Prediction of Blood Glucose Level Using Nonlinear System Identification Approach

Ibrahim Aljamaan,Ibraheem Al-Naib

doi:10.1109/access.2021.3139578

Ibrahim Aljamaan, Ibraheem Al-Naib

Open Access

https://doi.org/10.1109/access.2021.3139578

Copy DOI

Journal: IEEE Access	Publication Date: Jan 1, 2022
Citations: 10	License type: CC BY 4.0

Affiliation: Imam Abdulrahman Bin Faisal University

Abstract

Predicting the blood glucose level of type 1 diabetes mellitus of patients could prevent hypo/hyperglycemia incidents that are threats for the patients with this disease. A nonlinear system identification approach is proposed in this work to develop a mathematical model, which can be used to predict the blood glucose level over a given period with high accuracy. More specifically, the Hammerstein Box-Jenkins model is used to approximate the system, where two infinite impulse response filters represent the linear and noise processes, and a polynomial basis function represents the nonlinearity. The proposed identification method is based on the Steiglitz-McBride approach to predict the model parameters. Moreover, a simulation software licensed by the USA Food and Drug Administration that simulates the dynamics of the glucose-insulin system metabolism inside the body, called Type I Diabetes Metabolic Simulator (T1DMS), was used to generate the data. Thirty subjects of different age groups were considered, and the data was generated for a week with a sample per minute, i.e. 302430 data points. This data was then processed using a developed MATLAB code to predict the blood glucose level. Various scenarios were established to validate the proposed approach. The simulations showed very promising results with a very low average root mean square error of 1 mg/dl, which is seven times less compared to other prediction techniques. Other cost functions have also been used and they showed very good results. In the future, this approach can be embedded in closed-loop continuous blood glucose monitoring systems in order to give alerts to the patients and help in calculating the needed insulin dose.

Highlights

According to the World Health Organization, diabetes is defined as a lifelong disease, where the patients’ pancreas either stops producing insulin, known as type 1 diabetes, or the generated insulin cannot be efficiently used by the patients’ body, which is known as type 2 diabetes
Continuous Glucose Monitoring (CGM) is applied with a sampling time of 1 minute for a week-long term, where the input/outputs are the insulin injection rate and the blood glucose (BG) level in units U and mg/dl, respectively
The maximum prediction horizon was 96 hours which is presented in Ref. [49] but with an average root mean square error (RMSE) of 40 mg/dl, which is almost 40 times greater than the results found using the nonlinear system identification approach in this paper

Summary

Introduction

According to the World Health Organization, diabetes is defined as a lifelong disease, where the patients’ pancreas either stops producing insulin, known as type 1 diabetes, or the generated insulin cannot be efficiently used by the patients’ body, which is known as type 2 diabetes. Type 1 diabetes (T1D) affects a large number of children and teenagers [2]. One of the most common threats for T1D patients is hypo-glycemia, where the blood glucose (BG) level decreases below 70 mg/dl. This might lead to fatal consequences, such as unconsciousness or even death [3]. It is advantageous to predict the level of glucose for the 30 to 60 minutes or even more to have better management of it and to avoid any consequences. The focus of this work is to predict glucose levels with high accuracy for type 1 diabetes over a period of one hour to a few days

Objectives

Methods

Results

Conclusion