Artificial intelligence-assisted detection and optical differentiation of colorectal lesions in Lynch syndrome surveillance (CADLY2): a multicentre, open-label, randomised controlled superiority trial.
Robert Hüneburg, Querijn N E van Bokhorst, Maria Pellisé et al.
✦ AI-curated · Sources linked
In 30 seconds
The CADLY2 trial evaluated the impact of computer-aided detection (CADe) on adenoma detection rates during surveillance colonoscopy in patients with Lynch syndrome. In this multicentre, open-label, randomised controlled trial involving 757 adults, the adenoma detection rate was 30.9% for high-definition white-light (HD-WL) colonoscopy compared to 33.8% for CADe-assisted colonoscopy, with no significant difference (odds ratio 1.14, p=0.41).
Key findings
- Adenoma detection rate was 30.9% for HD-WL versus 33.8% for CADe assistance.
- The odds ratio for adenoma detection was 1.14 (95% CI 0.83-1.57, p=0.41).
- CADx sensitivity for lesion differentiation was 85.9% and specificity was 91.4%.
- Three adverse events occurred in the AI-assisted group, including two mild post-polypectomy bleedings.
Why it matters
This study highlights the limited effectiveness of AI-assisted colonoscopy in improving adenoma detection rates in Lynch syndrome surveillance, suggesting that current expert optical diagnosis may suffice in these specialized settings.