EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Artificial Intelligence Predicts Fitzpatrick Skin Type, Pigmentation, Redness, and Wrinkle Severity From Color Photographs of the Face

Rachel L Draelos, Chelsea E Kesty, Katarina R Kesty

Journal of Cosmetic Dermatology · 2025

DOI: 10.1111/jocd.70050 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Cosmetic Dermatology, 2025. Verfasst von Rachel L Draelos und 2 weiteren Autor:innen. Beteiligte Einrichtung: Vismedica AI, LLC, Durham, North Carolina, USA. Hauptthemen laut MEDLINE: Artificial Intelligence, Hyperpigmentation, Machine Learning, Skin Aging. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Kesty AI.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Due to high patient demand, increasing numbers of non‐dermatologists are performing skin assessments and carrying out laser interventions in medical spas, leading to inferior outcomes and higher complications. A machine learning tool that automatically analyzes patient skin has the potential to aid non‐dermatologists.

Aims

To develop a high‐performing machine learning model that predicts Fitzpatrick skin type, hyperpigmentation, redness, and wrinkle severity simultaneously.

Methods

We developed the SkinAnalysis dataset of 3662 images, labeled by a dermatologist across five skin scales. We trained and evaluated machine learning models across 15 different configurations, including three neural network architectures and two loss functions.

Results

The best‐performing model was an EfficientNet‐V2M architecture with a custom cross entropy loss. This model's mean test set accuracy across all labels was 85.41 ± 9.86 and its mean test set AUROC was 0.8306 ± 0.09599. An interesting trend emerged in which machine learning model performance was higher at the extremes of the scales, suggesting greater clinical ambiguity in the middle of the scales.

Conclusions

Machine learning models are capable of predicting multiple skin characteristics simultaneously from color photographs of the face. In the future, similar models could assist non‐dermatologists in patient skin evaluation to enhance treatment planning.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceHyperpigmentationMachine LearningSkin AgingSkin PigmentationHumansFaceNeural Networks, ComputerPhotographySeverity of Illness IndexSkin

Stichwörter der Autor:innen

Fitzpatrick skin typeartificial intelligencecomputer visionhyperpigmentationlaser rejuvenationlaser resurfacingmachine learningrednesswrinkles

Autor:innen und Institutionen

  • Vismedica AI, LLC, Durham, North Carolina, USA.
  • St. Petersburg Skin and Laser, St. Petersburg, Florida, USA.
  • Kesty AI, St. Petersburg, Florida, USA.

Förderung

  • Kesty AI

Zitieren

APA

Draelos, R. L., Kesty, C. E., & Kesty, K. R. (2025). Artificial Intelligence Predicts Fitzpatrick Skin Type, Pigmentation, Redness, and Wrinkle Severity From Color Photographs of the Face. Journal of Cosmetic Dermatology. https://doi.org/10.1111/jocd.70050

Vancouver

Draelos RL, Kesty CE, Kesty KR. Artificial Intelligence Predicts Fitzpatrick Skin Type, Pigmentation, Redness, and Wrinkle Severity From Color Photographs of the Face. Journal of Cosmetic Dermatology. 2025. doi:10.1111/jocd.70050

BibTeX
@article{Draelos2025,
  author = {Draelos, Rachel L and Kesty, Chelsea E and Kesty, Katarina R},
  title = {Artificial Intelligence Predicts Fitzpatrick Skin Type, Pigmentation, Redness, and Wrinkle Severity From Color Photographs of the Face},
  journal = {Journal of Cosmetic Dermatology},
  year = {2025},
  doi = {10.1111/jocd.70050}
}
Kostenlos starten →