Artificial Intelligence in Contact Dermatitis: Current and Future Perspectives

Abstract

Abstract: Contact dermatitis (CD), which includes both allergic CD and irritant CD, is a common inflammatory condition that can pose significant diagnostic challenges. Although patch testing is the gold standard for identifying causative allergens for allergic contact dermatitis (ACD), it is time-consuming, subjective, and requires expert interpretation. Recent advancements in artificial intelligence (AI), particularly in machine learning (ML) and deep learning, have shown promise in improving the accuracy, efficiency, and accessibility of CD diagnosis and management.

This review explores current applications of AI in CD, drawing from 12 original studies that investigated AI-based image analysis, biomarker discovery, and patient risk profiling. Convolutional neural networks demonstrated high diagnostic accuracy (up to 99.5%) in interpreting patch test images, while ML algorithms successfully identified transcriptomic signatures distinguishing allergic CD from irritant CD. In addition, AI has been used to predict positive patch test outcomes and identify high-risk patients based on clinical and occupational factors.

Despite these promising developments, limitations such as dataset bias, lack of standardization, and model interpretability remain. Nevertheless, AI represents a transformative tool in dermatology, offering the potential for standardized diagnostics, personalized care, and enhanced accessibility.