A Model for Predicting Polycystic Ovary Syndrome Using Serum AMH, Menstrual Cycle Length, Body Mass Index, and Serum Androstenedione in Chinese Reproductive-Aged Population: A Retrospective Cohort Study
March 2022
in “
Frontiers in Endocrinology
”
TLDR A model using hormone levels, cycle length, and BMI can help identify PCOS in Chinese women but isn't for screening teens.
A retrospective observational cohort study involving 11,720 ovarian stimulation cycle records developed a model for predicting Polycystic Ovary Syndrome (PCOS) in Chinese women of reproductive age. The model uses four parameters: serum Anti-Müllerian Hormone (AMH), menstrual cycle length, Body Mass Index (BMI), and serum Androstenedione. The model showed good correlations with an Area Under the Curve (AUC) of 0.855, 0.848, and 0.846 in the training, validation, and testing sets, respectively. The contributions of each predictor were: AMH 41.2%, menstrual cycle length 35.2%, BMI 4.3%, and Androstenedione 3.7%. The study concluded that this model could be a useful tool for early identification of undiagnosed PCOS, improving long-term health management for affected women. However, it is not suitable for PCOS screening in adolescents.
