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 ↗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.
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)
Stichwörter der Autor:innen
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}
}
EUVIMED