Online prediction of subcutaneous glucose concentration for type 1 diabetes using empirical models and frequency-band separation

AIChE Journal

Volumn 60, Issue 2, 2014, Pages 574-584

  Zhao, Chunhui ^a,b,c   Dassau, Eyal ^a,b   Zisser, Howard C ^a,b   Jovanovič, Lois ^a,b   Doyle, Francis J ^a,b   Seborg, Dale E ^a,b  

^a University of California   (United States)

^b SANSUM DIABETES RESEARCH INSTITUTE   (United States)

^c STATE KEY LABORATORY OF INDUSTRIAL CONTROL TECHNOLOGY   (China)

Author keywords

Frequency band separation; Global model; Glucose prediction; Type 1 diabetes

Indexed keywords

AUTO REGRESSIVE MODELS; GLOBAL MODELING; GLUCOSE CONCENTRATION; LATENT VARIABLE MODELING; PROACTIVE MANAGEMENT; SHORT TERM PREDICTION; TYPE 1 DIABETES; TYPE 1 DIABETES MELLITUS;

FORECASTING; SEPARATION;

GLUCOSE;

EID: 84892440430     PISSN: 00011541     EISSN: 15475905     Source Type: Journal    
DOI: 10.1002/aic.14288     Document Type: Article

References (32)

1. Rubin RR, Peyrot M. Quality of life and diabetes. Diabetes Metab Res Rev. 1999;15:205-218.
2. Rabasa-Lhoret R, Garon J, Langelier H. Effects of meal carbohydrate content on insulin requirements in type 1 diabetic patients treated intensively with the basal-bolus (ultralente-regular) insulin regimen. Diabetes Care. 1999;22:667-673.
3. Bremer T, Gough DA. Is blood glucose predictable from previous values? A solicitation for data. Diabetes. 1999;48:445-451.
4. Finan DA, Palerm CC. Doyle III FJ, Effect of input excitation on the quality of empirical dynamic models for type 1 diabetes. AIChE J. 2009;55:1135-1146.
5. Trajanoski Z, Regittnig W, Wach P. Simulation studies on neural predictive control of glucose using the subcutaneous route. Comput Meth Prog Bio. 1998;56:133-139.
6. Dua P, Doyle FJ III, Pistikopoulos EN. Model-based blood glucose control for type 1 diabetes via parametric programming. IEEE Trans Biomed Eng. 2006;53:1478-1491.
7. Sparacino G, Zanderigo F, Corazza S, Maran A, Facchinetti A, Cobelli C. Glucose concentration can be predicted ahead in time from continuous glucose monitoring sensor time-series. IEEE Trans Biomed Eng. 2007;54:931-937.
8. Zanderigo F, Sparacino G, Kovatchev B, Cobelli C. Glucose prediction algorithms from continuous monitoring data: assessment of accuracy via continuous glucose error-grid analysis. J Diabetes Sci Technol. 2007;1:645-651.
9. Reifman J, Rajaraman S, Gribok A. Predictive monitoring for improved management of glucose levels. J Diabetes Sci Technol. 2007;1:478-486.
10. Eren-Oruklu M, Cinar A, Quinn L. Estimation of future glucose concentrations with subject-specific recursive linear models. Diabetes Technol Ther. 2009;9:438-450.
11. Eren-Oruklu M, Cinar A, Quinn L. Hypoglycemia prediction with subject-specific recursive time-series models. J Diabetes Sci Technol. 2010;4:25-33.
12. Finan DA, Zisser H, Jovanovič L. Practical issues in the identification of empirical models from simulated type 1 diabetes data. Diabetes Technol Ther. 2007;9:438-450.
13. Finan DA, Palerm CC, Doyle FJ III. Identification of empirical dynamic models from type 1 diabetes subject data. In: Proc. Am Control Conf. Seattle, WA, 2008;2099-2104.
14. Palerm CC, Willis JP, Desemone J. Hypoglycemia prediction and detection using optimal estimation. Diabetes Technol Ther. 2005;7:3-14.
15. Zhao CH, Dassau E, Harvey RA. Predictive glucose monitoring for type 1 diabetes using latent variable-based multivariate statistical analysis. In: Proc IFAC, Milano, Italy, Vol. 18. 2011;7012-7017.
16. Zhao CH, Dassau E, Jovanovič L. Predicting subcutaneous glucose concentration using latent variable (LV)-based statistical analysis method for type 1 diabetes mellitus. J Diabetes Sci Technol. 2012;6:617-633.
17. Gani A, Gribok AV, Lu YH. Universal glucose models for predicting subcutaneous glucose concentration in Humans. IEEE Trans Inf Technol Biomed. 2010;14:157-165.
18. Gani A, Gribok AV, Rajaraman S. Predicting subcutaneous glucose concentration in humans: data-driven glucose modeling. IEEE Trans Biomed Eng. 2009;56:246-254.
19. Tikhonov AN, Arsenin VY. Solutions of Ill-Posed Problems. Washington DC: Winston, 1977.
20. Ljung L. System Identification: Theory for the User. Upper Saddle River, NJ: Prentice-Hall, 1999.
21. Rahaghi FN, Gough DA. Blood glucose dynamics. Diabetes Technol Ther. 2008;10:81-94.
22. Grosman B, Dassau E, Zisser H. Zone model predictive control: a strategy to minimize hyper- and hypoglycaemic events. J Diabetes Sci Technol. 2010;4:961-975.
23. Lu YH, Gribok AV, Ward WK. The importance of different frequency bands in predicting subcutaneous glucose concentration in Type 1 diabetic patients. IEEE Trans Biomed Eng. 2010;57:1839-1846.
24. Noujaim SE, Horwitz D, Sharma M. Accuracy requirements for a hypoglycemia detector: an analytical model to evaluate the effects of bias, precision, and rate of glucose change. J Diabetes Sci Technol. 2007;1:652-668.
25. Stahl F, Johansson R. Diabetes mellitus modeling and short-term prediction based on blood glucose measurements. Math Biosci Eng. 2009;217:101-117.
26. Yu H, MacGregor JF. Post processing methods (PLS-CCA): simple alternatives to preprocessing methods (OSC-PLS). Chemometr Intell Lab Syst. 2004;73:199-205.
27. Cserhati T, Kosa A, Balogh S. Comparison of partial least-square method and canonical correlation analysis in a quantitative structure-retention relationship study. J Biochem Bioph Methods. 1998;36:131-141.
28. Anderson TW. Canonical correlation analysis and reduced rank regression in autoregressive models. Ann Stat. 2002;30:1134-1154.
29. Hardoon DR, Szedmak S, Shawe-Taylor J. Canonical correlation analysis: an overview with application to learning methods. Neural Comp. 2004;16:2639-2664.
30. Burnham AJ, Viveros R, MacGregor JF. Frameworks for latent variable multivariate regression. J Chemometr. 1996;10:31-45.
31. Dayal B, Macgregor JF. Improved PLS algorithms. J Chemometr. 1997;11:73-85.
32. Lindgren F, Geladi P, Wold S. The kernel algorithm for PLS. J Chemometr. 1993;7:45-59.