This study found that using machine learning models, particularly Random Forest with 93% accuracy and 86% sensitivity, can effectively predict PCOS by analyzing features like antral follicle count, hair growth, and skin pigmentation, offering a promising alternative to traditional diagnostic methods.
19 citations
,
October 2024 in “BMC Medical Informatics and Decision Making” This study used machine learning models to analyze PCOS symptoms for early diagnosis, finding Support Vector Machine and VGG16 algorithms achieved high accuracy rates of 94.44% and 98.29% respectively.
July 2025 in “Indus journal of bioscience research.” This study found that women with polycystic ovary syndrome showed significant differences in clinical symptoms, hormone levels, and ovarian morphology compared to healthy controls, such as higher body mass index, menstrual irregularities, elevated luteinizing hormone, and polycystic ovarian morphology, suggesting these factors enhance diagnostic accuracy.
3 citations
,
May 2023 in “Endocrine Abstracts” This study identified three subgroups of women with PCOS with distinct androgen profiles, finding that the subgroup with adrenal-derived androgen excess had the highest insulin resistance and rates of hirsutism and hair loss.
5 citations
,
March 2022 in “Frontiers in Endocrinology” This study developed a mathematical model and online tool using serum AMH, androstenedione levels, UML, and BMI to screen for undiagnosed PCOS, particularly useful for Asian populations.
