AI-Assisted Colonoscopy Could Improve Adenoma Detection Rate

Artificial intelligence (AI)-assisted colonoscopy produced better outcomes over conventional colonoscopy (CC) in improving adenoma detection rate (ADR) among symptomatic and asymptomatic patients, researchers concluded from data from large randomized controlled trials.

Researchers conducted large-scale, multicenter randomized controlled trials to compare AI-assisted colonoscopy to CC for adenoma detection in an asymptomatic population, including asymptomatic patients aged 45 to 75 years undergoing colorectal cancer screening by direct colonoscopy or fecal immunochemical test (FIT). In the AI group, an AI polyp detection system (Eagle-Eye, Xiamen InnoVision) with real-time notification on the same monitor of the endoscopy system was used. The primary outcome was overall adenoma detection rate (ADR); secondary outcomes were mean number of adenomas per colonoscopy (APC), ADR according to endoscopist’s experience, and colonoscopy withdrawal time.

Out of 3059 patients, 1519 were randomized to AI and 1540 were randomized to CC. “The overall ADR (39.9% vs 32.4%, p<0.001), Advanced ADR (6.6% vs 4.9%, P=0.041), ADR of expert (42.3% vs 32.8%, p<0.001) and nonexpert endoscopists (37.5% vs 32.1%, p=0.023) and APC (0.59+/-0.97 vs 0.45+/-0.81, p<0.001) were all significantly higher in AI group,” the researchers reported. With baseline characteristics and bowel preparation quality between the two groups kept similar, the study revealed that the median withdrawal time in minutes (8.3 vs 7.8, p=0.004) was slightly longer in AI group.

 “Routine use of AI assistance for real-time adenoma detection in colonoscopy should be considered,” the researchers concluded.

—Priyam Vora

Reference:
Xu H, Tang R, Lam T et al. Artificial intelligence-assisted colonoscopy for colorectal cancer screening: a multicenter randomized controlled trial. Clin Gastroenterol Hepatol. Published on July 18, 2022. DOI: https://doi.org/10.1016/j.cgh.2022.07.006