Using artificial intelligence (AI) during screening colonoscopy could be a cost-saving strategy that could also boost the prevention of colorectal cancer (CRC) incidence and mortality, a researcher has reported.
Among a simulated cohort of patients at average risk of CRC, and compared to no screening, the relative reduction in the incidence of CRC was 44.2% with screening colonoscopy without AI tools and 48 .9% with screening colonoscopy with AI tools, for an additional gain of 4.8%. Additionally, compared to no screening, the relative reduction in CRC mortality was 48.7% for screening colonoscopy without IA versus 52.3% for screening colonoscopy with IA, for an additional gain by 3.6%, reported Yuichi Mori, MD, of Showa University Yokohama Northern Hospital in Japan.
AI detection tools were also associated with a savings of $57 per patient after reducing discounted costs from $3,400 to $3,343, which persisted in secondary colonoscopy modeling analysis, Mori said in a presentation to Digestive Disease Week (DDW). The results were published simultaneously in the Lancet Digital Health.
“At the U.S. population level, implementation of AI detection during screening colonoscopy resulted in an annual incremental prevention of 7,194 [CRC] cases and 2,089 related deaths, and an annual saving of US$290 million,” Mori and colleagues wrote.
“We are able to find cost reduction overall, which is very surprising as the primary use of AI increases costs, but this can be done by the colorectal cancer prevention effect,” Mori said at a DDW press conference.
“Using AI for polyp detection mainly increases costs because it can increase the detection of polyps, adenomas, and it can increase the number of polypectomies, and subsequently it can increase the number of colonoscopies monitoring,” Mori explained. “However, this type of increase may be mitigated by the benefits derived from the use of AI, namely the cancer prevention effect with the increase in ADR [adenoma detection rates] by AI. It is therefore very important to know how the use of AI contributes to the health system in terms of cost effectiveness.”
The study had some limitations, including that the authors assumed “a linear relationship between the cancer prevention effect and the increase in ADR, [and] there is an ongoing discussion as to whether there is a threshold effect of ADR in cancer prevention.” Furthermore, the authors “assumed the same increase in the detection rate of high-risk adenomas as low-risk adenomas under the use of AI for polyp detection, although the detection rate of advanced adenomas has not been shown in [a] previous meta-analysis.”
Mori and colleagues used microsimulation of the Markov model in a hypothetical cohort of 100,000 US patients who were screened by colonoscopy with or without AI every 10 years, starting at age 50 and ending at age 80. Patients had no personal or family history of CRC, adenomas, inflammatory bowel disease, or hereditary CRC syndrome.
“The costs of AI tools and the cost of processing downstream of screening detected diseases were estimated with annual discount rates of 3%,” they said.
The authors reported that, based on an assumption of 60% screening participation, colonoscopy screening reduced the incidence of CRC from 6.0% cases per 100,000 to 3.3% cases per 100,000, which corresponds to an absolute reduction of 2,638 cases per 100,000 and a relative reduction of 44.2%. versus no screening. Compared to colonoscopy without AI, implementation of AI further reduced CRC incidence from 3.3% to 3.0% cases per 100,000 people, and CRC mortality by 1.2 % to 1.1% per 100,000 people, they said.
“This corresponds to an additional 0.3% absolute reduction (8.4% relative reduction) in [CRC] incidence and 0.1% absolute reduction (6.9% relative reduction) of [CRC] mortality, compared to colonoscopy without AI,” the authors said.
Mori’s group also found that AI further reduced CRC treatment costs by 8.2%, from $1,636 to $1,502 per individual, although this “was partially offset by the cost the implementation of AI which increased screening costs from $1,764 to $1,841 per person (including colonoscopy monitoring and treatment of adverse events).
“I would argue that using AI during screening colonoscopy can be cost-effective in the United States,” Mori concluded.
Mori said his group is planning a large randomized trial in Europe and Japan, with long-term follow-up of CRC incidence as the primary endpoint.
The study was funded by the European Commission and the Japan Society of Promotion of Science.
Mori disclosed relationships with Olympus and Cybernet System. The co-authors disclosed multiple industry relationships.