Publication
Computer-assisted detection versus conventional colonoscopy for proximal colonic lesions: a multicenter, randomized, tandem-colonoscopy study
Publisher:
Elsevier BV
Date:
02-2023
DOI:
10.1016/J.GIE.2022.09.020
Abstract: Computer-assisted detection (CADe) is a promising technological advance that enhances adenoma detection during colonoscopy. However, the role of CADe in reducing missed colonic lesions is uncertain. The aim of this study was to determine the miss rates of proximal colonic lesions by CADe and conventional colonoscopy. This was a prospective multi-center randomized tandem colonoscopy study conducted in three Asian centers. Patients were randomized to receive CADe or conventional white light colonoscopy during the first withdrawal of the proximal colon (cecum to splenic flexure), immediately followed by tandem examination of the proximal colon with white light in both groups. The primary outcome was adenoma olyp miss rate which was defined as any adenoma olyp detected during the second examination. 223 patients (48.6% male, median age 63 years) were enrolled and 7 patients did not have tandem examination, leaving 108 patients in each group. There was no difference in the miss rate for proximal adenoma (CADe vs conventional: 20.0% vs 14.0%, P=0.07) and polyp (26.7% vs 19.6%, P=0.06). The CADe group however had significantly higher proximal polyp (58.0% vs 46.7% P=0.03) and adenoma (44.7% vs 34.6% P=0.04) detection rates than the conventional group. The mean number of proximal polyp and adenoma detected per patient during first examination were also significantly higher in the CADe group (polyp: 1.20 vs 0.86 P =0.03 adenoma: 0.91 vs 0.61 P =0.03). Subgroup analysis showed that CADe enhanced proximal adenoma detection in patients with fair bowel preparation, shorter withdrawal time and endoscopists with lower adenoma detection rate. This multi-center trial from Asia confirmed that CADe can further enhance proximal adenoma and polyp detection, but may not be able to reduce missed proximal colonic lesions.