Artificial Intelligence Applications in the Detection, Diagnosis, and Management of Candida albicans Infections: A Systematic Review

Candida albicans is one of the most common opportunistic fungal pathogens responsible for a wide range of infections, particularly among immunocompromised individuals and hospitalized patients. Early and accurate detection of C. albicans infections remains a significant clinical challenge due to limitations in conventional diagnostic methods, including time‑consuming culture techniques and variable sensitivity. In recent years, artificial intelligence (AI) and machine learning (ML) approaches have emerged as promising tools to improve the detection, diagnosis, and management of fungal infections. This systematic review aims to evaluate current applications of AI-based technologies in the identification and clinical management of C. albicans infections. Relevant studies published in major scientific databases were analyzed to assess AI models used in medical imaging, microbiological identification, genomic data analysis, and antifungal resistance prediction. The reviewed evidence indicates that AI-driven algorithms, particularly deep learning and pattern recognition models, can enhance diagnostic accuracy, reduce detection time, and support clinical decision‑making. Furthermore, AI tools have shown potential in predicting antifungal resistance and identifying high‑risk patients for invasive candidiasis. Despite promising outcomes, challenges remain regarding data availability, model validation, and integration into routine clinical practice. Overall, AI-based technologies represent a valuable and rapidly evolving approach for improving the diagnosis and management of C. albicans infections and may significantly contribute to advancing precision medicine in infectious diseases.

کلیدواژه ها:

Candida albicans ، artificial intelligence ، fungal infections ، antifungal resistance ، deep learning