Surveillance Modified by Artificial Intelligence in Endoscopy (SMARTIE)

Multicenter Evaluation Study of the CADe System ENDOMIND in Surveillance Endoscopy for Colorectal Cancer in German Outpatient Cohort

Evaluation of an artificial intelligence system for polyp detection (CADe)

We aim to evaluate the artificial intelligence system ENDOMIND that supports endoscopist in detection of polyps during surveillance endoscopy for colorectal cancer. 1070 patients out of 6 gastroenterologic practice are randomized 1:1 for conventional surveillance colonoscopy vs. surveillance with AI support. Primary endpoint is Adenoma detection rate.

Inclusion Criteria:

• indication CRC surveillance endoscopy
• indication post-polypectomy surveillance endoscopy
• positive fecal immunochemical test in patients >=50 years

Exclusion Criteria:

• reasonable suspicion of inflammatory bowl disease
• reasonable suspicion of familiar polyposis Syndrome
• Patient after radiation/resection of colonic parts