Artificial intelligence-assisted video colonoscopy for disease monitoring of ulcerative colitis: A prospective study.

Endoscopic remission computer-aided diagnosis mayo endoscopic subscore

Journal

Journal of Crohn's & colitis
ISSN: 1876-4479
Titre abrégé: J Crohns Colitis
Pays: England
ID NLM: 101318676

Informations de publication

Date de publication:
03 Jun 2024
Historique:
received: 14 02 2024
medline: 3 6 2024
pubmed: 3 6 2024
entrez: 3 6 2024
Statut: aheadofprint

Résumé

The Mayo endoscopic subscore (MES) is the most popular endoscopic disease activity measure of ulcerative colitis (UC). Artificial intelligence (AI)-assisted colonoscopy is expected to reduce diagnostic variability among endoscopists. However, no study has been conducted to ascertain whether AI-based MES assignments can help predict clinical relapse, nor has AI been verified to improve the diagnostic performance of non-specialists. This open-label, prospective cohort study enrolled 110 patients with UC in clinical remission. The AI algorithm was developed using 74713 images from 898 patients who underwent colonoscopy at three centers. Patients were followed up after colonoscopy for 12 months, and clinical relapse was defined as a partial Mayo score >2. A multi-video, multi-reader analysis involving 124 videos was conducted to determine whether the AI system reduced the diagnostic variability among six non-specialists. The clinical relapse rate for patients with AI-based MES = 1 (24.5% [12/49]) was significantly higher (log-rank test, P = 0.01) than that for patients with AI-based MES = 0 (3.2% [1/31]). Relapse occurred during the 12-month follow-up period in 16.2% (13/80) of patients with AI-based MES = 0 or 1 and 50.0% (10/20) of those with AI-based MES = 2 or 3 (log-rank test, P = 0.03). Using AI resulted in better inter- and intra-observer reproducibility than endoscopists alone. Colonoscopy using the AI-based MES system can stratify the risk of clinical relapse in patients with UC and improve the diagnostic performance of non-specialists.

Sections du résumé

BACKGROUNDS AND AIMS OBJECTIVE
The Mayo endoscopic subscore (MES) is the most popular endoscopic disease activity measure of ulcerative colitis (UC). Artificial intelligence (AI)-assisted colonoscopy is expected to reduce diagnostic variability among endoscopists. However, no study has been conducted to ascertain whether AI-based MES assignments can help predict clinical relapse, nor has AI been verified to improve the diagnostic performance of non-specialists.
METHODS METHODS
This open-label, prospective cohort study enrolled 110 patients with UC in clinical remission. The AI algorithm was developed using 74713 images from 898 patients who underwent colonoscopy at three centers. Patients were followed up after colonoscopy for 12 months, and clinical relapse was defined as a partial Mayo score >2. A multi-video, multi-reader analysis involving 124 videos was conducted to determine whether the AI system reduced the diagnostic variability among six non-specialists.
RESULTS RESULTS
The clinical relapse rate for patients with AI-based MES = 1 (24.5% [12/49]) was significantly higher (log-rank test, P = 0.01) than that for patients with AI-based MES = 0 (3.2% [1/31]). Relapse occurred during the 12-month follow-up period in 16.2% (13/80) of patients with AI-based MES = 0 or 1 and 50.0% (10/20) of those with AI-based MES = 2 or 3 (log-rank test, P = 0.03). Using AI resulted in better inter- and intra-observer reproducibility than endoscopists alone.
CONCLUSIONS CONCLUSIONS
Colonoscopy using the AI-based MES system can stratify the risk of clinical relapse in patients with UC and improve the diagnostic performance of non-specialists.

Identifiants

pubmed: 38828734
pii: 7686724
doi: 10.1093/ecco-jcc/jjae080
pii:
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Informations de copyright

© The Author(s) 2024. Published by Oxford University Press on behalf of European Crohn’s and Colitis Organisation.

Auteurs

Noriyuki Ogata (N)

Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Kanagawa, Japan.

Yasuharu Maeda (Y)

Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Kanagawa, Japan.
APC Microbiome Ireland, College of Medicine and Health, University College Cork, Cork, Ireland.

Masashi Misawa (M)

Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Kanagawa, Japan.

Kento Takenaka (K)

Department of Gastroenterology and Hepatology, Tokyo Medical and Dental University, Tokyo, Japan.

Kaoru Takabayashi (K)

Center for Diagnostic and Therapeutic Endoscopy, Keio University School of Medicine, Tokyo, Japan.

Marietta Iacucci (M)

APC Microbiome Ireland, College of Medicine and Health, University College Cork, Cork, Ireland.

Takanori Kuroki (T)

Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Kanagawa, Japan.

Kazumi Takishima (K)

Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Kanagawa, Japan.

Keisuke Sasabe (K)

Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Kanagawa, Japan.

Yu Niimura (Y)

Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Kanagawa, Japan.

Jiro Kawashima (J)

Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Kanagawa, Japan.

Yushi Ogawa (Y)

Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Kanagawa, Japan.

Katsuro Ichimasa (K)

Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Kanagawa, Japan.

Hiroki Nakamura (H)

Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Kanagawa, Japan.

Singo Matsudaira (S)

Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Kanagawa, Japan.

Seiko Sasanuma (S)

Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Kanagawa, Japan.

Takemasa Hayashi (T)

Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Kanagawa, Japan.

Kunihiko Wakamura (K)

Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Kanagawa, Japan.

Hideyuki Miyachi (H)

Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Kanagawa, Japan.

Toshiyuki Baba (T)

Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Kanagawa, Japan.

Yuichi Mori (Y)

Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Kanagawa, Japan.
Clinical Effectiveness Research Group, Institute of Health and Society, University of Oslo, Oslo Norway.

Kazuo Ohtsuka (K)

Department of Gastroenterology and Hepatology, Tokyo Medical and Dental University, Tokyo, Japan.
Endoscopic Unit, Tokyo Medical and Dental University, Tokyo, Japan.

Haruhiko Ogata (H)

Center for Diagnostic and Therapeutic Endoscopy, Keio University School of Medicine, Tokyo, Japan.
Clinical medical research center, International University of Health and Welfare, Narita, Japan.
Center for Diagnostic and Therapeutic Endoscopy, San-no Medical Center, Tokyo, Japan.

Shin-Ei Kudo (SE)

Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Kanagawa, Japan.

Classifications MeSH