Polycystic Ovary Syndrome (PCOS) is a prevalent and intricate endocrine disorder affecting a substantial proportion of the female population. This condition is characterized by a constellation of symptoms, encompassing irregular menstrual cycles, physical manifestations like excess hair growth or acne, and hormonal imbalances, such as elevated androgen levels. The diagnosis of PCOS is often challenging due to the heterogeneity of its symptoms and the need for a multidimensional assessment. The proposed system seeks to revolutionize PCOS diagnosis by amalgamating two potent technologies: Extreme Gradient Boosting (XGBoost) and Convolutional Neural Networks (CNNs) with meticulous feature selection. XGBoost handles structured clinical data, capturing intricate relationships, while CNNs extract features from medical images, crucial for identifying ovarian cysts, a common PCOS indicator. This fusion offers a holistic assessment, empowering healthcare professionals to make more accurate diagnoses, thereby improving patient care. By bridging structured and unstructured data, our system aims to enhance PCOS understanding and streamline diagnostics, benefiting women globally.