Modelling of blood glucose profiles non-invasively using a neural network algorithm

Author

Ghevondian, N. ; Nguyen, H.

Author_Institution

Fac. of Eng., Univesity of Technol., Sydney, NSW, Australia

Volume

2

fYear

1999

fDate

36434

Abstract

Monitoring blood glucose levels of Insulin-Dependent-Diabetes-Mellitus (IDDM) is essential for detecting onset of hypoglycaemia and hyperglycaemia. We have developed a method based on a neural network algorithm for estimating blood glucose levels non-invasively using only physiological parameters such as skin impedance and heart rate. Results have shown that an accuracy of 10% can be achieved

Keywords

backpropagation; biomedical measurement; blood; chemical variables measurement; computerised monitoring; feedforward neural nets; medical signal processing; neurophysiology; organic compounds; patient monitoring; physiological models; IDDM; Insulin-Dependent-Diabetes-Mellitus; backpropagation training; blood glucose profiles; heart rate; hyperglycaemia; hypoglycaemia; monitoring; multilayer feedforward neural network; neural network algorithm; noninvasive modelling; physiological parameters; skin impedance; Biological neural networks; Biomedical monitoring; Blood; Diabetes; Heart rate; Impedance; Multi-layer neural network; Neural networks; Skin; Sugar;

fLanguage

English

Publisher

ieee

Conference_Titel

[Engineering in Medicine and Biology, 1999. 21st Annual Conference and the 1999 Annual Fall Meetring of the Biomedical Engineering Society] BMES/EMBS Conference, 1999. Proceedings of the First Joint

Conference_Location

Atlanta, GA

ISSN

1094-687X

Print_ISBN

0-7803-5674-8

Type

conf

DOI

10.1109/IEMBS.1999.804082

Filename

804082