Learning and deskilling effects of artificial intelligence in colonoscopy among endoscopists with different levels of experience: a pragmatic, prospective trial.
EndoscopyJun 3, 2026 (epub)
Clinical ResearchGastroenterology
Tom Andre Pedersen, Yuichi Mori, Edoardo Botteri et al.
✦ AI-curated · Sources linked
In 30 seconds
This pragmatic, multicenter trial evaluated the impact of computer-aided detection (CADe) on polyp detection rates (PDR-5) among 13 endoscopists with varying experience levels. The study found that CADe significantly increased PDR-5 in inexperienced endoscopists from 31.9% to 39.5% (OR 1.43, 95%CI 1.11-1.84), but no significant changes were observed in experienced endoscopists or after CADe removal.
Key findings
- CADe increased PDR-5 in inexperienced endoscopists from 31.9% to 39.5% (OR 1.43, 95%CI 1.11-1.84).
- No significant change in PDR-5 was observed in inexperienced endoscopists after CADe removal (31.9% to 36.3%, OR 1.03, 95%CI 0.79-1.34).
- Experienced endoscopists showed no significant CADe effect on PDR-5.
Why it matters
Understanding the effects of CADe on endoscopist performance is crucial for optimizing training and improving polyp detection rates, particularly among less experienced practitioners. This could enhance patient outcomes in colonoscopy procedures.