Bayesian network meta-analysis shows AI-assisted colonoscopy improves adenoma detection in adults

Photo by Navy Medicine / Unsplash

European journal of gastroenterology & hepatology Published May 4, 2026 Medically reviewed May 5, 2026 Study authors: Rafi Raheela, Yasmin Nida, Ghani Mubashir, Siddiqui Muhammad Nameer, Mahmood Abdul Rafay, Ali Sarmad… PubMed ↗ DOI ↗ By Dr. Julia Lee, PhD · Oncology, Genomics & Drug Development

Key Takeaway

Consider AI-assisted colonoscopy for adenoma detection, noting small system differences and uncertain high-risk lesion benefits.

This Bayesian network meta-analysis examined the performance of artificial intelligence-assisted colonoscopy against standard colonoscopy in adults undergoing the procedure. The study included 34 106 participants and assessed multiple outcomes including adenoma detection rate, adenomas per colonoscopy, withdrawal time, and detection of advanced or sessile serrated lesions. The certainty of evidence was moderate.

The analysis demonstrated that artificial intelligence-assisted colonoscopy significantly improved adenoma detection rate compared with standard colonoscopy. EndoAngel achieved an odds ratio of 1.84 with a SUCRA of 0.9, while EndoAID showed an odds ratio of 1.64 and a SUCRA of 0.7. CAD-EYE and GI Genius also showed improvements with odds ratios of 1.46 and 1.45 respectively, both with a SUCRA of 0.5. EndoAID demonstrated the largest benefit for adenomas per colonoscopy with a mean difference of 0.62.

Regarding withdrawal time, EndoAngel modestly increased this metric with a mean difference of 1.14 minutes. However, no system significantly improved the detection of advanced or sessile serrated lesions. The authors note that differences between systems are small and benefits for high-risk lesions remain uncertain. Further head-to-head trials and cost-effectiveness studies are needed to clarify the clinical value of these technologies.

Study Details

Study typeMeta analysis

Sample sizen = 106

EvidenceLevel 1

PublishedJun 2026

PMID42066011

View Original Abstract ↓

BACKGROUND: Colorectal cancer is a major global health burden, with most cases arising from adenomatous polyps. Although colonoscopy is the gold standard for detection, its effectiveness is operator-dependent. Artificial intelligence-assisted systems have been developed to improve adenoma detection, but their comparative performance remains unclear. METHODS: We performed a systematic review and Bayesian network meta-analysis of randomized controlled trials comparing artificial intelligence-assisted with standard colonoscopy. PubMed, Scopus, and Google Scholar were searched up to 4 November 2025. Eligible studies included adults undergoing colonoscopy and reporting adenoma detection rate (ADR) and adenomas per colonoscopy (APC). Secondary outcomes included withdrawal time and detection of advanced and sessile serrated lesions. Risk of bias was assessed using Cochrane RoB 2.0, and certainty of evidence was evaluated with CINeMA. RESULTS: A total of 48 randomized controlled trials (34 106 participants) were included. Artificial intelligence-assisted colonoscopy significantly improved ADR compared with standard colonoscopy. EndoAngel showed the greatest effect [odds ratio (OR): 1.84, surface under the cumulative ranking curve (SUCRA): 0.9], followed by EndoAID (OR: 1.64, SUCRA: 0.7), CAD-EYE (OR: 1.46, SUCRA: 0.5), and GI Genius (OR: 1.45, SUCRA: 0.5). For APC, EndoAID demonstrated the largest benefit (mean difference: 0.62). EndoAngel modestly increased withdrawal time (mean difference: 1.14 minutes). No system significantly improved detection of advanced or sessile serrated lesions. Heterogeneity was low, and certainty of evidence was moderate. CONCLUSION: Artificial intelligence-assisted colonoscopy improves adenoma detection; however, differences between systems are small, and benefits for high-risk lesions remain uncertain. Further head-to-head trials and cost-effectiveness studies are needed.