Artificial intelligence excels at catching pre-cancerous cells

Authors of a new study on detecting precancerous polyps in colorectal cancer screening came to the conclusion that “Artificial Intelligence (AI) may detect colorectal polyps that have been missed due to perceptual pitfalls.”

They go on to say “By reducing such miss rate, Artificial Intelligence may increase the detection of colorectal neoplasia leading to a higher degree of Colorectal Cancer (CRC) prevention.”

According to a news release, a team of international researchers led by Mayo Clinic reported that AI “reduced by twofold the rate at which pre-cancerous polyps were missed in colorectal cancer screening.”

The Mayo Clinic defines a colon polyp as “a small clump of cells that forms on the lining of the colon” and says most are harmless. Yet, it cautions, “over time, some colon polyps can develop into colon cancer, which may be fatal when found in its later stages.”

According to the World Health Organization, colorectal cancer constituted 1.93 million new cases (the third most common) worldwide in 2020, with 916,000 deaths (second leading case of cancer death, after lung cancer).

“A colonoscopy is an exam used to detect changes or abnormalities in the large intestine (colon) and rectum,” the Mayo Clinic defines the procedure to check for pre-cancerous and cancerous growths.

How was the study carried out?

There were 230 participants in the study who were undergoing colorectal cancer screening or surveillance in eight centres (Italy, UK, US). They were randomly divided into two groups and underwent two same-day, back-to-back colonoscopies.

116 patients underwent colonoscopies with AI-first, followed by colonoscopy without AI, while 114 had the standard colonoscopy first, followed by colonoscopy with AI.

Estimates suggest the rate at which pre-cancerous colorectal polyps is missed as 25 percent. In the recent study published in Gastroenterology, 15.5 percent in the group that had the AI colonoscopy first, whereas the miss rate was 32.4 percent in the group that had standard colonoscopy first.

The news release notes that “The 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," says senior author Michael B. Wallace, MD, division chair of gastroenterology and hepatology at Sheikh Shakhbout Medical City in Abu Dhabi, United Arab Emirates and the Fred C. Andersen Professor of Medicine at Mayo Clinic in Jacksonville, Florida. "Using artificial intelligence to detect colon polyps and potentially save lives is welcome and promising news for patients and their families."

Moreover, false negatives, when somebody has a particular condition but the tests do not pick up on it, were much lower with the group that had the AI colonoscopy first. Their false-negative rates  – 6.8 percent – were about a quarter of the group that had standard colonoscopy first – 29.6 percent.

The researchers concluded that “AI resulted in an approximately two-fold reduction in miss rate of colorectal neoplasia, supporting AI-benefit in reducing perceptual errors for small and subtle lesions at standard colonoscopy.”