A review of personalized blood glucose prediction strategies for T1DM patients

This paper presents a methodological review of models for predicting blood glucose (BG) concentration, risks and BG events. The surveyed models are classified into three categories, and they are presented in summary tables containing the most relevant data regarding the experimental setup for fitting and testing each model as well as the input signals and the performance metrics. Each category exhibits trends that are presented and discussed. This document aims to be a compact guide to determine the modeling options that are currently being exploited for personalized BG prediction.

[1]  C. Cobelli,et al.  The UVA/PADOVA Type 1 Diabetes Simulator , 2014, Journal of diabetes science and technology.

[2]  Denis Gillet,et al.  A therapy parameter-based model for predicting blood glucose concentrations in patients with type 1 diabetes , 2015, Comput. Methods Programs Biomed..

[3]  Yinghui Lu,et al.  The Importance of Different Frequency Bands in Predicting Subcutaneous Glucose Concentration in Type 1 Diabetic Patients , 2010, IEEE Transactions on Biomedical Engineering.

[4]  Javier Fernández de Cañete,et al.  Artificial neural networks for closed loop control of in silico and ad hoc type 1 diabetes , 2012, Comput. Methods Programs Biomed..

[5]  P Schaepelynck,et al.  Advances in pump technology: insulin patch pumps, combined pumps and glucose sensors, and implanted pumps. , 2011, Diabetes & metabolism.

[6]  Sergio Romero-Vivo,et al.  On the prediction of glucose concentration under intra-patient variability in type 1 diabetes: A monotone systems approach , 2012, Comput. Methods Programs Biomed..

[7]  Giuseppe De Nicolao,et al.  Neural Network Incorporating Meal Information Improves Accuracy of Short-Time Prediction of Glucose Concentration , 2012, IEEE Transactions on Biomedical Engineering.

[8]  Giovanni Sparacino,et al.  “Smart” Continuous Glucose Monitoring Sensors: On-Line Signal Processing Issues , 2010, Sensors.

[9]  Ján Murgaš,et al.  Robust Gain-Scheduled Controller Design for T1DM Individualised Model , 2015 .

[10]  Giovanni Sparacino,et al.  A new index to optimally design and compare continuous glucose monitoring glucose prediction algorithms. , 2011, Diabetes technology & therapeutics.

[11]  Riccardo Bellazzi,et al.  Data Mining Technologies for Blood Glucose and Diabetes Management , 2009, Journal of diabetes science and technology.

[12]  Ali Cinar,et al.  Hypoglycemia Early Alarm Systems Based On Multivariable Models. , 2013, Industrial & engineering chemistry research.

[13]  Eyal Dassau,et al.  Switched LPV Glucose Control in Type 1 Diabetes , 2016, IEEE Transactions on Biomedical Engineering.

[14]  Irl B. Hirsch,et al.  Multivariable adaptive identification and control for artificial pancreas systems , 2015 .

[15]  Carlo Novara,et al.  A nonlinear blind identification approach to modeling of diabetic patients , 2014 .

[16]  Dale E. Seborg,et al.  Predicting Subcutaneous Glucose Concentration Using a Latent-Variable-Based Statistical Method for Type 1 Diabetes Mellitus , 2012, Journal of diabetes science and technology.

[17]  Pavel Zakharov,et al.  Characteristics of a multisensor system for non invasive glucose monitoring with external validation and prospective evaluation. , 2011, Biosensors & bioelectronics.

[18]  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.

[19]  Roman Hovorka,et al.  Home use of closed-loop insulin delivery for overnight glucose control in adults with type 1 diabetes: a 4-week, multicentre, randomised crossover study. , 2014, The lancet. Diabetes & endocrinology.

[20]  Josep Vehí,et al.  Comparison of interval and Monte Carlo simulation for the prediction of postprandial glucose under uncertainty in type 1 diabetes mellitus , 2011, Comput. Methods Programs Biomed..

[21]  Claudio Cobelli,et al.  Closed-Loop Artificial Pancreas Systems: Physiological Input to Enhance Next-Generation Devices , 2014, Diabetes Care.

[22]  Chiara Zecchin,et al.  Online Glucose Prediction in Type-1 Diabetes by Neural Network Models , 2014 .

[23]  Francis J. Doyle,et al.  Design of an artificial pancreas using zone model predictive control with a Moving Horizon State Estimator , 2014, 53rd IEEE Conference on Decision and Control.

[24]  Luigi del Re,et al.  Nonlinear gain in online prediction of blood glucose profile in type 1 diabetic patients , 2010, 49th IEEE Conference on Decision and Control (CDC).

[25]  Rolf Johansson,et al.  Subspace-based linear multi-step predictors in type 1 diabetes mellitus , 2015, Biomed. Signal Process. Control..

[26]  Christofer Toumazou,et al.  A Bio-Inspired Glucose Controller Based on Pancreatic β-Cell Physiology , 2012, Journal of diabetes science and technology.

