Since 2020, DERM has assessed over 230,000 NHS patients for suspicion of skin cancer, helping Secondary Care organisations remove the need for up to 95% of face-to-face NHS urgent suspected skin cancer appointments.
We are the only CE Class III AI as a Medical Device for skin cancer and have pioneered a market-leading approach to performance monitoring for AI in clinical use.
We’re committed to providing the best technology and being completely transparent about our results.
This table is a summary of our performance since December 2023 up to Q4 2025 Post Market Surveillance Reports, with analysis based on
90,236
lesion outcomes
How do we set our performance targets?
Our performance targets are based on the highest clinical performance as published in the literature and agreed by our Clinical Advisory Committee ,which is composed of leading UK and international dermatologists and health economics experts
| Target | Dec 2023 to Nov 2025 | |
|---|---|---|
| Negative predictive value (NPV) Melanoma |
99% | 99.9% N=89,790 |
| Sensitivity All skin cancer |
98% N=9742 |
|
| Melanoma | 95% | 97% N=1889 |
| Invasive melanoma | 95% | 98% N=1041 |
| SCC | 95% | 98% N=2334 |
| BCC | 90% | 98% N=5420 |
Patient perspectives of artificial intelligence as a medical device in a skin cancer pathway
Kawsar A, Hussain K, Kalsi D, et al.
Accuracy of an Artificial Intelligence as a medical device as part of a UK-based skin cancer teledermatology service
Helen Marsden, Chronis Kemos, Marcello Venzi, Mariana Noy, Shameera Maheswaran, Nicholas Francis, Christopher Hyde, Daniel Mullarkey, Dilraj Kalsi and Lucy Thomas
Effectiveness of an image analyzing AI-based Digital Health Technology to identify Non-Melanoma Skin Cancer and other skin lesions: results of the DERM-003 study
Marsden H, Morgan C, Austin S, Degiovanni C, Venzi M, Kemos C, Greenhalgh J, Mullarkey D, Palamaras I.
Real-world post-deployment performance of a novel machine learning-based digital health technology for skin lesion assessment and suggestions for post-market surveillance
Dilraj Kalsi, Lucy Thomas, Chris Hyde, Dan Mullarkey, Jack Greenhalgh, Justin M Ko
Assessment of Accuracy of an Artificial Intelligence Algorithm to Detect Melanoma in Images of Skin Lesions
Phillips, M. et al.
Detection of Malignant Melanoma Using Artificial Intelligence: An Observational Study of Diagnostic Accuracy
Phillips, M., Greenhalgh, J., Marsden, H., Palamaras, I.
Some research featured in this e-book is from other researchers.
In addition to the data we publish, much of which has been externally audited, Skin Analytics is working with a number of external partners to evaluate and support the expansion of our services across the NHS, including a number of independent and health economics evaluations.
DERM has predominantly been used to assess and triage referrals in the post-referral clinical pathway for suspected skin cancer; attention has now shifted to its potential role in community diagnostic hubs.
This service evaluation by the University of Exeter focused on safety, effectiveness, and cost-effectiveness, aiming to determine the overall standard of care achieved with the introduction of DERM.
DERM is safe. DERM performance was in line with our targets and high risk skin cancer detection rates increase vs. local published detection rates by 26.5% on average.
When health economic analysis is based on real-world evidence and comparisons, DERM ‘is clearly the most cost-effective strategy’.
The interview study confirmed a positive attitude towards the service across patients and staff.
The pathway is accessible – all patients receive timely access to care, including the (expected) 7-10% of patients who are not able to undergo a DERM assessment.
NHSE’s Outpatient Recovery and Transformation Programme (OPRT) team commissioned Edge Health to write an independent report evaluating the use of AI in skin cancer pathways.
Edge Health were tasked with exploring all AI technologies with appropriate regulatory clearance to be deployed within autonomous pathways. DERM was the only technology that met the requirements, so much of the report focuses on our performance.
DERM’s performance is at least as good as face-to-face dermatologist evaluations. The Negative Predictive Value (NPV) for correctly excluding melanoma in a matched-prevalence population were 99.8% for DERM and 98.9% for dermatologists.*
DERM is the only AIaMD with the necessary evidence base demonstrating its safety and effectiveness for regulatory approval at this level.
AI-enabled pathways lower system costs by reducing the need for face-to-face reviews and biopsies. Illustrative budget impact modelling suggests up to £86 in savings per case in autonomous pathways.
AIaMD can rapidly process initial assessments, which could reduce waiting times for secondary care reviews, thereby enhancing patient experience and service delivery.
*Based upon:
1. An independent analysis of 33,693 real-world lesions assessed by DERM (including 835 melanoma), and
2. A systematic review and meta-analysis of all studies involving consultant dermatologists up to April 2024
The Department of Health and Social Care (DHSC) funded deployment and a real-world evaluation of DERM as part of the AI in Health and Care Award.
Working with the University of Surrey, Unity Insights conducted an evaluation of DERM in four NHS sites, across 9,649 patients between February 2022 and April 2023.
In secondary care, DERM demonstrated high pathway sensitivity for malignant melanoma (97%), achieving its target rates of 95%.
DERM effectively triages high risk lesions to the appropriate management outcome.
85% of patients rated the AI-enabled teledermatology service as good or very good.
