Neural modeling of the blood glucose level for Type 1 Diabetes Mellitus patients

This paper presents the application of a recurrent multilayer perceptron neural network for modeling blood glucose dynamics in Type 1 Diabetes Mellitus (T1DM). Training is performed based on an extended Kalman filtering (EKF) learning algorithm. Then, the EKF performance is compared with the well-known Levenberg-Marquardt (LM) learning algorithm. The goal is to derive a dynamical mathematical model for T1DM considering the response of a patient to meal and subcutaneous insulin infusion. Thus, the main contribution of this work is to propose a modeling methodology for blood glucose dynamics based in Artificial Neural Networks (ANN). Experimental data, given by a continuous glucose monitoring system, are utilized for identification purposes and for applicability trials of the proposed scheme in T1DM therapy.