EUVIMEDEUVIMED entdecken
Open Access

Independent assessment of the WHO Skin Neglected Tropical Diseases application for leprosy detection

Patrícia Deps, Bianca Barros Canhamaque Amorim, Taynah Repsold, Douglas Almonfrey, Rachel Bertolani do Espírito Santo, Rafael Maffei Loureiro, Nkechi Anne Enechukwu, Thiago Zanetti Barreiro, Mecciene Mendes Rodrigues, Andrea Maia Fernandes Fonseca, Gleice Nunes Lima, Marcos César Florian und 1 weitere

Revista Panamericana de Salud Pública · 16.04.2026 · 50 · 1

DOI: 10.26633/rpsp.2026.40 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Revista Panamericana de Salud Pública, erschienen am 16.04.2026. Verfasst von Patrícia Deps und 12 weiteren Autor:innen. Beteiligte Einrichtung: Department of Public Health Post-Graduate Programme of Infectious Diseases Federal University of Espírito Santo Vitória Brazil Department of Public H…. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: World Health Organization.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

To independently evaluate the World Health Organization (WHO) Skin Neglected Tropical Diseases (NTDs) application, focusing on the diagnostic performance of its underlying artificial intelligence model for leprosy detection. The primary objective was to determine the proportion of images in which leprosy appeared among the model’s Top-5 diagnostic predictions. The secondary objective was to qualitatively analyze diagnostic error patterns.

Methods

A data set of 439 anonymized clinical images from confirmed leprosy cases (1996–2024) was analyzed, spanning the full clinical spectrum (indeterminate, tuberculoid, borderline/dimorphous, and lepromatous/Virchowian forms) and including reactional and atypical presentations. After excluding 16 images due to processing errors, 423 images were retained: 367 classical leprosy lesions and 56 reactional or atypical leprosy-related presentations. All images were evaluated using the WHO desktop version of the visual classifier. Top-5 sensitivity (recall) for leprosy was estimated, alongside a qualitative error analysis focusing on intrapatient inconsistencies and challenging lesion types.

Results

The model achieved an overall Top-5 sensitivity (recall) of 84.9%, with higher sensitivity for classical lesions (87.2%) than for reactional or atypical presentations (69.6%). Qualitative review revealed inconsistent predictions for visually similar lesions from the same patient, and misclassifications concentrated among necrotic, inflammatory, and infiltrative lesions.

Conclusions

The WHO Skin NTDs application demonstrates substantial promise as a clinical decision-support and educational tool, especially for classical leprosy. Performance gaps for reactional and atypical forms highlight the need for algorithmic refinement. Enhancing data set diversity and integrating patient-level context may improve diagnostic robustness.

Schlagwörter

Stichwörter der Autor:innen

Leprosyartificial intelligencedecision support systems, clinicaldeep learningdermatologymobile applicationsneglected diseases

Autor:innen und Institutionen

  • Department of Public Health Post-Graduate Programme of Infectious Diseases Federal University of Espírito Santo Vitória Brazil Department of Public Health, Post-Graduate Programme of Infectious Diseases, Federal Univers…
  • Department of Electronic Engineering Federal Institute of Espírito Santo Vitória Brazil Department of Electronic Engineering, Federal Institute of Espírito Santo, Vitória, Brazil.
  • Department of Radiology Hospital Israelita Albert Einstein São Paulo Brazil Department of Radiology, Hospital Israelita Albert Einstein, São Paulo, Brazil.
  • Dermatology and Infectious Disease Unit Department of Internal Medicine Nnamdi Azikiwe University, Nnewi Campus Nnewi Nigeria Dermatology and Infectious Disease Unit, Department of Internal Medicine, Nnamdi Azikiwe Univ…
  • Department of Dermatology Federal University of Pernambuco Campus Agreste Caruaru Brazil Department of Dermatology, Federal University of Pernambuco, Campus Agreste, Caruaru, Brazil.
  • Serviço de Infectologia de Petrolina (SEINPe) Secretaria de Saúde da Prefeitura Municipal de Petrolina Petrolina Brazil Serviço de Infectologia de Petrolina (SEINPe), Secretaria de Saúde da Prefeitura Municipal de Petro…

Förderung

  • World Health Organization

Zitieren

APA

Deps, P., Amorim, B. B. C., Repsold, T., Almonfrey, D., do Espírito Santo, R. B., Loureiro, R. M., Enechukwu, N. A., Barreiro, T. Z., Rodrigues, M. M., Fonseca, A. M. F., Lima, G. N., Florian, M. C., & Ruiz-Postigo, J. A. (2026). Independent assessment of the WHO Skin Neglected Tropical Diseases application for leprosy detection. Revista Panamericana de Salud Pública, 50, 1. https://doi.org/10.26633/rpsp.2026.40

Vancouver

Deps P, Amorim BBC, Repsold T, Almonfrey D, do Espírito Santo RB, Loureiro RM, et al. Independent assessment of the WHO Skin Neglected Tropical Diseases application for leprosy detection. Revista Panamericana de Salud Pública. 2026;50:1. doi:10.26633/rpsp.2026.40

BibTeX
@article{Deps2026,
  author = {Deps, Patrícia and Amorim, Bianca Barros Canhamaque and Repsold, Taynah and Almonfrey, Douglas and do Espírito Santo, Rachel Bertolani and Loureiro, Rafael Maffei and Enechukwu, Nkechi Anne and Barreiro, Thiago Zanetti and Rodrigues, Mecciene Mendes and Fonseca, Andrea Maia Fernandes and Lima, Gleice Nunes and Florian, Marcos César and Ruiz-Postigo, Jose Antonio},
  title = {Independent assessment of the WHO Skin Neglected Tropical Diseases application for leprosy detection},
  journal = {Revista Panamericana de Salud Pública},
  year = {2026},
  volume = {50},
  pages = {1},
  doi = {10.26633/rpsp.2026.40}
}
Kostenlos starten →