Digital Tools for the Detection of Dermatitis: A Systematic Review

Contact dermatitis (CD) plays a significant role in occupational health due to its frequent occurrence and environmental triggers and is among the most common occupational diseases in Western countries. Despite its prevalence, occupational contact dermatitis (OCD) is often overlooked by occupational physicians, largely due to limited knowledge and a lack of validated detection tools. Advances in digital technologies and artificial intelligence (AI) offer promising opportunities for improving early detection, yet an overview of available digital tools and their effectiveness in dermatitis detection is lacking. A systematic review was conducted in PubMed, Embase, Cinahl, and Scopus. The search focused on original studies published in peer‐reviewed journals between 2014 and 2024. Forty‐three studies evaluating digital tools for dermatitis detection were included, categorized as models ( n = 31) or devices ( n = 12). Models represent AI algorithms not yet in practical use, while devices are tools already implemented. Convolutional Neural Networks (CNNs) were the most commonly used computational technique. Median sensitivity and specificity were 0.84 and 0.97 for all tools, 0.85 and 0.97 for models, and 0.78 and 0.97 for devices. The results provided in this review will serve as valuable input for the development of new tools to enhance early OCD detection.