Skip to main content

Advertisement

Advertisement

ADVERTISEMENT

News

Novel AI System Shows Success in Detection of Adenomas

A novel artificial intelligence (AI) detection system significantly improved the number of adenomas detected per colonoscopy, according to a study published in The American Journal of Gastroenterology.

Researchers assessed the effectiveness of a novel AI system, CAD-EYE, in improving the quality of colonoscopies by measuring adenoma per colonoscopy (APC). The investigation was a US-based, multicenter, prospective randomized trial comparing CAD-EYE–assisted colonoscopy (CAC) to standard high-definition colonoscopy (CC) in average-risk subjects aged 45 and older undergoing screening or surveillance colonoscopy.

A total of 1031 subjects participated in the trial, with 510 undergoing CAC and 523 undergoing CC. Both groups were similar in age, gender, ethnicity, and colonoscopy indication. The primary outcome was APC, while secondary outcomes included the positive predictive value (PPV) of adenomas and the adenoma detection rate (ADR).

Results indicated that CAC significantly increased APC compared to CC, with values of 0.99 ± 1.6 vs 0.85 ± 1.5 (P = 0.02), yielding an incidence rate ratio of 1.17 (1.03–1.33, P = 0.02). Withdrawal times were similar between the groups (11.28 ± 4.59 minutes for CAC vs 10.8 ± 4.81 minutes for CC; P = 0.11). The difference in PPV of a polyp being an adenoma between CAC and CC was within the established threshold, at 48.6% vs 54% (95% CI −9.56% to −1.48%). No significant differences were found in ADR (46.9% vs 42.8%), advanced adenoma detection (6.5% vs 6.3%), sessile serrated lesion detection rate (12.9% vs 10.1%), and polyp detection rate (63.9% vs 59.3%) between the two groups. However, CAC resulted in a higher number of polyps per colonoscopy (1.68 ± 2.1 vs 1.33 ± 1.8, incidence rate ratio 1.27; 1.15–1.4; P < 0.01).

These findings support the integration of AI-assisted colonoscopy to enhance the quality of colonoscopy procedures, the authors concluded.

 

Reference
Desai M, Ausk K, Brannan D, et al. Use of a novel artificial intelligence system leads to the detection of significantly higher number of adenomas during screening and surveillance colonoscopy: results from a large, prospective, US multicenter, randomized clinical trial. Am J Gastroenterol. 2024;119(7):1383-1391. doi:10.14309/ajg.0000000000002664

© 2024 HMP Global. All Rights Reserved.

Advertisement

Advertisement

Advertisement