Skin Type Determination Using Image Artificial Intelligence

NCT07765303 | Recruiting

• 3 other identifiers: 2024-07010-013655/20243756/2025
• Study Type: observational
• Target: 1,500
• Locations: 9 countries
• Sites: 11

Brief Summary

Skin color, how easily a person burns or tans in the sun (skin phototype), and the amount of chronic sun damage in the skin are important factors in skin health. These characteristics influence a person's risk of skin cancer, how skin diseases appear, how well treatments work, and how accurately doctors and artificial intelligence (AI) systems can diagnose skin conditions. However, current methods for classifying these characteristics are often imprecise and rely heavily on subjective assessments. As a result, both healthcare professionals and patients may incorrectly classify skin type, which can lead to inaccurate risk assessments and less personalized care. This study aims to develop and validate AI algorithms that can accurately classify skin pigmentation, skin phototype, and accumulated sun damage using photographs of the skin. Unlike existing approaches, the study combines several different methods to create a more objective "ground truth" for training the AI. These methods include skin color measurements using spectrophotometry or colorimetry, assessments using the Monk Skin Tone Scale, questionnaires about sun sensitivity, and clinical evaluations by trained observers. By combining these data sources, the researchers hope to create a more reliable and scientifically robust classification system. The study will recruit adults aged 18 years and older from several countries, including countries from all continents. Participants will complete a questionnaire about their skin, propensity to burn and sun exposure history. Researchers will then take standardized close-up and dermoscopic images of the skin on the arm and forearm, measure skin pigmentation using objective instruments when available, and assess skin phototype and sun damage. No invasive procedures will be performed, and no personally identifiable information will be collected. The collected images and measurements will be used to train deep learning AI models. The researchers aim to develop algorithms that can classify skin pigmentation with at least 85% accuracy, skin phototype with at least 75% accuracy, and sun damage with at least 80% accuracy compared with the combined reference assessments. The algorithms will then be tested in independent datasets, including large dermatology image databases from Sweden, to evaluate how well they perform in different populations. The study has several potential benefits. More accurate classification of skin characteristics could improve personalized skin cancer risk assessments and allow prevention advice to be tailored to individual needs. This may help identify people who would benefit from closer surveillance and stronger sun protection recommendations while avoiding unnecessary restrictions for people at lower risk. Improved classification could also enhance the diagnosis and management of inflammatory skin diseases and skin cancers, which can appear differently in people with different skin tones. An additional goal is to address known biases in dermatology AI systems, which often perform less accurately in individuals with darker skin. By including participants with a wide range of skin tones and backgrounds, the researchers aim to contribute to the benchmarking of AI-driven medical devices wich hopefully can result in the development of fairer and more equitable AI tools. The study involves minimal risk. Only photographs of the arm and forearm will be taken, and researchers will avoid capturing tattoos, prominent scars, or other identifying features. All data will be stored securely and only accessible to authorized researchers. The potential benefits of improving skin disease diagnosis, skin cancer prevention, and fairness in medical AI are considered to outweigh the small privacy risks associated with participation.

Conditions

Skin Ageing; Skin

Keywords

skin tone; pigmentation; skin color; chronic sun damage; photodamage; sun sensitivity; phototype; Fitzpatrick type

Outcome Measures

Primary Outcomes (4)

• Agreement between AI-derived skin pigmentation (tone) classification and objective skin pigmentation measured by colorimetry/ spectrophotometry (Individual Typology Angle, ITA)

  Skin pigmentation will be measured objectively using spectrophotometry/ colorimetry and summarized as the Individual Typology Angle (ITA). AI-derived skin pigmentation classification will be compared with ITA values using correlation and agreement analyses. ITA is considered the primary reference standard for objective assessment of skin pigmentation in the interpretation of AI performance.

  At completion of model development and testing (approximately 2029).

• Accuracy of AI-based skin phototype classification

  Accuracy of the deep learning algorithm in classifying skin phototype from clinical and dermoscopic images compared with the reference standard based on the validated Fitzpatrick skin phototype assessment (consisting of 6 categories).

  At completion of model development and testing (approximately 2029).

• Agreement between AI-derived skin pigmentation (tone) classification and clinician-assessed Monk Skin Tone Scale category

  Skin pigmentation will be assessed visually by trained investigators using the Monk Skin Tone Scale (categories 1 (fair) to 10 (dark)). AI-derived classifications will be compared with clinician-assigned Monk categories using agreement and correlation analyses. The Monk Skin Tone Scale represents the principal visual reference standard for skin tone classification.

  At completion of model development and testing (approximately 2029).

