Abstract
Polycystic ovary syndrome (PCOS) is a complex and heterogeneous disorder that commonly affects women in the reproductive age group. The disorder has features that propose a blend of functional reproductive disorders, such as anovulation and hyperandrogenism, and metabolic disorders, such as hyperglycemia, hypertension, and obesity in women. Until today, the three implemented groups of criteria for the diagnosis of PCOS are from the National Institutes of Health (NIH) in the 1990s, Rotterdam 2003, and the Androgen Excess Polycystic Ovary Syndrome 2009 criteria. Currently, the most widely utilized criteria are the 2003 Rotterdam criteria, which validate the diagnosis of PCOS with the incidence of two out of the three criteria: hyperandrogenism (clinical and/or biochemical), irregular cycles, and polycystic ovary morphology. Currently, the anti-Müllerian hormone in serum is introduced as a substitute for the follicular count and is controversially emerging as an official polycystic ovarian morphology/PCOS marker. In adolescents, the two crucial factors for PCOS diagnosis are hyperandrogenism and irregular cycles. Recently, artificial intelligence, specifically machine learning, is being introduced as a promising diagnostic and predictive tool for PCOS with minimal to zero error that would help in clinical decisions regarding early management and treatment. Throughout this review, we focused on the pathophysiology, clinical features, and diagnostic challenges in females with PCOS.