A Neural Network Approach in Predicting the Blood Glucose Level for Diabetic Patients

Authors: Zarita Zainuddin, Ong Pauline, C. Ardil

Abstract:

Diabetes Mellitus is a chronic metabolic disorder, where the improper management of the blood glucose level in the diabetic patients will lead to the risk of heart attack, kidney disease and renal failure. This paper attempts to enhance the diagnostic accuracy of the advancing blood glucose levels of the diabetic patients, by combining principal component analysis and wavelet neural network. The proposed system makes separate blood glucose prediction in the morning, afternoon, evening and night intervals, using dataset from one patient covering a period of 77 days. Comparisons of the diagnostic accuracy with other neural network models, which use the same dataset are made. The comparison results showed overall improved accuracy, which indicates the effectiveness of this proposed system.

Keywords: Diabetes Mellitus, principal component analysis, time-series, wavelet neural network.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1082155

References:

[1] World Health Organization. Available: http://www.who.int
[2] American Diabetes Asscociation. Available: http://www.diabetes.org
[3] Gan, D. editor. Diabetes atlas, 2nd ed. Brussels: International Diabetes Federation, 2003. Available at http://www.eatlas.idf.org/webdata/docs/Atlas%202003-Summary.pdf
[4] C.V. Doran, N.H. Hudson,K.T. Moorhead, J.G. Chase, G.M. Shaw, and C.E. Hann, "Derivative weighted active insulin control modeling and clinical trials for ICU patients," Medical Engineering and Physics, vol. 26, pp. 855-866, 2004.
[5] P. Dua, F.J. Doyle III, E.N. Pistikopoulos, "Model-based blood glucose control for type I diabetes via parametric programming," IEEE Transactions on Biomedical Engineering, vol. 53, pp. 1478-1491, 2006.
[6] C. Owens, H. Zisser, L. Jovanovic, B. Srinivasan, D. Bonvin, and F.J. Doyle III, "Run-to-run control of blood glucose concentrations for people with type I diabetes mellitus," IEEE Transactions on Biomedical Engineering, vol. 53, pp. 996-1005, 2006.
[7] P.G. Fabietti, V. Canonico, M.O. Federici, M. Massimo, and E. Sarti, "Control oriented model of insulin and glucose dynamics in type I diabetics," Medical and Biological Engineering and Computing, vol. 44, pp. 69-78, 2006.
[8] M.S. Ibbini, M.A. Masadeh, and M.M.B. Arner, "A semiclosed-loop optimal control system for blood glucose level in diabetics," Journal of Medical Engineering and Technology, vol. 28, pp. 189-196, 2004.
[9] B.R. Chang, and H.F. Tsai, "Forecast approach using neural network adaption to support vector regression grey model and generalized auto-regressive conditional heteroscedasticity,: Expert Systems with Application, vol. 34, pp. 925-934, 2008.
[10] M. Engin, S. Demirag, E.Z. Engin, G. Celebi, F. Ersan, E. Asena, and Colako─ƒlu, "The classification of human tremor signals using artificial neural network," Expert Systems with Applications, vol. 33, pp. 754-761, 2007.
[11] M. Ture, and I. Kurt, "Comparison of four different time series methods to forecast hepatitis A virus infection," Expert Systems with Applications, vol. 31, pp. 41-46, 2006.
[12] A.K. El-Jabali, "Neural network modeling and control of type I diabetes mellitus," Bioprocess Biosystem Engineering, vol. 27, pp. 75-79, 2005.
[13] T.N. Hung, G. Nejhded, and W.J. Timothy, "Neural-network detection of Hypoglycemic episodes in children with type I diabetes using physiological parameters," Proceedings of the 28th IEEE EMBS Annual International Conference, New York, 2006, pp. 6053-6056.
[14] C. Li, and R. Hu, "PID control based on BP neural network for the regulation of blood glucose level in diabetes," Proceedings of the 7th International Conference on Bioinformatics and Bioengineering, Boston, pp. 1168-1172, 2007.