• Agreement between AI-derived photodamage classification and the Clinical Photonumeric Scale for Photodamage Assessment

  Photodamage will be assessed using the validated Clinical Photonumeric Scale (0-3 for 3 defined pigmentation categories) for Photodamage Assessment. AI-derived photodamage classifications will be compared with the photonumeric scale scores using agreement and correlation analyses. This outcome evaluates the agreement between AI-derived classifications and a validated photonumeric clinical assessment of photodamage.

  At completion of model development and testing (approximately 2029).

Secondary Outcomes (4)

• Agreement between AI-derived facial photodamage classification and the Glogau Photoaging Scale

  At completion of model development and testing (approximately 2029).

• Agreement between AI-derived skin pigmentation classification and participant self-reported skin tone

  At completion of model development and testing (approximately 2029).

• Agreement between AI-derived skin pigmentation classification and observer-reported skin tone

  At completion of AI model (approximately 2029)

• Agreement between AI-derived forearm photodamage classification and the Forearm Skin Photoaging Scale

  At completion of model development and testing (approximately 2029).

Study Arms (1)

Participants undergoing skin imaging and skin characteristic assessment

Adults aged 18 years and older recruited at participating study sites who undergo standardized clinical and dermoscopic skin imaging, skin pigmentation assessment, skin phototype assessment, photodamage assessment, and questionnaire completion. Data collected from participants will be used to develop and validate artificial intelligence algorithms for classification of skin pigmentation, skin phototype, and photodamage.

Other: Skin imaging and skin characteristic assessment

Interventions

Skin imaging and skin characteristic assessment OTHER

Participants undergo standardized clinical and dermoscopic skin imaging, skin pigmentation measurements, skin phototype assessments, photodamage assessments, and completion of questionnaires. Data are collected for the development and validation of artificial intelligence algorithms for classification of skin pigmentation, phototype, and photodamage.

Participants undergoing skin imaging and skin characteristic assessment

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Adults aged 18 years and older will be recruited from dermatology clinics, hospital waiting areas, universities, and other public settings at participating study sites (at present 11 but more are being recruited). The study aims to include individuals representing a broad range of skin pigmentation levels, skin phototypes, and degrees of photodamage. Participants will undergo non-invasive skin imaging, skin characteristic assessments, and questionnaire-based data collection to support the development and validation of artificial intelligence algorithms for classification of skin pigmentation, phototype, and photodamage.

You may qualify if:

• Aged 18 years or older
• Able and willing to provide informed consent (oral or written, according to local regulations)
• Willing to complete the study questionnaire
• Willing to undergo non-invasive skin imaging and skin characteristic assessments of predefined sites on the upper arm and forearm

You may not qualify if:

• Younger than 18 years of age
• Unable to provide informed consent
• Unable to complete study procedures
• Tattoos, prominent scars, wounds, skin lesions, dressings, or other identifiable features at the predefined imaging sites that may interfere with image acquisition, assessment quality, or participant anonymity

Sponsors & Collaborators

• Region Skane: lead
• Sahlgrenska University Hospital: collaborator
• Odense University Hospital: collaborator
• Hospital Universitario 12 de Octubre: collaborator
• Queen Elizabeth Central Hospital, Blantyre, Malawi: collaborator
• University of Chile: collaborator
• Universidad de los Andes, Chile: collaborator
• Mahidol University: collaborator
• Monash University: collaborator
• The University of Queensland: collaborator
• Erasmus University Rotterdam: collaborator
• Xiangya Hospital of Central South University: collaborator
• University of Colombo: collaborator

Study Sites (11)

Hospital de Clínicas de Porto Alegre

Porto Alegre, Brazil

RECRUITING

Clinica Universidad de los Andes

Santiago, Chile

NOT YET RECRUITING

Hospital Clínico Universidad de Chile

Santiago, Chile

RECRUITING

Xiangya Hospital, Central South University

Changsha, China

NOT YET RECRUITING

Department of Dermatology, Odense University Hospital

Odense, Denmark

NOT YET RECRUITING

Queen Elisabeth Central Hospital

Blantyre, Malawi

NOT YET RECRUITING

Department of Dermatology, Hospital Universitario 12 de Octubre

Madrid, Spain

COMPLETED

University of Colombo

Colombo, Sri Lanka

ENROLLING BY INVITATION

Department of Dermatology Lund, Skåne University Hospital

Lund, Skåne County, 22185, Sweden

RECRUITING

Department of Dermatology, Sahlgrenska University Hospital

Gothenburg, Västra Götaland County, Sweden

RECRUITING

Siriraj Hospital, Mahidol University

Bangkok, Thailand

RECRUITING

Related Publications (18)

• Liu X, Sangers TE, Nijsten T, Kayser M, Pardo LM, Wolvius EB, Roshchupkin GV, Wakkee M. Predicting skin cancer risk from facial images with an explainable artificial intelligence (XAI) based approach: a proof-of-concept study. EClinicalMedicine. 2024 Mar 19;71:102550. doi: 10.1016/j.eclinm.2024.102550. eCollection 2024 May.

