Glycemia Prediction Accuracy of Simple Linear Models with Online Parameter Identification

Matúš Rebro; Marián Tárník; Ján Murgaš

doi:10.15866/iremos.v9i5.10171

Glycemia Prediction Accuracy of Simple Linear Models with Online Parameter Identification

Matúš Rebro^(1*), Marián Tárník⁽²⁾, Ján Murgaš⁽³⁾

^(*) Corresponding author

Authors' affiliations

DOI: https://doi.org/10.15866/iremos.v9i5.10171

Abstract

This paper deals with the glycemia prediction accuracy comparison of 7 simple linear model structures, with prediction based on Continuous Glucose Monitoring (CGM) data. Different model structures presented are ARX, ARMAX and Box Jenkins models and their single and multiple input variations, which can represent known or not known meal intake. For each model structure the recursive parameter identification algorithm is presented. All prediction model structures are tested on 7 selected CGM datasets of several type 1 diabetes subjects, acquired in DiaDAQ project. Prediction performance is evaluated using a model fit metrics and an error grid analysis. The results show good prediction performance with low variability among different model structures, despite the simplicity of the prediction algorithm.
Copyright © 2016 Praise Worthy Prize - All rights reserved.

Keywords

Glycemia Prediction; Diabetes; CGM; ARX; ARMAX; Box Jenkins; Recursive Least Squares; Error Grid Analysis

Full Text:

PDF

References

M. S. Boyne, D. M. Silver, J. Kaplan, and C. D. Saudek, Timing of changes in interstitial and venous blood glucose measured with a continuous subcutaneous glucose sensor, Diabetes, Vol. 55(No.11): 2790-2794, 2003.
http://dx.doi.org/10.2337/diabetes.52.11.2790

D. B. Keenan, J. J. Mastrototaro, G. Voskanyan, and G. M. Steil, Delays in minimally invasive continuous glucose monitoring devices: A review of current technology, J Diabetes SciTechnol, Vol. 3(No.5): 1207-1214, 2009.
http://dx.doi.org/10.1177/193229680900300528

A. R. Maurizi and P. Pozzilli, Do we need continuous monitoring in type 2 diabetes ?, Diabetes Metab Res Rev, 2013.
http://dx.doi.org/10.1002/dmrr.2450

C. Cobelli, E. Renard, and B. Kovatchev, Artificial pancreas: Past, present, future, Diabetes, Vol. 60(No.11): 2672-2682, 2011.
http://dx.doi.org/10.2337/db11-0654

M. M. Nærum, Model predictive control for insulin administration in people with type 1 diabetes,Master’s thesis, Technical University of Denmark Informatics and Mathematical Modelling, 2010.
http://dx.doi.org/10.1186/isrctn13984129

D. Boiroux, V. Bátora, M. Hagdrup, M. Tárník, J. Murgaš, S. Schmidt, K. Nørgaard, N. K. Poulsen, H. Madsen, and J. B. Jørgensen, Comparison of prediction models for a dual-hormone artificial pancreas, 9th IFAC Symposium on Biological and Medical Systems, 2015.
http://dx.doi.org/10.1016/j.ifacol.2015.10.106

M. Cescon, Modeling and Prediction in Diabetes Physiology, Ph.D. dissertation, Department of Automatic Control, Lund University, Sweden, 2013.
http://dx.doi.org/10.1007/978-3-642-54464-4_9

L. Ljung, System Identification (2nd Ed.): Theory for the User.(Prentice-Hall, 1999).
http://dx.doi.org/10.1109/mra.2012.2192817

K. J. Astrøm, B. Wittenmark, Adaptive Control: Second Edition. (Dover Publications, 2008).
http://dx.doi.org/10.2307/1269433

J. Jia, H. Huang, Y. Yang, K. Lv, and F. Ding, Two-stage least squares based iterative identification algorithm for box-jenkins model, Applied Mathematics & Information Sciences, Vol. 8(No.3): 1355-1360, 2014.
http://dx.doi.org/10.12785/amis/080352

W. L. Clarke, D. Cox, L. A. Gonder-Frederick,W. Carter, and S. L. Pohl, Evaluating clinical accuracy of systems for self-monitoring of blood glucose, Diabetes Care, Vol. 10(No.5): 622-628, 1987.
http://dx.doi.org/10.2337/diacare.10.5.622

B. P. Kovatchev, D. J. Cox, L. A. Gonder-Frederick, and W. L. Clarke, Evaluating the accuracy of continuous glucose-monitoring sensors, Diabetes Care, Vol. 27(No.8): 1922-1928, 2004.
http://dx.doi.org/10.2337/diacare.27.8.1922

Tárník, M., Bátora, V., Ludwig, T., Ottinger, I., Miklovičová, E., Murgaš, J., Prediction of Glycemia Based on Diabetes Self-Monitoring Data, (2015) International Review of Automatic Control (IREACO), 8 (2), pp. 113-119.
http://dx.doi.org/10.15866/ireaco.v8i2.5232

R. Arahal, M., Barrero, F., Durán, M., Martín, C., Harmonic Distribution in Finite State Model Predictive Control, (2015) International Review of Electrical Engineering (IREE), 10 (2), pp. 172-179.
http://dx.doi.org/10.15866/iree.v10i2.5609

Molina-Cabrera, A., Rios, M., A Kalman Latency Compensation Strategy for Model Predictive Control to Damp Inter-Area Oscillations in Delayed Power Systems, (2016) International Review of Electrical Engineering (IREE), 11 (3), pp. 296-304.
http://dx.doi.org/10.15866/iree.v11i3.8661

Kulkarni, S., Wagh, S., Singh, N., Challenges in Model Predictive Control Application for Transient Stability Improvement Using TCSC, (2015) International Review of Automatic Control (IREACO), 8 (2), pp. 163-169.
http://dx.doi.org/10.15866/ireaco.v8i2.5562

Vozák, D., Veselý, V., Stable Predictive Control with Input Constraints Based on Variable Gain Approach, (2014) International Review of Automatic Control (IREACO), 7 (2), pp. 131-139.
http://dx.doi.org/10.15866/ireaco.v7i2.707

El Kachani, A., Chakir, E., Jarou, T., Ait Laachir, A., Zerouaoui, J., Hadjoudja, A., Robust Model Predictive Control Applied to a WRIG-Based Wind Turbine, (2016) International Review of Automatic Control (IREACO), 9 (4), pp. 216-226.
http://dx.doi.org/10.15866/ireaco.v9i4.8670

Saletovic, E., APM – Simple and Fast MPC Algorithm for LTI SISO Systems, (2014) International Review of Automatic Control (IREACO), 7 (4), pp. 420-427.

Refbacks

There are currently no refbacks.

Username
Password
Remember me