AUTHOR=Pang Bo , Wang Qiong , Yang Min , Xue Mei , Zhang Yicheng , Deng Xiangling , Zhang Zhixin , Niu Wenquan TITLE=Identification and Optimization of Contributing Factors for Precocious Puberty by Machine/Deep Learning Methods in Chinese Girls JOURNAL=Frontiers in Endocrinology VOLUME=Volume 13 - 2022 YEAR=2022 URL=https://www.frontiersin.org/journals/endocrinology/articles/10.3389/fendo.2022.892005 DOI=10.3389/fendo.2022.892005 ISSN=1664-2392 ABSTRACT=Background and objectives: As the worldwide secular trends are toward earlier puberty, seeking contributing factors for precocious puberty is critical. We aimed to identify and optimize contributing factors responsible for the development of precocious puberty by invoking machine learning/deep learning algorithms in school-aged children. Methods: A cross-sectional study was conducted on children aged 6-16 years from 26 schools in Beijing based on cluster sample techniques. Information was collected online via questionnaires. Machine/deep learning algorithms were performed using the PyCharm shipping Python (v3.7.6). Results: Of 11308 children enrolled, there are 5527 girls, and 408 of them experienced precocious puberty. Training 13 machine learning algorithm revealed that gradient boosting machine (GBM) performed best in predicting precocious puberty. By comparison, six top factors including maternal age at menarche, parental body mass index (BMI), waist-to-height ratio, maternal BMI, screen time and physical activity were sufficient in prediction performance, which was further validated by deep learning sequential model, with the accuracy reaching 92.90%. Conclusions: We identified six important factors from both parents and children that can help predict the risk of precocious puberty in Chinese school-aged girls.