Artificial intelligence (AI) is actively being explored as an assistive tool for clinicians to help spot diseases and disorders at an early stage. New research published in the United European Gastroenterology Journal is the first to assess AI-assisted colonoscopy for patients with Lynch syndrome (LS), according to the scientists at the National Center for Hereditary Tumor Diseases at Bonn University Hospital, who conducted the study in collaboration with the Institute of Medical Informatics, Statistics and Epidemiology at the University of Leipzig.
“We here present first data suggesting that real-time AI-assisted colonoscopy is a promising approach to optimize endoscopic surveillance in LS patients, in particular to improve the detection of flat adenomas,” wrote the researchers.
Lynch syndrome is an inherited genetic disorder that is linked to an increased risk of developing cancer at a younger age than average, especially colon cancer (up to 70 percent), endometrial (up to 70 percent), urinary organs (up to 25 percent), ovarian (up to 20 percent), stomach and small bowel (up to 13 percent), and other cancers according to the American College of Gastroenterology. The genetic disorder is due to mutations in five genes that are known as the “mismatch repair” genes: LH1, MSH2, MSH6, PMS2, and EPCAM which can be passed on from a parent with Lynch syndrome to their children.
“In recent years, several clinical trials in the general population have demonstrated that AI-assisted colonoscopy is a promising approach, showing significant improvement in the detection of polyps and adenomas compared with standard white light endoscopy,” the researchers wrote. “In the present work, we show that this may also apply to high-risk patient groups such as LS patients.”
To conduct the study, 96 Lynch syndrome patients and 46 participants in a control group were studied with the use of standard endoscopy while 50 patients were studied using AI-assisted colonoscopy during the period between December 2021-2022. According to a statement from the University of Bonn, the AI-assisted examinations detected more adenomas (36 percent) than the standard examinations (26 percent).
“AI-assisted colonoscopy detected more completely flat (0-lIb) adenomas than high-definition colonoscopy in our study,” the researchers wrote. “These lesions are characteristic of LS and previous studies have shown that flat adenomas are more likely to be missed. Therefore, our AI system may help improve the detection of such flat polyps that are easily missed during colonoscopy.”
This was the first randomized controlled trial to compare white-light endoscopy to AI-assisted endoscopy for adenoma detection in Lynch syndrome patients, according to the researchers. With this initial proof-of-concept, the scientists recommend multiple center trials with a larger number of patients as a next step.
“We here present first data suggesting that real-time AI-assisted colonoscopy is a promising approach to optimize endoscopic surveillance of Lynch patients, in particular to improve the detection of flat lesions that are easily missed,” the researchers reported.
Copyright © 2022 Cami Rosso All rights reserved.