The Eumelanin Human Skin Colour Scale: a proof-of-concept study.
Ophelia E Dadzie, Rick A Sturm, Damilola Fajuyigbe...
https://pubmed.ncbi.nlm.nih.gov/35349165/Actively Recruiting
Led by Region Skane · Updated on 2026-10-13
1500
Participants Needed
13
Research Sites
52 weeks
Total Duration
Skin pigmentation, skin phototype, and photodamage are important factors affecting skin cancer risk, appearance of skin diseases, treatment responses, and the accuracy of AI diagnosis in dermatology. However, current classification methods are often subjective and can lead to misclassification, reducing the precision of personalized care. This international multicenter observational study aims to develop and validate AI algorithms that classify these skin characteristics more accurately using a combination of objective measures and clinical assessments. Participants aged 18 years and older from multiple countries will complete questionnaires about their skin and sun exposure. Researchers will capture standardized clinical and dermoscopic images of the upper arm and forearm, and perform skin pigmentation measurements using techniques like colorimetry or spectrophotometry when available. The study combines data from questionnaires, objective measurements, clinical scales, and trained observers to create a reliable reference standard for skin pigmentation, phototype, and photodamage. These data will then be used to train and test deep learning AI models. Participants will provide non-invasive skin images and complete questionnaires without any invasive procedures or collection of personal identifiers. The study will assess how well the AI models classify skin characteristics compared to combined reference methods, focusing on accuracy and agreement measures. External validation will also be performed using independent dermatology image datasets to evaluate model performance across diverse populations. The study aims to improve personalized skin cancer risk assessment, support better dermatology care, and address biases in AI systems related to skin tone. Participation involves minimal risk and secure data handling.
CONDITIONS
Skin Type Determination Using Image Artificial Intelligence
Å
Åsa Ingvar, MD PhD
A
Anna Asphult, Research nurse
Explore thousands of other clinical trials that might be a better match.
Sign up to get personalized trial recommendations delivered to your inbox.
Already have an account? Log in here
Region Skane
Lead Sponsor
Sahlgrenska University Hospital
Collaborating Sponsor
You may qualify if you...
You will not qualify if you...
Duration - 2 to 4 weeks
Participants are screened for eligibility to participate in the trial.
Duration - Single visit or short period as scheduled by the study
Participants complete questionnaires about their skin and sun exposure, and undergo standardized clinical and dermoscopic imaging of the upper arm and forearm along with non-invasive skin pigmentation and photodamage assessments.
1 visit (in-person)
Duration - Until study completion in 2028
Researchers use collected images, measurements, and questionnaire data to develop and test AI algorithms for classifying skin pigmentation, phototype, and photodamage. External validation with independent datasets is also performed.
No participant visits; data analysis only
Study Type
OBSERVATIONAL
Masking
N/A
Allocation
N/A
Model
N/A
Primary Purpose
N/A
Number of Arms
1
Have more questions? Get in touch with our team for quick support
Ophelia E Dadzie, Rick A Sturm, Damilola Fajuyigbe...
https://pubmed.ncbi.nlm.nih.gov/35349165/Roxana Daneshjou, Mary P Smith, Mary D Sun...
https://pubmed.ncbi.nlm.nih.gov/34550305/Tobechi Ebede, Art Papier
https://pubmed.ncbi.nlm.nih.gov/17010750/Roxana Daneshjou, Catarina Barata, Brigid Betz-Stablein...
https://pubmed.ncbi.nlm.nih.gov/34851366/Sophie S Lim, Tasneem F Mohammad, Indermeet Kohli...
https://pubmed.ncbi.nlm.nih.gov/37550876/D R English, B K Armstrong, A Kricker...
https://pubmed.ncbi.nlm.nih.gov/9610717/Susan C Taylor, Stéphanie Arsonnaud, Janusz Czernielewski...
https://pubmed.ncbi.nlm.nih.gov/16315565/Sarah Haggenmüller, Roman C Maron, Achim Hekler...
https://pubmed.ncbi.nlm.nih.gov/34509059/Xianjing Liu, Tobias E Sangers, Tamar Nijsten...
https://pubmed.ncbi.nlm.nih.gov/38545426/P Guitera, S W Menzies, G Argenziano...
https://pubmed.ncbi.nlm.nih.gov/27177158/Region Skane
Lead Sponsor
Sahlgrenska University Hospital
Collaborating Sponsor