Protocol for a multicenter randomized controlled trial to assess the usefulness of computer-aided detection systems for colonoscopy in colorectal cancer screening in the Asia-Pacific region (project CAD/NCCH2217).

Abstract

Ensuring the high quality of colonoscopies in colorectal cancer (CRC) screening is essential to reducing CRC. Recently, computer-aided detection systems (CADe) that use artificial intelligence have attracted much attention as potentially useful tools for improving lesion detection in colonoscopy. However, evidence on the efficacy of CADe in CRC screening is lacking. We have planned a multi-national, multi-center, randomized controlled trial in the Asia-Pacific region to assess whether colonoscopy with CADe (test method) yields higher lesion detection (primary endpoint: adenoma detection rate) than colonoscopy without CADe (standard method) in CRC screening populations. The study will include 1400 participants aged 50-79 years who are due to undergo colonoscopy for CRC screening, whether as a primary screening colonoscopy or following a positive fecal immunochemical test. If the efficacy of CADe is proven from this study, the use of CADe in colonoscopy for CRC screening will become standard, leading to improved CRC screening.