The American Gastroenterological Association has released new clinical guidelines on the use of AI in colonoscopies.
The guidelines make no recommendation explicitly for or against the use of computer-aided detection systems in colonoscopy. AGA found that while AI can enhance the detection of colorectal polyps, it remains unclear as to how effectively it can prevent colorectal cancer.
Here are seven other notes on the new guidelines:
1. “We are confident that using AI will lead to more polyps removed and more colonoscopies,” Benjamin Lebwohl, MD, a guideline author, told Sci Tech Daily in a March 20 report. “We’re less sure about the extent to which it will lead to less colon cancer. AI-assisted colonoscopy technology is promising and exciting. It’s reasonable for practitioners to use the tech now, but we’re not yet at a point where we can recommend universal adoption.”
2. AGA is the first gastroenterological society in the U.S. to create an AI guideline for polyp detection, according to Sci Tech Daily.
3. The guidelines note that computer-aided detection systems can increase the detection of low-risk polyps, which may result in more frequent and costly follow-up colonoscopies with “uncertain benefits” in preventing cancer.
4. Widespread adoption of CADe could also strain resources and limit access for high-risk patients in need of colonoscopies.
5. “If AI is going to be impactful, it needs to be better than the human eye,” guideline author Shahnaz Sultan, MD, told Sci Tech. “Right now, AI is detecting easy-to-detect lesions. This is version 1.0. Before we can recommend everyone use AI, we need version 4.0, where it helps detect polyps that are truly difficult to find.”
6. AGA made plans to update the guidelines in one to two years as more data on the use of CADe in colonoscopy becomes available.
7. Key areas of future research include practitioner input, patient outcome, rethinking CRC surveillance overall and transparency in AI research.
The post AI shows promise in colonoscopy, but uncertainty remains appeared first on Becker’s ASC.
