Abstract
This paper presents a neural network-based system for the computation of appropriate hourly insulin doses for insulin-pumps adjustments, using short historical discontinuous measurements of blood glucose levels. Our database consists of 25000 records of blood glucose measurements and corresponding insulin doses levels adjustments. Ten discontinuous measurements per day were carried out on 747 patients under pump treatment. In order to predict the next-time insulin-dose, one neural network for each period have been trained. So, each one of the ten neural networks specialized to a specific period of the day. The efficient data concept is introduced. Training with efficient learning data allowed to achieve very good generalization on both efficient and non-efficient data. A computer program based on the trained neural networks is under clinical validation test. A neural network-based injection-pump is also beeing prototyped.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
P. Ladyzinski, J. Wojcicki and J. Blachowicz, “Prediction of the insulin doses during long-term intensive insulin treatment in diabetic pregnant women using fuzzy logic technique,” in 3rd Symposium on Computers In Diabetes, 1996.
F. Skrabal, Z. Trajanoski, H. Kontschieder, P. Kotanko, and P. Wach, “Portable system for on-line continuous ex vivo monitoring of subcutaneous tissue glucose using open tissue perfusion,” in Med & Biol Eng Comp, vol. 33, pp. 116–118, 1995.
S. Andreassen, J.J. Benn, R. Hovorka, K.G. Olesen and E.R. Carson, “A probabilistic approach to glucose prediction an insulin dose adjustment,” Comput. Methods Programs Biomed., no. 41, pp. 153–165, 1994.
T. Deutsch, E.D. Lehmann, E.R. Carson, A.V. Roudsari, K.D. Hopkins and P.H. Sönksen, “Time series analysis and control of blood levels in diabetic patients,” Comput. Methods Programs Biomed., no. 41, pp. 167–182, 1994.
Z. Trajanoski and P. Wach, “Regularization networks for glucose system identification,” in Proc 16th Ann Int Conf IEEE Eng Med Biol Soc, Baltimore, USA, pp. 1083–1084, 1994.
D. E. Rumelhart, J. L. McClelland, and PDP Research Group, Parallel Distributed Processing: Exploration in the Microstructure of Cognition, vol. 1 & 2. Cambridge, MA; MIT Press, 1986.
M. Pinget, M. Milgram, N. Jeandidier, F. Andrianasy, S. Boivin and Ph.Friess, “Intravenous glucose controlled insulin infusion using discontinuous capillary blood glucose measurements by means of neural network,” 9th Biennal ISIGIID Meeting, 1996.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Andrianasy, F., Milgram, M. (1997). Neural network-based insulin infusion control for an insulin-pump, using discontinuous blood glucose measurements. In: Mira, J., Moreno-Díaz, R., Cabestany, J. (eds) Biological and Artificial Computation: From Neuroscience to Technology. IWANN 1997. Lecture Notes in Computer Science, vol 1240. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0032557
Download citation
DOI: https://doi.org/10.1007/BFb0032557
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63047-0
Online ISBN: 978-3-540-69074-0
eBook Packages: Springer Book Archive