People worried about a mole photograph it and get a risk assessment at once, instead of waiting for a dermatologist's review.
The client wanted anyone concerned about a skin spot to learn quickly whether it needs attention, anywhere in the world, instead of waiting for a manual review.
What changed
What stood in the way.
- Every photo users submitted went to manual dermatological review, so assessments were delayed and the service could not keep up with demand.
- The legacy app needed a modular architecture, GDPR-compliant data handling and support for more languages and regions.
- 5M+skin checks to date (as reported)
- 3M+users worldwide (as reported)
- 90%sensitivity in identifying potential skin cancers, the client's clinically validated figure (as reported)
What we built.
- A clinically validated AI model embedded in the app to assess the risk level of uploaded skin lesion images in real time, reducing reliance on manual review.
- The iOS app rebuilt in Swift, the Android app refactored from Java to Kotlin, and the backend restructured into a modular, cloud-ready architecture.
- GDPR-compliant workflows under Dutch data protection law, with encrypted storage and consent management.
- Location-based UV Index alerts, histopathology report uploads, a subscription model with a monthly free allowance, and secure messaging with clinical reviewers.
- Swift
- Kotlin
- Cloud-ready modular backend
- AI model integration
- GDPR compliance
What this work shows about us.
The model gives the first assessment at once, while clinical reviewers answer follow-up questions through secure messaging.
Native Swift and Kotlin apps and a modular backend let the model plug in without disrupting the flow, under GDPR.
Want to build a similar AI skin check app? Tell us what you want to change. Our AI assistant, Ask Unthinkable, helps you define your requirements, then connects you with the right team.
Start your plan ↗If we built it today, with AI.
What we would add now, moment by moment.
An agent would explain a high-risk result in plain words, offer to send the scan and history to a dermatologist and book the follow-up. The dermatologist still makes the diagnosis.
An agent would remind a user to re-check a spot it was told to watch, compare the new photo with the old one and flag any change for a clinician.
Where this work fits.
- Hospitals & clinicsYour hospital is meant to deliver care without making patients wait.
- Care coordination & remote monitoringThe right clinician knows in time, and families know what happens next.
- Health GaugePeople see the readings from all their wearables in one app, and are reminded on their wrist to take their medication.
- MayaMDPatients with chronic conditions check their symptoms, share their vitals and see their doctor by video, from home.
Facts and figures from the project records; nothing added.
Want this for your business?
Tell us what you run or what you're building. Our AI assistant, Ask Unthinkable, helps you define your requirements, then connects you with a senior AI engineer.
Send us a note instead
An AI agent. This prototype uses prepared answers and sends nothing.
We use essential cookies to run this site. With your consent we also use analytics cookies to see which pages help. Privacy policy