AI-assisted colonoscopies are associated with high detection and removal rates of non-neoplastic lesions, according to a new study presented at the American College of Gastroenterology's 2024 Annual Scientific Meeting.
While AI-assisted colonoscopies with computer-aided detection are associated with improved adenoma detection rates, they also led to a statistically and clinically significant increase in exams that detected lesions that, after resection, were all found to be benign, compared with unassisted colonoscopies, according to a Nov. 4 Medscape report.
The implications of unnecessary benign detection include increased procedural risks, as well as costs, such as pathology costs and other healthcare expenditures without any health benefits, according to study lead author Tessa Herman, MD, chief resident of internal medicine at the University of Minnesota and Minneapolis Veterans Affairs Health Care System.
Researchers looked at 441 non-AIAC colonoscopies between November 2022 and April 2023 and 599 AIAC colonoscopies between May 2023 and October 2023.
In the non-AIAC cohort, 37 cases (8.4%) had polypectomies that revealed only benign lesions, as compared with 74 cases (12.4%) in the AIAC cohort.
The most common resected lesions were benign colonic mucosa, lymphoid aggregates and hyperplastic polyps.
Applied to 15 million colonoscopies conducted in the U.S. annually, with the full adoption of AIAC, 600,000 more colonoscopies could result in benign, nonadenomatous lesions being removed, compared with traditional colonoscopy.