The Yield of Artificial Intelligence (GI Genius) in Lynch Syndrome - A Randomized Tandem-colonoscopy Trial

We aim to investigate the incremental detection rate of polyps using AI- assisted colonoscopy compared with high-definition white-light endoscopy (HD-WLE). We will conduct a single-center randomized tandem colonoscopy trial of patients with Lynch syndrome with and without AI. Patients will undergo tandem colonoscopy, the second colonoscopy with either HD-WLE or an AI- assisted device.

We will include patients with a known pathogenic variant (PV) / likely PV in one of the MMR genes, who are undergoing endoscopic screening and surveillance in our institute. Patients will undergo a first colonoscopy with HD-WLE, and will be randomized at 1:1 ratio to undergo a second colonoscopy with either HD-WLE or an AI- assisted device. All visualized polyps will be removed and size, histology and numbers of polyps detected on each exam will be recorded. We will evaluate the adenoma detection rate and polyp detection rate in each arm and the number of adenomas / polyps in each arm.