Effects of External Factors in CGM Sensor Glucose Concentration Prediction

It is naturally desirable to avoid hypo/hyperglycemic events andcommercial devices exist that can alert the patient before they occur. It is known, however, that percentage of false alerts for those devices is still high and much is still needed to be done to improve that.The purpose of this paper is to design a blood glucose prediction system that can be used aspart of a continuous glucose monitoring (CGM) device. With the help of a Kalman filter, glucose concentration is first reducedof its random noise component, and a neural network is then used for prediction of glucose upto two hours. Finally, this system is thoroughly tested for accuracy against various externalfactors. It is shown that such factors as patient's body weight, his/her exercise period andlifestyle may influence how well glucose concentration is predicted and therefore should betaken into account for early and accurate detection of hypo/hyperglycemic episodes.

[1]  Giovanni Sparacino,et al.  Online Denoising Method to Handle Intraindividual Variability of Signal-to-Noise Ratio in Continuous Glucose Monitoring , 2011, IEEE Transactions on Biomedical Engineering.

[2]  Giovanni Sparacino,et al.  An Online Self-Tunable Method to Denoise CGM Sensor Data , 2010, IEEE Transactions on Biomedical Engineering.

[3]  B. Buckingham,et al.  The extended Kalman filter for continuous glucose monitoring. , 2005, Diabetes technology & therapeutics.

[4]  Giuseppe De Nicolao,et al.  A new neural network approach for short-term glucose prediction using continuous glucose monitoring time-series and meal information , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[5]  D. B. Keenan,et al.  Delays in Minimally Invasive Continuous Glucose Monitoring Devices: A Review of Current Technology , 2009, Journal of diabetes science and technology.

[6]  Sensor calibration models for a non-invasive blood glucose measurement sensor , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[7]  G. Steil,et al.  The role of the independent variable to glucose sensor calibration. , 2003, Diabetes technology & therapeutics.

[8]  C. C. Palerm,et al.  Hypoglycemia prediction and detection using optimal estimation. , 2005, Diabetes technology & therapeutics.

[9]  S. Kun,et al.  Development of a non-invasive blood glucose monitor: application of artificial neural networks for signal processing , 2000, Proceedings of the IEEE 26th Annual Northeast Bioengineering Conference (Cat. No.00CH37114).

[10]  S. Shanthi,et al.  Neural Network Based Filter for Continuous Glucose Monitoring : Online Tuning with Extended Kalman Filter Algorithm , 2012 .

[11]  Christopher E. Hann,et al.  Integral-based filtering of continuous glucose sensor measurements for glycaemic control in critical care , 2006, Comput. Methods Programs Biomed..

[12]  A. Nirmalkumar,et al.  Determination of Blood Glucose Concentration by Back Propagation Neural Network , 2010 .

[13]  Brent D. Cameron,et al.  Development of a Neural Network for Prediction of Glucose Concentration in Type 1 Diabetes Patients , 2008, Journal of diabetes science and technology.

[14]  B.W. Bequette,et al.  A Dual-Rate Kalman Filter for Continuous Glucose Monitoring , 2006, 2006 International Conference of the IEEE Engineering in Medicine and Biology Society.

[15]  Bruce A Buckingham,et al.  Evaluation of factors affecting CGMS calibration. , 2006, Diabetes technology & therapeutics.