[27]  Bruce Buckingham,et al.  Toward closing the loop: an update on insulin pumps and continuous glucose monitoring systems. , 2010, Endocrinology and metabolism clinics of North America.

[28]  Akihisa Imagawa,et al.  Coefficient of variation of R-R interval closely correlates with glycemic variability assessed by continuous glucose monitoring in insulin-depleted patients with type 1 diabetes. , 2015, Diabetes research and clinical practice.

[29]  Konstantina S. Nikita,et al.  An Insulin Infusion Advisory System Based on Autotuning Nonlinear Model-Predictive Control , 2011, IEEE Transactions on Biomedical Engineering.

[30]  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.

[31]  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.

[32]  Jing Zhou,et al.  Receding Horizon Control of type I diabetes based on a data-driven linear time-varying state-space model , 2010, Proceedings of the 2010 American Control Conference.

[33]  I. Chien,et al.  Modified control algorithms for patients with type 1 diabetes mellitus undergoing exercise , 2014 .

[34]  Christofer Toumazou,et al.  Live demonstration: A handheld Bio-inspired Artificial pancreas for treatment of diabetes , 2014, 2014 IEEE Biomedical Circuits and Systems Conference (BioCAS) Proceedings.

[35]  Janet M. Allen,et al.  Feasibility of Closed-Loop Insulin Delivery in Type 2 Diabetes: A Randomized Controlled Study , 2014, Diabetes Care.

[36]  Giuseppe De Nicolao,et al.  MPC based Artificial Pancreas: Strategies for individualization and meal compensation , 2012, Annu. Rev. Control..

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

[38]  Tarunraj Singh,et al.  Blood glucose control algorithms for type 1 diabetic patients: A methodological review , 2013, Biomed. Signal Process. Control..

[39]  Cheng-Liang Chen,et al.  Modeling the physiological glucose-insulin dynamic system on diabetics. , 2010, Journal of theoretical biology.

[40]  B. Wayne Bequette,et al.  Challenges and recent progress in the development of a closed-loop artificial pancreas , 2012, Annu. Rev. Control..

[41]  Giovanna Elizabeth Castillo Estrada,et al.  Innovative approach for online prediction of blood glucose profile in type 1 diabetes patients , 2010, Proceedings of the 2010 American Control Conference.

[42]  José Ignacio Hidalgo,et al.  Modeling glycemia in humans by means of Grammatical Evolution , 2014, Appl. Soft Comput..

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

[44]  Qian Wang,et al.  Developing personalized empirical models for Type-I diabetes: An extended Kalman filter approach , 2013, 2013 American Control Conference.

[45]  Giovanni Sparacino,et al.  Jump neural network for online short-time prediction of blood glucose from continuous monitoring sensors and meal information , 2014, Comput. Methods Programs Biomed..

[46]  Roman Hovorka,et al.  Day and Night Home Closed-Loop Insulin Delivery in Adults With Type 1 Diabetes: Three-Center Randomized Crossover Study , 2014, Diabetes Care.

[47]  G. Jaramillo,et al.  Prediction of postprandial blood glucose under intra-patient variability and uncertainty and its use in the design of insulin dosing strategies for type 1 diabetic patients , 2011 .

[48]  Ali Cinar,et al.  Adaptive control strategy for regulation of blood glucose levels in patients with type 1 diabetes , 2009 .

[49]  R. Hovorka,et al.  Nonlinear model predictive control of glucose concentration in subjects with type 1 diabetes. , 2004, Physiological measurement.

[50]  Giovanni Sparacino,et al.  Diabetes: Models, Signals, and Control , 2009 .

[51]  Youqing Wang,et al.  A novel adaptive-weighted-average framework for blood glucose prediction. , 2013, Diabetes technology & therapeutics.

[52]  Josep Vehí,et al.  Prediction of postprandial blood glucose under uncertainty and intra-patient variability in type 1 diabetes: A comparative study of three interval models , 2012, Comput. Methods Programs Biomed..

[53]  Marc D. Breton,et al.  Overnight Glucose Control With an Automated, Unified Safety System in Children and Adolescents With Type 1 Diabetes at Diabetes Camp , 2014, Diabetes Care.

[54]  Jaques Reifman,et al.  Update on Mathematical Modeling Research to Support the Development of Automated Insulin Delivery Systems , 2010, Journal of diabetes science and technology.

[55]  Eleni I. Georga,et al.  Prediction of glucose concentration in type 1 diabetic patients using support vector regression , 2010, Proceedings of the 10th IEEE International Conference on Information Technology and Applications in Biomedicine.

[56]  Dimitrios I. Fotiadis,et al.  A predictive model of subcutaneous glucose concentration in type 1 diabetes based on Random Forests , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[57]  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.

[58]  Ricardo Femat,et al.  Neural modeling of the blood glucose level for Type 1 Diabetes Mellitus patients , 2011, 2011 IEEE International Conference on Automation Science and Engineering.

[59]  Claudio Cobelli,et al.  Artificial Pancreas: from in-silico to in-vivo , 2015 .

