Services on Demand
Journal
Article
Spanish (pdf)
Article in xml format
Article references
Automatic translation
Send this article by e-mailIndicators
Cited by SciELO 
Access statistics
Related links
Similars in
SciELO
Share
Permalink
Gen
Print version ISSN 0016-3503On-line version ISSN 2477-975X
Abstract
FRAGENAS, Andreina et al. Does colonoscopy assisted by Artificial Intelligence surpass conventional colonoscopy? Comparative study. First report in Venezuela. Gen [online]. 2025, vol.79, n.1, pp.2-12. Epub Mar 09, 2025. ISSN 0016-3503. https://doi.org/10.61155/gen.v79i1.726.
Introduction:
The development of artificial intelligence (AI) is revolutionizing daily medical practice, and gastroenterology is no exception. When applied to colonoscopy, these systems increase PDR and ADR rates while reducing the incidence of colorectal cancer.
Objective:
To determine the diagnostic accuracy of AI-assisted colonoscopy in detecting polyps and adenomas.
Materials and Methods:
A cross-sectional observational study was conducted with a sample of 161 consecutive patients undergoing screening or follow-up colonoscopies at the Endoscopy Unit, Gastroenterology Service, Cancer Prevention Clinic (Anticancer Society of Venezuela). The procedures were performed using Fujinon 4500 and 7000-IA series equipment operated by expert endoscopists. The study period spanned from January 2022 to June 2024.
Results:
Overall PDR: 32%; overall ADR: 22%. When analyzed by equipment type, the 4500 series achieved a PDR of 25.84% and an ADR of 15.73%, while the 7000-IA series achieved a PDR of 41.63% and an ADR of 30.77%.
Conclusion:
AI assisted colonoscopy effectively doubles PDR and ADR rates compared to conventional colonoscopy, demonstrating high specificity (95.12% vs. 79.31%). Keywords: Artificial Intelligence (AI), PDR, ADR, polyps, adenoma, hyperplastic.
Keywords : Artificial Intelligence (AI); PDR; ADR; polyps; adenoma; hyperplastic.
