Prediction of pregnancy diabetes based on machine learning

Conference: BIBE 2019 - The Third International Conference on Biological Information and Biomedical Engineering
06/20/2019 - 06/22/2019 at Hangzhou, China

Proceedings: BIBE 2019

Pages: 6Language: englishTyp: PDF

Personal VDE Members are entitled to a 10% discount on this title

Du, Fan; Zhong, Weiyang (Smart Health Big Data Analysis and Location Services Engineering Lab of Jiangsu Province, Nanjing University of Posts and Telecommunications, Nanjing, China)
Wu, Wei; Wang, Jun (Department of Psychiatry, The Affiliated Brain Hospital of Nanjing Medical University, Nanjing, China)
Peng, Danhong; Xu, Tian; Wang, Gongdao (Department of Obstetrics and Gynecology, Zhongda Hospital, Southeast University, Nanjing)
Hou, Fengzhen (School of Science, China Pharmaceutical University, Nanjing China)

Gestational diabetes (GDM) refers to the normal metabolism of glucose before pregnancy and the occurrence of diabetes during pregnancy. This disease is a serious threat to the health of this pregnant woman and infant, so it is important to accurately predict whether the target is a gestational diabetes patient based on various indicators. Based on the measured data of the hospital, this paper uses decision tree, logistic regression and DenseNet to predict the target when the disease is sick or to be sick in the future, and discuss their prediction accuracy separately, which can help doctors make rapid diagnosis and make timely prevention. In the end, it was found that the DenseNet model can better predict whether the target is gestational diabetes or not, and the model flexibility is better.