AI-assisted colonoscopy improves cancer prevention while increasing cost and patient burden

September 22 2022

2 minutes to learn

Supply / Disclosures

Mori has reported monetary relationships with Cybernet System Corp. and Olympus Corp. Please see the research for all related monetary disclosures from different authors.

We had been unable to course of your request. Please attempt once more later. If this concern nonetheless happens, please contact

AI-assisted colonoscopy has elevated the proportion of sufferers requiring intensive monitoring by 35% within the US and 20% in Europe, which can enhance most cancers prevention however improve prices and affected person accountability.

An essential a part of the prices and burdens for sufferers with polyps is colonoscopy monitoring after polyp resection. Present colonoscopy pointers suggest frequent statement of sufferers with polyps.” Yuichi Morey, Masters, Ph.D., From the Scientific Efficacy Analysis Group on the College of Oslo in Norway, colleagues wrote in Scientific gastroenterology and hepatology. Just lately, using synthetic intelligence to detect polyps has been proven to be growing [adenoma detection rate] From monoscopic about 12%. Whereas there’s a good thing about elevated ADR, there’s additionally an elevated burden related to extra intense colonoscopy monitoring.”

    The proportion of patients recommended post-intensive CRC monitoring:


In a pooled evaluation of 9 randomized managed trials in China, Italy, Japan, and america, Morey and colleagues in contrast colonoscopy with and with out AI in 5,796 sufferers (51% males; median age, 53 years). The first consequence was the proportion of sufferers beneficial to endure subsequent intensive monitoring, which was outlined as 3-year monitoring primarily based on pointers from the ASGE, the European Society of Gastrointestinal Endoscopy, and the Japanese Society of Gastrointestinal Endoscopy.

A complete of 2894 sufferers underwent AI-assisted colonoscopy and 2902 sufferers underwent normal colonoscopy. The researchers reported the next incidence of opposed drug reactions amongst sufferers within the AI ​​group in comparison with the non-AI group in all trials.

When following US and Japanese pointers, the proportion of sufferers beneficial for intensive monitoring elevated from 8.4% (95% CI, 7.4-9.5) within the non-AI group to 11.3% (95% CI, 10.2-12.6) within the AI ​​group with a distinction An absolute danger ratio of two.9% (95% CI, 1.4-4.4) and a hazard ratio of 1.35 (95% CI, 1.16-11.57). The proportions additionally elevated when European pointers had been adopted, from 6.1% (95% CI, 5.3-7) to 7.4% (95% CI, 6.5-8.4) with an absolute distinction of 1.3% (95% CI, .01-2.6) and a hazard ratio of 1.22 ( 95% CI, 1.01-1.47).

Amongst sufferers who underwent colonoscopy for colorectal most cancers screening, the proportion of sufferers who beneficial intensive surveillance elevated from 8.1% (95% CI, 6.1-10.5) to 10.8% (95% CI, 8.6-14.4) with an absolute distinction of two.7% (95% CI, -0.5 to five.9) and a danger ratio of 1.32 (95% CI, 0.95-1.84) when US and Japanese pointers had been adopted. When European pointers had been adopted, it elevated from 6% (95% CI, 4.3-8.1) to six.6% (95% CI, 4.8-8.8) with an absolute distinction of 0.6% (95% CI, -2 to three.2) and a danger ratio 1.09 (95% CI, 0.72-1.64).

Morey and colleagues conclude, “Our research demonstrated the impact of AI on baseline danger stratification, shifting a big proportion of sufferers into higher-risk classes with little impact on the proportion of sufferers in low-risk teams.” This, in flip, prompts extra intensive monitoring after polyp elimination, which can result in more practical most cancers prevention.

They continued, “Such surveillance methods should bear in mind the steadiness between excessive efficacy, on the one hand, and endoscopic capability and danger of overdiagnosis, on the opposite.” “Giant, population-based trials with long-term follow-up will deliver clear solutions to those essential questions.”