Interobserver Agreement of Modified Paris Classification and Histology Prediction of Colorectal Lesions in Patients with Inflammatory Bowel Disease.

Background and aimsSCENIC guidelines (International Consensus Statement on Surveillance and Management of Dysplasia in IBD) recommend that visible dysplasia in patients with longstanding inflammatory bowel disease should be endoscopically characterized using a modified Paris classification. This study aims to determine the interobserver agreement (IOA) of the modified Paris classification and endoscopists' accuracy for pathology prediction of IBD visible lesions.MethodsA total of 100 de-identified endoscopic still images and 30 videos of IBD visible colorectal lesions were graded by 10 senior and 4 trainee endoscopists from 5 tertiary care centers. The endoscopists were asked to assign 4 classifications for each image: 1. Standard Paris, 2. Modified Paris, 3. Pathology prediction, 4. Lesion Border. Agreement was measured using Light's Kappa coefficient. Consensus of ratings was assessed according to strict majority.ResultsThe overall Light's Kappa for all study endpoints was between 0.32 and 0.49. In subgroup analysis between junior and senior endoscopists, Light's Kappa continued to be less than 0.6 with a slightly higher agreement amongst juniors. Lesions with lowest agreement and no consensus were mostly classified as Is, IIa and mixed for Paris and sessile and superficial elevated for modified Paris classifications. Endoscopists' accuracy for prediction of dysplastic, non-dysplastic and serrated pathology was 77%, 56% and 30% respectively. There was a strong association (p<0.001) between the given morphology classification and the predicted pathology with Ip lesions carrying a much lower expectation of dysplasia than Is/IIc/III and mixed lesions. The agreement for border prediction was 0.5 for junior and 0.3 for senior endoscopists.ConclusionThis study demonstrates very low IOA for Paris and Modified Paris classifications and low accuracy and IOA for lesion histopathology prediction. Revisions of these classifications are required to create a clinically useful risk stratification tool and enable eventual application of augmented intelligence tools.