Efficacy of artificial intelligence in detecting precancerous lesions among a colorectal cancer screening population undergoing surveillance colonoscopies in Italy: a randomized control trial (GENIAL-CO Follow-Up study): GI Signals

Endoscopy rct · n=914 · Oct 6, 2026 · Dig Liver Dis · IF 4.2

Efficacy of artificial intelligence in detecting precancerous lesions among a colorectal cancer screening population undergoing surveillance colonoscopies in Italy: a randomized control trial (GENIAL-CO Follow-Up study).

New evidenceartificial intelligencecolonoscopypolypectomycolorectal cancer screening

Clinical takeawayIn surveillance colonoscopy within an organized screening program, CADe did not significantly change ADR (66.6% vs 61.0%) or advanced ADR (7.3% vs 6.3%), increased adenomas per colonoscopy (1.80 vs 1.32) and lengthened withdrawal (16.4 vs 14.5 min). The marginal gain is small when baseline detection is high; this is not a reason to abandon CADe where ADR is lower.

What it foundCADe-assisted colonoscopy did not improve ADR (66.6% vs 61.0%, p = 0.160) or AADR (7.3% vs 6.3%, p = 0.263) but increased APC (1.80±2.19 vs 1.32±1.75, p < 0.001) and WT (16.35±8.32 vs 14.52±7.24 min, p < 0.001) in surveillance colonoscopy.

ContextChallenges prior assumptions that CADe universally improves adenoma detection, particularly in surveillance colonoscopy settings.

No standard claimed for this paper

Every paper is compared to the standard governing its question. This one is not: either no standard in the corpus matches it, or the comparison did not hold up on review and was withdrawn rather than published unverified. Both are logged.

Spada C … Costamagna G · Digestive and Liver Disease : Official Journal of the Italian Society of Gastroenterology and the Italian Association for the Study of the Liver · IF 4.2 · PubMed ↗Permalink