Comparative assessment of glucose prediction models for patients with type 1 diabetes mellitus applying sensors for glucose and physical activity monitoring
作者： Konstantia Zarkogianni , Konstantinos Mitsis , Eleni Litsa , M-T Arredondo , G Ficο
DOI: 10.1007/S11517-015-1320-9
关键词:
摘要: The present work presents the comparative assessment of four glucose prediction models for patients with type 1 diabetes mellitus (T1DM) using data from sensors monitoring blood concentration. are based on a feedforward neural network (FNN), self-organizing map (SOM), neuro-fuzzy wavelets as activation functions (WFNN), and linear regression model (LRM), respectively. For development evaluation models, 10 T1DM 6-day observation period have been used. models’ predictive performance is evaluated considering 30-, 60- 120-min horizon, both mathematical clinical criteria. Furthermore, addition input physical activity considered its effect investigated. continuous glucose-error grid analysis indicates that benefits mainly in hypoglycemic range when additional information related to fed into models. obtained results demonstrate superiority SOM over FNN, WFNN, LRM leading better terms
springer.com
sci-hub.se 参考文章(30)
Zarita Zainuddin, Cemal Ardil, Ong Pauline, A Neural Network Approach in Predicting the Blood Glucose Level for Diabetic Patients World Academy of Science, Engineering and Technology, International Journal of Computer, Electrical, Automation, Control and Information Engineering. ,vol. 3, pp. 436- 443 ,(2009)
Guilherme A. Barreto, Time Series Prediction with the Self-Organizing Map: A Review Perspectives of Neural-Symbolic Integration. pp. 135- 158 ,(2007) , 10.1007/978-3-540-73954-8_6
Roman Hovorka, Valentina Canonico, Ludovic J Chassin, Ulrich Haueter, Massimo Massi-Benedetti, Marco Orsini Federici, Thomas R Pieber, Helga C Schaller, Lukas Schaupp, Thomas Vering, Malgorzata E Wilinska, Nonlinear model predictive control of glucose concentration in subjects with type 1 diabetes Physiological Measurement. ,vol. 25, pp. 905- 920 ,(2004) , 10.1088/0967-3334/25/4/010
E. I. Georga, V. C. Protopappas, Diego Ardigo, M. Marina, I. Zavaroni, D. Polyzos, D. I. Fotiadis, Multivariate Prediction of Subcutaneous Glucose Concentration in Type 1 Diabetes Patients Based on Support Vector Regression IEEE Journal of Biomedical and Health Informatics. ,vol. 17, pp. 71- 81 ,(2013) , 10.1109/TITB.2012.2219876
J.A. Florian, R.S. Parker, Empirical Modeling for Glucose Control in Critical Care and Diabetes European Journal of Control. ,vol. 11, pp. 601- 616 ,(2005) , 10.3166/EJC.11.601-618
Céline Druet, Véronique Baltakse, Didier Chevenne, Sophie Dorgeret, Isabelle Zaccaria, Ying Wang, Claire Levy-Marchal, Independent effect of visceral adipose tissue on metabolic syndrome in obese adolescents. Hormone Research in Paediatrics. ,vol. 70, pp. 22- 28 ,(2008) , 10.1159/000129674
K. Zarkogianni, E. Litsa, A. Vazeou, K. S. Nikita, Personalized glucose-insulin metabolism model based on self-organizing maps for patients with Type 1 Diabetes Mellitus bioinformatics and bioengineering. pp. 1- 4 ,(2013) , 10.1109/BIBE.2013.6701604
Scott M. Pappada, Brent D. Cameron, Paul M. Rosman, Development of a neural network for prediction of glucose concentration in type 1 diabetes patients. Journal of diabetes science and technology. ,vol. 2, pp. 792- 801 ,(2008) , 10.1177/193229680800200507
C. Pérez-Gandía, A. Facchinetti, G. Sparacino, C. Cobelli, E.J. Gómez, M. Rigla, A. de Leiva, M.E. Hernando, Artificial neural network algorithm for online glucose prediction from continuous glucose monitoring. Diabetes Technology & Therapeutics. ,vol. 12, pp. 81- 88 ,(2010) , 10.1089/DIA.2009.0076
K. Zarkogianni, K. Mitsis, M.-T. Arredondo, G. Fico, A. Fioravanti, K. S. Nikita, Neuro-fuzzy based glucose prediction model for patients with Type 1 diabetes mellitus biomedical and health informatics. pp. 252- 255 ,(2014) , 10.1109/BHI.2014.6864351