EUVIMEDScopri EUVIMED
Systematische ÜbersichtOpen access · CC BY 4.0

Predicting psoriasis severity using machine learning: a systematic review

Vorhersage der Schwere von Psoriasis mittels Machine Learning: systematische Übersicht

Eric P McMullen iD, Yousif A Al Naser iD, Mahan Maazi, Rajan S Grewal, Dana Abdel Hafeez, Tia R Folino, Ronald B Vender iD

Clinical and Experimental Dermatology · 2025-02-24 · 50 (3) · 520-528

DOI: 10.1093/ced/llae348 ↗

Auf einen Blick

Die systematische Übersicht fasst 30 Arbeiten zur Vorhersage der Psoriasis-Schwere mit ML zusammen. Die meisten Modelle waren bildbasiert; prospektive klinische Anwendungen bleiben begrenzt.

Fragestellung

Welche Literatur gibt es zur Vorhersage der Psoriasis-Schwere mit Machine-Learning-Algorithmen, und welche Lücken bestehen in der klinischen Anwendung?

Methode

Systematische Übersicht; Suche in OVID Embase, OVID MEDLINE, ACM Digital Library, Scopus und IEEE Xplore von Beginn an bis August 2024.

Ergebnisse

30 Artikel erfüllten die Einschlusskriterien. 1 Arbeit nutzte Serum-Biomarker, 29 bildbasierte Modelle. Am häufigsten wurde der Psoriasis Area and Severity Index verwendet, danach die body surface area.

Einschränkungen

Kleine und heterogene Literaturbasis.

Schlussfolgerung der Autor:innen

Die Fortschritte bei der Beurteilung der Schwere von Hautläsionen durch ML in der Dermatologie sind vorangekommen, aber prospektive klinische Anwendungen bleiben begrenzt.

Kernaussagen

  • 30 eingeschlossene Artikel zur Vorhersage der Psoriasis-Schwere
  • 29 von 30 Modellen waren bildbasiert
  • Prospektive klinische Anwendungen bleiben begrenzt

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

At a glance

Systematische Übersicht in Clinical and Experimental Dermatology, published online on 2024-08-22. Written by Eric P McMullen and 6 co-authors. Institution: Division of Dermatology, Department of Medicine, University of Toronto, Toronto, ON, Canada. Major MEDLINE topics: Psoriasis, Machine Learning. Cited 14 times so far (Crossref); 43 references. The full text is freely available (open access, CC BY 4.0).

Auf einen BlickAbstractSubjectsDati bibliograficiCiteRelated studies

Abstract (original language)

Background

In dermatology, the applications of machine learning (ML), an artificial intelligence (AI) subset that enables machines to learn from experience, have progressed past the diagnosis and classification of skin lesions. A lack of systematic reviews exists to explore the role of ML in predicting the severity of psoriasis.

Objectives

To identify and summarize the existing literature on predicting psoriasis severity using ML algorithms and to identify gaps in ­current clinical applications of these tools.

Methods

OVID Embase, OVID MEDLINE, ACM Digital Library, Scopus and IEEE Xplore were searched from inception to August 2024.

Results

In total, 30 articles met our inclusion criteria and were included in this review. One article used serum biomarkers, while the remaining 29 used image-based models. The most common severity assessment score employed by these ML models was the Psoriasis Area and Severity Index score, followed by body surface area, with 15 and 5 articles, respectively.

Conclusions

The small size and heterogeneity of the existing body of literature are the primary limitations of this review. Progress in assessing skin lesion severity through ML in dermatology has advanced, but prospective clinical applications remain limited. ML and AI promise to improve psoriasis management, especially in nonimage-based applications requiring further exploration. Large-scale prospective trials using diverse image datasets are necessary to evaluate and predict the clinical value of these predictive AI models.

Subjects

MeSH terms (MEDLINE)

PsoriasisMachine LearningHumansSeverity of Illness IndexBiomarkers

Substances

Biomarkers

Authors and institutions

  • Division of Dermatology, Department of Medicine, University of Toronto, Toronto, ON, Canada.
  • Medical Radiation Sciences, McMaster University, Hamilton, ON, Canada.
  • Department of Diagnostic Imaging, Trillium Health Partners, Mississauga, ON, Canada.
  • Faculty of Medicine, University of British Columbia, Vancouver, BC, Canada.
  • Michael G. DeGroote School of Medicine, McMaster University, Hamilton, ON, Canada.
  • Divison of Neurosurgery, Department of Surgery, McMaster University, Hamilton, ON, Canada.

ORCID profiles: Eric P McMullen, Yousif A Al Naser, Ronald B Vender

Cite

APA

McMullen, E. P., Al Naser, Y. A., Maazi, M., Grewal, R. S., Abdel Hafeez, D., Folino, T. R., & Vender, R. B. (2025). Predicting psoriasis severity using machine learning: a systematic review. Clinical and Experimental Dermatology, 50(3), 520-528. https://doi.org/10.1093/ced/llae348

Vancouver

McMullen EP, Al Naser YA, Maazi M, Grewal RS, Abdel Hafeez D, Folino TR, et al. Predicting psoriasis severity using machine learning: a systematic review. Clinical and Experimental Dermatology. 2025;50(3):520-528. doi:10.1093/ced/llae348

BibTeX
@article{McMullen2025,
  author = {McMullen, Eric P and Al Naser, Yousif A and Maazi, Mahan and Grewal, Rajan S and Abdel Hafeez, Dana and Folino, Tia R and Vender, Ronald B},
  title = {Predicting psoriasis severity using machine learning: a systematic review},
  journal = {Clinical and Experimental Dermatology},
  year = {2025},
  volume = {50},
  number = {3},
  pages = {520--528},
  doi = {10.1093/ced/llae348}
}
Start for free →