Glucose prediction data analytics for diabetic patients monitoring

Diabetes Mellitus (DM) is one of the leading health complication around the world causing national economic burden and low quality of life. This increases the need to focus on prevention and early detection to improve the management and treatment of diabetes. The aim of this paper is to present a comprehensive critical review focusing on recent glucose prediction models and a best fit model is proposed based on the evaluation to perform data analytics in a wireless body area network system. The proposed glucose prediction algorithm is based on autoregressive (ARX) model which consider exogenous inputs such as CGM data, blood pressure (BP), total cholesterol (TC), low-density lipoprotein cholesterol (LDL), high density lipoproteins (HDL). A dataset of 442 diabetic patients is used to evaluate the performance of the algorithm through mean absolute error (MAE), root-mean-square error (RMSE), and coefficient of determination (R2). The experimental results demonstrate that the proposed prediction algorithm can improve the prediction accuracy of glucose. Potential research work and challenges are pointed out for further development of glucose prediction models.

[1]  C. Cobelli,et al.  Artificial neural network algorithm for online glucose prediction from continuous glucose monitoring. , 2010, Diabetes technology & therapeutics.

[2]  Ruben H. Zamar,et al.  Least angle regression for model selection , 2014 .

[3]  Srinivasan Rajaraman,et al.  Predicting Subcutaneous Glucose Concentration in Humans: Data-Driven Glucose Modeling , 2009, IEEE Transactions on Biomedical Engineering.

[4]  Konstantina S. Nikita,et al.  Personalized glucose-insulin metabolism model based on self-organizing maps for patients with Type 1 Diabetes Mellitus , 2013, 13th IEEE International Conference on BioInformatics and BioEngineering.

[5]  Luigi del Re,et al.  Short-term prediction of blood glucose concentration using interval probabilistic models , 2014, 22nd Mediterranean Conference on Control and Automation.

[6]  Dimitrios I. Fotiadis,et al.  Short-term vs. long-term analysis of diabetes data: Application of machine learning and data mining techniques , 2013, 13th IEEE International Conference on BioInformatics and BioEngineering.

[7]  Giovanni Sparacino,et al.  Glucose Concentration can be Predicted Ahead in Time From Continuous Glucose Monitoring Sensor Time-Series , 2007, IEEE Transactions on Biomedical Engineering.

[8]  Bekir Karlik,et al.  Diagnosing diabetes using neural networks on small mobile devices , 2012, Expert Syst. Appl..

[9]  Edward Aboufadel,et al.  Quantification of the Variability of Continuous Glucose Monitoring Data , 2011, Algorithms.

[10]  K. Balachandran,et al.  Performance analysis of training algorithms of multilayer perceptrons in diabetes prediction , 2015, 2015 International Conference on Advances in Computer Engineering and Applications.

[11]  Ying Wang,et al.  Independent Effect of Visceral Adipose Tissue on Metabolic Syndrome in Obese Adolescents , 2008, Hormone Research in Paediatrics.

[12]  Cynthia R. Marling,et al.  Blood Glucose Level Prediction Using Physiological Models and Support Vector Regression , 2013, 2013 12th International Conference on Machine Learning and Applications.

[13]  Konstantina S. Nikita,et al.  A Review of Emerging Technologies for the Management of Diabetes Mellitus , 2015, IEEE Transactions on Biomedical Engineering.

[14]  B Wayne Bequette,et al.  Continuous Glucose Monitoring: Real-Time Algorithms for Calibration, Filtering, and Alarms , 2010, Journal of diabetes science and technology.

[15]  Stavroula G. Mougiakakou,et al.  Multi-model data fusion to improve an early warning system for hypo-/hyperglycemic events , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[16]  K. Sangeetha,et al.  Data analysis for chronic disease -diabetes using map reduce technique , 2016, 2016 International Conference on Computer Communication and Informatics (ICCCI).

[17]  Michael Schumacher,et al.  Sensor Monitoring of Physical Activity to Improve Glucose Management in Diabetic Patients: A Review , 2016, Sensors.

[18]  Wang Youqing,et al.  Dynamic model with time varying delay for type 1 diabetes mellitus identified by using expectation maximization algorithm , 2016, 2016 35th Chinese Control Conference (CCC).

