Liu, Yang and Zhao, Zhijie and Wang, Jiaying and Li, Ang and Zhang, Jialin (2019) Research on Diabetes Management Strategy Based on Deep Belief Network. In: Wireless and Satellite Systems. 10th EAI International Conference, WiSATS 2019, Harbin, China, January 12–13, 2019, Proceedings, Part I.
31601.pdf
Download (248kB)
Abstract
Diabetes is a chronic disease that seriously endangers human health. Early detection, early diagnosis and early treatment can reduce the possibility of diabetic complications and mortality, which can be solved effectively by prediction model, assisting doctors to make more comprehensive and reliable diagnosis and treatment decisions, and improving diabetes management strategies. Thus, a diabetes prediction model based on Deep Belief Network (DBN) is proposed. Based on the Pima Indians Diabetes data set, the relative strength between the input attributes and the output targets of the model is calculated by using the weight matrix among the layers of the DBN diabetes prediction model. The results showed that plasma glucose concentration, body mass index, diabetic pedigree function, gestational frequency and age are important indexes for diabetes diagnosis. Then, this paper proposes three management strategies, including diabetes prevention education, diabetes individual prevention and diabetes community prevention to improve the management and control of diabetes in China.
| Item Type: | Conference or Workshop Item (UNSPECIFIED) |
|---|---|
| Date Deposited: | 04 Mar 2026 12:02 |
| Last Modified: | 20 Nov 2026 11:12 |
| URI: | https://eprints.eai.eu/id/eprint/22411 |
