Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników
Tytuł artykułu

Accurate prediction of continuous blood glucose based on support vector regression and differential evolution algorithm

Warianty tytułu
Języki publikacji
Type 1 diabetes (T1D) is a chronic disease requiring patients to know their blood glucose values in order to ensure blood glucose levels as close to normal as possible. Hence, the ability to predict blood glucose levels is of a great interest for clinical researchers. In this sense, the literature is rich with several solutions that can predict blood glucose levels. Unfortunately, these methods require the patient to specific their daily activities: meal intake, insulin injection and emotional factors, which can be error prone. To reduce this burden on the patent, this work proposes to use only continuous glucose monitoring (CGM) data to predict blood glucose levels independently of other factors. To support this, support vector regression (SVR) and differential evolution (DE) algorithms were investigated. The proposed method is validated using real CGM data of 12 patients. The obtained average of root mean square error (RMSE) was 9.44, 10.78, 11.82 and 12.95 mg/dL for prediction horizon (PH) respectively equal to 15, 30, 45 and 60 min. The results of the present study and comparison with some previous works show that the proposed method holds promise. The SVR based on DE algorithm achieved high prediction accuracy while being robustness, automatic, and requiring no human intervention.
  • Université de Tunis, ENSIT, LR13ES03 SIME, Montfleury, Tunisia; Laboratoire d'Informatique et des Systèmes, UMR, CNRS 7020, Ecole d'Ingénieurs SeaTech, Université de Toulon, France
  • Centre Hospitalier Intercommunal de Toulon La Seyne, 54, rue Henri Sainte Claire Deville, Toulon Cedex, France
  • Université de Tunis, ENSIT, LR13ES03 SIME, Montfleury, Tunisia
  • Laboratoire d'Informatique et des Systèmes, UMR, CNRS 7020, Ecole d'Ingénieurs SeaTech, Université de Toulon, France
  • Laboratoire d'Informatique et des Systèmes, UMR, CNRS 7020, Ecole d'Ingénieurs SeaTech, Université de Toulon, France
  • [1] A.D. Association. Diagnosis and classification of diabetes mellitus. Diabetes Care 2011;34(January (1)):62–9.
  • [2] Thakkar CS, Kshirsagar R, Naik V, Ghosh A, Vijayakumar V, Saklani A, et al. (E)-9-oxooctadec-10-en-12-ynoic acid from Ixora brachiata Roxb. increases glucose uptake in L6 myotubes by activating the PI3K pathway. Fitoterapia 2016.
  • [3] Association AD. Standards of medical care. Diabetes Care 2011;34(January (1)):11–61.
  • [4] Klonoff DC. Continuous glucose monitoring – roadmap for 21st century diabetes therapy. Diabetes Care 2005;28(May (5)):1231–9.
  • [5] Bremer T, Gough D. Is blood glucose predictable from previous values? A solicitation for data. Diabetes 1999;44:445–51.
  • [6] Sparacino G, Zanderigo S, Aran A, Cobelli C. Continuous glucose monitoring and hypo/hyperglycemia. Diabetes Res Clin Pract 2006;74(2):S160–3.
  • [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 May 2007;54(5):931–7.
  • [8] Palerm C, Willis J, Desemone J, Bequette B. Hypoglycemia prediction and detection using optimal estimation. Diabetes Technol Ther 2005;7(1):3–14.
  • [9] Pappada S, Cameron B, Rosman P, Bourey R, Papadimos T, Oloruntu W, et al. Neural network-based real-time prediction of glucose in patients with insulindependent diabetes. Diabetes Technol Ther 2011;13(2):135–41.
  • [10] Pappada SM, Cameron BD, Rosman PM. Development of a neural network for prediction of glucose. J Diabetes Sci Technol 2008;2(September (5)).
  • [11] Sandham W, Nikoletou D, Hamilton D, Patterson K, Japp A, Macgregor C. Blood glucose prediction for diabetes therapy using a recurrent artificial neural network. Proceedings of the 9th European Signal Processing Conference (EUSIPCO'98), vol. 11; 1998. p. 673–6.
  • [12] Mougiakakou SG, Prountzou K, Nikita KS. A real time simulation model of glucose-insulin metabolism. Proceedings of the 27th Annual International Conference of the Engineering in Medicine and Biology Society (IEEE-EMBS'05), vol. 1; September 2005. p. 298–301.
  • [13] Zarkogianni K, Mougiakakou SG, Prountzou A, Vazeou A. An insulin infusion advisory system for type 1 diabetes patients based on non-linear model predictive control methods. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society; 2007. p. 5972–5.
  • [14] Georga EI, Vasilios C, Ardigo D, Marina M, Zavaroni I, Polyzos D, et al. Multivariate prediction of subcutaneous glucose concentration in type 1 diabetes patients based on support vector regression. IEEE J Biomed Health Inform 2013;17(January (1)):71–81.
  • [15] Georga EI, Protopappas V, Polyzos D, Fotiadis D. Evaluation of short-term predictors of glucose concentration in type 1 diabetes combining feature ranking with regression models. Med Biol Eng Comput 2015;53(12):1305–18.
