Routine use of AI in colonoscopies linked to decreased skill in adenoma detection by clinicians without AI assistance.
Key Details
- 1Observational study involved 1,443 non-AI assisted colonoscopies across four centers in Poland.
- 2After routine AI adoption, experienced endoscopists' adenoma detection rate fell from 28.4% to 22.4% (a 20% relative decrease) in procedures without AI.
- 3AI-assisted procedures maintained a 25.3% detection rate during the same period.
- 4Authors caution the findings may indicate a risk of skill erosion (deskilling) for health professionals with extensive AI use.
- 5Study calls for further research into long-term consequences of AI in clinical workflows and strategies to preserve clinicians’ skills.
Why It Matters
This is the first real-world study suggesting that continuous use of imaging AI tools could degrade clinicians’ core diagnostic abilities, raising important questions about safety, training, and oversight as AI adoption in endoscopy—and wider radiology—accelerates.
Source
EurekAlert
Related News
•EurekAlert
AI-Powered OCT Enables Rapid 'Optical Biopsy' for Early Endometrial Cancer Detection
A team at Washington University has developed a catheter-based 3D OCT system with AI to quickly and noninvasively detect early endometrial cancers.
•EurekAlert
AI Clinical Reasoning in Diagnostics and Digital Fatigue in Healthcare
Recent JMIR features explore large language models in clinical diagnostics and digital fatigue among healthcare professionals.
•EurekAlert
KAIST, MIT, Microsoft Develop Efficient AI Image Upsampling for Robotics
KAIST, MIT, and Microsoft have created 'Upsample Anything,' a training-free AI method to restore high-resolution visual data from compressed images with up to 16x improved GPU memory efficiency.