Abstract
Background and study aims
Adenoma detection rate (ADR) is a key performance measure with variability among endoscopists.
Artificial intelligence (AI) in colonoscopy could reduce this variability and has
shown to improve ADR. This study assessed the impact of AI on ADR among Danish endoscopists
of varying experience levels.
Patients and methods
We conducted a prospective, quasi-randomized, controlled, multicenter trial involving
patients aged 18 and older undergoing screening, surveillance, and diagnostic colonoscopy
at four centers. Participants were assigned to AI-assisted colonoscopy (GI Genius,
Medtronic) or conventional colonoscopy. Endoscopists were classified as experts (>
1000 colonoscopies) or non-experts (≤ 1000 colonoscopies). The primary outcome was
ADR. We performed a subgroup analysis stratified on endoscopist experience and a subset
analysis of the screening population.
Results
A total of 795 patients were analyzed: 400 in the AI group and 395 in the control
group. The AI group demonstrated a significantly higher ADR than the control group
(59.1% vs. 46.6%, P < 0.001). The increase was significant among experts (59.9% vs. 47.3%, P < 0.002) but not among non-experts. AI assistance significantly improved ADR (74.4%
vs. 58.1%, P = 0.003) in screening colonoscopies. Polyp detection rate (PDR) was also higher in
the AI group (69.8% vs. 56.2%, P < 0.001). There was no significant difference in the non-neoplastic resection rate
(NNRR) (15.1% vs. 17.1%, P = 0.542).
Conclusions
AI-assisted colonoscopy significantly increased ADR by 12.5% overall, with a notable
16.3% increase in the screening population. The unchanged NNRR indicates that the
higher PDR was due to increased ADR, not unnecessary resections.
Keywords
Endoscopy Lower GI Tract - Polyps / adenomas / ... - CRC screening - Endoscopic resection
(polypectomy, ESD, EMRc, ...) - Colorectal cancer
Bibliographical Record
Ronja Maria Birgitta Lagström, Karoline Bendix Bräuner, Julia Bielik, Andreas Weinberger
Rosen, Julie Gräs Crone, Ismail Gögenur, Mustafa Bulut. Improvement in adenoma detection
rate by artificial intelligence-assisted colonoscopy: Multicenter quasi-randomized
controlled trial. Endosc Int Open 2025; 13: a25215169.
DOI: 10.1055/a-2521-5169