Use of Artificial Intelligence Improves Colonoscopy Performance in Adenoma Detection: A Systematic Review and Meta-Analysis.

Abstract

Background and aims: Artificial intelligence (AI) is increasingly used to improve adenoma detection during colonoscopy. This meta-analysis aimed to provide an updated evaluation of computer-aided detection (CADe) systems and their impact on key colonoscopy quality indicators.

Methods: We searched the Embase, PubMed and MEDLINE databases from inception until February 15, 2024, for randomised control trials (RCTs) comparing the performance CADe systems with routine unassisted colonoscopy in the detection of colorectal adenomas.

Results: 28 RCTs were selected for inclusion involving 23861 participants. Random-effects meta-analysis demonstrated a 20% increase in ADR (RR 1.20, 95% CI 1.14-1.27, p<0.01) and 55% decrease in AMR (RR 0.45, 95% CI 0.37-0.54, p<0.01) with AI-assisted colonoscopy. Subgroup analyses involving only expert endoscopists demonstrated a similar effect size (RR 1.19, 95% CI 1.11-1.27, p<0.001), with similar findings seen in analysis of differing CADe systems and healthcare settings. CADe use also significantly increased adenomas per colonoscopy (weighted mean difference 0.21, 95% CI 0.14-0.29, p<0.01), primarily due to increased diminutive lesion detection, with no significant difference seen in detection of advanced adenoma. Sessile serrated lesion detection (RR 1.10, 95% CI 0.93-1.30, p=0.27) and miss rates (RR 0.44, 95% CI 0.16-1.19, p=0.11) were similar. There was an average 0.15 minute prolongation of withdrawal time with AI-assisted colonoscopy (weighted mean difference 0.15, 95% CI 0.04-0.25, p = 0.01) and a 39% increase in the rate of non-neoplastic resection (RR 1.39, 95% CI 1.23-1.57, p<0.001).

Conclusions: AI-assisted colonoscopy significantly improved adenoma, but not sessile serrated lesion, detection irrespective of endoscopist experience, system type or healthcare setting.