AI decision support for detecting skin cancer in primary care

Artificial Intelligent Decision Support for Skin Cancer Diagnostics in Primary Care - a Multicentre Randomized Controlled Trial.

Not applicable Interventional Linkoeping University · NCT06932172

This study will test whether an AI tool called Dermalyser helps primary care clinicians tell skin cancers from harmless skin lesions when patients come in with suspicious spots.

Quick facts

PhaseNot applicable
Study typeInterventional
Enrollment3000 (estimated)
Ages18 Years and up
SexAll
SponsorLinkoeping University Government
Locations8 sites (Finspång, Docent and 7 other locations)
Trial IDNCT06932172 on ClinicalTrials.gov

What this trial studies

This is a cluster-randomized trial conducted at about 30 primary care centers across Sweden, Germany, Scotland, the Netherlands, and Australia. Participating centers are randomized to either use the Dermalyser AI decision support tool or continue standard clinical assessment. The trial prospectively compares diagnostic accuracy, reliability, and clinical utility of the AI-assisted pathway versus usual care for patients presenting with suspicious skin lesions. Outcomes will capture how well the tool distinguishes malignant from benign lesions and how it affects clinical decisions in routine primary care.

Who should consider this trial

Good fit: Adults who attend a participating primary care center with one or more skin lesions that they or their clinician find suspicious for skin cancer and who can give informed consent are eligible.

Not a fit: People with darker brown or black skin (Fitzpatrick skin types V–VI) are excluded from the study and therefore will not receive potential benefits from this specific trial.

Why it matters

Potential benefit: If successful, the AI tool could lead to faster and more accurate identification of skin cancers in primary care, reducing missed cancers and unnecessary referrals.

How similar studies have performed: Numerous retrospective and image-based studies report high AI accuracy for detecting skin cancer from dermatoscopic images, but prospective evaluations in real-world primary care settings are scarce.

Eligibility criteria

Show full inclusion / exclusion criteria
Inclusion Criteria:

* Patients attending a primary care facility in order to have one or more skin lesions checked for skin cancer, or patients presenting with one or more skin lesions raising suspicion of skin cancer when noticed by the primary care physician.
* Willingness and ability to provide informed consent.

Exclusion Criteria:

* Individuals with skin type V and VI according to the Fitzpatrick's scale (darker brown or black coloured skin)

Where this trial is running

Finspång, Docent and 7 other locations

Study contacts

How to participate

  1. Review the eligibility criteria above with your treating physician.
  2. Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
  3. Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.
Conditions Skin CancerArtificial IntelligencePrimary careDiagnostics
Last reviewed 2026-06-13 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.