Influence of artificial intelligence on the performance of endosonographers in detection of solid pancreatic tumors: a tandem randomized video study.
Julieta Montanelli, Leonardo Sosa-Valencia, Peter Vilmann et al.
✦ AI-curated · Sources linked
In 30 seconds
This randomized controlled trial evaluated the impact of an AI-based software system on endosonographers' performance in detecting solid pancreatic tumors (SPTs) using curated EUS videos. Among 57 endosonographers, diagnostic accuracy improved from 70.8% without AI to 77.1% with AI assistance (P < 0.001), particularly for high-complexity clips.
Key findings
- Diagnostic accuracy improved from 70.8% without AI to 77.1% with AI (P < 0.001).
- Stand-alone AI accuracy was 92.3%.
- AI assistance significantly increased diagnostic confidence (P < 0.001).
- No significant difference in AI effect was found between experience levels.
Why it matters
The integration of AI in endoscopic ultrasound may enhance diagnostic accuracy and confidence in detecting challenging pancreatic tumors, potentially leading to earlier and more accurate diagnoses.