  PMID: 38545426 BACKGROUND

• Haggenmuller S, Maron RC, Hekler A, Utikal JS, Barata C, Barnhill RL, Beltraminelli H, Berking C, Betz-Stablein B, Blum A, Braun SA, Carr R, Combalia M, Fernandez-Figueras MT, Ferrara G, Fraitag S, French LE, Gellrich FF, Ghoreschi K, Goebeler M, Guitera P, Haenssle HA, Haferkamp S, Heinzerling L, Heppt MV, Hilke FJ, Hobelsberger S, Krahl D, Kutzner H, Lallas A, Liopyris K, Llamas-Velasco M, Malvehy J, Meier F, Muller CSL, Navarini AA, Navarrete-Dechent C, Perasole A, Poch G, Podlipnik S, Requena L, Rotemberg VM, Saggini A, Sangueza OP, Santonja C, Schadendorf D, Schilling B, Schlaak M, Schlager JG, Sergon M, Sondermann W, Soyer HP, Starz H, Stolz W, Vale E, Weyers W, Zink A, Krieghoff-Henning E, Kather JN, von Kalle C, Lipka DB, Frohling S, Hauschild A, Kittler H, Brinker TJ. Skin cancer classification via convolutional neural networks: systematic review of studies involving human experts. Eur J Cancer. 2021 Oct;156:202-216. doi: 10.1016/j.ejca.2021.06.049. Epub 2021 Sep 8.

  PMID: 34509059 BACKGROUND

• Dadzie OE, Sturm RA, Fajuyigbe D, Petit A, Jablonski NG. The Eumelanin Human Skin Colour Scale: a proof-of-concept study. Br J Dermatol. 2022 Jul;187(1):99-104. doi: 10.1111/bjd.21277. Epub 2022 May 8.

  PMID: 35349165 BACKGROUND

• Daneshjou R, Barata C, Betz-Stablein B, Celebi ME, Codella N, Combalia M, Guitera P, Gutman D, Halpern A, Helba B, Kittler H, Kose K, Liopyris K, Malvehy J, Seog HS, Soyer HP, Tkaczyk ER, Tschandl P, Rotemberg V. Checklist for Evaluation of Image-Based Artificial Intelligence Reports in Dermatology: CLEAR Derm Consensus Guidelines From the International Skin Imaging Collaboration Artificial Intelligence Working Group. JAMA Dermatol. 2022 Jan 1;158(1):90-96. doi: 10.1001/jamadermatol.2021.4915.

  PMID: 34851366 BACKGROUND

• Daneshjou R, Smith MP, Sun MD, Rotemberg V, Zou J. Lack of Transparency and Potential Bias in Artificial Intelligence Data Sets and Algorithms: A Scoping Review. JAMA Dermatol. 2021 Nov 1;157(11):1362-1369. doi: 10.1001/jamadermatol.2021.3129.

  PMID: 34550305 BACKGROUND

• Steele L, Tan XL, Olabi B, Gao JM, Tanaka RJ, Williams HC. Determining the clinical applicability of machine learning models through assessment of reporting across skin phototypes and rarer skin cancer types: A systematic review. J Eur Acad Dermatol Venereol. 2023 Apr;37(4):657-665. doi: 10.1111/jdv.18814. Epub 2023 Jan 2.

  PMID: 36514990 BACKGROUND

• Williams JR, Frey C, Cohen GF. Cutaneous Sarcoidosis in Skin of Color. J Drugs Dermatol. 2023 Jul 1;22(7):695-697. doi: 10.36849/JDD.7008.

  PMID: 37410043 BACKGROUND

• Hogue L, Harvey VM. Basal Cell Carcinoma, Squamous Cell Carcinoma, and Cutaneous Melanoma in Skin of Color Patients. Dermatol Clin. 2019 Oct;37(4):519-526. doi: 10.1016/j.det.2019.05.009.

  PMID: 31466591 BACKGROUND

• Guitera P, Menzies SW, Argenziano G, Longo C, Losi A, Drummond M, Scolyer RA, Pellacani G. Dermoscopy and in vivo confocal microscopy are complementary techniques for diagnosis of difficult amelanotic and light-coloured skin lesions. Br J Dermatol. 2016 Dec;175(6):1311-1319. doi: 10.1111/bjd.14749. Epub 2016 Oct 12.

