A Systematic Review on: Polycystic Ovary Syndrome Using Machine Learning

Abstract

Abstract: Polycystic Ovary Syndrome (PCOS) is a medical condition which causes hormonal disorder in women in their childbearing years. The hormonal imbalance leads to a delayed or even absent menstrual cycle. Women with PCOS majorly suffer from excessive weight gain, facial hair growth, acne, hair loss, skin darkening and irregular periods leading to infertility in rare cases. Early detection and diagnosis of PCOS are crucial for timely intervention and management. The existing methodologies and treatments are insufficient for early-stage detection and prediction. Machine learning can play a significant role in automating PCOS detection based on medical data and patient information. To deal with this problem, we propose a system which can help in early detection and prediction of PCOS treatment from an optimal and minimal set of parameters. In this study, we present an online application that enables women to conveniently estimate their likelihood of having the condition while remaining in the comfort of their own homes until assistance becomes accessible. Using feature selection approaches, we select only the non-invasive, readily measurable characteristics at home, resulting in a minimal but optimal set of clinical data for the same prediction. We employ the random-forest classifier, which has demonstrated encouraging outcomes when used in conjunction with machine learning techniques to diagnose PCOS. The Kaggle dataset, which consists of data points with clinical variables such as weight increase, LHS levels, hair loss, acne, BMI, and follicles in the left and right ovary, is used in this work.