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
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.
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: Suggested Citation