Evidence generation plan for artificial intelligence (AI) technologies for assessing and triaging skin lesions referred to the urgent suspected skin cancer pathway
5 Minimum evidence standards
During the evidence generation period, new technologies may become available. This section summarises the minimum evidence requirements that a new technology would need to meet to be considered in the NICE evaluation after the evidence generation period.
The evidence considered by NICE primarily focuses on diagnostic accuracy, clinical outcomes and the impact of the technology on the teledermatology pathway for urgent suspected skin cancer referral. The technology demonstrated potential to support triage for cancerous and non-cancerous lesions, but the current evidence base is not sufficient to fully recommend using it in routine NHS practice. More evidence is needed on:
-
the impact of the technology on the care pathway, including referrals, workload and costs associated with its implementation
-
accuracy of the technology in people with black or brown skin (Fitzpatrick skin types 5 and 6)
-
diagnostic accuracy of the technology.
This evidence is essential to future NICE decision making. The evidence should be collected when the technology is implemented in the following different ways:
-
as an autonomous tool, and
-
used with a healthcare professional review.
Data about the impact of the technology when used in a pre-referral setting was outside of the scope of the assessment but is of interest to the clinical community so would be useful.
This page was last updated: