Dermatophytosis is one of the most common superficial fungal infections worldwide. However, its diagnosis and management remain challenging because its clinical manifestations often overlap with those of other dermatoses, conventional mycological tests have inherent limitations, the disease is prone to recurrence, and antifungal resistance has received increasing attention. This review summarizes current applications of artificial intelligence (AI) in dermatophytosis, with a focus on the use of machine learning and deep learning in clinical photographs, non-invasive skin imaging, and laboratory diagnostics, while also discussing their roles in treatment support, follow-up assessment, patient education, and adherence management. In addition, with the accumulation of molecular diagnostic, mass spectrometric, and epidemiological data, AI may also provide auxiliary support for extended applications such as resistance risk recognition. Current evidence suggests that AI can improve the efficiency, consistency, and objectivity of dermatophytosis diagnosis and provide quantitative support for treatment response assessment and long-term follow-up. With further improvement in research quality and the accumulation of clinical application experience, AI is expected to become increasingly integrated into dermatophytosis management workflows.