Pros and cons of artificial intelligence implementation during colonoscopy to enhance adenoma detection rates
Recommended Citation
Aleissa MA, Luca MC, Singh J, Drelichman E, Bhullar J. Pros and cons of artificial intelligence implementation during colonoscopy to enhance adenoma detection rates. Colorectal Dis 2025; 27.
Document Type
Conference Proceeding
Publication Date
8-30-2025
Publication Title
Colorectal Dis
Abstract
Aim: Colorectal cancer prevention realis on early detection with colonoscopy, adenoma detection rate (ADR) considers as a key quality indicator. Artificial intelligence (AI)-assisted colonoscopy has emerged to improve ADR through real-time polyp identification, supported by randomized controlled trials and meta-analyses demonstrating increased detection rates and reduced missed adenomas. Despite this, concerns persist regarding its real-world applicability and cost-effectiveness. Methods: This systematic review followed PRISMA guidelines and searched PubMed and Web of Science databases for articles in English published between January 2000 and August 2024. We included meta-analyses and systematic reviews that assessed AI's role in ADR during colonoscopy. Articles related to non-adenoma indications were excluded. Of the 24 articles identified, 22 met the inclusion criteria. Data extraction was independently performed by two researchers for accuracy and consistency. Results: 22 articles met the inclusion criteria, with significant heterogeneity (I2 = 28%-91%) observed in multiple studies. The number of studies per metanalysis ranged from 5 to 33. AI demonstrated improvement in ADR, with an approximate 20% increase across multiple studies. However, its effectiveness in detecting flat or serrated adenomas remains unproven. Endoscopists with low ADR benefit more from AI-colonoscopies, while expert endoscopists outperformed AI in ADR. No significant change in withdrawal time was observed when comparing AI-assisted colonoscopy to conventional endoscopy. Conclusion: While AI-assisted colonoscopy enhances procedural quality, particularly for those with lower ADR, its real-world efficacy lags behind expert performance. Concerns persist about its limited impact on trainee skill development and potential overreliance hindering observational proficiency. Meta-analyses specifically evaluating AI's role in trainee learning remain absent. Further research is critical to clarify AI's benefits in cancer prevention.
Volume
27
