Skin Analytics' dermatology AI backed for NHS use

An artificial intelligence-powered tool for triaging patients with suspicious skin lesions, developed by Skin Analytics, will be used by the NHS to reduce waiting times.

DERM (Deep Ensemble for Recognition of Malignancy), which was approved in the UK as a Class IIA medical device in 2022, analyses images to assess and triage skin lesions, and may be able to refer patients to non-urgent pathways if their case is likely to be benign.

It is currently the only AI that can be autonomously deployed within the NHS using core NHS funding, according to the company's founder and chief executive, Neil Daly.

The recommendation for NHS use delivered by health technology assessment (HTA) agency NICE comes after DERM was put through its paces in a pilot study carried out at several NHS trusts in England, showing that it was able to support healthcare workers in referring patients to the urgent two week skin cancer referral laid out in national guidelines.

The software uses an algorithm to analyse images of suspicious skin lesions that are displayed on a smartphone with a high-quality magnifying lens attachment. It can recognise the most common malignant, pre-malignant, and benign skin lesions, including melanoma, which is the fifth most common cancer in the UK and the most dangerous form of the common skin cancers.

According to NICE's Early Value Assessment (EVA) guidance on the technology, automated use of DERM "could result in more lesions being correctly identified as non-cancer without a biopsy, compared with teledermatology or face-to-face assessment. So, fewer biopsies would be needed, and people would be correctly discharged from the service."

London-based Skin Analytics will have to generate additional evidence on DERM's benefits over the next three years to finalise a full NICE recommendation.

"We're incredibly proud of the work we've been doing with the NHS over the last five years to achieve this recommendation from NICE," said Daly. "Having seen more than 165,000 patients and found more than 15,500 cancers since launching, we are ready to make our Class III autonomous skin cancer AI available to more UK patients."

According to NICE, UK dermatology services receive one million referrals each year from primary care, and roughly two-thirds (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.

Ashley Dalton, Minister for Public Health and Prevention, said: "By embracing the power of AI, this exciting technology could help us slash waiting times, meaning that people with suspected skin cancer get the help they need, or peace of mind, faster," adding that it is another part of the NHS is shifting from analogue to digital.