Polycystic Ovary Syndrome (PCOS) Disease Prediction Using Machine Learning

In this day and age, there has been a growing concern about the high prevalence of serious medical conditions mainly among women. This project focuses on Polycystic Ovary Syndrome (PCOS), a common and severe health condition affecting females worldwide. Long term consequences like increased risk of Type 2 Diabetes Mellitus and Gestational Diabetes can be mitigated through early detection and management of PCOS. However, complications associated with PCOS may be better managed if detected early enough. The purpose of our project is to construct a strong diagnostic model using ensemble learning and machine learning techniques. Besides random forest, catboost classifier; XGBoost, KNN, howbeit we have integrated further models such as Support Vector Machines (SVM). We test our approach on a benchmark PCOS dataset using both 70:30, 80:20 split ratios with the XGBoost algorithm attaining an impressive accuracy level of 99% compared to other models.