• Prof. J. I. Nandalwar
• Dr. P. M. Jawandhiya

Polycystic Ovary Syndrome (PCOS) is a multifaceted endocrine disorder that impacts a significant proportion of women in their reproductive years. Characterized by a wide array of clinical manifestations, including menstrual irregularities, hyperandrogenism, and polycystic ovarian morphology, the diagnosis and management of PCOS remain challenging due to its heterogeneous presentation. This study aims to elucidate the relationships between various clinical, metabolic, and hormonal characteristics associated with PCOS and their diagnostic relevance.Using a comprehensive dataset comprising 44 parameters collected from 541 participants across multiple hospitals, we employed advanced data preprocessing techniques, exploratory data analysis (EDA) to investigate these interrelationships. Features analyzed include BMI, follicle count, hormonal markers such as AMH and LH/FSH ratio, and lifestyle variables. Correlation analysis revealed significant interactions between BMI, follicle count, and hormonal imbalances, underscoring their role in PCOS pathophysiology. We identified follicle count, BMI, and AMH as the most predictive features in classifying PCOS cases. The findings emphasize the importance of a holistic diagnostic approach that integrates metabolic and hormonal data, offering valuable insights for personalized treatment and early intervention strategies. This research not only advances understanding of PCOS but also provides a foundation for the development of predictive models that can enhance clinical decision-making and improve patient outcomes. Future work will explore longitudinal datasets and integrate additional biomarkers to refine diagnostic and therapeutic approaches for PCOS.

"Decoding PCOS: Unveiling the Metabolic and Clinical Landscape of PCOS Using Machine Learning-A Data-Driven Approach ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 12, page no.g148-g165, December-2024, Available :http://www.jetir.org/papers/JETIR2412619.pdf

"Decoding PCOS: Unveiling the Metabolic and Clinical Landscape of PCOS Using Machine Learning-A Data-Driven Approach ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 12, page no. ppg148-g165, December-2024, Available at : http://www.jetir.org/papers/JETIR2412619.pdf