Abstract
INTRODUCTION: Erectile dysfunction (ED) represents a significant global public health challenge in men's health, with its prevalence exacerbated by population aging. Given the rapid advancement of artificial intelligence (AI) in healthcare, there is growing interest in its novel applications for ED diagnosis and treatment. OBJECTIVES: This systematic review synthesizes existing research on AI's role in ED management, examining its current development, application in diagnosis and treatment, and key benefits and challenges. METHODS: We executed a PRISMA-guided systematic review across PubMed, Web of Science, and Chinese databases (CNKI/Wanfang) through June 19, 2025. Analysis targeted three domains: (1) the technological evolution of AI tools specific to ED, (2) applications in clinical diagnosis, prediction, and personalized treatment, and (3) the emerging role of large language models (LLMs). RESULTS: The review identified major milestones in AI's technological evolution for ED and highlighted its significant clinical advantages, particularly through intelligent questionnaires and wearable devices enabling precise diagnosis, alongside efficacy in developing personalized treatments and predicting disease progression. While AI, particularly LLMs, demonstrates emerging potential, critical challenges persist. CONCLUSION: This review establishes a critical theoretical and technical foundation for implementing AI in men's healthcare, demonstrating its significant potential to transform the management of ED through improved diagnostics, personalized treatment, and predictive capabilities. While the interpretive nature of the synthesis presents an inherent limitation, cross-validation among researchers enhanced the reliability of the findings. However, clinical adoption remains contingent upon addressing key challenges related to data privacy, ethical considerations, and interoperability.