Establishment and validation of a nomogram model for predicting ovulation in the PCOS women

Abstract

Background: The mechanisms underlying ovulatory dysfunction in PCOS remain debatable. This study aimed to identify the factors affecting ovulation among PCOS patients based on a large sample-sized randomized control trial. Methods: Data were obtained from a multi-centered randomized clinical trial, the PCOSAct, which was conducted between 2011 and 2015. Univariate and multivariate analysis using binary logistic regression were used to construct a prediction model and nomogram. The accuracy of the model was assessed using receiver operating characteristic (ROC) curves and calibration curves. Results: The predictive variables included in the training dataset model were luteinizing hormone (LH), free testosterone, body mass index (BMI), period times per year, and clomiphene treatment. The ROC curve for the model in the training dataset was 0.81 (95% CI [0.77, 0.85]), while in the validation dataset, it was 0.7801 (95% CI [0.72, 0.84]). The model showed good discrimination in both the training and validation datasets. Decision curve analysis demonstrated that the nomogram designed for ovulation had clinical utility and superior discriminative ability for predicting ovulation. Conclusions: The nomogram composed of LH, free testosterone, BMI, period times per year and the application of clomiphene may predict the ovulation among PCOS patients.