Autonomous AI Skin Cancer Tool Frees Up Thousands of NHS Dermatology Appointments, Study Finds
Key Takeaways:
- Over 16 months, Skin Analytics’ DERM technology reviewed 8,391 people referred urgently for suspected skin cancer at Chelsea and Westminster Hospital NHS Foundation Trust, accounting for 94% of the trust’s urgent skin cancer referrals.
- The autonomous AI medical device saved 2,851 hours of clinician time, a 62% gain in clinical capacity that could equate to more than 8,500 additional face-to-face dermatology appointments.
- Biopsy rates fell to 27% under the AI-supported pathway, compared with 43% under conventional face-to-face care.
Autonomous AI as a first review for skin cancer referrals
New research from Chelsea and Westminster Hospital has found that using an autonomous AI medical device to detect skin cancer can free up thousands of NHS dermatology appointments, easing pressure on a specialty facing rising demand and significant workforce shortages.
The study examined the use of Skin Analytics’ DERM technology as the first point of review for skin cancer referrals. DERM classified skin lesions and autonomously discharged cases it identified as non-cancerous, while referring higher-risk cases on for review by a teledermatologist.
Over a 16-month period beginning in December 2024, the technology reviewed 8,391 people using clinical and dermoscopic images captured on a smartphone. This represented 94% of all urgent skin cancer referrals across the trust.
Freeing specialist time for those who need it most
Dr Lucy Thomas, lead author and consultant dermatologist at Chelsea and Westminster Hospital NHS Foundation Trust, said: “We believe the greatest value of autonomous AI lies not in the technology itself, but in the specialist capacity it unlocks.
“Every hour saved reviewing low-risk lesions can be reinvested in patients with skin cancer, helping them access timely treatment and improving prognosis, or in patients with severe inflammatory skin disease, where earlier access to specialist care and effective treatments can transform quality of life.”
Fewer biopsies and more discharges without clinician review
The project also recorded a notable reduction in biopsy rates. Under the DERM-supported pathway, the biopsy rate was 27%, compared with 43% under conventional face-to-face care.
Across the trust’s two hospitals, DERM autonomously discharged 31% and 25% of people respectively without any clinician review. Teledermatologists then discharged a further 24% and 25% of people at each site.
A 62% gain in clinical capacity
When these discharges were combined with reduced teledermatology processing time and fewer surgical requests than seen with face-to-face appointments, DERM was found to have saved 2,851 hours of clinician time. This amounts to a 62% gain in clinical capacity, which the researchers suggest could equate to more than 8,500 additional face-to-face dermatology appointments being freed up.
Neil Daly, founder and chief executive of Skin Analytics, said: “These results show what is possible when hospital trusts implement AI at scale.
“Every case DERM safely discharges is time given back to a dermatologist, and to a patient who needs it most.
“The NHS is showing real leadership on how it is using autonomous AI in cancer care, and this new Chelsea and Westminster data adds compelling weight to the case for adoption.”
Rising referrals and an overstretched workforce
The findings come at a time of growing strain on dermatology services. Urgent suspected skin cancer referrals in England have almost tripled since 2009, yet only around 6% of these referrals result in an urgent skin cancer diagnosis. At the same time, around one in four dermatologist roles in the UK currently sits unfilled.
As AI tools such as DERM become part of how suspected skin cancer is assessed, clinicians across the referral pathway increasingly need to understand how these technologies work and where they fit into care. The College of Contemporary Health’s AI Essentials for Primary Care course is designed to help primary care professionals build confidence in understanding and engaging with AI in clinical practice.
Performance and adoption across the NHS
DERM is CE-marked as a Class III AI medical device and has been shown to identify skin cancers at the level of a dermatologist. Recent nationwide monitoring demonstrated that it correctly identified 98% of the skin cancers that presented.
The technology is now in use at more than 25 NHS trusts, where it has assessed more than 250,000 people and identified more than 25,000 cancers.
Supporting, not replacing, dermatologists
Dr Thomas emphasised that the aim of autonomous AI is to make better use of specialist expertise rather than to substitute for it.
“If these findings are replicated across larger populations and different healthcare settings, autonomous AI could become an important part of creating a more sustainable dermatology service – not by replacing dermatologists, but by allowing scarce specialist expertise to be focused where it can make the greatest difference to patients’ lives,” she added.
The study was partly supported by a grant from La Roche-Posay (L’Oréal Dermatological Beauty), and its findings were presented at the European Academy of Dermatology and Venereology Congress 2026.
CCH insight
AI is already changing how people are assessed and referred across the NHS, from the first appointment in primary care through to specialist review. Understanding what these tools can and cannot do is quickly becoming an essential clinical skill.
Our AI Essentials for Primary Care CPD course helps healthcare professionals build the knowledge and confidence to engage with AI safely and effectively in everyday practice.
Explore AI Essentials for Primary Care now →
Source: Digital Health
