Optimized computer-assisted technique for increasing adenoma detection during colonoscopy: a randomized controlled...

Efforts to improve colonoscopy have recently focused on improving adenoma detection through individual interventions. We evaluated an optimized computer-assisted technique (CADopt) versus standard colonoscopy.

A prospective randomized controlled trial was conducted enrolling adults (45-80 years) undergoing elective colonoscopy. Participants were randomized (1:1) to the intervention group (CADopt), and control group. In the CADopt group, endoscopists used a computer-aided polyp detection combined with linked color imaging, water exchange colonoscopy, and cecal retroflexion. In the control group, standard colonoscopy was performed. Primary outcome was Adenoma Detection Rate (ADR) in the intervention and control groups. Secondary outcomes included polyp detection rate (PDR), advanced ADR (AADR), sessile-serrated lesion detection rates (SDR), and Adenoma per colonoscopy (APC).

A total of 467 patients were recruited and randomized (CADopt group 229 patients, 50.2% female vs 238 patients, 48.3% female in the control group). ADR was 49.3% (95% CI 42.7-56.0) for the CADopt group vs 38.2% (95% CI 32.0-44.7) for the control group (p = 0.016). PDR, AADR, SDR, and APC were 78.2% (95% CI 72.2-83.3), 13.1% (95% CI 9.0-18.2), 6.6% (95% CI 3.7-10.6), and 0.86 (95% CI 0.70-1.02) for the CADopt group versus 59.2% (95% CI 52.7-65.5), 8.0% (95% CI 4.9-12.2), 7.1% (95% CI 4.2-11.1), and 0.75 (95% CI 0.58-0.92) for the control group, respectively.

Using an optimized computer-assisted technique led to significant improvements in ADR, PDR, and a trend towards AADR improvements.