A Hybrid Dynamic Wavelet-Based Modeling Method for Blood Glucose Concentration Prediction in Type 1 Diabetes

Mohsen Kharazihai Isfahani, Maryam Zekri, Hamid Reza Marateb, Elham Faghihimani

DOI: 10.4103/jmss.JMSS_62_19


Background: Diabetes mellitus (DM) is a chronic disease that affects public health. The prediction of blood glucose concentration (BGC) is essential to improve the therapy of type 1 DM (T1DM). Methods: Having considered the risk of hyper- and hypo-glycemia, we provide a new hybrid modeling approach for BGC prediction based on a dynamic wavelet neural network (WNN) model, including a heuristic input selection. The proposed models include a hybrid dynamic WNN (HDWNN) and a hybrid dynamic fuzzy WNN (HDFWNN). These wavelet-based networks are designed based on dominant wavelets selected by the genetic algorithm-orthogonal least square method. Furthermore, the HDFWNN model structure is improved using fuzzy rule induction, an important innovation in the fuzzy wavelet modeling. The proposed networks are tested on real data from 12 T1DM patients and also simulated data from 33 virtual patients with an UVa/ Padova simulator, an approved simulator by the US Food and Drug Administration. Results: A comparison study is performed in terms of new glucose-based assessment metrics, such as gFIT, glucose-weighted form of ESODn (gESODn), and glucose-weighted R2 (gR2). For real patients’ data, the values of the mentioned indices are accomplished as gFIT = 0.97 ± 0.01, gESODn = 1.18 ± 0.38, and gR2 = 0.88 ± 0.07. HDFWNN, HDWNN and jump NN method showed the prediction error (root mean square error [RMSE]) of 11.23 ± 2.77 mg/dl, 10.79 ± 3.86 mg/dl and 16.45 ± 4.33 mg/dl, respectively. Conclusion: Furthermore, the generalized estimating equation and post hoc tests show that proposed models perform better compared with other proposed methods.


Blood glucose prediction, diabetes mellitus, fuzzy rule induction, fuzzy wavelet neural network, wavelet neural network

Full Text:



Hall JE. Guyton and Hall Textbook of Medical Physiology. 13rd ed. Philadelphia, PA: Elsevier; 2016. p. 19, 1145.

Cho NH, Shaw JE, Karuranga S, Huang Y, da Rocha Fernandes JD, Ohlrogge AW, et al. IDF Diabetes Atlas: Global estimates of diabetes prevalence for 2017 and projections for 2045. Diabetes Res Clin Pract 2018;138:271-81.

Schlienger JL. Complications du diabete de type 2. La Presse Medicale 2013;42:839-48.

Fattah H, Vallon V. The potential role of SGLT2 inhibitors in the treatment of type 1 diabetes mellitus. Drugs 2018;78:717-26.

Smith B, Sarver JG, Fournier RL. A comparison of islet transplantation and subcutaneous insulin injections for the treatment of diabetes mellitus. Comput Biol Med 1991;21:417-27.

Wong XW. Model-Based Therapeutics for Type 1 Diabetes Mellitus. 2008.

Das S, Nath A, Dey R, Chaudhury S, editors. Glucose regulation in diabetes patients via insulin pump: A feedback linearisation approach. In: Innovations in Infrastructure. Singapore: Springer; 2019.

Copp DA, Gondhalekar R, Hespanha JP. Simultaneous model predictive control and moving horizon estimation for blood glucose regulation in Type 1 diabetes. Optim Contr Appl Met 2018;39:904-18.

Zhang R, Xue A, Gao F. Model predictive control under constraints. In: Model Predictive Control: Approaches Based on the Extended State Space Model and Extended Non-minimal State Space Model. Singapore: Springer Singapore; 2019. p. 59-63.

Zhang S. Wavelet Adaptive and Predictive Control with Applications to Chemical Looping System [Dissertation]. Mechanical Engineering: University of Illinois at Urbana-Champaign; 2014.

