Figure - available from: Endoscopy International Open
This content is subject to copyright.
The Simple Endoscopic Score for Crohn’s Disease (SES-CD) 13 . The score is calculated for each of the segments – terminal ileum, right colon, transverse colon, left colon and rectum – and the sum of each segmental score produces the total SES-CD.
Source publication
Background and study aims Recent evidence supports the use of pan-enteric capsule endoscopy (CE) for the diagnosis and follow-up of Crohn’s disease (CD). The aim of this study was to examine the agreement between CE and ileocolonoscopy (IC) for determining the severity and classification of lesions in ileocolonic CD.
Patients and methods In a prosp...
Citations
... This new capsule has a wider angle of view and adaptive frame rate (4-35 frames/second) to ensure adequate SB visualization regardless of bowel movement, increasing the detection of SB pathology without compromising the procedure's safety and tolerability [37] and allows complete evaluation of both SB and colon [38]. PCC can provide monitoring of CD activity in established CD patients and guide management [39] while for patients with suspected CD, PCC and IC findings have similar ileocolonic disease activity scores and additional scores regarding ulcer size, affected area and ulcerated surface [40]. Furthermore, PCC has a superior diagnostic sensitivity compared to MRE for patients with suspected CD [41]. ...
and Warwick-7 shire, Clifford Bridge Rd, Coventry CV2 2DX; Brian.lei@uhcw.nhs.uk 8 Abstract: Colon capsule endoscopy (CCE) has regained popularity for lower gastrointestinal inves-26 tigations, since COVID-19. While there have been systematic reviews and meta-analyses on colonic 27 polyps and cancer detection using CCE, there is a lack of comprehensive evidence concerning co-28 lonic inflammation. Therefore, this systematic review and meta-analysis aimed to assess the diag-29 nostic accuracy of CCE for colonic inflammation, predominantly ulcerative colitis (UC) and Crohn's 30 disease (CD). Method: We systematically searched electronic databases (EMBASE, MEDLINE, Pub-31 Med Central, and Cochrane Library) for studies comparing the diagnostic accuracy between CCE 32 and optical endoscopy as standard reference. A meta-analysis was conducted, pooling sensitivity, 33 specificity, and coefficient correlations. Results: Our search identified 3925 publications, and 23 34 studies with 1353 patients were included. Nine studies focused on the diagnostic accuracy of CCE 35 in UC, and ten on Crohn's disease (CD). Four remaining studies evaluated other colonic inflamma-36 tory conditions. In UC, CCE had a pooled sensitivity of 94% (95% CI, 91-98%) and specificity of 55% 37 (95% CI, 25-86%) with a pooled correlation coefficient of 0.79 (95%CI,0.74-0.84). In CD, CCE had a 38 pooled sensitivity of 92% (95% CI, 89-95%) and specificity of 88% (95% CI, 84-92%) with a pooled 39 correlation coefficient of 0.68 (95%CI,0.54-0.78). Conclusion: CCE has a high sensitivity in inflam-40 matory bowel diseases, including UC, Crohn's TI disease and colitis and a comparable specificity 41 when adequate bowel preparation is adequate. The critical challenges in CCE revolve around the 42 variability in bowel preparation and procedural completion rate, the absence of standardised dis-43 ease activity scores, the imperfect diagnostic accuracy of colonoscopy as the gold standard and the 44 uncertainty around final diagnosis without histology confirmation in CCE. Further studies are 45 needed to evaluate the diagnostic accuracy of CCE for other colonic inflammatory conditions, such 46 as diverticulitis and infective and checkpoint inhibitor colitis. 47 48 Citation: Lei, I.I.; Thorndal, C.; Man-zoor, M.S.; Koulaouzidis, A.; Parsons , N.; Noble, C.; Huhulea, C.; Wenzek, H.; White, E.; Arasaradnam, R.P. The Diagnostic
Background and study aim:
Pan-enteric capsule endoscopy (PCE) is a highly sensitive but time-consuming tool for detecting pathology. Artificial intelligence (AI) algorithms might offer a possibility to assist in the review and reduce the analysis time of PCE. This study examines the agreement between PCE assessments aided by AI technology and standard evaluations in patients suspected of Crohn's disease (CD).
Patients and methods:
PCEs from a prospective blinded, multicenter study, including patients suspected of CD (ClinicalTrials.Gov NCT03134586), were processed by the deep learning solution AXARO® (Augmented Endoscopy, Paris, France). Based on the image output, two observers classified the patient's PCE as normal, suggestive of CD, ulcerative colitis, or cancer. The primary outcome was per-patient sensitivities and specificities for detecting CD and Inflammatory bowel disease (IBD). Complete reading of PCE served as the reference standard.
Results:
131 patients' PCEs were analyzed, with a median recording time of 303 minutes. The AXARO® framework reduced output to a median of 470 images (2.1%) per patient, and the pooled median review time was 3.2 minutes per patient. For detecting CD, the observers had a sensitivity of 96% and 92% and a specificity of 93% and 90%. For the detection of IBD, both observers had a sensitivity of 97% and a specificity of 91% and 90%. The negative predictive value was 95% for CD and 97% for IBD.
Conclusions:
Using the AXARO® framework reduced the initial review time substantially while maintaining high diagnostic accuracy - suggesting its use as a rapid tool to "rule out" IBD in PCEs of patients suspected of Crohn's disease.