[15] J.J. Liszka-Hackzell, "Prediction of blood glucose levels in diabetic patients using a hybrid AI technique," Computers and Biomedical Research, vol. 32, pp. 132-144, 1999.
[16] S.G. Mougiakakou, A. Prountzou, D. Iliopoulou, K.S. Nikita, A.Vazeou, and C.S. Bartsocas, "Neural network based glucose-insulin metabolism models for children with type I diabetes," Proceedings of the 28th IEEE EMBS Annual International Conference, New York, 2006, pp. 3545-3548.
[17] K. Zarkogianni, S.G. Mougiakakou, A. Prountzou, A. Vazeou, C.S. Bartsocas, and K.S. Nikita, "An insulin infusion advisory system for type I diabetes patients based on non-linear model predictive control methods," Proceedings of the 29th IEEE EMBS Annual International Conference, Lyon, 2007, pp. 5971-5974.
[18] V. Tresp, T. Briegel, and J. Moody, "Neural-network models for the blood glucose metabolism for a diabetic," IEEE Transactions on Neural Networks, vol. 10, pp. 1204-1213, 1999.
[19] D. Dazzi, F. Taddei, A. Gavarini, E. Uggeri, R. Negro, and A. Pezzarossa, "The control of blood glucose in the critical diabetic patient: A neuro-fuzzy approach," Journal of Diabetes and Its Complications, vol. 15, pp. 80-87, 2001.
[20] Phee, H.K., Tung, W.L. & Quek, C. (2007). A personalized approach to insulin regulation using brain-inspired neural semantic memory in diabetic glucose control. IEEE Congress on Evolutionary Computation, Singapore, pp. 2644-2651.
[21] K. Polat, and S. G├╝nes, :An expert system approach based on principal component analysis and adaptive neuro-fuzzy inference system to diagnosis of diabetes disease," Digital Signal Processing, vol. 17, pp. 702-710, 2007.
[22] T.N. Hung, G. Nejhded, T.N. Son, and W.J. Timothy, "Detection of hypoglycemic episodes in children with type I diabetes using an optimal Bayesian neural network algorithm," Proceedings of the 29th IEEE EMBS Annual International Conference, Lyon, 2007, pp. 3140-3143.
[23] R. Abu Zitar, "Towards neural network model for insulin/glucose in diabetics," International Journal of Computing & Information Sciences, vol. 1, pp. 25-32, 2003.
[24] R. Abu Zitar, and A. Al-Jabali, "Towards neural network model for insulin/glucose in diabetics-II.," Informatica, vol. 29, pp. 227-232, 2005.
[25] P. Kok, "Prediction blood glucose levels of diabetics using artificial neural networks," Research Assignment for Master of Science, Delft University of Technology, 2004.
[26] S.A. Quchani, and E. Tahami, "Comparison of MLP and Elman neural network for blood glucose level prediction in type I diabetics," Proceedings of the 3rd International Federal of Medical and Biological Engineering, Kuala Lumpur, 2007, pp. 54-58.
[27] G. Baghdadi, and A.M. Nasrabadi, "Controlling blood glucose levels in diabetics by neural network predictor," Proceedings of the 29th Annual International Conference of the IEEE EMBS, Lyon, 2007, pp. 3216-3219.
[28] A.J. Richard, and W.W. Dean, Applied multivariate statistical analysis. New Jersey: Prentice-Hall, 2002, ch 4.
[29] Q. Zhang, "Using wavelet network in nonparametric estimation," IEEE Transactions on Neural Networks, vol. 8, pp. 227-236, 1997.
[30] Q. Zhang, and A. Beveniste, "Wavelet Networks," IEEE Transactions on Neural Networks, vol. 3, pp. 889-898, 1992.
[31] B. Biswal, P.K. Dash, B.K. Panigrahi, and J.B.V. Reddy, "Power signal classification using dynamic wavelet network," Applied Soft Computing, vol. 9, pp. 118-125, 2009.
[32] S. Srivastava, M. Singh, M. Hanmandlu, and A.N. Jha, "New fuzzy wavelet neural networks for system identification and control," Applied Soft Computing, vol. 6, pp. 1-17, 2005.
[33] H. Zhang, B. Zhang, W. Huang, and Q. Tian, "Gabor wavelet associated memory for face recognition," IEEE Transactions on Neural Networks, vol. 16, pp. 275-278, 2005.
[34] J.C. Hargreaves, "Timing of ice-age terminations determined by wavelet methods," Paleoceanography, vol. 18, pp. 1035-1048, 2003.