On the Prediction of Polycystic Ovarian Syndrome

Polycystic Ovary Syndrome (PCOS) stands as a prevalent endocrine disorder with a far-reaching impact on women and girls globally. Its effects span from skin pigmentation changes and hair loss, to potential infertility and the onset of mental health disorders such as anxiety and depression. The widespread occurrence of PCOS and the severity of its consequences reinforces the urgent need to address this medical condition. Present methods for accurately diagnosing PCOS can be costly and inconclusive. This challenge has driven the research presented in this paper, which aims to incorporate data science techniques into the PCOS diagnostic process in the hopes of developing a more rigorous and less subjective method for diagnosing the syndrome. We introduce, and illustrate the performance of, a new classification algorithm for the problem.