Artificial Intelligence Versus Conventional Scoring for Assessing Small Bowel Capsule Endoscopy Cleanliness in Crohn's Disease
United European Gastroenterology Journal · 2026-06 · 14 (5)
DOI: 10.1002/ueg2.70242 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift United European Gastroenterology Journal, online erschienen am 09.06.2026. Verfasst von Raphaëlle Rouveyre und 12 weiteren Autor:innen. Beteiligte Einrichtung: Nantes Université, Institut des Maladies de l'Appareil Digestif (IMAD), Hépato-Gastro-Entérologie et Assistance Nutritionnelle, Inserm CIC 1413, Nant…. Hauptthemen laut MEDLINE: Capsule Endoscopy, Crohn Disease, Intestine, Small, Artificial Intelligence. Die Arbeit nennt 13 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Background and Aims Evaluation of cleanliness in capsule endoscopy is essential to validate the exam. However, reliable evaluation of bowel cleanliness remains challenging. The validated KODA score provides robust assessment but is time‐consuming and impractical in routine practice. We aimed to evaluate the performance of an AI‐based tool (AXAROlite, Augmented Endoscopy) compared with the KODA score for assessing small bowel cleanliness in CD patients.
Methods
This was a post hoc analysis of a multicenter randomized controlled trial (NCT05117996) including 142 CD patients undergoing SBCE after either a standard PEG‐based or simplified clear liquid preparation. All videos were evaluated for cleanliness using the KODA score by trained readers. The same videos were analyzed using the AI‐based AXAROlite tool. Correlation, agreement, and diagnostic performance of AXAROlite were compared with the KODA score. Clinical factors influencing AI‐assessed cleanliness were also investigated.
Results
AXAROlite and KODA showed strong correlation for whole small bowel ( ρ = 0.61; p < 0.001). AXAROlite demonstrated excellent diagnostic accuracy for detecting adequate cleanliness defined as KODA > 2.25 (AUROC = 0.85, 95% CI 0.79–0.92), with an optimal threshold of 72% clean frames (sensitivity 86%, specificity 72%). Mean cleanliness decreased progressively from proximal to distal small bowel with both methods ( p = 0.001). The AXROlite score was independently reduced in patients with active disease and a longer small bowel transit time.
Conclusions
AXAROlite provides a rapid, fully automated, and accurate evaluation of small bowel cleanliness in CD, comparable to the validated KODA score. Its integration into routine workflows may streamline reporting and reduce inter‐observer variability.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Nantes Université, Institut des Maladies de l'Appareil Digestif (IMAD), Hépato-Gastro-Entérologie et Assistance Nutritionnelle, Inserm CIC 1413, Nantes, France.
- Sorbonne Université, Centre for Digestive Endoscopy, Saint Antoine Hospital, APHP, Paris, France.
- Department of Gastroenterology, Centre Hospitalier Départemental (CHD) la Roche sur Yon, La-Roche-sur-Yon, France.
- Department of Gastroenterology, Jules Verne Clinic, Nantes, France.
- Department of Gastroenterology, Private Hospital Confluent, Nantes, France.
- CHU Rennes, University Rennes, INSERM, CIC 1414, Institut NUMECAN (Nutrition Metabolism and Cancer), Rennes, France.
ORCID-Profile: Catherine Le Berre, Mathurin Flamant
Zitieren
APA
Rouveyre, R., Le Berre, C., Leenhardt, R., Collins, M., De Massin, A., Flamant, M., Trang-Poisson, C., Bouguen, G., Dib, N., Histace, A., Soude, T., Dray, X., & Bourreille, A. (2026). Artificial Intelligence Versus Conventional Scoring for Assessing Small Bowel Capsule Endoscopy Cleanliness in Crohn's Disease. United European Gastroenterology Journal, 14(5). https://doi.org/10.1002/ueg2.70242
Vancouver
Rouveyre R, Le Berre C, Leenhardt R, Collins M, De Massin A, Flamant M, et al. Artificial Intelligence Versus Conventional Scoring for Assessing Small Bowel Capsule Endoscopy Cleanliness in Crohn's Disease. United European Gastroenterology Journal. 2026;14(5). doi:10.1002/ueg2.70242
BibTeX
@article{Rouveyre2026,
author = {Rouveyre, Raphaëlle and Le Berre, Catherine and Leenhardt, Romain and Collins, Michael and De Massin, Astrid and Flamant, Mathurin and Trang-Poisson, Caroline and Bouguen, Guillaume and Dib, Nina and Histace, Aymeric and Soude, Theo and Dray, Xavier and Bourreille, Arnaud},
title = {Artificial Intelligence Versus Conventional Scoring for Assessing Small Bowel Capsule Endoscopy Cleanliness in Crohn's Disease},
journal = {United European Gastroenterology Journal},
year = {2026},
volume = {14},
number = {5},
doi = {10.1002/ueg2.70242}
}
EUVIMED