Authors' objectives: This report aims to identify and summarise evidence that addresses the following research question: What is the clinical and cost effectiveness of AI-assisted endoscopy in identifying lower gastrointestinal (GI) cancers and pre-cancerous lesions compared to standard, non-AI assisted endoscopy?

Authors' results and conclusions: Meta-analyses found that use of AI-assisted (also called computer aided detection (CADe)-assisted) colonoscopy improves adenoma detection rate (ADR) by 23%, polyp detection rate (PDR) by 20% and sessile serrated lesion detection rate (SSLDR) by 21% when compared with standard white light colonoscopy. A subgroup analysis suggested that in populations where the risk of adenoma was low, the improvement in ADR was greater than in populations with a high risk of adenoma. A second subgroup analysis suggested that experienced endoscopists who had conducted more than 2,000 colonoscopies experienced a greater improvement in ADR than inexperienced or trainee endoscopists who had conducted fewer than 1,000 colonoscopies. There was no evidence for an improvement in the detection rate for advanced adenomas or carcinomas. There was evidence that fewer adenomas and sessile serrated lesions were missed with CADe-assisted colonoscopy. HTW developed a new cost-utility analysis using the results of our updated meta-analysis of ADR and lifetime cost and quality-adjusted life years (QALYs) estimates based on recent NICE diagnostic guidance. Overall costs and QALYs were similar for the strategies modelled. However, CADe was estimated to provide very small QALY gains at a slightly higher cost than the comparator. The incremental cost-effectiveness ratio (ICER) of £4,197 per QALY gained indicates that CADe may be cost effective compared with standard colonoscopy. In probabilistic sensitivity analysis, CADe was cost effective at a threshold of £20,000 per QALY gained in 89% of estimates. It was indicated that most patients expected to be informed when AI would be used, but this should not be too detailed. Patients expected practitioners to retain ultimate responsibility in any final decisions but were hopeful that the introduction of AI would result in quicker and more accurate diagnoses.

Authors' recommendations: The evidence supports the routine adoption of CADe colonoscopy for the detection of lower gastrointestinal cancer and pre-cancerous lesions. Compared with standard colonoscopy, CADe is associated with improved detection of adenomas, polyps, and sessile serrated lesions, without considerable increases to withdrawal time. Economic modelling suggests that CADe is cost effective compared with standard colonoscopy with an incremental cost-effectiveness ratio (ICER) of £4,197 per quality-adjusted life year (QALY) gained.

Authors' methods: The Evidence Appraisal Report is based on a literature search (strategy available on request) for published clinical and economic evidence on the health technology of interest. It is not a full systematic review but aims to identify the best available evidence on the health technology of interest. Researchers critically evaluate and synthesise this evidence. We include the following clinical evidence in order of priority: systematic reviews; randomised trials; non-randomised trials. We only include evidence for “lower priority” evidence where outcomes are not reported by a “higher priority” source. We also search for economic evaluations or original research that can form the basis of an assessment of costs/cost comparison. We carry out various levels of economic evaluation, according to the evidence that is available to inform this.

Authors' identified further research: HTW recommends the collection of data on the real-world implementation and effectiveness of CADe.

Project Status: Completed

Year Published: 2024

URL for published report: https://healthtechnology.wales/reports-guidance/ai-assisted-endoscopy-for-gastrointestinal-cancer/

English language abstract: An English language summary is available

Publication Type: Rapid Review

Country: Wales, United Kingdom

Organisation Name: Health Technology Wales

Contact Address: c/o Digital Health Care Wales, 21 Cowbridge Road East Cardiff CF11 9AD

Contact Name: Susan Myles, PhD

Contact Email: healthtechnology@wales.nhs.uk