Ann Dermatol.  2020 Aug;32(4):298-305. 10.5021/ad.2020.32.4.298.

Predictive Model for Differential Diagnosis of Inflammatory Papular Dermatoses of the Face

Affiliations
  • 1Department of Dermatology, Seoul National University Bundang Hospital, Seongnam, Korea
  • 2Department of Dermatology, SMG-SNU Boramae Medical Center, Korea
  • 3Department of Dermatology, Seoul National University College of Medicine, Seoul, Korea

Abstract

Background
The clinical features of inflammatory papulardermatoses of the face are very similar. Their clinical manifestationshave been described on the basis of a small numberof case reports and are not specific.
Objective
This studyaimed to use computer-aided image analysis (CAIA) to comparethe clinical features and parameters of inflammatorypapular dermatoses of the face and to develop a formalizeddiagnostic algorithm based on the significant findings.
Methods
The study included clinicopathologically confirmedinflammatory papular dermatoses of the face: 8 casesof eosinophilic pustular folliculitis (EPF), 13 of granulomatousperiorificial dermatitis-lupus miliaris disseminatusfaciei (GPD-LMDF) complex, 41 of granulomatous rosacea-papulopustular rosacea complex (GR-PPR) complex,and 4 of folliculitis. Clinical features were evaluated, andarea density of papular lesions was quantitatively measuredwith CAIA. Based on these variables, we developed a predictivemodel for differential diagnosis using classificationand regression tree analysis.
Results
The EPF group showedlesion asymmetry and annular clusters of papules in all cases.The GPD-LMDF complex group had significantly higher perioculardensity. The GR-PPR complex group showed a higherarea density of unilateral cheek papules and the highest total area density. According to the predictive model, 3 variableswere used for differential diagnosis of the 4 diseasegroups, and each group was diagnosed with a predictedprobability of 67%∼100%.
Conclusion
We statisticallyconfirmed the distinct clinical features of inflammatory papulardermatoses of the face and proposed a diagnostic algorithmfor clinical diagnosis.

Keyword

Algorithms; Computer-assisted; diagnosis; Decision trees; Facial dermatoses; Granulomatous rosacea; Perioral dermatitis
Full Text Links
  • AD
Actions
Cited
CITED
export Copy
Close
Share
  • Twitter
  • Facebook
Similar articles
Copyright © 2021 by Korean Association of Medical Journal Editors. All rights reserved.     E-mail: koreamed@kamje.or.kr