Combined gastric and colorectal cancer screening may be cost effective in Europe with the implementation of AI

Aims Screening for gastric neoplasia (GN) is not recommended in low-intermediate incidence countries. Artificial Intelligence (AI)might increase the cost-effectiveness of screening strategies. We aimed to assess the cost-effectiveness of AI for GN detection in settings with different gastric cancer incidence and different accuracies of AI systems.

Methods Cost-effectiveness analysis comparing different screening strategies (no screening vs single esophagogastroduodenoscopy (EGD) at 50 years vs stand-alone EGD every 5/10 years vs EGD every 5/10 years combined with screening colonoscopy in Netherlands, Italy and Portugal, according to different AI accuracy. A Markov model was constructed with transition probabilities derived from literature review. Primary outcome was the incremental cost-effectiveness ratio (ICER) of the different strategies vs no screening. Deterministic and probabilistic sensitivity analyses were conducted.

Results Without the use of AI, one single endoscopy at 50 years (Netherlands, Italy, Portugal), endoscopy associated with colonoscopy every 10 years (Italy and Portugal) and endoscopy associated with colonoscopy every 5 years (Portugal) are cost-effective when compared with no screening. If AI increases the accuracy of endoscopy by at least 1% when compared with WLE accuracy (89%), combined screening every 5 years also becomes cost-effective in Italy and if AI accuracy reaches at least 96% accuracy combined screening every 10 years is also cost-effective in the Netherlands.

Conclusions Combined screening through EGD/colonoscopy can be cost-effective in European countries. Implementation of AI at reasonable costs may improve cost-effectiveness of GC screening.

 

MissingLinkText

Conflicts of interest

Authors do not have any conflict of interest to disclose.

Publication History

Article published online:
14 April 2023