AUTHOR=Ding Ting , Ren Wu , Wang Tian , Han Yun , Ma Wenqing , Wang Man , Fu Fangfang , Li Yan , Wang Shixuan 

TITLE=Assessment and quantification of ovarian reserve on the basis of machine learning models

JOURNAL=Frontiers in Endocrinology

VOLUME=Volume 14 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/endocrinology/articles/10.3389/fendo.2023.1087429

DOI=10.3389/fendo.2023.1087429

ISSN=1664-2392

ABSTRACT=Background: Early detection of ovarian aging is of huge importance, while no ideal marker or acknowledged evaluation system existed. The purpose of this study was to develop a better prediction model to assess and quantify the ovarian reserve using machine learning methods.
Methods: This is a multicenter and nationwide population-based study including a total of 1020 healthy women. For these healthy women, their ovarian reserve was quantified in the form of ovarian age, which was assumed equal to their chronological age, and the LASSO regression was used to select features to construct models. Seven machine learning methods: artificial neural network (ANN), support vector machine (SVM), generalized linear models (GLM), K-Nearest-Neighbors Regression (KNN), Gradient Boosting Decision Tree (GBDT), extreme gradient boosting (XGBoost), and light gradient boosting machine (LightGBM) were applied to construct prediction models separately. And Pearson correlation coefficiency (PCC), mean absolute error (MAE), and mean squared error (MSE) were used to compare the efficiency and stability of these models. 
Results: Anti-müllerian hormone (AMH) and antral follicle count (AFC) were detected to have the highest absolute PCC value of 0.45 and 0.43 with age and held similar age distribution curves. The LightGBM model was thought to be the most suitable model for ovarian age after ranking analysis combining PCC, MAE, and MSE values. The LightGBM model got a PCC value of 0.82, 0.56, and 0.70 for the training set , the test set, and the entire dataset. And the LightGBM method still held the least MAE and cross-validated MSE value, seperately. Further, in two different age groups (20-35, and >35 years old), the LightGBM model also got the least MAE value of 2.88 for women in the age of 20 to 35 years old and the second least MAE value of 5.12 for women over the age of 35 years old. 
Conclusion: Machine learning methods combining multi-features were reliable to assess and quantify ovarian reserve, and the LightGBM method turned out to be the approach with the best result, especially in the child-bearing age group of 20 to 35 years old.