A cloud-based artificial intelligence system named Caddie has shown significant improvement in the detection of adenomas, especially the hard-to-detect lesions in the proximal colon. This was observed when used by non-expert endoscopists in the UK. The findings were presented at UEG week. Rawen Kader, MRCP, PhD, a clinical research fellow at University College London, emphasized that while most previous trials in this field were conducted by expert endoscopists, the main advantage of AI polyp detection was expected to benefit non-expert endoscopists.
Key findings from the study:
- The adenoma detection rate (ADR) was 8% higher with Caddie compared to the standard of care.
- Proximal ADR increased from 15% to 23% with Caddie.
- The study involved 739 adults, with 614 included in the analysis. They were assigned to either standard of care or intervention with Caddie.
- The procedures were carried out by 26 endoscopists across nine academic and community hospitals in the UK.
- The primary outcome showed an 8% increase in the adenoma detection rate for non-expert endoscopists using Caddie, rising from 25% to 33%.
- The odds of detecting adenomas were 50% higher with Caddie compared to the standard of care.
- The significant increase in detection with Caddie was observed in more challenging polyps, such as flat non-polypoid sessile polyps and those typically found in the proximal colon.
- There was no significant difference in adenomas per extraction and false positive rate between the two arms, but both results favored the Caddie system.
- Kader highlighted that an increase in ADR correlates with a reduced risk of post-colonoscopy colorectal cancer (PCCRC). The risk of PCCRC is higher in non-expert endoscopists, and AI could be crucial in reducing this variability and the prevalence of PCCRC.
- AI in Medical Procedures: How might the integration of AI in medical procedures, like endoscopy, revolutionize healthcare and improve patient outcomes?
- Training and Expertise: If AI systems like Caddie can assist non-expert endoscopists in achieving results comparable to experts, how might this impact the training and expertise required in the field?
- Future of AI in Healthcare: With the success of Caddie in adenoma detection, what other areas in healthcare could benefit from similar AI-driven enhancements?