Artificial Intelligence Applications in Medical Mycology: Current and Future

Abstract

The application of artificial intelligence (AI) in the medical mycology field represents a new era in the diagnosis and management of fungal infections. AI technologies, particularly machine learning (ML) and deep learning (DL) methods, enhance diagnostic accuracy by leveraging large datasets and complex algorithms. This review examines current applications of AI in laboratory and clinical settings for fungal diagnostics. In the laboratory, AI models analyze microscopic images from potassium hydroxide (KOH) examinations, fungal culture tests, and histopathologic slides, which improves the detection rates of fungal pathogens significantly. In the clinical setting, AI assists the diagnosis of fungal infections using medical images, exhibiting high efficacy in binary classification tasks. However, challenges include small sample sizes, class imbalances, reliance on expert-labeled data, and the black box nature of AI models. Explainable AI offers potential solutions by providing human-comprehensible insights into AI decision-making processes. In addition, human-computer collaboration can enhance diagnostic accuracy, particularly for less experienced clinicians. The development of generative AI models, e.g., large language models and multimodal AI, promises to create extensive datasets and integrate various data sources for comprehensive diagnostics. Addressing these limitations through prospective clinical validation and continuous feedback will be essential for realizing the full potential of AI in medical mycology.