A comprehensive review on machine learning approaches to anticipate the occurrence of polycystic ovarian syndrome (PCOS) among women

One of the endocrinopathies that affects women the most frequently is polycystic ovary syndrome. Worldwide, the prevalence of PCOS ranges from 2.2% to 26%. It is a chronic condition that lasts a lifetime and is accompanied by the symptoms of insulin resistance, which raises the risk of cardiovascular diseases. Machine learning is helping in producing promising results in medical field. Majority of the researches have been conducted by the use of various machine learning models and features selection methods to predict PCOS at an early stage. Hence, the present paper is focused on reviewing the literature extensively to summarize the previous work related to the use of machine learning in predicting PCOS and to provide recommendations for future work.