Related Experiment Video
Updated: May 16, 2026
Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
Published on: July 11, 2025
The role of artificial intelligence in adenoma detection during colonoscopy: a systematic review and meta-analysis of
Alimohammad Bananzadeh1,2, Mahshid Bahadori1, Seyed Mohammad Kazem Tadayon1,3
1Colorectal Research Center, Shiraz University of Medical Sciences, Shiraz, Iran.
Background:
Colonoscopy is the gold standard for colorectal cancer screening; however, it is limited by a substantial adenoma miss rate. We aimed to provide an updated and comprehensive synthesis of evidence from randomized controlled trials (RCTs) on the efficacy of artificial intelligence (AI)-assisted versus conventional colonoscopy in detecting colorectal adenomas.
Methods:
A systematic literature search of PubMed, Scopus, and Web of Science was conducted up to 6 May 2025. Primary outcomes included the adenoma detection rate (ADR), adenomas per colonoscopy (APC), sessile serrated lesion detection rate (SSLDR), SSLs per colonoscopy (SSLPC), adenoma miss rate (AMR), and SSL miss rate (SSLMR). Pooled risk ratios (RR) and mean differences (MD) with 95% confidence intervals (CIs) were calculated using a random-effects model.
Results:
A total of 46 RCTs, involving 37,206 participants, were included. AI-assisted colonoscopy significantly increased ADR (RR = 1.22, 95% CI: 1.17-1.27, I2 = 60.49%), SSLDR (RR = 1.25, 95% CI: 1.12-1.40, I2 = 11.08%), APC (MD = 0.22, 95% CI: 0.18-0.26, P < 0.001), and SSLPC (MD = 0.02, 95% CI: 0.005-0.04, P = 0.01). AI also substantially reduced the AMR (RR = 0.53, 95% CI: 0.44-0.65, P < 0.001) but not SSLMR (RR = 0.64, 95% CI: 0.25-1.66, P = 0.36).
Conclusions:
This comprehensive meta-analysis confirms that AI-assisted colonoscopy significantly improves the detection of conventional adenomas and reduces miss rates. While it also improves the SSLDR, its effect on reducing their miss rate remains inconclusive.