Shi D, Dassau E, Doyle FJ. Adaptive Zone Model Predictive Control of Artificial Pancreas Based on Glucose- and Velocity-Dependent Control Penalties. IEEE Trans Biomed Eng 2019;66:1045-54.

Srinivasan C, Meenatchisundaram S, George VJJoARiD, Systems C. Design and Realization of MPC Controller for Type 1 Diabetes System. J Dyn Control Syst 2018;10:1-8.

Laguna Sanz AJ, Doyle FJ 3rd, Dassau E. An Enhanced Model Predictive Control for the Artificial Pancreas Using a Confidence Index Based on Residual Analysis of Past Predictions. J Diabetes Sci Technol 2017;11:537-44. Back to cited text no. 13

Nimri R, Audon P, Pinsker JE, Dassau E. Closing the Loop. Diabetes Technol Ther 2018;20:S41-54.

Stahl F, Johansson R. Diabetes mellitus modeling and short-term prediction based on blood glucose measurements. Math Biosci 2009;217:101-17.

Oviedo S, Vehi J, Calm R, Armengol J. A review of personalized blood glucose prediction strategies for T1DM patients. Int J Numer Method Biomed Eng 2017;33:e2833.

Solomatine D, See LM, Abrahart RJ. Data-Driven Modelling: Concepts, Approaches and Experiences. In: Abrahart RJ, See LM, Solomatine DP, editors. Practical Hydroinformatics: Computational Intelligence and Technological Developments in Water Applications. Berlin, Heidelberg: Springer Berlin Heidelberg; 2008. p. 17-30.

Contreras I, Oviedo S, Vettoretti M, Visentin R, Vehi J. Personalized blood glucose prediction: A hybrid approach using grammatical evolution and physiological models. PLoS One 2017;12:e0187754.

Dalla Man C, Camilleri M, Cobelli C. A system model of oral glucose absorption: Validation on gold standard data. IEEE Trans Biomed Eng 2006;53:2472-8.

Dalla Man C, Raimondo DM, Rizza RA, Cobelli C. GIM, simulation software of meal glucose-insulin model. J Diabetes Sci Technol 2007;1:323-30.

Zecchin C. Online Glucose Prediction in Type-1 Diabetes by Neural Network Models; 2014.

Ben Ali J, Hamdi T, Fnaiech N, Di Costanzo V, Fnaiech F, Ginoux JM. Continuous blood glucose level prediction of type 1 diabetes based on artificial neural network. Biocybern Biomed Eng 2018;38:828-40.

Quchani SA, Tahami E, editors. Comparison of MLP and Elman Neural Network for Blood Glucose Level Prediction in Type 1 Diabetics. Berlin, Heidelberg: Springer Berlin Heidelberg; 2007.

Baghdadi G, Nasrabadi AM. Controlling blood glucose levels in diabetics by neural network predictor. Conf Proc IEEE Eng Med Biol Soc 2007;2007:3216-9.

Zecchin C, Facchinetti A, Sparacino G, Cobelli C. Jump neural network for online short-time prediction of blood glucose from continuous monitoring sensors and meal information. Comput Methods Programs Biomed 2014;113:144-52.

Zekri M, Sadri S, Sheikholeslam F. Adaptive fuzzy wavelet network control design for nonlinear systems. Fuzzy Sets Syst. 2008;159:2668-95.

Zhang Q, Benveniste A. Wavelet networks. IEEE Trans Neural Netw 1992;3:889-98.

Billings SA, Wei HL. A new class of wavelet networks for nonlinear system identification. IEEE Trans Neural Netw 2005;16:862-74.

Zainuddin Z, Pauline O, Ardil CJ. A neural network approach in predicting the blood glucose level for diabetic patients. Int J Comput Intell 2009;5:72-9.

Elleri D, Allen JM, Kumareswaran K, Leelarathna L, Nodale M, Caldwell K, et al. Closed-loop basal insulin delivery over 36 hours in adolescents with type 1 diabetes: Randomized clinical trial. Diabetes Care 2013;36:838-44.

