Dermatology AI solutions for telehealth, pharmacy and primary care
One photo in. Ranked condition suggestions out, in under a second. Three deployment models, live in production.
Used by leading healthcare platforms • 3M+ API calls served • Scientific Reports (Nature Portfolio)
CE-marked Class I medical device (MDD), MDR Class IIa in progress · MHRA device registered (UK) · FDA Breakthrough Device Designation, clearance pending
Where Autoderm sits in your product
Autoderm handles one part of the journey. You decide where the skin check appears, and what happens once the results are on screen. Both of those stay yours to design.
Autoderm API
One image in, five suggestions
Confidence levels, not a diagnosis
Three deployments
Online pharmacy
Before the consultation
Online pharmacies and retail chains
Sits on the pharmacy site. Customers check a concern anonymously and land on a next step: an OTC product, a pharmacist conversation, or a GP booking.
Online pharmacy deploymentTeledermatology
Before the consultation
Teledermatology and telemedicine services
Users arrive with an informational suggestion already in hand, so clinician time goes to the cases that need it. The free check doubles as the entry point to a paid one.
Teledermatology deploymentVirtual primary care
Before the consultation
Virtual primary care and GP networks
Sits in the booking or prescription flow, where patient traffic is already highest. People can check a skin concern in the same session, then arrive with an informational suggestion in hand, or resolve it without an appointment.
Virtual primary care deploymentWhat the API returns
One call, one image, one structured response. Everything below is available from the first request.
Five ranked condition suggestions per image, each with a confidence score
70+ conditions across nine dermatology categories: benign, pre-malignant, malignant, inflammatory, infectious, genodermatoses, pigmentation, hair and nail
A response in under a second
No identifiable patient data stored. Images are processed and anonymised
A standard REST call and a JSON response, with no SDK lock-in
ICD-10 reference codes alongside each result, for information only
Full white-labelling. No Autoderm branding is visible to end users unless the partner chooses to show it
Where Autoderm stops
Autoderm analyses the image and returns the ranked list. Everything after that is designed by the integrating organisation:
whether confidence scores are shown to end users
where users go for further information on a condition
what the next step offers, whether a product, a consultation, a booking or nothing at all
which end user instructions apply
Autoderm reviews and confirms the compliance of the interface before deployment, so those decisions are made with the manufacturer rather than around it.
What the evidence actually says
Every figure traces to a named study. The full portfolio, with methodology and journals of record, sits on the clinical evidence page.
93%
Top-5 suggestion accuracy
Coachella Study 2025
92%
GP satisfaction rate
Escalé-Besa et al., 2023
40%
Dermatology referral reduction
Boots UK GP Reader Study, 2024
48%
GP alone
→
69%
GP+AI
Top-1 accuracy
Boots UK GP Reader Study, 2024
Population-scale melanoma awareness
~5%
potentially signposted via AI
myGP PMS Report, May 2024 (79 flags of 18,359 analyses)
Zero safety incidents since 2018
2M+
API calls, 6 countries
Post-market surveillance, MHRA/BfArM/FDA MAUDE/ClinicalTrials.gov. Distinct from user-reported dissatisfaction (image quality), not a safety measure.
Bias evaluated across skin tones
Fitzpatrick17K bias evaluation completed across 26 conditions and FST I–VI. No systemic bias detected. Direct same-model cross-population comparisons available (Sweden FST I–II vs. Uganda FST VI on V0.1), with subsequent dataset diversification in V2.x.
Fitzpatrick17K Bias Evaluation, 2024
How the Autoderm API integrates
A dedicated success manager guides the deployment from first call to go-live.
Scope and contract
Custom pricing and contract terms, set for your deployment's volume, compliance requirements and rollout timeline.
Onboard and integrate
Hands-on integration assistance builds the check into your platform, pharmacy site or practice app.
View our API documentationLaunch and support
Priority support and custom SLAs carry through go-live and beyond.
Regulatory & data
protection standards
Autoderm is developed with strict adherence to European and international requirements for safe, privacy-preserving AI in healthcare.
Common questions about the dermatology API
Does Autoderm provide diagnoses?
No. Autoderm returns informational condition suggestions with confidence levels. All outputs require review by a healthcare professional before any clinical decision is made. Clinical responsibility remains with the healthcare professional and the platform’s defined care pathways.
How many conditions does it cover?
70+ conditions across nine dermatology categories, covering the concerns people most commonly present with.
How long does integration take?
A first working call is typically made on day one. Full integration depends on the surrounding product. The interface then needs compliance confirmation from Autoderm before deployment.
What does top-5 suggestion accuracy mean?
It is the proportion of cases where the correct condition appeared in Autoderm’s ranked list of five suggestions. The Coachella Study 2025 recorded 93% top-5 suggestion accuracy across 91 confirmed cases. It is not a diagnostic accuracy claim: the output is a ranked list of possible conditions, not a single diagnosis.
Online pharmacy