Automatic International Hidradenitis Suppurativa Severity Score System (AIHS4): A Novel Tool to Assess the Severity of Hidradenitis Suppurativa Using Artificial Intelligence

18 Pages Posted: 29 Apr 2022

See all articles by Ignacio Hernández Montilla

Ignacio Hernández Montilla

Legit.Health

Alfonso Medela

Legit.Health

Taig Mac Carthy

Legit.Health - Department of Clinical Endpoint Innovation

Andy Aguilar

Legit.Health

Pedro Gómez Tejerina

Legit.Health

Alejandro Vilas Sueiro

affiliation not provided to SSRN

Ana María González Pérez

Complejo Asistencial de Zamora

Laura Vergara de la Campa

affiliation not provided to SSRN

Loreto Luna Bastante

affiliation not provided to SSRN

Rubén García Castro

affiliation not provided to SSRN

Fernando Alfageme Roldán

affiliation not provided to SSRN

Abstract

Hidradenitis suppurativa (HS) is a painful chronic inflammatory skin disease that affects up to 4% of the European adult population. International Hidradenitis Suppurativa Severity Score System (IHS4) is a dynamic scoring tool that was developed to be incorporated into the doctor's daily clinical practice and clinical studies. This helps measuring disease severity and guiding the therapeutic strategy. However, IHS4 assessment is a time-consuming and manual process, with high inter-observer variability and high dependence on observer's expertise. To tackle these issues, we introduce AIHS4, an automatic equivalent of IHS4 that deploys a deep learning lesion-detecting algorithm, called Legit.Health-IHS4net . AIHS4 was trained on Legit.Health-HS-IHS4 , a new dataset manually annotated by six specialists and processed by a novel knowledge unification algorithm. Our results show that, with current dataset size, our algorithm assesses the severity of HS cases with a performance comparable to that of the most expert physician. Furthermore, the algorithm can be implemented into CADx systems to support doctors in their clinical practice and act as a new endpoint in clinical trials. This proves the usefulness of artificial intelligence in the practice of evidence-based dermatology: algorithms trained on the consensus of large clinical boards have the potential of empowering dermatologists in their daily practice and replacing current standard clinical endpoints.

Note:
Funding Information: This project has been funded by the Department of Economic Development and Infrastructures of the Basque Government (HAZITEK Program) and the European Regional Development Fund (ERDF).

Declaration of Interests: The authors state no conflict of interest.

Keywords: Hidradenitis Suppurativa, IHS4, artificial intelligence, Automatic severity assessment, CADx system, Clinical Decision Support

Suggested Citation

Hernández Montilla, Ignacio and Medela, Alfonso and Mac Carthy, Taig and Aguilar, Andy and Gómez Tejerina, Pedro and Vilas Sueiro, Alejandro and González Pérez, Ana María and Vergara de la Campa, Laura and Luna Bastante, Loreto and García Castro, Rubén and Alfageme Roldán, Fernando, Automatic International Hidradenitis Suppurativa Severity Score System (AIHS4): A Novel Tool to Assess the Severity of Hidradenitis Suppurativa Using Artificial Intelligence. Available at SSRN: https://ssrn.com/abstract=4076680 or http://dx.doi.org/10.2139/ssrn.4076680

Alfonso Medela

Legit.Health

Bilbao, 48013
Spain

Taig Mac Carthy

Legit.Health - Department of Clinical Endpoint Innovation

Spain

Andy Aguilar

Legit.Health ( email )

Pedro Gómez Tejerina

Legit.Health ( email )

Alejandro Vilas Sueiro

affiliation not provided to SSRN ( email )

No Address Available

Ana María González Pérez

Complejo Asistencial de Zamora ( email )

Spain

Laura Vergara de la Campa

affiliation not provided to SSRN ( email )

No Address Available

Loreto Luna Bastante

affiliation not provided to SSRN ( email )

No Address Available

Rubén García Castro

affiliation not provided to SSRN ( email )

No Address Available

Fernando Alfageme Roldán

affiliation not provided to SSRN ( email )

No Address Available

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
44
Abstract Views
152
PlumX Metrics