Employing AI-powered smartphone applications and online services for the purposes of identification of skin conditions holds significant promise for enhancing the dermatological care of patients, according to a new position statement.¹

This new statement was crafted by the Congress of the European Academy of Dermatology and Venereology (EADV) Artificial Intelligence Task Force, with the aim being to provide guidance and information related to the utilization of web-based services and AI-enhanced smartphone applications for management of skin disease and particularly skin cancer.²

The research involved in this position statement was led by Tobias E. Sangers, MD, from the Department of Dermatology at Leiden University Medical Center in the Netherlands. It was viewed to be especially valuable, given the rising divergence of opinions on harms or possible benefits of new technology’s use in patient care.

“The recommendations presented herein aim to provide guidance for clinicians, researchers, consumers, app developers, (inter)-national professional dermatology societies and regulators ensuring the safe and proper implementation of this technology worldwide,” Sangers and colleagues wrote.

Background and Findings

The investigators initiated the concept of the position statement by first carrying out an extensive literature review so as to shape their initial draft. For their maintenance of a comprehensive and an unbiased viewpoint, the EADV AI Task Force worked on 2 successive online forums.

In the task force’s online sessions, members of the task force contributed their insights on the subject as well as their own suggestions. The feedback they were able to receive during these interactions underwent an extensive review and analysis, with the results being thoughtful adjustments to the investigators’ initial draft.

The new modifications resulting from the online sessions were carried out with the purpose of enhancing the overall statement's lucidity, precision, and relevance.

The task force considered the following elements when reviewing the statement on AI’s use in dermatology: Inaccuracy risks, variance, quantity, and quality of image training data, the assurance of reliability, assessment of risks and benefits, explainability of AI, human preference incorporation, risks of improper AI use, commercial influence which is non-medical, professional skills declines, security of medical data, direct and indirect costs, regulatory approval, and multidisciplinary implementation.

The investigators described their major recommendations and the related sub-recommendations of the EADV AI Task Force with regard to the relationship with AI-assisted smartphone apps and web-based services and their use with skin disease.

Their main recommendations for the use of these technological innovations were the following:

• “To ensure user trust, app developers should prioritize transparency in data quality, accuracy, intended use, privacy and costs," the first read.
• “Apps and web-based services should ensure a uniform user experience for diverse groups of patients," the second read.
• “European authorities should adopt a rigorous and consistent regulatory framework for dermatology apps to ensure their safety and accuracy for users," the third read.

“In conclusion, the utilisation of AI-assisted smartphone apps and web-based services in diagnosing and treating skin diseases has the potential to greatly benefit patients in their dermatology journeys,” they wrote. “By prioritising innovation, fostering collaboration and implementing effective regulations, we can ensure the successful integration of these apps into clinical practice.”

References

1. ^{Sangers, TE, Kittler, H, Blum, A, Braun, RP, Barata, C, Cartocci, A, et al. Position statement of the EADV Artificial Intelligence (AI) Task Force on AI-assisted smartphone apps and web-based services for skin disease. J Eur Acad Dermatol Venereol. 2023; 00: 1–9. https://doi.org/10.1111/jdv.19521.}
2. ^{Freeman K, Dinnes J, Chuchu N, Takwoingi Y, Bayliss SE, Matin RN, et al. Algorithm based smartphone apps to assess risk of skin cancer in adults: systematic review of diagnostic accuracy studies. BMJ. 2020; 368:m127.}