A novel artificial intelligence-assisted "vascular-healing" diagnosis for prediction of future clinical relapse in patients with ulcerative colitis: a prospective cohort study.
Ulcerative colitis
artificial intelligence
colonoscopy
Journal
Gastrointestinal endoscopy
ISSN: 1097-6779
Titre abrégé: Gastrointest Endosc
Pays: United States
ID NLM: 0010505
Informations de publication
Date de publication:
10 Jan 2024
10 Jan 2024
Historique:
received:
03
10
2023
revised:
05
01
2024
accepted:
09
01
2024
medline:
13
1
2024
pubmed:
13
1
2024
entrez:
12
1
2024
Statut:
aheadofprint
Résumé
Image-enhanced endoscopy (IEE) has attracted attention as a method for detecting inflammation and predicting outcomes in patients with ulcerative colitis (UC); however, the procedure requires specialist endoscopists. Artificial intelligence (AI)-assisted IEE may help non-experts to provide objective accurate predictions using optical imaging. We aimed to develop a novel AI-based system using 8853 images from 167 patients with UC to diagnose "vascular-healing" and establish the role of AI-based vascular-healing for predicting the outcomes of patients with UC. This open-label, prospective cohort study analyzed data for 104 patients with UC in clinical remission. Endoscopists performed colonoscopy using the AI system, which identified the target mucosa as AI-based vascular-active or vascular-healing. Mayo endoscopic subscore (MES), AI outputs, and histological assessment were recorded for six colorectal segments from each patient. Patients were followed-up for 12 months. Clinical relapse was defined as a partial Mayo score >2 RESULTS: The clinical relapse rate was significantly higher in the AI-based vascular-active group [23.9% (16/67)] compared with the AI-based vascular-healing group [3.0% (1/33)] (P=0.01). In a sub-analysis predicting clinical relapse in patients with MES ≤1, the area under the curve for the combination of complete endoscopic remission and vascular-healing (0.70) was increased compared with that for complete endoscopic remission alone (0.65). AI-based vascular healing diagnosis system may potentially be used to provide more confidence to physicians to accurately identify patients in remission of UC who would likely relapse rather than remain stable.
Sections du résumé
BACKGROUND AND AIMS
OBJECTIVE
Image-enhanced endoscopy (IEE) has attracted attention as a method for detecting inflammation and predicting outcomes in patients with ulcerative colitis (UC); however, the procedure requires specialist endoscopists. Artificial intelligence (AI)-assisted IEE may help non-experts to provide objective accurate predictions using optical imaging. We aimed to develop a novel AI-based system using 8853 images from 167 patients with UC to diagnose "vascular-healing" and establish the role of AI-based vascular-healing for predicting the outcomes of patients with UC.
METHODS
METHODS
This open-label, prospective cohort study analyzed data for 104 patients with UC in clinical remission. Endoscopists performed colonoscopy using the AI system, which identified the target mucosa as AI-based vascular-active or vascular-healing. Mayo endoscopic subscore (MES), AI outputs, and histological assessment were recorded for six colorectal segments from each patient. Patients were followed-up for 12 months. Clinical relapse was defined as a partial Mayo score >2 RESULTS: The clinical relapse rate was significantly higher in the AI-based vascular-active group [23.9% (16/67)] compared with the AI-based vascular-healing group [3.0% (1/33)] (P=0.01). In a sub-analysis predicting clinical relapse in patients with MES ≤1, the area under the curve for the combination of complete endoscopic remission and vascular-healing (0.70) was increased compared with that for complete endoscopic remission alone (0.65).
CONCLUSIONS
CONCLUSIONS
AI-based vascular healing diagnosis system may potentially be used to provide more confidence to physicians to accurately identify patients in remission of UC who would likely relapse rather than remain stable.
Identifiants
pubmed: 38215859
pii: S0016-5107(24)00015-4
doi: 10.1016/j.gie.2024.01.010
pii:
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Informations de copyright
Copyright © 2024 American Society for Gastrointestinal Endoscopy. Published by Elsevier Inc. All rights reserved.