Colon to Rectum

Gut. 2022;71(4):757–65

Repici A, Spadaccini M, Antonelli G, Correale L, Maselli R, Galtieri PA, Pellegatta G, Capogreco A, Milluzzo SM, Lollo G, Di Paolo D, Badalamenti M, Ferrara E, Fugazza A, Carrara S, Anderloni A, Rondonotti E, Amato A, De Gottardi A, Spada C, Radaelli F, Savevski V, Wallace MB, Sharma P, Rösch T, Hassan C

Artificial intelligence and colonoscopy experience: Lessons from 2 randomized trials

Background and aims: Artificial intelligence has been shown to increase adenoma detection rate (ADR) as the main surrogate outcome parameter of colonoscopy quality. To which extent this effect may be related to physician experience is not known. The authors performed a randomized trial with colonoscopists in their qualification period (AID-2) and compared these data with a previously published randomized trial in expert endoscopists (AID-1).
Methods: In this prospective, randomized controlled non-inferiority trial (AID-2), 10 non-expert endoscopists (< 2000 colonoscopies) performed screening/surveillance/diagnostic colonoscopies in consecutive 40–80 year-old subjects using high-definition colonoscopy with or without a real-time deep-learning computer-aided detection (CADe). The primary outcome was ADR in both groups with histology of resected lesions as reference. In a post-hoc analysis, data from this randomized controlled trial (RCT) were compared with data from the previous AID-1 RCT involving 6 experienced endoscopists in an otherwise similar setting.
Results: In 660 patients (62.3 ± 10 years; men/women: 330/330) with equal distribution of study parameters, overall ADR was higher in the CADe than in the control group (53.3% vs. 44.5%; relative risk [RR] = 1.22; 95% confidence interval [CI]: 1.04–1.40; p < 0.01 for non-inferiority and p = 0.02 for superiority). Similar increases were seen in adenoma numbers per colonoscopy and in small and distal lesions. No differences were observed with regards to detection of non-neoplastic lesions. When pooling these data with those from the AID-1 study, use of CADe (RR = 1.29; 95% CI: 1.16–1.42) and colonoscopy indication, but not the level of examiner experience (RR = 1.02; 95% CI: 0.89–1.16) were associated with ADR differences in a multivariate analysis.

Conclusions: In less experienced examiners, computer-aided detection assistance during colonoscopy increased adenoma detection rate (ADR) and a number of related polyp parameters as compared with the control group. Experience appears to play a minor role as determining factor for ADR.

Prof. Dr. A. Repici, Gastroenterology and Endoscopy Unit, IRCCS Humanitas Research Hospital, Rozzano, Italy,

DOI: DOI: 10.1136/gutjnl-2021-324471

Back to overview

this could be of interest:

Associations of body-mass index at different ages with early-onset colorectal cancer

Gastroenterology. 2022;162(4):1088–97.e3

Multicenter derivation and validation of a colitis-associated colorectal cancer risk prediction web tool

Gut. 2022;71(4):705–15

More articles on the topic