Clinical trial · Observational
ARTIficial Intelligence-based Smartphone Application for Skin Cancer Detection
Clinical Performance and Patient Experience of an Artificial Intelligence-based Smartphone Application (Skinvision ®) in the Early Detection of Skin Cancer: A Cross-Sectional Study in a Real-life Setting.
NCT05246163CI-TRIAL-00077708ARTISunknownClinicalTrials.gov clinicaltrialsProvenance
- Source
- ClinicalTrials.gov
- Retrieved
- Sep 8, 2026
- Layer
- normalized (units and labels harmonized; values unchanged)
- Run
- ING-CLINICALTRIALS-20260908-000001
Summary
Brief summary (as posted)
The aim of this project is to assess whether a specific smartphone application (Skinvision App®) can be used as a tool to preselect skin lesions suspicious for skin cancer that require urgent medical advice.
Conditions
Conditions (1)
Free-text conditions as registered, with the CancerIndex entity they were reconciled to and the match type.
| Condition (as posted) | Mapped entity | Match | Confidence |
|---|---|---|---|
| Skin Cancer | Malignant Skin Neoplasm | ALIAS | 0.90 |
Interventions
Interventions (0)
Data not yet available
No intervention recorded.
Design
Arms and outcomes
Arms (0)
[]Primary outcomes (1)
- measure
- Diagnostic performance of the Skinvision application
- timeFrame
- Up to 24 months
- description
- To evaluate the sensitivity and specificity of the application. The risk assessment of the application will be compared to the gold standard. The gold standard is defined as the histopathologic diagnosis (in biopsied and excised lesions) or clinical assessment by one or two experienced dermatologists. The risk assessment of the application is defined as low (green), medium (orange) or high (red) risk. The biopsied or excised skin lesions will be categorized as benign or malignant.
Secondary outcomes (3)
- measure
- Usability and reproducibility of the Skinvision application
- timeFrame
- Up to 24 months
- description
- To examine the usability and reproducibility of the application. Lesion-specific parameters will be collected (e.g., localization, hair or other disturbing factors, etc). A repeated analysis of one or more specific lesions will be made in different lighting conditions and from different camera positions. Given the evolution of the camera quality, different smartphones will be tested. Finally, the patient will also be asked to perform an analysis to assess the user friendliness.
Eligibility
Eligibility (as posted)
- Sex
- All
- Minimum age
- 18 Years
Show eligibility criteria text
Inclusion Criteria: * Patients with one or two lesions meeting at least one of the following criteria: * New mole in an adult (\> 18 years old); * 'Ugly duckling' sign (i.e. mole that looks different from other moles in the same person) * Changing mole (size, color, shape or structure); * Rapid growing lesion * Non-healing lesion * Written informed consent of the patient Exclusion Criteria: * Lack of informed consent for study participation
References
Publications (1)
- DERIVEDKips J, Papeleu J, Shen A, Mylle S, Genouw E, Hoorens I, Verhaeghe E, Brochez L. Artificial intelligence-based smartphone application for skin cancer detection: a prospective diagnostic accuracy study. Br J Dermatol. 2026 May 19;194(6):1077-1086. doi: 10.1093/bjd/ljag057. PMID 41701029