Application of machine learning algorithm incorporating dietary intake in prediction of gestational diabetes mellitus
XGBoost and LightGBM algorithms outperform logistic regression in predicting GDM among Chinese pregnant women. In addition, dietary data may have a positive effect on improving model performance, which deserves more in-depth investigation with larger sample size.
Authors
- Tianze Ding (ORCID: https://orcid.org/0009-0006-7425-2093)
- Jie Zhu (ORCID: https://orcid.org/0000-0001-5304-7708)
- Kefeng Yang (ORCID: https://orcid.org/0000-0002-6973-6150)
- Peijie Liu (ORCID: https://orcid.org/0000-0002-1847-3952)
- Jie Jia (ORCID: https://orcid.org/0000-0002-7024-1980)
- Hui Wu (ORCID: https://orcid.org/0000-0001-8748-9176)
Institutions
- Texas State University (US)
- Shanghai Jiao Tong University (CN)
- XinHua Hospital (CN)
- Shanghai University of Traditional Chinese Medicine (CN)
- Seventh People's Hospital of Shanghai (CN)
Publication Details
- Journal
- Endocrine Connections
- Published
- 2024-10-07
- DOI
- https://doi.org/10.1530/ec-24-0169
- Citations
- 7
- Primary Topic
- Artificial Intelligence in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 4.95
Funders
- Texas State University
- National Natural Science Foundation of China