Illustration of the examine’s findings. Credit score: BMJ Drugs (2025). DOI: 10.1136/bmjmed-2025-001446
A staff of Norwegian researchers, by worldwide collaboration, discovered that the usage of synthetic intelligence (AI) throughout colonoscopy elevated the detection of polyps by about 8%, however the threat of most cancers was minimally affected.
Colorectal most cancers is without doubt one of the most typical types of most cancers within the western world. In Norway, roughly 5,000 individuals are affected by colorectal most cancers annually. Norway has not too long ago initiated a nationwide screening program for colorectal most cancers.
At present, colorectal most cancers screening in Norway is carried out utilizing a check that detects blood in stool (FIT screening). If a specific amount of blood is detected within the stool, the affected person is referred for a colonoscopy. Nonetheless, the Norwegian Directorate of Well being has clarified that the stool check will probably be changed with colonoscopy for all 55-year-olds in Norway inside the subsequent 5 years.
Throughout colorectal most cancers screening with colonoscopy, AI is usually used as an assistant to determine polyps through the examination.
The medical advantages of AI should be documented like different instruments for analysis and remedy. This was the explanation for creating worldwide tips for the usage of AI in colonoscopy examinations, by BMJ Fast Suggestions, led by the Norwegian basis MAGIC.
Such instruments additionally characterize essentially the most explored space for AI in medical drugs. A current systematic overview performed as a part of the rule work summarized 44 randomized research with over 30,000 sufferers. AI detects extra polyps however has not assessed long-term results equivalent to most cancers prevalence and mortality.
A brand new massive microsimulation examine, led by the College of Oslo, has analyzed the impact of AI on the prevalence of most cancers and mortality, in addition to drawbacks within the type of extra follow-up colonoscopies when utilizing AI in colorectal most cancers screening. The researchers have reviewed information from about 15 research along with the systematic overview.
The findings had been urgently revealed this week in BMJ Drugs, as a foundation for the rules BMJ Fast Suggestions.
“The project shows that while artificial intelligence can reduce cancer risk by improving the detection of polyps, it must be weighed against the drawbacks of increased follow-up burden. The risk of cancer, which is the most important for patients, is minimally affected,” says doctor and Ph.D. candidate Natalie Halvorsen from the Scientific Effectiveness Analysis Group at UiO.
Three completely different tips based mostly on the Norwegian researchers’ work
“The guideline was urgently published on March 27 in BMJ due to its significant impact on the use of AI in colorectal cancer screening,” explains Halvorsen.
The advice in advises in opposition to utilizing AI as a routine for common colonoscopy screening of adults. Nonetheless, it’s famous that there’s uncertainty within the suggestion and that well being financial assessments ought to be included within the subsequent dynamic replace, which can change the suggestions.
Along with the advice in BMJ Fast Suggestions, the American Gastroenterology Affiliation (AGA) and the European Society of Gastrointestinal Endoscopy (ESGE) revealed their very own suggestions on AI this week, based mostly on the work led by the Norwegian researchers. They draw completely different conclusions than BMJ.
AGA states that no suggestion could possibly be made (gastrojournal.org) both for or in opposition to utilizing AI-assisted colonoscopy. ESGE recommends (thieme-connect.de) use based mostly on the idea {that a} majority of sufferers present process colonoscopy screening would favor help.
“This shows the complexity of the recommendations and how the different recommendation criteria are weighed differently, such as drawbacks of overdiagnosis and increased burden on the health care system,” says Halvorsen.
“The guidelines show that we have good methods to evaluate AI tools and that we can collaborate globally on knowledge and recommendations for practice. So far, there are few examples of AI tools benefiting patients, but the development of knowledge is so rapid that we must dynamically update recommendations. We achieved this during COVID-19 and should also do so for AI,” emphasizes Professor Per Olav Vandvik, founding father of MAGIC and chief of BMJ Fast Suggestions on the College of Oslo.
Burden on sufferers and well being care techniques
The brand new guideline and huge examine revealed in BMJ Drugs are a part of the EU-funded Opera-project (uio.no). Opera, led by UiO Professor Yuichi Mori, goals to research whether or not the usage of AI will help scale back circumstances and mortality of colorectal most cancers.
“Our findings show that artificial intelligence detects more polyps but has only a very modest effect on cancer risk, which must be weighed against increased burden on the health care systems. The introduction of AI in health care should be limited to tools that have shown clinical benefits” says Halvorsen.
“It is important to remember that AI tools can have negative effects on individual patients and on the health care system. This means that both benefits and drawbacks should be carefully assessed before introducing AI into health care,” says Mori.
Key findings embrace:
Discount in most cancers threat: Utilizing AI in colonoscopy had little or no clinically related impact on the chance or mortality of colorectal most cancers after screening: AI lowered most cancers threat over 10 years from 0.82% with out AI to 0.71% with AI. For colonoscopy after FIT screening, the chance fell from 5.82% to five.77%.
Elevated follow-up: Using AI resulted in a 20% improve in follow-up colonoscopies for sufferers over 10 years as a result of elevated detection of polyps. This results in extra examinations for particular person sufferers and extra burden on well being care techniques.
The mission reveals that though AI can scale back most cancers threat by bettering the detection of polyps, it should be weighed in opposition to the drawbacks of elevated follow-up burden. The danger of most cancers, which is most essential for sufferers, is minimally affected.
Extra data:
Natalie Halvorsen et al, Advantages, burden, and harms of laptop aided polyp detection with synthetic intelligence in colorectal most cancers screening: microsimulation modelling examine, BMJ Drugs (2025). DOI: 10.1136/bmjmed-2025-001446
Supplied by
College of Oslo
Quotation:
AI in colonoscopy: Examine finds improve in polyp detection however minimal most cancers threat impression (2025, March 28)
retrieved 28 March 2025
from https://medicalxpress.com/information/2025-03-ai-colonoscopy-polyp-minimal-cancer.html
This doc is topic to copyright. Aside from any honest dealing for the aim of personal examine or analysis, no
half could also be reproduced with out the written permission. The content material is offered for data functions solely.
