Artificial system

Failure rate of precancerous polyps in colorectal cancer screening reduced by artificial intelligence

Artificial intelligence has twice reduced the rate at which precancerous polyps were missed in colorectal cancer screening, reported a team of international researchers led by the Mayo Clinic. The study is published in Gastroenterology.

Most colon polyps are harmless, but some develop into colon or rectal cancer over time, which can be fatal if discovered at an advanced stage. Colorectal cancer is the second deadliest cancer in the world, with an estimated 1.9 million cases and 916,000 deaths worldwide in 2020, according to the World Health Organization. A colonoscopy is a test used to detect changes or abnormalities in the large intestine (colon) and rectum.

Between February 2020 and May 2021, 230 study participants each underwent two consecutive colonoscopies on the same day at eight hospitals and community clinics in the United States, United Kingdom, and Italy. A colonoscopy used AI; the other, a standard colonoscopy, did not.

The rate at which precancerous colorectal polyps are missed has been estimated at 25%. In this study, the failure rate was 15.5% in the group that underwent IA colonoscopy first. The failure rate was 32.4% in the group that underwent standard colonoscopy first. AI colonoscopy detected more polyps that were smaller, flatter, and in the proximal and distal colon.

Colorectal cancer is almost entirely preventable with proper screening. The use of artificial intelligence to detect colon polyps and potentially save lives is welcome and promising news for patients and their families.”

Michael B. Wallace, MD, lead author, Division Director of Gastroenterology and Hepatology at Sheikh Shakhbout Medical City in Abu Dhabi, United Arab Emirates and Fred C. Andersen Professor of Medicine at Mayo Clinic in Jacksonville, Fla

Additionally, false negative rates were 6.8% in the group that underwent the AI ​​colonoscopy first. It was 29.6% in the group that underwent a standard colonoscopy first. A false negative result indicates that you do not have a particular condition, when in fact you do.


Journal reference:

Wallace, MB, et al. (2022) Impact of artificial intelligence on the failure rate of colorectal neoplasia. Gastroenterology.