Bowel cleansing quality evaluation in colon capsule endoscopy: what is the reference standard?

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. Trial registration: All included images were derived from the CAREforCOLON 2015 trial (Registered with The Regional Health Research Ethics Committee (Registration number: S-20190100), the Danish data protection agency (Ref. 19/29858), and ClinicalTrials.gov (registration number: NCT04049357)).