Automatic International Hidradenitis Suppurativa Severity Score System (AIHS4): A Novel Tool to Assess the Severity of Hidradenitis Suppurativa Using Artificial Intelligence
An artificial-intelligence system for automatically assessing hidradenitis suppurativa severity with performance comparable to expert assessment.
Automatic International Hidradenitis Suppurativa Severity Score System (AIHS4): A Novel Tool to Assess the Severity of Hidradenitis Suppurativa Using Artificial Intelligence
Authors
Ignacio Hernández Montilla, Alfonso Medela, Taig Mac Carthy, Andy Aguilar, Pedro Gómez Tejerina, Alejandro Vilas Sueiro, Ana María González Pérez, Laura Vergara de la Campa, Loreto Luna Bastante, Rubén García Castro, Fernando Alfageme Roldán.
Abstract
The International Hidradenitis Suppurativa Severity Score System is useful in care and research, but manual assessment is time-consuming and affected by observer variability. AIHS4 applies artificial intelligence to automate lesion assessment and severity scoring.
The study used 221 disease images annotated by six specialists. With that dataset, the model’s severity estimates were comparable to those of the most experienced physician in the annotation group.
This was a retrospective image study on a small dataset assembled from public atlases. It did not evaluate clinical decisions or patient outcomes, and photographs cannot reproduce palpation used to distinguish some hidradenitis lesions. The comparison therefore supports further evaluation, not autonomous assessment or replacement of a clinical endpoint.
Publication
Published in Skin Research and Technology on 5 June 2023.
Available at https://doi.org/10.1111/srt.13357.
Related Research
AEDV 2022: Automatic urticaria scoring with artificial intelligence
Automatic urticaria scoring using artificial intelligence for precise hive counting. Presentation delivered in Spanish.
Read publicationAEDV 2022: Deep-learning algorithm for optimising triage and referral
Deep-learning algorithm for optimising the triage and referral of patients with skin conditions. Presentation delivered in Spanish.
Read publicationAEDV 2023: Validation of a deep-learning algorithm for melanoma diagnosis
Results from validating a deep-learning algorithm for melanoma diagnosis. Presentation delivered in Spanish.
Read publicationInterested in medical AI?
Learn more about Legit.Health and our work in dermatology AI.
Explore Legit.Health