Artificial Intelligence Versus Conventional Scoring for Assessing Small Bowel Capsule Endoscopy Cleanliness in Crohn's Disease
Abstract
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.
Related
- Assessing spoken discourse in aphasia using multimodal artificial intelligence
- The use of artificial intelligence in assessing fever in the returning traveller: A scoping review
- Facial cleanliness, environmental factors, and the burden of trachoma in a pastoral conflict area of Tiaty East, Baringo County, Kenya
- Growing up with artificial intelligence: An amplifier of inequalities and a public health issue
- Notification: Artificial Intelligence in Autism Spectrum Disorder Diagnosis: A Scoping Review of Face, Voice, and Text Analysis Methods.
BibTeX
@article{rouveyre2026artificial,
title = {{Artificial Intelligence Versus Conventional Scoring for Assessing Small Bowel Capsule Endoscopy Cleanliness in Crohn's Disease}},
author = {Raphaëlle Rouveyre and Catherine Le Berre and Romain Leenhardt and Michael Collins and Astrid de Massin and Mathurin Flamant and Caroline Trang-Poisson and Guillaume Bouguen and Nina Dib and Aymeric Histace and Theo Soude and Xavier Dray and Arnaud Bourreille},
journal = {United European Gastroenterology Journal},
year = {2026},
month = jun,
doi = {10.1002/ueg2.70242},
url = {https://hal.science/hal-05664789v1},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - JOUR
TI - Artificial Intelligence Versus Conventional Scoring for Assessing Small Bowel Capsule Endoscopy Cleanliness in Crohn's Disease
AU - Raphaëlle Rouveyre
AU - Catherine Le Berre
AU - Romain Leenhardt
AU - Michael Collins
AU - Astrid de Massin
AU - Mathurin Flamant
AU - Caroline Trang-Poisson
AU - Guillaume Bouguen
AU - Nina Dib
AU - Aymeric Histace
AU - Theo Soude
AU - Xavier Dray
AU - Arnaud Bourreille
PY - 2026
DA - 2026/06/09
JO - United European Gastroenterology Journal
DO - 10.1002/ueg2.70242
UR - https://hal.science/hal-05664789v1
AB - 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.
SN - 2050-6406
SN - 2050-6414
ER -