Title :
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
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;
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
Print_ISBN :
0-7803-5674-8
DOI :
10.1109/IEMBS.1999.804082
