Docbot
Dr. Karnes is a clinical and translational gastroenterologist/scientist with a primary interest in colorectal cancer prevention. After several years as an RO1-funded researcher and Director of Research in the Colorectal Neoplasia Clinic at the Mayo Clinic, he transitioned to private practice for 10 years and was subsequently recruited to UCI in 2012 to spearhead efforts to reduce colorectal cancer burden in Orange County. Toward this end, he established a browser-based Colonoscopy Quality Database to promote high-quality colonoscopy exams. This database now contains over 12K colonoscopies and 28K polyp images with pathology, providing unique opportunities for research. He co-founded Docbot to leverage these data and others to generate artificial intelligence algorithms to improve and report colonoscopy quality and thereby reduce colorectal cancer burden. This effort resulted in several highly accurate deep learning algorithms, including polyp detection/localization, optical pathology, IBD mucosal severity scoring, and measures of cecal intubation, preparation quality, and withdrawal time. These algorithms simultaneously process and display outputs during live colonoscopy and are now under clinical validation.