  • [16] Soman KP, Loganathan R, Ajay V. Machine learning with SVM and other kernel methods. Prentice Hall; 2009.
  • [17] Nuryani N, Ling SS, Nguyen HT. Electrocardiographic signals and swarm-based support vector machine for hypoglycemia detection. Ann Biomed Eng 2012;40:934–45.
  • [18] Smola AJ, Scholkopf B. A tutorial on support vector regression. Stat Comput 2004;14(August (3)):199–222.
  • [19] Weiwei W. Time series prediction based on SVM and GA. Conf Proc Electron Measure Instrum 2007;2-307–10.
  • [20] Storn R. Differential evolution: a simple and efficient heuristic for global optimization over continuous spaces. J Glob Opt 1997;11(December (4)):341–59.
  • [21] Storn R, Price K. Differential evolution – a simple and efficient adaptive scheme for global optimization over continuous spaces, vol. 3. Berkeley: ICSI; 1995.
  • [22] Xuemei L, Jin-hu L, Lixing D, Gang X, Jibin L. Building cooling load forecasting model based on LS-SVM. Asia- Pacific Conf Inf Process 2009;1:55–8.
  • [23] Tan G, Yan J, Gao C. Prediction of water quality time series data based on least squares support vector machine. Procedia Eng 2012;31:1194–9.
  • [24] Fei SW, Sun Y. Forecasting dissolved gases content in power transformer oil based on support vector machine with genetic algorithm. Electr Power Syst Res 2008;78:507–14.
  • [25] Sun W, Liang Y. Research of least squares support vector regression based on differential evolution algorithm in short-term load forecasting model. J Renew Sustain Energy 2014;6(5):053137.
  • [26] Djakouré-Platonoff C, Radermercker R, Reach G, Slama G, Selam J. Accuracy of the continuous glucose monitoring system in inpatient and outpatient conditions. Diabetes Metab 2003;28:159–62.
  • [27] Benhamou PY, Catargi B, Delenne B, Guerci B, Hanaire H. Real time continuous glucose monitoring (CGM) integrated into the treatment of type 1 diabetes: consensus of experts from SFD, EVADIAC and SFE. Diabetes Metab 2012;38:67–83.
  • [28] Basu A, Dube S, Slama M. Time lag of glucose from intravascular to interstitial compartment. Hum Diabetes 2013;62:4083–7.
  • [29] Schmelzeisen-Redeker G, Staib AA, Strasser M, Muller U, Schoemaker M. Overview of a novel sensor for continuous glucose monitoring. Diabetes Sci Technol 2013;7:808–14.
  • [30] Sachedina N, Pickup J. Performance assessment of the Medtronic-MiniMed Continuous Glucose Monitoring System and its use for measurement of glycaemic control in Type 1 diabetic subjects. Diabetic Med 2003;20(12):1012–5.
  • [31] Rossetti P, Bondia J, Vehí J, Fanelli C. Estimating plasma glucose from interstitial glucose: the issue of calibration algorithms in commercial continuous glucose monitoring devices. Sensors 2010;10(12):10936–52.
  • [32] Koutny T. Glucose predictability,blood capillary permeability,and glucose utilization ratein subcutaneous, skeletal muscle, and visceral fat tissues. Comput Biol Med 2013;(43):1680–6.
  • [33] Hayashia Y, Setiono R. Combining neural network predictions for medical diagnosis. Comput Biol Med 2002; (32):237–46.
  • [34] Han J. Accuracy and error measures Concepts and Techniques. Data mining. United States of America: Elsevier; 2006. p. 770.
  • [35] Mougiakakou SG, Prountzou A, Iliopoulou D, Nikita KS, Vaze A, Bartsocas CS. Neural network based glucose-insulin metabolism models for children with type 1 diabetes. Proc. 28th Annu. Int. Conf. IEEE Eng. Med. Biol. Soc.; August/ September 2006. pp. 3545–8.
  • [36] Pérez-Gandia C, Facchinetti A, Sparacino G, Cobelli C, Gomez EJ, Rigla M, et al. Artificial neural network algorithm for online glucose prediction from continuous glucose monitoring. Diabetes Technol Therapeut 2010;12(1):81–8.
  • [37] Robertson G, Lehmann ED, Sandham W, Hamilton D. Blood glucose prediction using artificial neural networks trained with the AIDA diabetes simulator: a proof-of-concept pilot study. J Electr Comput Eng 2011;2011:2.
  • [38] Zecchin C, Facchinetti A, Sparacino G, De Nicolao G, Cobelli C. Neural network incorporating meal information improves accuracy of short-time prediction of glucose concentration. IEEE Trans Bio-Med Eng 2012;59(6):1550–60.
  • [39] Turksoy K, Bayrak E, Quinn L, Littlejohn E, Rollins D, Cinar A. Hypoglycemia early alarm systems based on multivariable. Ind Eng Chem Res 2013;52:12329–36.
  • [40] Bode B, Gross K, Rikalo N, Schwartz S, Wahl T, Page C, et al. Alarms based on realtime sensor glucose values alert patients to hypo- and hyperglycemia: the guardian continuous monitoring system. Diabetes Technol Ther 2004;6:105–13.
Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2018).
Typ dokumentu
Identyfikator YADDA
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.