Artificial intelligence (AI) technologies to help detect or characterise colorectal polyps

1 Purpose of this document

NICE's assessment of artificial intelligence (AI) technologies to help detect or characterise colorectal polyps recommends that CADDIE, CAD EYE, ENDO-AID, EndoScreener, GI Genius, MAGENTIQ-COLO can be used in the NHS during the evidence generation period to help detect colorectal polyps, for people who do not have diagnosed inflammatory bowel disease or Lynch syndrome. The other technologies that were assessed can only be used in research and are not covered in this plan.

This plan outlines the evidence gaps and what data needs to be collected for a NICE review of the technologies again in the future. It is not a study protocol but suggests an approach to generating the information needed to address the evidence gaps. Evidence generated through other study approaches will also be considered. For assessing comparative treatment effects, well-conducted randomised controlled trials are the preferred source of evidence.

The companies are responsible for ensuring that data collection and analysis take place.

Guidance on commissioning and procurement of the technologies will be provided by NHS England, who are developing a digital health technology policy framework to further outline commissioning pathways.

NICE will withdraw the guidance if the companies do not meet the conditions in section 4 on monitoring.

After the end of the evidence generation period (4 years), the companies should submit the evidence to NICE in a format that can be used for decision making. NICE will review all the evidence and assess whether the technologies can be routinely adopted in the NHS.