AI-assisted colonoscopy improves cancer prevention at increased cost and patient burden

September 22, 2022

Read in 2 minutes

Source/Disclosure

Disclosure:
Mori reports financial ties with Cybernet System Corp. and Olympus Corp. See research for relevant financial disclosures of all other authors.

Your request could not be processed. Please try again later. If this issue persists, please contact us at customerservice@slackinc.com.

AI-assisted colonoscopy increased the proportion of patients requiring intensive surveillance by 35% in the US and 20% in Europe, potentially improving cancer prevention, but at the expense of costs and patient liability increased.

“A significant portion of the cost and burden for patients with polyps is post-polyp removal colonoscopy surveillance. Current guidelines recommend frequent surveillance colonoscopies for patients with polyps. increase.” Yuichi Mori Doctor of Medicine, PhD, Researchers from the Clinical Efficacy Research Group at the University of Oslo in Norway wrote: Clinical Gastroenterology and Hepatology“Recently, we have shown an increase in the use of artificial intelligence for polyp detection. [adenoma detection rate] Approximately 12% of individual endoscopists. While increasing ADR has benefits, it also increases the burden associated with more intensive surveillance colonoscopies. ”

    Percentage of patients recommended for subsequent intensive CRC surveillance:

Source: https://www.cghjournal.org/article/S1542-3565(22)00818-7/pdf

In a pooled analysis of nine randomized controlled trials from China, Italy, Japan, and the United States, Mori et al. We compared microscopy. The primary outcome was defined as his 3-year follow-up based on ASGE, European Gastroenterological Endoscopy Society, and Japanese Gastroenterological Endoscopy Society guidelines, and it was recommended to undergo subsequent intensive surveillance. percentage of patients.

A total of 2,894 patients underwent AI-assisted colonoscopy and 2,902 patients underwent standard colonoscopy. The researchers reported that her ADR was higher in patients in the AI ​​group compared to the non-AI group across all trials.

According to US and Japanese guidelines, the percentage of patients for whom intensive surveillance was recommended ranged from 8.4% (95% CI, 7.4-9.5) in the non-AI group to 11.3% (95% CI, 10.2-12.6%) in the AI ​​group. ). with an absolute difference of 2.9% (95% CI, 1.4-4.4) and a risk ratio of 1.35 (95% CI, 1.16-11.57). Following European guidelines, the proportion also increased from 6.1% (95% CI, 5.3-7) to 7.4% (95% CI, 6.5-8.4), with an absolute difference of 1.3% (95% CI, .01-2.6). was. A risk ratio of 1.22 (95% CI, 1.01-1.47).

Among patients undergoing colonoscopy for colorectal cancer screening, the proportion of patients recommended for intensive surveillance ranged from 8.1% (95% CI, 6.1-10.5) to 10.8% (95% CI). , 8.6-14.4) with an absolute difference of 2.7% (95% CI, –0.5 to 5.9) and a risk ratio of 1.32 (95% CI, 0.95 to 1.84) when following US and Japanese guidelines. Following European guidelines increased from 6% (95% CI, 4.3-8.1) to 6.6% (95% CI, 4.8-8.8) with an absolute difference of 0.6% (95% CI, -2 to 3.2) . A risk ratio of 1.09 (95% CI, 0.72-1.64).

“Our study showed the impact of AI on baseline risk stratification, which shifts a significant proportion of patients to higher risk categories, while a proportion of patients in low risk categories has It had little impact,” Mori and colleagues concluded. “This may encourage more intensive surveillance after polypectomy, leading to more effective cancer prevention.

“Surveillance strategies need to take into account such increases, striking a balance between higher efficacy on the one hand and the risk of endoscopy capacity and overdiagnosis on the other,” they said. He continued: “A large population-based trial with long-term follow-up will provide definitive answers to these important questions.”

See also  Rotten egg breath could be a 'symptom' of risky gastroesophageal reflux condition

Leave a Comment

This site uses Akismet to reduce spam. Learn how your comment data is processed.