Using AI During Colonoscopy Increases Polyp Detection Rates and Reduces Costs

A polyp is a small growth of tissue in the colon that can develop into colorectal cancer. Patients with polyps have a higher risk of developing cancer in the future.

– Using artificial intelligence (AI) during colonoscopy, endoscopic examination with a camera, may be helpful in detecting precancerous polyps, says Yuichi Mori, physician and associate professor of the Clinical Effectiveness Research Group from the University of Oslo.

The artificial intelligence tool used during colonoscopy relies on the same technology as facial recognition on cell phones. By marking polyps in red or green boxes, the tool assists doctors during colonoscopy, helping them see polyps they might have otherwise missed.

– The technology is useful when the polyps are small or difficult to detect, says Mori.

More patients are recommended for follow-up colonoscopy every three years

A possible flaw with the new technology is that doctors detect more small, harmless polyps using the tool, which then need to be removed. Even if the removal of small polyps does not have more significant side effects, one in a thousand people will suffer bleeding or a small rupture of the colon during the removal.

Mori and his co-researchers compared outcomes after colorectal cancer screening, with and without the use of AI. Approximately 5,800 patients were included in the study.

– The use of AI tools during colonoscopy has led to a 20% increase in the number of patients with polyps recommended for screening every three years in Europe, says Mori. Usually, patients undergo recommended check-ups every 10 years.

The research was published in Impact of artificial intelligence on colonoscopy surveillance after polyp removal: A pooled analysis of randomized trial.

More screening can lead to overdiagnosis

As patients need to undergo more screenings, the use of AI during colonoscopy can lead to overdiagnosis, patient strain, and higher financial costs for health services. Some patients also find colonoscopy uncomfortable. Taking laxatives and drinking two to three liters of clear liquid before the exam can be difficult.

We don’t know if more colonoscopies will reduce the risk of getting colorectal cancer over time, or if it will just increase the financial strain on hospitals. This requires longitudinal clinical efficacy studies and studies of the financial costs of using AI during colonoscopies.”

Yuichi Mori, Doctor and Associate Professor, Clinical Effectiveness Research Group, University of Oslo

Reduced costs when using artificial intelligence in scouting

Mori and his co-researchers have in another new paper investigated whether the use of AI in colorectal cancer screening actually results in higher financial costs to healthcare services. The study shows that using AI tools during colorectal cancer screening in the United States reduced costs by $57 per person.

– Using AI in screening can prevent about 7,200 colorectal cancer cases and about 2,000 related deaths at the US population level. This will save the company $290 million per year in the long term. The study is based on modeling, and we don’t yet know if the estimates are correct. To be able to find out, we will need large-scale clinical studies, says Mori.

The research was published in Cost-effectiveness of artificial intelligence for screening colonoscopy: a modeling study.

Mori is currently working on the EU-funded OperA research project, a portfolio of large-scale clinical studies investigating the long-term effects of using AI in screening.

– The aim is to change the standard of treatment by establishing reliable clinical evidence and, in the long term, to improve patient outcomes, for example when detecting colorectal cancer. The OperA project will find the answer to these important questions, Mori says.

New colorectal cancer screening program in Norway

Norway recently introduced a national screening program for colorectal cancer. Men and women aged 55 will be offered screening by colonoscopy or faecal samples from this fall.

– I am happy that Norway is now introducing a screening program for colorectal cancer, and I hope it will help to reduce cancer, says Mori.

– It is not yet known whether AI can help make a difference in screening, but I hope it will be used when it can be useful, he concludes.