What happened
DERM, from Skin Analytics, is AI software that assesses images of skin lesions referred on the NHS urgent suspected skin cancer pathway. It can work alone or with a second read by a clinician. The National Institute for Health and Care Excellence (NICE) published an early value assessment on 1 May 2025. In one study, automated DERM detected 96.0% of cancers against 93.8% for face-to-face dermatologists. In another, it detected 94.0% against 97.0% for teledermatology, with overlapping confidence intervals. The committee found no evidence that DERM is less sensitive than either. Unity Insights, which evaluated DERM at three NHS sites, reported data suggesting that automated DERM would flag fewer non-cancer lesions for further review than teledermatology alone. NICE's assessors estimated that automated DERM could about halve urgent referrals to a dermatologist among eligible lesions. NICE allowed DERM in NHS teledermatology for a three-year evidence generation period. Most evidence came from people with white skin, so NICE requires clinician review for people with black or brown skin. It is unclear whether DERM frees dermatology capacity.
Sources
-
Assessment report, by authors with no tie to the system.
Comparative evidence suggests that DERM may be able to identify a cancer lesion with similar accuracy to teledermatology or face-to-face dermatology assessment. Using automated DERM could identify more non-cancer lesions that do not need further review and so redirect more cases to non-urgent dermatology pathways compared with using teledermatology alone.
-
Assessment report, by authors with no tie to the system.
An analysis by the EAG suggested that, of eligible lesions, automated use of DERM could approximately halve the number of referrals to a dermatologist within the urgent skin cancer pathway.
Details
AI system
- Workflow
-
DERM assessed lesion images after a primary care referral to the urgent suspected skin cancer pathway. DERM ran alone or with a clinician's second read.
Follow-up
- Conditions for replication
-
A clinician reviews the lesions of people with black or brown skin. Services monitor DERM's accuracy regularly.
Entry details
- Sector
-
Healthcare (dermatology).
- Purpose
-
Skin Analytics built DERM to assess skin lesion images and identify lesions that are not cancer so that they can leave the urgent skin cancer pathway.
Not yet checked: model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.
Cite this record
Peter H. Vartanian. (2026). NICE assessors estimate that DERM could halve urgent skin referrals (AIBD-0738). Artificial Intelligence Benefits Database, edition of 31 October 2026. https://petervartanian.xyz/aibd/records/AIBD-0738.html (archived at https://doi.org/10.7910/DVN/AADSII, version 4.0)