Artificial intelligence-assisted detection and optical differentiation of colorectal lesions in Lynch syndrome surveillance (CADLY2): a multicentre, open-label, randomised controlled superiority trial.
- Open access
- 1 cites
AI-assisted colonoscopy in Lynch syndrome surveillance did not significantly increase adenoma detection rates, with a 33.8% rate compared to 30.9% in standard procedures.
- Why it matters: Detecting adenomas in Lynch syndrome is crucial for preventing colorectal cancer, but evidence on AI tools' effectiveness in this high-risk group remains limited and inconsistent.
- What they did: A multicentre, randomized trial involving 757 patients compared high-definition white-light colonoscopy alone versus with AI assistance, measuring adenoma detection and lesion differentiation performance.
- The result: AI assistance did not significantly improve adenoma detection (odds ratio 1.14, p=0.41), and CADx performance was comparable to expert diagnosis, indicating limited added benefit in this setting.