Computer-aided detection in surveillance colonoscopy: a population-based randomized trial.
Laura Codesido-Prado, Pedro Davila-Piñón, Raquel Almazán et al.
✦ AI-curated · Sources linked
In 30 seconds
This population-based randomized controlled trial evaluated the effectiveness of computer-aided detection (CADe) in increasing adenoma detection rates (ADR) during surveillance colonoscopy. Among 4824 included procedures, the overall ADR was similar between CADe-assisted (58.8%) and standard colonoscopy (57.4%; aRR 1.02, 95%CI 0.95-1.10). CADe showed a benefit for lower performing endoscopists but not for high performers.
Key findings
- Overall ADR was 57.4% for standard colonoscopy and 58.8% for CADe-assisted colonoscopy.
- CADe increased ADR for low performing endoscopists (45.5% vs. 52.1%; aRR 1.15, 95%CI 1.01-1.30).
- No significant difference in ADR for high performing endoscopists (65.9% vs. 63.5%; aRR 0.96, 95%CI 0.88-1.05).
Why it matters
Understanding the effectiveness of CADe in surveillance colonoscopy is crucial for optimizing adenoma detection strategies, particularly in varying endoscopist performance levels. This study suggests that CADe may not universally enhance detection rates.