Endoscopist-Level and Procedure-Level Factors Associated With Increased Adenoma Detection With the Use of a Computer-Aided Detection Device.

Abstract

To investigate the impact of procedure-related and endoscopist-related factors on the effectiveness of a computer-aided detection (CADe) device in adenomas per colonoscopy (APC) detection. The SKOUT clinical trial was conducted at 5 US sites. We present prespecified analyses of procedure-related and endoscopist-related factors, and association with APC across treatment and control cohorts. There were numeric increases in APC between SKOUT vs standard colonoscopy in community-based endoscopists, withdrawal time of ≥8 minutes, for endoscopists with >20 years of experience, and endoscopists with baseline adenoma detection rate <45%. The application of CADe devices in clinical practice should be carefully evaluated. Larger studies should explore differences in endoscopist-related factors for CADe.