PRACTICE (AI optical diagnosis)

Safety of artificial intelligence-assisted optical diagnosis for leaving colorectal polyps in situ during colonoscopy (PRACTICE): a non-inferiority, randomised controlled trial

Patient / Population Intervention / Exposition Comparaison Critère de jugement

In 895 adults undergoing colonoscopy with computer-aided detection and diagnosis at four Italian centres, a leave-in-situ strategy for rectosigmoid polyps ≤5 mm optically diagnosed as non-neoplastic was non-inferior to resecting all detected polyps for adenoma detection rate.

N
895
Schéma
Multicentre open-label non-inferiority RCT, Italy
Critère
Adenoma detection rate (ADR), 10% absolute non-inferiority margin
Pertinence
3
RésultatADR 44.7% (95% CI 40.4–49.5) vs 46.5% (41.8–51.2); absolute difference −1.8 percentage points (95% CI −8.9 to 4.9; P=0.013). 197 vs 211 adenomas or cancers detected; no perforation or bleeding in either group.
Antonelli G, et al. Lancet Gastroenterol Hepatol. 2025;10(10):915-923. 10.1016/S2468-1253(25)00140-2
Discussion et critique

First randomised test of the guideline-endorsed leave-in-situ strategy, here with AI-supported optical diagnosis: oncological safety, measured as ADR, was preserved while unnecessary polypectomies were avoided. Open-label, four Italian centres, and ADR is a surrogate — the trial cannot show that polyps left behind never progress. Randomised, so it sits in the cluster as a safety trial rather than a detection trial.