The UK’s National Health Service (NHS) has published a report showing that Skin Analytics’ AI tool DERM could be used to assess images of lesions for skin cancer.
The report reviewed Skin Analytics’ Deep Ensemble for the Recognition of Malignancy, dubbed DERM, on more than 33,500 NHS patients. The AI-based tool demonstrated a negative predictive value (NPV) of 99.8%, outperforming traditional face-to-face dermatologists who had an NPV of 98.9%.
DERM’s effectiveness suggests potential cost savings for the NHS, with an estimated return of £2.30 for every £1 invested, and £86 saved per case. These savings primarily result from reducing the need for in-person appointments and biopsies, which are more expensive.
DERM is the only UKCA Class IIa AI as a Medical Device (AIaMD) designed to assess images of skin lesions for skin cancer available on the UK market. Using a smartphone-compatible device, the device captures dermoscopic images of skin lesions, which are then analysed by a deep learning algorithm that continuously improves its diagnostic accuracy through repeated analytical tasks.
According to GlobalData epidemiologists, the number of diagnosed incident cases of melanoma in the UK will grow from 16,459 cases in 2019 to 18,321 cases by 2029. The NHS report highlights that there has been a significant increase – 170% – in urgent referrals for suspected skin cancer over the last decade, but not enough dermatologists are being trained to meet this demand.
Skin Analytics CEO Neil Daly said: “NHS data suggests that at the end of 2022, 11% of urgent skin cancer referrals were waiting more than four weeks for a first assessment, amounting to 17,454 patients in Q3 FY 2022/2023.
“Since 2020, we have seen over 116,000 NHS patients for suspicion of cancer and the use of our technology, DERM, has helped NHS Secondary Care partners reduce the need for more than 63% of face-to-face urgent suspected skin cancer appointments.”
Earlier this year, nine NHS trusts secured £2m in funding from the NHS England Cancer Programme to roll out the DERM device. According to the Cambridge-headquartered company, Skin Analytics has seen more than 116,000 NHS patients and detected more than 7,000 cancer cases to date.
Across the pond, the US Food and Drug Administration (FDA) cleared DermaSensor’s AI-powered skin cancer detection device in January 2024. This follows a pivotal study led by the Mayo Clinic, which enrolled over 1,000 patients across 22 study centres – demonstrating a 96% sensitivity rate for the device across 224 identified skin cancers.
