Artificial Intelligence Predicts Gestational Diabetes

by Colleen Fleiss on Dec 22 2020 11:10 PM

Artificial Intelligence Predicts Gestational Diabetes
Machine learning helped predict women at high risk of developing gestational diabetes, revealed a new study published in the Endocrine Society’s Journal of Clinical Endocrinology & Metabolism. Machine learning is a form of artificial intelligence.
Gestational diabetes is a common complication during pregnancy that affects up to 15 percent of pregnant women. High blood sugar in the mother can be dangerous for the baby and lead to complications like stillbirth and premature delivery. Most women are diagnosed with gestational diabetes during the second trimester, but some women are at high risk and could benefit from earlier intervention.

“Our study leveraged artificial intelligence to predict gestational diabetes in the first trimester using electronic health record data from a Chinese hospital,” said study author He-Feng Huang Ph.D. of the Shanghai Jiao Tong University School of Medicine and the International Peace Maternity and Child Health Hospital in Shanghai, China.

“These findings can help clinicians identify women at high risk of diabetes in early pregnancy and start interventions such as diet changes sooner. The artificial intelligence technology will continue to improve over time and help us better understand the risk factors for gestational diabetes.”

The researchers analyzed nearly 17,000 electronic health records from a hospital in China in 2017 with machine learning models to predict women at high risk for gestational diabetes. They compared their predictions with 2018 electronic health record data and found they were successful at identifying who would develop gestational diabetes. The prediction models also found an association between low body mass and gestational diabetes. Other authors of the study include: Yan-Ting Wu, Chen-Jie Zhang, Cheng Li, Yu Wang, Jian-Xia Fan, and Lei Chen of the Shanghai Jiao Tong University School of Medicine and the International Peace Maternity and Child Health Hospital; Ben Willem Mol and Andrew Kawai of Monash University in Melbourne, Australia; Jian-Zhong Sheng of the Zhejiang University in Zhejiang, China; and Yi Shi of the Shanghai Jiao Tong University.

The manuscript received funding from the National Key Research and Development Program of China, the National Natural Science Foundation of China, the Foundation of Shanghai Municipal Commission of Health and Family Planning, the Clinical Skills Improvement Foundation of Shanghai Jiaotong University School of Medicine, the Natural Science Foundation of Shanghai, the Shanghai Shenkang Hospital Development Center, Clinical Technology Innovation Project, the Program of Shanghai Academic Research Leader, the CAMS Innovation Fund for Medical Sciences, and the Outstanding Youth Medical Talents of Shanghai Rising Stars of Medical Talent Youth Development Program.