Staff reported the effect of the AI teledermatology service on capacity as “transformational”.
Health economics compared teledermatology both with and without DERM against face-to-face referrals – all instances highlighted savings for the NHS.
Edge Health worked on behalf of the East Midlands Academic Health Science Network to evaluate our pathway at University Hospitals Leicester.
We recommend that you see a case study of the pathway previously conducted.
Despite being in its pilot phase, the AI tool demonstrated its capability to enhance patient access to dermatology services.
Whilst the pathway alone saves more money than it costs, the initial benefit-cost ratio does not include nonquantified benefits such as reduced Waiting List Initiative clinics, reduced biopsies and reduced long-term care costs.
The pathway could offer considerable benefits to the wider Dermatology cohort, healthcare staff, and the health system if implemented at scale, with potential yearly savings across the Midlands ranging between £2.1M and £5.7M.
Including the British Association of Dermatologists AGMs
Effectiveness of an image-analysing artificial intelligence-based digital health technology to diagnose nonmelanoma skin cancer and benign skin lesions
Helen Marsden, Ioulios Palamaras, Polychronis Kemos, Jack Greenhalgh
Using artificial intelligence to triage skin cancer referrals: outcomes from a pilot study
Karmel Abu Baker, Elizabeth Roberts, Karen Harman, Dan Mullarkey, Dilraj Kalsi
Clinical performance of an artificial intelligence-based medical device deployed within an urgent suspected skin cancer pathway
Rachel Jenkins, Christopher Felix Brewer, Dilraj Kalsi, Daniel Mullarkey
Great expectations: implementing artificial intelligence software into a regional skin cancer teledermatology service
Philippa Walker-Smith, Anne-Marie Christie, Annabel Scott, Arani Chandrakumar
Comparing the number-needed-to-biopsy ratio for melanoma diagnosis between teledermatology, an artificial intelligence device with teledermatology, and face-to-face models of care
Radhika Bali, Jenny Chung, Lucy Thomas, Khawar Hussain, Louise Fearfield
Multicentre prospective clinical performance analysis of an artificial intelligence as a medical device deployed within urgent suspected skin cancer pathways
Felix Brewer, Jonathan Kentley, Dilraj Kalsi, Dan Mullarkey, Lucy Thomas
Modelling the cost-effectiveness of an artificial intelligence as a medical device
Zhivko Zhelev, David Puttergill, Dilraj Kalsi, Dan Mullarkey, Christopher Hyde
Developing a clinical audit methodology for monitoring dermatologist performance in artificial intelligence-enabled teledermatology pathways
Joshua Luck, Audrey Menezes, Dilraj Kalsi, Dan Mullarkey, Niall Wilson
Comparative real-world performance of an artificial intelligence as a medical device and consultant teledermatologists in diagnosing benign skin lesion subtypes
Rebecca Golenya , Joshua Luck , Dan Mullarkey , Dilraj Kalsi
Steps towards safely deploying the world’s first autonomous artificial intelligence as a medical device for skin cancer into a National Health Service teledermatology pathway
Saman Zaman , Louise Fearfield , Lucy Thomas
The use of artificial intelligence as a medical device and teledermatology in the assessment of Merkel cell carcinoma: a National Health Service case series
Karan Punjabi , Joshua Luck , Dilraj Kalsi , Dan Mullarkey
Prospective, multicentre, real-world sensitivities of an artificial intelligence as a medical device assessment and teledermatologist assessment in appropriately managing melanoma, squamous cell carcinoma and rare skin cancers referred on the urgent suspected cancer pathway
Joshua Luck , Dilraj Kalsi , Dan Mullarkey , Lucy Thomas , Justin Ko
Multi-centre prospective clinical performance analysis of an Artificial Intelligence as a Medical Device deployed within UK NHS urgent suspected skin cancer pathways
Felix Brewer, Mahan Salehi, Joshua Luck, Dilraj Kalsi, Daniel Mullarkey
Developing a post-market surveillance audit methodology for an artificial intelligence as a medical device deployed autonomously in urgent suspected skin cancer pathways
Karan Punjabi, Joshua Luck, Dilraj Kalsi, Dan Mullarkey
A Multi-Centre Clinical Performance Review of an Artificial Intelligence as a Medical Device in Excluding a Diagnosis of Melanoma in Urgent Suspected Skin Cancer Pathways.
Dan Mullarkey, Dr Dilraj Kalsi, Joshua Luck & Dr Karan Punjabi
Embedding Algorithmic Auditing into the UK National Health Service: A multistakeholder, collaborative monitoring framework for assuring regulatory compliance, fairness, and safety
Dr Aditya Kale, Dr Qasim Malik, Dr Sonam Vadera, Dr Jeffry Hogg, Ms Jaspret Gill, Prof Alastair Denniston, Dr Xiaoxuan Liu
Since 2018, we have worked with teams from Health Enterprise East, the York Health Economics Consortium, Imperial Trust, as well as the Exeter Test Group to ensure that our services are truly sustainable for the NHS.
Today, we are uniquely well-placed to answer on the cost effectiveness of using DERM in secondary care, with over three years of comprehensive real-world evidence, derived from the assessment of more than 70,000 patients across 14 NHS sites (at the time of research).
Results from our health economic analysis show that Skin Analytics delivers robust NHS dermatology cost savings
