AI-assisted colonoscopy improves cancer prevention with increased cost, patient burden
Click Here to Manage Email Alerts
AI-assisted colonoscopy increased the proportion of patients requiring intensive surveillance by 35% in the United States and 20% in Europe, potentially improving cancer prevention but increasing costs and patient responsibility.
“An important part of costs and burden for patients with polyps is colonoscopy surveillance after polyp removal. Current guidelines recommend frequent surveillance colonoscopy for patients with polyps,” Yuichi Mori, MD, PhD, of the Clinical Effectiveness Research Group at the University of Oslo in Norway, and colleagues wrote in Clinical Gastroenterology and Hepatology. “Recently, the use of artificial intelligence for polyp detection has been shown to increase [adenoma detection rate] of individual endoscopists by about 12%. While there is benefit of increased ADR, there is also increased burden associated more intensive surveillance colonoscopy.”
In a pooled analysis of nine randomized controlled trials across China, Italy, Japan and the United States, Mori and colleagues compared colonoscopy with or without AI assistance in 5,796 patients (51% men; mean age, 53 years). The primary outcome was the proportion of patients recommended to undergo subsequent intensive surveillance, defined as surveillance after 3 years based on guidelines from the ASGE, the European Society of Gastrointestinal Endoscopy and the Japan Gastroenterological Endoscopy Society.
A total of 2,894 patients underwent AI-assisted colonoscopy and 2,902 patients underwent standard colonoscopy. Researchers reported higher ADRs among patients in the AI group compared with the non-AI group across all trials.
When following U.S. and Japanese guidelines, the proportion of patients recommended for intensive surveillance increased 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). Proportions also increased when following the European guidelines, 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) and a risk ratio of 1.22 (95% CI, 1.01-1.47).
Among patients who underwent colonoscopy for colorectal cancer screening, the proportion of patients recommended intensive surveillance increased 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, 0.95-1.84) when following U.S. and Japanese guidelines. When following European guidelines, it 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) and a risk ratio of 1.09 (95% CI, 0.72-1.64).
“Our study showed an impact by AI on baseline risk stratification, which shifted a considerable proportion of patients to higher risk categories with little influence on the proportion of patients in low-risk categories,” Mori and colleagues concluded. “This in turn prompts a more intensive post-polypectomy surveillance that may lead to a more effective cancer prevention.
“Surveillance strategies should take such an increase into account balancing between higher efficacy, on one hand, and endoscopy capacity and risk of overdiagnosis, on the other,” they continued. “Large-scale, population-based trials with long-term follow-up will bring clear answers to these important questions.”
Perspective
Back to Top
Christine Lee, MD
CRC is the second leading cause of cancer death worldwide, and colonoscopy remains the gold standard in colon cancer prevention.
AI technology shows great promise in increasing adenoma detection rate with aim to increase the quality of colonoscopies and reduce variability in patient outcomes. Variability, however, is not solely based upon the experience of the endoscopist. Multiple factors can contribute to variable results, including bowel prep quality, sedation level and hemodynamic parameters of the patient during endoscopy, the endoscopist’s diligence, quality of the equipment and time.
The increase in ADR has the potential to shorten surveillance intervals. Whether this translates into increased lives saved, globally, needs to be further examined. Additionally, it is unclear what is the ideal ADR where the benefit of increase in colon cancer prevention levels off. Increased ADR beyond a threshold may result in additional cost and burden for patients and health systems without clinically significant benefit.
The exact relationship between ADR and future cancer prevention is still unknown and “a large-scale, population-based trial with long-term follow-up” is indeed needed.
Collapse
Read more about
Click Here to Manage Email Alerts