Randomized controlled trial of an artificial intelligence diagnostic system for the detection of esophageal squamous cell carcinoma in clinical practice
Randomisierte kontrollierte Studie eines KI-Diagnosesystems zum Nachweis des Plattenepithelkarzinoms des Ösophagus in der klinischen Praxis
Endoscopy · 2025-03 · 57 (03) · 210-217
DOI: 10.1055/a-2421-3194 ↗Auf einen Blick
In einer prospektiven randomisierten Studie verbesserte das KI-System die Detektionsrate von ESCC nicht. Bei Nicht-Expert:innen lag sie bei 47 % mit KI und 45 % ohne KI.
Fragestellung
Verbessert ein KI-Diagnosesystem die Detektion von ESCC bei Endoskop:innen in der klinischen Praxis?
Methode
Prospektive, einzentrumige, explorative, randomisierte kontrollierte Studie bei Hochrisikopatient:innen mit Screening- oder Surveillance-Ösophagogastroduodenoskopie.
Ergebnisse
320 Patient:innen analysiert. Detektionsrate bei Nicht-Expert:innen: 47 % in der KI-Gruppe vs. 45 % in der Kontrollgruppe (P = 0,93). Bei Expert:innen: 87 % vs. 57 % (P = 0,20); alle Endoskop:innen: 57 % vs. 50 % (P = 0,70).
Schlussfolgerung der Autor:innen
Die Studie konnte keine Verbesserung der Ösophaguskarzinom-Detektionsrate durch das KI-Diagnosesystem für ESCC zeigen.
Kernaussagen
- Bei Nicht-Expert:innen kein Unterschied: 47 % vs. 45 %
- Auch bei Expert:innen kein signifikanter Unterschied
- Alle Endoskop:innen: 57 % vs. 50 %; keine Verbesserung
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Randomisierte kontrollierte Studie in der Zeitschrift Endoscopy, online erschienen am 18.11.2024. Verfasst von Eisuke Nakao und 13 weiteren Autor:innen. Beteiligte Einrichtung: Gastroenterology, Cancer Institute Hospital, Japanese Foundation For Cancer Research, Tokyo, Japan. Hauptthemen laut MEDLINE: Esophageal Neoplasms, Esophageal Squamous Cell Carcinoma, Artificial Intelligence. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 24 Literaturangaben. Gefördert von: JSPS KAKENHI Grant, Daiwa Securities Health Foundation, Takeda Science Foundation.
Abstract (Originalsprache)
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Gastroenterology, Cancer Institute Hospital, Japanese Foundation For Cancer Research, Tokyo, Japan.
- AI Medical Service, AI Medical Service Inc., Tokyo, Japan.
- Clinical Planning and Strategy, Cancer Institute Hospital, Japanese Foundation For Cancer Research, Tokyo, Japan.
- Center for Digital Transformation for Health, Kyoto University School of Medicine, Kyoto, Japan.
- Gastrointestinal Oncology, Osaka International Cancer Institute., Osaka, Japan.
- Gastroenterology and Proctology, Tada Tomohiro Institute of Gastroenterology and Proctology, Saitama, Japan.
ORCID-Profile: Eisuke Nakao, Toshiyuki Yoshio, Shoichi Yoshimizu, Yusuke Horiuchi
Förderung
- JSPS KAKENHI Grant
- Daiwa Securities Health Foundation
- Takeda Science Foundation
Zitieren
APA
Nakao, E., Yoshio, T., Kato, Y., Namikawa, K., Tokai, Y., Yoshimizu, S., Horiuchi, Y., Ishiyama, A., Hirasawa, T., Kurihara, N., Ishizuka, N., Ishihara, R., Tada, T., & Fujisaki, J. (2025). Randomized controlled trial of an artificial intelligence diagnostic system for the detection of esophageal squamous cell carcinoma in clinical practice. Endoscopy, 57(03), 210-217. https://doi.org/10.1055/a-2421-3194
Vancouver
Nakao E, Yoshio T, Kato Y, Namikawa K, Tokai Y, Yoshimizu S, et al. Randomized controlled trial of an artificial intelligence diagnostic system for the detection of esophageal squamous cell carcinoma in clinical practice. Endoscopy. 2025;57(03):210-217. doi:10.1055/a-2421-3194
BibTeX
@article{Nakao2025,
author = {Nakao, Eisuke and Yoshio, Toshiyuki and Kato, Yusuke and Namikawa, Ken and Tokai, Yoshitaka and Yoshimizu, Shoichi and Horiuchi, Yusuke and Ishiyama, Akiyoshi and Hirasawa, Toshiaki and Kurihara, Nozomi and Ishizuka, Naoki and Ishihara, Ryu and Tada, Tomohiro and Fujisaki, Junko},
title = {Randomized controlled trial of an artificial intelligence diagnostic system for the detection of esophageal squamous cell carcinoma in clinical practice},
journal = {Endoscopy},
year = {2025},
volume = {57},
number = {03},
pages = {210--217},
doi = {10.1055/a-2421-3194}
}
EUVIMED