A Nonlinear State Space Model for the Blood Glucose Metabolism of a Diabetic (Ein nichtlineares Zustandsraummodell für den Blutglukosemetabolismus eines Diabetikers)

The blood glucose metabolism of a diabetic is a complex nonlinear process closely linked to a number of internal factors which are not easily accessible to measurement. Based on accessible information – such as occasional blood glucose measurements and information about food intake and physical exercise – the system appears highly stochastic and the quantity of main interest, the blood glucose concentration, is very difficult to model and to predict. In this paper we describe a stochastic nonlinear state space model for modeling the blood glucose concentration of a diabetic patient. The model structure is based on physiological prior knowledge and the main nonlinearities are modeled using artificial neural networks. Offline training of the model is performed using a newly developed Monte-Carlo generalized EM (expectation maximization) algorithm. Online prediction is performed using particle filters. Our experimental results show that our approach provides better prediction results than a number of competing approaches.

[1]  Volker Tresp,et al.  Neural-network models for the blood glucose metabolism of a diabetic , 1999, IEEE Trans. Neural Networks.

[2]  Volker Tresp,et al.  Fisher Scoring and a Mixture of Modes Approach for Approximate Inference and Learning in Nonlinear State Space Models , 1998, NIPS.

[3]  K. Prank,et al.  Predictive Neural Networks for Learning the Time Course of Blood Glucose Levels from the Complex Interaction of Counterregulatory Hormones , 1998, Neural Computation.

[4]  Volker Tresp,et al.  A Solution for Missing Data in Recurrent Neural Networks with an Application to Blood Glucose Prediction , 1997, NIPS.

[5]  S Andreassen,et al.  DIAS--the diabetes advisory system: an outline of the system and the evaluation results obtained so far. , 1997, Computer methods and programs in biomedicine.

[6]  V. Tresp,et al.  Missing and noisy data in nonlinear time-series prediction , 1995, Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing.

[7]  Petros G. Voulgaris,et al.  On optimal ℓ∞ to ℓ∞ filtering , 1995, Autom..

[8]  Lee A. Feldkamp,et al.  Neurocontrol of nonlinear dynamical systems with Kalman filter trained recurrent networks , 1994, IEEE Trans. Neural Networks.

[9]  N. Gordon,et al.  Novel approach to nonlinear/non-Gaussian Bayesian state estimation , 1993 .

[10]  L. Fahrmeir,et al.  On kalman filtering, posterior mode estimation and fisher scoring in dynamic exponential family regression , 1991 .

[11]  P L Miller,et al.  Combining statistical, rule-based, and physiologic model-based methods to assist in the management of diabetes mellitus. , 1990, Computers and biomedical research, an international journal.

[12]  E Salzsieder,et al.  Computer-aided systems in the management of type I diabetes: the application of a model-based strategy. , 1990, Computer methods and programs in biomedicine.

[13]  E R Carson,et al.  Computer-assisted diabetic management: a complex approach. , 1990, Computer methods and programs in biomedicine.

[14]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[15]  A. Schiffrin,et al.  Computer-assisted Insulin Dosage Adjustment , 1985, Diabetes Care.

[16]  Abderrahmane Haddad,et al.  Estimation theory with applications to communications and control , 1972 .

[17]  V. Tresp,et al.  Dynamic Neural Regression Models , 2000 .

[18]  E. Carson,et al.  A probabilistic approach to glucose prediction and insulin dose adjustment: description of metabolic model and pilot evaluation study. , 1994, Computer methods and programs in biomedicine.

[19]  R. Engelbrecht,et al.  DIACONS — A Consultation System to Assist in the Management of Diabetes , 1988 .

[20]  E. Carson,et al.  Diabeta — An Expert System for the Management of Diabetes , 1986 .

[21]  M. Berger,et al.  Praxis der Insulintherapie , 1983 .