Advanced Machine Learning for Diagnosis of Polycystic Ovarian Syndrome (PCOS)

Polycystic Ovary Syndrome (PCOS) is one of the most common type of endocrine disorder in reproductive age women (15-49 years). An estimated one in five (20%) Indian women suffer from PCOS. The main focus of this paper is to detect PCOS patients based on clinical and metabolic parameters. In this paper we are using Advanced Machine Learning approaches like Random Forest, AdaBoost, XGBoost, Bagging.The results are analysed and performance of the algorithms is validated on the basis of accuracy, precision, recall, F1 Score, AUC_ROC. The performancemetrics indicate the highest i.e. 97% accuracy of XGBoostalgorithms in the diagnosis of PCOSon giving data.