[19]  Ali Cinar,et al.  Hypoglycemia Prediction with Subject-Specific Recursive Time-Series Models , 2010, Journal of diabetes science and technology.

[20]  Björn Eskofier,et al.  Blood glucose level prediction based on support vector regression using mobile platforms , 2016, 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[21]  K. Eskaf,et al.  Predicting blood glucose levels in diabetics using feature extraction and Artificial Neural Networks , 2008, 2008 3rd International Conference on Information and Communication Technologies: From Theory to Applications.

[22]  Dimitrios I. Fotiadis,et al.  Non-linear dynamic modeling of glucose in type 1 diabetes with kernel adaptive filters , 2016, EMBC.

[23]  G. Baghdadi,et al.  Controlling Blood Glucose Levels in Diabetics By Neural Network Predictor , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[24]  Yinghui Lu,et al.  Predicting human subcutaneous glucose concentration in real time: A universal data-driven approach , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[25]  Ankur Agarwal,et al.  Predictive Modeling for Wellness and Chronic Conditions , 2014, 2014 IEEE International Conference on Bioinformatics and Bioengineering.

[26]  Scott M. Pappada,et al.  Neural network-based real-time prediction of glucose in patients with insulin-dependent diabetes. , 2011, Diabetes technology & therapeutics.

[27]  Youqing Wang,et al.  Dynamic model with time varying delay for type 1 diabetes mellitus identified by using expectation maximization algorithm , 2016, CCC 2016.

[28]  Chunhui Zhao,et al.  Rapid Model Identification for Online Subcutaneous Glucose Concentration Prediction for New Subjects With Type I Diabetes , 2015, IEEE Transactions on Biomedical Engineering.

[29]  Srinivasan Rajaraman,et al.  Predictive Monitoring for Improved Management of Glucose Levels , 2007, Journal of diabetes science and technology.

[30]  Zarita Zainuddin,et al.  A Neural Network Approach in Predicting the Blood Glucose Level for Diabetic Patients , 2009 .

[31]  Konstantina S. Nikita,et al.  Neuro-fuzzy based glucose prediction model for patients with Type 1 diabetes mellitus , 2014, IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI).

[32]  Francis J Doyle,et al.  Experimental Evaluation of a Recursive Model Identification Technique for Type 1 Diabetes , 2009, Journal of diabetes science and technology.

[33]  Yinghui Lu,et al.  Universal Glucose Models for Predicting Subcutaneous Glucose Concentration in Humans , 2010, IEEE Transactions on Information Technology in Biomedicine.

[34]  Dimitrios I. Fotiadis,et al.  Multivariate Prediction of Subcutaneous Glucose Concentration in Type 1 Diabetes Patients Based on Support Vector Regression , 2013, IEEE Journal of Biomedical and Health Informatics.

[35]  E. Daskalaki,et al.  Real-time adaptive models for the personalized prediction of glycemic profile in type 1 diabetes patients. , 2012, Diabetes technology & therapeutics.

[36]  Cynthia R. Marling,et al.  A Machine Learning Approach to Predicting Blood Glucose Levels for Diabetes Management , 2014, AAAI Workshop: Modern Artificial Intelligence for Health Analytics.

[37]  L. Quinn,et al.  Estimation of future glucose concentrations with subject-specific recursive linear models. , 2009, Diabetes technology & therapeutics.

[38]  Helen X. Gao,et al.  International Diabetes Federation World Diabetes Congress 2015. , 2016, Journal of diabetes.

[39]  Anpeng Huang,et al.  Glucose-tracking: A postprandial glucose prediction system for diabetic self-management , 2015, 2015 2nd International Symposium on Future Information and Communication Technologies for Ubiquitous HealthCare (Ubi-HealthTech).

[40]  Giovanni Sparacino,et al.  Glucose Prediction Algorithms from Continuous Monitoring Data: Assessment of Accuracy via Continuous Glucose Error-Grid Analysis , 2007, Journal of diabetes science and technology.

[41]  Kavi Kumar Khedo,et al.  Wireless Body Area Network System Architecture for Real-Time Diabetes Monitoring , 2016 .