  PMID: 27177158 BACKGROUND

• Ebede T, Papier A. Disparities in dermatology educational resources. J Am Acad Dermatol. 2006 Oct;55(4):687-90. doi: 10.1016/j.jaad.2005.10.068.

  PMID: 17010750 BACKGROUND

• Lindqvist PG, Landin-Olsson M, Olsson H. Low sun exposure habits is associated with a dose-dependent increased risk of hypertension: a report from the large MISS cohort. Photochem Photobiol Sci. 2021 Feb;20(2):285-292. doi: 10.1007/s43630-021-00017-x. Epub 2021 Feb 18.

  PMID: 33721253 BACKGROUND

• Taylor SC, Arsonnaud S, Czernielewski J; Hyperpigmentation Scale Study Group. The Taylor Hyperpigmentation Scale: a new visual assessment tool for the evaluation of skin color and pigmentation. Cutis. 2005 Oct;76(4):270-4.

  PMID: 16315565 BACKGROUND

• English DR, Armstrong BK, Kricker A, Winter MG, Heenan PJ, Randell PL. Demographic characteristics, pigmentary and cutaneous risk factors for squamous cell carcinoma of the skin: a case-control study. Int J Cancer. 1998 May 29;76(5):628-34. doi: 10.1002/(sici)1097-0215(19980529)76:53.0.co;2-s.

  PMID: 9610717 BACKGROUND

• Tan K, Lo SN, Cust AE, Wolfe R, Mar V. Sensitivity of two Australian melanoma risk tools to identify high-risk individuals among people presenting with their first primary melanoma. Australas J Dermatol. 2022 Aug;63(3):352-358. doi: 10.1111/ajd.13841. Epub 2022 May 6.

  PMID: 35522684 BACKGROUND

• Vuong K, Armstrong BK, Drummond M, Hopper JL, Barrett JH, Davies JR, Bishop DT, Newton-Bishop J, Aitken JF, Giles GG, Schmid H, Jenkins MA, Mann GJ, McGeechan K, Cust AE. Development and external validation study of a melanoma risk prediction model incorporating clinically assessed naevi and solar lentigines. Br J Dermatol. 2020 May;182(5):1262-1268. doi: 10.1111/bjd.18411. Epub 2019 Sep 22.

  PMID: 31378928 BACKGROUND

• Okoji UK, Taylor SC, Lipoff JB. Equity in skin typing: why it is time to replace the Fitzpatrick scale. Br J Dermatol. 2021 Jul;185(1):198-199. doi: 10.1111/bjd.19932. Epub 2021 Apr 22. No abstract available.

  PMID: 33666245 BACKGROUND

• Lim SS, Mohammad TF, Kohli I, Hamzavi I, Rodrigues M. Optimisation of skin phototype classification. Pigment Cell Melanoma Res. 2023 Nov;36(6):468-471. doi: 10.1111/pcmr.13110. Epub 2023 Aug 7.

  PMID: 37550876 BACKGROUND

• Barsh GS. What controls variation in human skin color? PLoS Biol. 2003 Oct;1(1):E27. doi: 10.1371/journal.pbio.0000027. Epub 2003 Oct 13.

  PMID: 14551921 BACKGROUND

MeSH Terms

Conditions

Photosensitivity Disorders

Condition Hierarchy (Ancestors)

Skin Diseases; Skin and Connective Tissue Diseases

Central Study Contacts

Åsa Ingvar, MD PhD

CONTACT

+46 46172243; asa.ingvar@skane.se

Anna Asphult, Research nurse

CONTACT

+46 46 172113; teleforskning.hud.sus@skane.se

Study Design

• Study Type: observational
• Observational Model: OTHER
• Time Perspective: CROSS SECTIONAL
• Target Duration: 1 Day
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: June 15, 2026
• First Posted: August 14, 2026
• Study Start: April 28, 2025
• Primary Completion (Estimated): December 31, 2027
• Study Completion (Estimated): December 31, 2028
• Last Updated: August 14, 2026

Record last verified: 2026-06

Data Sharing

• IPD Sharing: Will share
• Shared Documents: STUDY PROTOCOL, ICF
• Time Frame: IPD will be shared when the study is completed, 2029-2030.
• Access Criteria: No limitations. Images, measurement data, basic participant characteristics.

Locations

BR (1); CN (1); DK (1); CL (2); TH (1); MA (1); SE (2); SR (1); ES (1)