EUVIMEDEUVIMED entdecken
Crossref

Using Artificial Intelligence to Automate the Analysis of Psoriasis Severity: A Pilot Study

Chia-Lun Chou, Chien-Kun Su, Shermein Kyra Dela Cruz, Syu-Jyun Peng

Dermatology · 21.11.2025 · 242 (2) · 190-200

DOI: 10.1159/000549640 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Dermatology, online erschienen am 21.11.2025. Verfasst von Chia-Lun Chou und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Dermatology, Shuang Ho Hospital, Taipei Medical University, New Taipei City, Taiwan. Hauptthemen laut MEDLINE: Psoriasis, Artificial Intelligence, Deep Learning. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 24 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

The Psoriasis Area and Severity Index (PASI) score is widely used to assess psoriasis severity; however, manual PASI scoring is susceptible to environmental variability and subjective interpretation. This study leverages artificial intelligence to improve the consistency and objectivity of psoriasis severity classification based on features extracted from 2D clinical images.

Methods

This study employed the YOLOv8 deep learning model to classify psoriatic lesions according to the severity of erythema, thickness, and scaling – key subcomponents of the PASI scoring system. Severity was assessed as follows: (0), mild (1), moderate (2), severe (3), or very severe (4). Model training and analysis were conducted in a cloud-based environment (Google Colab) using three different datasets. Stratified k-fold cross-validation was employed to ensure robustness by preserving the distribution of PASI scores across folds. Model performance was assessed using a confusion matrix and accuracy metrics.

Results

In experiments, the YOLOv8 model proved highly effective in classifying psoriasis images based on PASI scores. Stratified k-fold cross-validation was shown to enhance model reliability across diverse datasets.

Conclusions

This study represents a significant advancement in the application of AI to the automated classification of lesion severity based on erythema, thickness, and scaling – key subcomponents of PASI.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PsoriasisArtificial IntelligenceDeep LearningHumansSeverity of Illness IndexPilot ProjectsReproducibility of Results

Stichwörter der Autor:innen

Artificial deep neural networkArtificial intelligenceDeep learningPsoriasisPsoriasis Area and Severity Index

Autor:innen und Institutionen

  • Department of Dermatology, Shuang Ho Hospital, Taipei Medical University, New Taipei City, Taiwan.
  • Department of Electrical Engineering, Chung Hua University, Hsinchu, Taiwan.
  • In-Service Master Program in Artificial Intelligence in Medicine, College of Medicine, Taipei Medical University, Taipei, Taiwan, sjpeng2019@tmu.edu.tw.
  • Clinical Big Data Research Center, Taipei Medical University Hospital, Taipei Medical University, Taipei, Taiwan, sjpeng2019@tmu.edu.tw.

Zitieren

APA

Chou, C. L., Su, C. K., Cruz, S. K. D., & Peng, S. J. (2025). Using Artificial Intelligence to Automate the Analysis of Psoriasis Severity: A Pilot Study. Dermatology, 242(2), 190-200. https://doi.org/10.1159/000549640

Vancouver

Chou CL, Su CK, Cruz SKD, Peng SJ. Using Artificial Intelligence to Automate the Analysis of Psoriasis Severity: A Pilot Study. Dermatology. 2025;242(2):190-200. doi:10.1159/000549640

BibTeX
@article{Chou2025,
  author = {Chou, Chia-Lun and Su, Chien-Kun and Cruz, Shermein Kyra Dela and Peng, Syu-Jyun},
  title = {Using Artificial Intelligence to Automate the Analysis of Psoriasis Severity: A Pilot Study},
  journal = {Dermatology},
  year = {2025},
  volume = {242},
  number = {2},
  pages = {190--200},
  doi = {10.1159/000549640}
}
Kostenlos starten →