Physician Information Staff
MONDAY, May 2, 2022 (HealthDay News) — Artificial intelligence cuts the failure rate of colorectal neoplasms by almost half, according to a study published online March 15 in Gastroenterology.
Michael B. Wallace, MD, of the Mayo Clinic Jacksonville in Florida, and colleagues enrolled 230 patients undergoing colorectal cancer screening or monitoring at one of eight centers in Italy, the UK and the US to undergo two on the same day, return -back colonoscopies with or without artificial intelligence (AI; deep learning CADe) followed by the other.
The researchers found that the missed adenoma rate (AMR) was 15.5% (38 of 246) in the arm with IA and 32.4% (80 of 247) in the first colonoscopy arm without IA ( adjusted odds ratio [OR], 0.38). The AMR was specifically lower for AI-first for lesions ≤ 5 mm (15.9 vs. 35.8%; OR: 0.34) and non-polypoid lesions (16.8 vs. 45.8%; OR: 0.24). Additionally, AMR was lower in both the proximal (18.3 vs. 32.5%; OR, 0.46) and distal (10.8 vs. 32.1%; OR, 0.25) colon. . At the second colonoscopy, the average number of adenomas was lower in the first AI group compared to the first non-AI colonoscopy group. In the first AI and non-AI arms, the false negative rates were 6.8% (three of 44 patients) and 29.6% (13 of 44), respectively (OR, 0.17).
People also read…
“AI resulted in an approximately two-fold reduction in the failure rate of colorectal neoplasia, supporting the benefit of AI in reducing perceptual errors for small and subtle lesions during colonoscopy. standard,” the authors write.
One author disclosed financial ties to Cosmo Artificial Intelligence-AI Ltd., which funded the study.