Comparative Study of Machine Learning Algorithms for Prediction Of Polycystic Ovary Syndrome
Neeta Chavan, Saakshi Karkera, Aishvarya Birambole, Isha Chavan, Risa Samanta
Abstract
A medical condition known as Polycystic ovary syndrome (PCOS) influences women during their childbearing years and causes hormonal imbalances. A menstrual cycle that is delayed or even absent is the result of hormonal imbalance. Symptoms of PCOS includes massive weight gain, facial hair growth, acne, hair loss, pigmentation of the skin, irregular periods, and, in rare instances, sterility. For early detection and prediction, the current techniques and treatments fall short. To solve this issue, we have used machine learning techniques and compared their effectiveness based on the parameters like f1 score, MCC and accuracy. Five distinct Machine Learning classifiers, including Logistic Regression, Support-Vector Machines, K-Nearest Neighbor, Random Forest, and Gradient Boosting Decision Tree were used for comparison. K-Nearest Neighbor and Random Forest was ensembled to obtain less log-loss and more accuracy.