Intelligent detection for Polycystic Ovary Syndrome (PCOS): Taxonomy, datasets and detection tools

Recent research on Polycystic Ovary Syndrome (PCOS) detection increasingly employs intelligent algorithms to assist gynecologists in more accurate and efficient diagnoses. However, intelligent PCOS detection faces notable challenges: absence of standardized feature taxonomies, limited research on available datasets, and insufficient understanding of existing detection tools' capabilities. This paper addresses these gaps by introducing a novel analytical framework for PCOS diagnostic research and developing a comprehensive taxonomy comprising 108 features across 8 categories. Furthermore, we analyzed available datasets and assessed current intelligent detection tools. Our findings reveal that 12 publicly accessible datasets cover only 54% of the 108 features identified in our taxonomy. These datasets frequently lack multimodal integration, regular updates, and clear license information-constraints that potentially limit detection tool development. Additionally, our analysis of 42 detection tools identifies several limitations: high computational resource requirements, inadequate multimodal data processing, insufficient longitudinal analysis capabilities, and limited clinical validation. Based on these observations, we highlight critical challenges and future research directions for advancing intelligent PCOS detection tools.