Because of AI, colonoscopists using a cloud-based polyp detector found 0.82 adenomas per colonoscopy against 0.62 without it, and 43.2% of patients had an adenoma against 35.9%.

EAGLE randomized screening and surveillance colonoscopy patients at eight centers in four European countries to standard colonoscopy or colonoscopy with CADDIE, a cloud-based real-time polyp-detection aid. The aided arm found more adenomas per colonoscopy (0.82 vs 0.62), more large polyps and more sessile serrated lesions, with no rise in unnecessary resections.

Sources

• primaryKader et al., npj Digital Medicine 2025: A novel cloud-based artificial intelligence for real-time detection of colorectal neoplasia – a randomized controlled trial (EAGLE)doi.org
• primaryClinicalTrials.gov NCT05730192 (Odin Medical), results posted 2026-10-26clinicaltrials.gov

Editor's notes

verify: the headline outcome is adenoma detection, a surrogate for interval colorectal cancer, which the trial did not measure; the paper itself says the link between adenomas per colonoscopy and interval cancer needs more research. verify: the registry results record (posted 2026-10-26) reports the detection-rate counts as 180 of 417 and 152 of 424 colonoscopies, which is 43.2% and 35.8%; the paper's abstract gives 35.9% for the control arm. verify: achieved start is the paper's randomization window (May to November 2023); the registry gives an actual start of 2023-05-10 and a primary completion of 2023-11-20, used as the achieved end. verify: the paper is from December 2025 and the registry results are new this week; no earlier entry or inbox line covers this trial.

History

• Oct 26, 2026Added by the daily scout.

Cite this entry