TOPLINE:
Synthetic intelligence (AI)–assisted colonoscopy will increase the adenoma detection charge (ADR) and reduces the adenoma miss charge, whatever the endoscopist’s expertise, know-how system, or healthcare setting.
METHODOLOGY:
- Missed lesions throughout colonoscopy considerably contribute to instances of post-colonoscopy colorectal most cancers, with as much as 25% of adenomatous lesions doubtlessly being missed.
- Researchers carried out a scientific evaluation and meta-analysis to guage whether or not AI-driven computer-aided detection (CADe) techniques enhance adenoma detection in contrast with routine colonoscopy.
- It included 28 randomized managed trials printed between 2019 and 2024 involving 23,861 individuals who underwent colonoscopy for screening, post-polypectomy surveillance, or symptomatic causes utilizing a high-definition endoscope.
- The first outcomes have been the ADR and the adenoma miss charge, and secondary outcomes have been adenomas per colonoscopy, sessile serrated lesion detection charges and miss charges, and withdrawal time.
TAKEAWAY:
- AI-assisted colonoscopy elevated the ADR by 20% (P P
- In research involving solely knowledgeable endoscopists, AI-assisted colonoscopy confirmed a 19% enhance within the ADR in contrast with routine colonoscopy (P
- Using AI led to a rise in withdrawal time of simply 9 seconds on common (P = .01).
- AI use elevated adenomas per colonoscopy (weighted imply distinction, 0.21; P
IN PRACTICE:
“General, this examine helps using CADe techniques for improved efficiency of colonoscopy,” the authors wrote.
SOURCE:
This examine, led by Jonathan Makar, Division of Drugs, College of Melbourne, Melbourne, Australia, was published online in Gastrointestinal Endoscopy.
LIMITATIONS:
The truth that solely one of many management arms within the included randomized managed trials used a placebo raises the potential of efficiency bias or the Hawthorne impact. Vital heterogeneity in affected person ages, bowel preparation scores, and colonoscopy indications have been famous throughout the research and will confound the outcomes. The omission of per-protocol or intention-to-treat analyses in some research raises the potential for attrition bias.
DISCLOSURES:
The examine didn’t obtain any particular funding. The authors declared no conflicts of curiosity.
This text was created utilizing a number of editorial instruments, together with AI, as a part of the method. Human editors reviewed this content material earlier than publication.
