Computer-aided detection with or without mucosal-exposure devices in colonoscopy: a systematic review and...

Recent advances in endoscopic technologies aim to enhance visualization during the procedure. This systematic review and meta-analysis aimed to compare the effectiveness of combining mucosal-exposure devices and computer-aided detection systems (CADe) versus CADe alone for adenoma detection during colonoscopy. Additionally, we conducted subgroup analysis by colonoscopy indication, and trial sequential analysis (TSA) to assess the robustness of the evidence.

We searched PubMed, Embase, and Cochrane Library for randomized controlled trials (RCTs) from inception to January 2025. We pooled risk ratios (RR) for dichotomous outcomes and mean differences (MD) for continuous outcomes with their respective 95% confidence intervals (CIs).

Three RCTs (2,404 patients) were included. The integration of CADe and mucosal-exposure device significantly improved the adenoma detection rate (ADR) (RR 1.12; 95% CI [1.03, 1.21]) and adenomas per colonoscopy (APC) (MD 0.15; 95% CI [0.06, 0.24]) compared with CADe alone. However, the advanced adenoma detection rate, number of advanced adenomas per colonoscopy, cecal intubation time, and withdrawal time were similar between both approaches. The subgroup analysis for screening colonoscopy yielded consistent findings. In the TSA for ADR, the cumulative z-line crossed the boundary for effect and came within 43 patients of achieving the required sample size, while for APC, the cumulative z-line crossed the boundary for effect and reached the required sample size.

Combining CADe with mucosal-exposure devices during colonoscopy increased both ADR and APC without extending procedure time. However, this combination did not enhance the detection of advanced adenomas compared to CADe alone.