Scientific publications
Bowel cleansing quality evaluation in colon capsule endoscopy: what is the reference standard? Scientific Publication
Benedicte Schelde-Olesen 1 2 , Anastasios Koulaouzidis 2 3 4 , Ulrik Deding 2 3 , Ervin Toth 5 , Konstantinos John Dabos 6 , Abraham Eliakim 7 , Cristina Carretero 8 , Begoña González-Suárez 9 , Xavier Dray 10 , Thomas de Lange 11 12 , Hanneke Beaumont 13 , Emanuele Rondonotti 14 , Uri Kopylov 7 , Pierre Ellul 15 , Enrique Pérez-Cuadrado-Robles 16 , Alexander Robertson 17 , Irene Stenfors 18 , Alejandro Bojorquez 8 , Stefania Piccirelli 19 , Gitte Grunnet Raabe 3 , Reuma Margalit-Yehuda 7 , Isabel Barba 8 , Giulia Scardino 14 , Salome Ouazana 10 , Thomas Bjørsum-Meyer 2 3
Background: The diagnostic accuracy of colon capsule endoscopy (CCE) depends on a well-cleansed bowel. Evaluating the cleansing quality can be difficult with a substantial interobserver variation.
Objectives: Our primary aim was to establish a standard of agreement for bowel cleansing in CCE based on evaluations by expert readers. Then, we aimed to investigate the interobserver agreement on bowel cleansing.
Design: We conducted an interobserver agreement study on bowel cleansing quality.
Methods: Readers with different experience levels in CCE and colonoscopy evaluated bowel cleansing quality on the Leighton-Rex scale and Colon Capsule CLEansing Assessment and Report (CC-CLEAR), respectively. All evaluations were reported on an image level. A total of 24 readers rated 500 images on each scale.
Results: An expert opinion-based agreement standard could be set for poor and excellent cleansing but not for the spectrum in between, as the experts agreed on only a limited number of images representing fair and good cleansing. The overall interobserver agreement on the Leighton-Rex full scale was good (intraclass correlation coefficient (ICC) 0.84, 95% CI (0.82-0.85)) and remained good when stratified by experience level. On the full CC-CLEAR scale, the overall agreement was moderate (ICC 0.62, 95% CI (0.59-0.65)) and remained so when stratified by experience level.
Conclusion: The interobserver agreement was good for the Leighton-Rex scale and moderate for CC-CLEAR, irrespective of the reader's experience level. It was not possible to establish an expert-opinion standard of agreement for cleansing quality in CCE images. Dedicated training in using the scales may improve agreement and enable future algorithm calibration for artificial intelligence supported cleansing evaluation.
CITATION Therap Adv Gastroenterol. 2024 Oct 23:17:17562848241290256. doi: 10.1177/17562848241290256. eCollection 2024
