Artificial intelligence technology which analyses suspicious skin lesions has been conditionally recommended by NICE. The AI skin cancer system can now be used in the NHS for the next three years while further evidence is collected.
DERM (Deep Ensemble for Recognition of Malignancy), developed by Skin Analytics, analyses images to assess and triage skin lesions, potentially redirecting benign cases to non-urgent pathways. Healthcare staff use a smartphone with a high-quality magnifying lens to take high-quality images of suspicious skin lesions.
After a patient has been referred, the skin lesion can be remotely assessed, diagnosed, or monitored without requiring a physical in-person visit. DERM uses an algorithm to analyse the images, examining visual characteristics and comparing them to its bank of images of known skin conditions.
When suspicious lesions are found the patient can be directed to a human dermatology specialist for further investigation while people with other skin conditions are reassured and offered advice.
Dr Anastasia Chalkidou, HealthTech programme director at NICE, said: "DERM has shown promising results in its ability to accurately distinguish between cancerous and non-cancerous skin lesions, with evidence suggesting it could halve the number of referrals to dermatologists within the urgent skin cancer pathway while maintaining patient safety. DERM is an example of how we can harness artificial intelligence to benefit both patients and healthcare professionals. Our evaluation shows this technology maintains diagnostic accuracy while reducing the burden on specialist dermatology services."
In the UK, dermatology services receive one million referrals each year from primary care. About 60% are urgent referrals for suspected skin cancer. Of these, only 6% are confirmed to be skin cancer and the remaining 94% are either non-urgent or non-cancer cases.
Once the three-year evidence generation period is complete, a NICE committee will reconsider the evidence and publish new guidance.
Read more about the DERM system and the recommendation on the NICE website here.