Man CD, Micheletto F, Lv D, Breton M, Kovatchev B, Cobelli C. The UVA/PADOVA Type 1 Diabetes Simulator: New Features. J Diabetes Sci Technol 2014;8:26-34.

Zecchin C, Facchinetti A, Sparacino G, De Nicolao G, Cobelli C. Neural network incorporating meal information improves accuracy of short-time prediction of glucose concentration. IEEE Trans Biomed Eng 2012;59:1550-60.

Bock A, Francois G, Gillet D. A therapy parameter-based model for predicting blood glucose concentrations in patients with type 1 diabetes. Comput Methods Programs Biomed 2015;118:107-23.

Dalla Man C, Rizza RA, Cobelli C. Meal simulation model of the glucose-insulin system. IEEE Trans Biomed Eng 2007;54:1740-9.

Billings SA. Nonlinear system identification: NARMAX Methods in the Time, Frequency, and Spatio-Temporal Domains: Chichester, UK: John Wiley & Sons; 2013.

Georga EI, Protopappas VC, Polyzos D, Fotiadis DI. Evaluation of short-term predictors of glucose concentration in type 1 diabetes combining feature ranking with regression models. Med Biol Eng Comput 2015;53:1305-18.

Garcia-Garcia F, Hovorka R, Wilinska ME, Elleri D, Hernando ME. Modelling the effect of insulin on the disposal of meal-attributable glucose in type 1 diabetes. Med Biol Eng Comput 2017;55:271-82.

Dankers A, Hof PM, Bombois X, Heuberger PS. Identification of dynamic models in complex networks with prediction error methods: Predictor input selection. IEEE Trans Automat Contr 2016;61:937-52.

Korenberg M, Billings SA, Liu YP, McIlroy PJ. Orthogonal parameter estimation algorithm for non-linear stochastic systems. Int J Contr 1988;48:193-210.

Mao KZ, Billings SA. Algorithms for minimal model structure detection in nonlinear dynamic system identification. Int J Contr 1997;68:311-30.

Madar J, Abonyi J, Szeifert F. Genetic programming for the identification of nonlinear input – Output models. Ind Eng Chem Res 2005;44:3178-86.

Kharazihai Isfahani M, Zekri M, Marateb HR, Mananas MA. Fuzzy jump wavelet neural network based on rule induction for dynamic nonlinear system identification with real data applications. PLoS One 2019;14:e0224075.

Berger M, Rodbard D. Computer simulation of plasma insulin and glucose dynamics after subcutaneous insulin injection. Diabetes Care 1989;12:725-36.

Lehmann ED, Deutsch T. A physiological model of glucose-insulin interaction in type 1 diabetes mellitus. J Biomed Eng 1992;14:235-42.

Sadri AR, Zekri M, Sadri S, Gheissari N, Mokhtari M, Kolahdouzan F. Segmentation of Dermoscopy Images Using Wavelet Networks. IEEE Trans Bio-Med Eng 2013;60:1134-41.

Sparacino G, Zanderigo F, Corazza S, Maran A, Facchinetti A, Cobelli C. Glucose concentration can be predicted ahead in time from continuous glucose monitoring sensor time-series. IEEE Trans Biomed Eng 2007;54:931-7.

Del Favero S, Facchinetti A, Cobelli C. A glucose-specific metric to assess predictors and identify models. IEEE Trans Biomed Eng 2012;59:1281-90. Back to cited text no. 48

Ma Y, Mazumdar M, Memtsoudis SG. Beyond repeated-measures analysis of variance: Advanced statistical methods for the analysis of longitudinal data in anesthesia research. Reg Anesth Pain Med 2012;37:99-105.

Vermeulen KM, Post WJ, Span MM, van der Bij W, Koeter GH, Ten Vergert EM. Incomplete quality of life data in lung transplant research: Comparing cross sectional, repeated measures ANOVA, and multi-level analysis. Respir Res 2005;6:101.


  • There are currently no refbacks.