OBJECTIVES: VCE is an examination for diagnosing gastrointestinal (GI) tract abnormalities of the small intestine. A camera-equipped device of pill shape and size is swallowed by the subject and records more than 50,000 images as it passes through the GI tract. At the end of the procedure, the images produced are examined by a gastroenterologist. Typical duration of capsule endoscopy (CE) videos is approximately eight hours and examination require around three hours, depending on the experience of the gastroenterologist. The study evaluated the economic and clinical performance of the automatic detection AI-based tool in detecting and classified the potential abnormalities by lowering the experience requirements and reducing the time for CE video examination.

METHODS: A micro-costing analysis, based on costs of the Greek healthcare system, was performed to identify the costs of development of the new AI technology and an array of the most important indicators to enable performance identification. The most important KPIs were i) the sensitivity of automated detection of small bowel abnormalities, ii) the system usability, iii) the average time for completion of small bowel VCE reading (in min), iv) the number of personnel involved in screening. The analysis of costs and consequences was performed incrementally between the current practice and the new AI technology.

RESULTS: The annual cost of use of the new AI technology costs more than current practice (€68.300 vs. €61.674). The sensitivity of automated detection of small bowel abnormalities was 0.89 with the new AI technology vs. 0.90 of current practice resulting in 0.01 difference and the average time for completion of small bowel VCE reading was (60min vs. 240min) in favour of new AI technology. The system usability score of the new technology was 76.4%.

CONCLUSIONS: AI could automate parts of the process with less personnel and significantly reducing the time for CE video examination.