AI Medical Service Inc., Tokyo, Japan
,
Ken Namikawa
1   Gastroenterology, Cancer Institute Hospital, Japanese Foundation For Cancer Research, Tokyo, Japan (Ringgold ID: RIN13609)
,
Yoshitaka Tokai
1   Gastroenterology, Cancer Institute Hospital, Japanese Foundation For Cancer Research, Tokyo, Japan (Ringgold ID: RIN13609)
,
1   Gastroenterology, Cancer Institute Hospital, Japanese Foundation For Cancer Research, Tokyo, Japan (Ringgold ID: RIN13609)
,
1   Gastroenterology, Cancer Institute Hospital, Japanese Foundation For Cancer Research, Tokyo, Japan (Ringgold ID: RIN13609)
,
Akiyoshi Ishiyama
1   Gastroenterology, Cancer Institute Hospital, Japanese Foundation For Cancer Research, Tokyo, Japan (Ringgold ID: RIN13609)
,
Toshiaki Hirasawa
1   Gastroenterology, Cancer Institute Hospital, Japanese Foundation For Cancer Research, Tokyo, Japan (Ringgold ID: RIN13609)
,
Nozomi Kurihara
3   Clinical Planning and Strategy, Cancer Institute Hospital, Japanese Foundation For Cancer Research, Tokyo, Japan (Ringgold ID: RIN13609)
,
Naoki Ishizuka
3   Clinical Planning and Strategy, Cancer Institute Hospital, Japanese Foundation For Cancer Research, Tokyo, Japan (Ringgold ID: RIN13609)
4   Center for Digital Transformation for Health, Kyoto University School of Medicine, Kyoto, Japan
,
Ryu Ishihara
5   Gastrointestinal Oncology, Osaka International Cancer Institute., Osaka, Japan
,
Tomohiro Tada
2   AI Medical Service, AI Medical Service Inc., Tokyo, Japan
6   Gastroenterology and Proctology, Tada Tomohiro Institute of Gastroenterology and Proctology, Saitama, Japan
7   Surgical Oncology, University of Tokyo Graduate School of Medicine, Tokyo, Japan
,
Junko Fujisaki
1   Gastroenterology, Cancer Institute Hospital, Japanese Foundation For Cancer Research, Tokyo, Japan (Ringgold ID: RIN13609)
› Institutsangaben
Gefördert durch: Daiwa Securities Health Foundation
Gefördert durch: JSPS KAKENHI Grant 19K08408
Gefördert durch: Takeda Science Foundation

Clinical Trial: Registration number (trial ID): UMIN000039924, Trial registry: UMIN Japan (http://www.umin.ac.jp/english/), Type of Study: Prospective, single-center, exploratory, and randomized controlled trial


Zoom Image

Abstract

Background Artificial intelligence (AI) has made remarkable progress in image recognition using deep learning systems. It has been used to detect esophageal squamous cell carcinoma (ESCC); however, none of the previous reports were investigations in a clinical setting, being retrospective in design. We therefore conducted this trial to determine how AI can help endoscopists detect ESCC in a clinical setting.

Methods This was a prospective, single-center, exploratory, and randomized controlled trial. High risk patients with ESCC undergoing screening or surveillance esophagogastroduodenoscopy were enrolled and randomly assigned to either the AI or control groups. In the AI group, the endoscopists watched both the AI monitor that detected ESCC with annotation and the normal monitor simultaneously; in the control group, the endoscopists watched only the normal monitor. In both groups, the endoscopists observed the esophagus using white-light imaging (WLI), followed by narrow-band imaging (NBI), then iodine staining. The primary end point was the enhanced detection rate of ESCC by nonexperts using AI. The detection rate was defined as the ratio of WLI/NBI-detected ESCCs to all ESCCs detected by iodine staining.

Results 320 patients were included in the analysis. The detection rate of ESCC among nonexperts was 47% in the AI group and 45% in the control group (P = 0.93), with no significant difference, which was similarly found for experts (87% vs. 57%; P = 0.20) and all endoscopists (57% vs. 50%; P = 0.70).

Conclusions This study could not demonstrate an improvement in the esophageal cancer detection rate using the AI diagnostic support system for ESCC.

Supplementary Material



Publikationsverlauf

Eingereicht: 22. Februar 2024

Angenommen nach Revision: 24. September 2024

Accepted Manuscript online:
24. September 2024

Artikel online veröffentlicht:
18. November 2024

© 2024. Thieme. All rights reserved.

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