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

[61]  P. Balamurugan,et al.  Performance comparison of featured neural network with gradient descent and levenberg-marquart algorithm trained neural networks for prediction of blood glucose values with continuous glucose monitoring sensor data , 2012, 2012 International Conference on Emerging Trends in Science, Engineering and Technology (INCOSET).

[62]  W. Tamborlane,et al.  The Artificial Pancreas: Are We There Yet? , 2014, Diabetes Care.

[63]  Roman Hovorka,et al.  Evaluation of a portable ambulatory prototype for automated overnight closed‐loop insulin delivery in young people with type 1 diabetes , 2012, Pediatric diabetes.

[64]  Yan Zhang,et al.  A data driven nonlinear stochastic model for blood glucose dynamics , 2015, Comput. Methods Programs Biomed..

[65]  C. Gireesh,et al.  Blood Glucose Prediction Algorithms for Hypoglycemic and/or Hyperglycemic Alerts , 2012 .

[66]  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.

[67]  Gary Scheiner,et al.  Think Like a Pancreas: A Practical Guide to Managing Diabetes with Insulin , 2004 .

[68]  J. Ulbrecht,et al.  Personalized State-space Modeling of Glucose Dynamics for Type 1 Diabetes Using Continuously Monitored Glucose, Insulin Dose, and Meal Intake , 2014, Journal of diabetes science and technology.

[69]  Yuri B. Shtessel,et al.  High-order sliding-mode control for blood glucose: Practical relative degree approach , 2013 .

[70]  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.

[71]  Hervé Cormerais,et al.  Artificial pancreas for type 1 diabetes: Closed-loop algorithm based on Error Dynamics Shaping , 2012 .

[72]  Konstantina S. Nikita,et al.  Comparative assessment of glucose prediction models for patients with type 1 diabetes mellitus applying sensors for glucose and physical activity monitoring , 2015, Medical & Biological Engineering & Computing.

[73]  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).

[74]  Eyal Dassau,et al.  Moving-horizon-like state estimation via continuous glucose monitor feedback in MPC of an artificial pancreas for type 1 diabetes , 2014, 53rd IEEE Conference on Decision and Control.

[75]  Mariano De Paula,et al.  On-line policy learning and adaptation for real-time personalization of an artificial pancreas , 2015, Expert Syst. Appl..

[76]  Dale E. Seborg,et al.  Model-based personalization scheme of an artificial pancreas for Type 1 diabetes applications , 2013, 2013 American Control Conference.

[77]  Fabian León-Vargas,et al.  Postprandial response improvement via safety layer in closed-loop blood glucose controllers , 2015, Biomed. Signal Process. Control..

[78]  G. P. Rangaiah,et al.  Personalized Hybrid Models for Exercise, Meal, and Insulin Interventions in Type 1 Diabetic Children and Adolescents , 2013 .

[79]  Shankar C. Subramanian,et al.  Nonlinear glucose–insulin control considering delays—Part II: Control algorithm , 2014 .

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

[81]  Sergei V. Pereverzyev,et al.  A meta-learning approach to the regularized learning - Case study: Blood glucose prediction , 2012, Neural Networks.

[82]  Germán Campetelli,et al.  Extended adaptive predictive controller with robust filter to enhance blood glucose regulation in type I diabetic subjects , 2013, Comput. Chem. Eng..

[83]  Josep Vehí,et al.  Identification of intra-patient variability in the postprandial response of patients with type 1 diabetes , 2014, Biomed. Signal Process. Control..

[84]  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).

[85]  Lauren M. Huyett,et al.  Closed-Loop Artificial Pancreas Systems: Engineering the Algorithms , 2014, Diabetes Care.

[86]  C. Cobelli,et al.  Artificial Pancreas: Past, Present, Future , 2011, Diabetes.

[87]  Peng Li,et al.  A new insulin-glucose metabolic model of type 1 diabetes mellitus: An in silico study , 2015, Comput. Methods Programs Biomed..

[88]  Marc D. Breton,et al.  Modular Closed-Loop Control of Diabetes , 2012, IEEE Transactions on Biomedical Engineering.

[89]  F. Doyle,et al.  Prevention of Nocturnal Hypoglycemia Using Predictive Alarm Algorithms and Insulin Pump Suspension , 2010, Diabetes Care.

[90]  G. Charpentier,et al.  Preliminary Evaluation of a New Semi-Closed-Loop Insulin Therapy System Over the Prandial Period in Adult Patients With Type 1 Diabetes , 2014, Journal of diabetes science and technology.

[91]  Claudio Cobelli,et al.  Meal Simulation Model of the Glucose-Insulin System , 2007, IEEE Transactions on Biomedical Engineering.

[92]  M. Pasquier,et al.  Predicting hypoglycemia in diabetic patients using data mining techniques , 2013, 2013 9th International Conference on Innovations in Information Technology (IIT).

[93]  Hui-Chen Wang,et al.  Recent developments in blood glucose sensors , 2015, Journal of food and drug analysis.

[94]  Dale E. Seborg,et al.  Control-Relevant Models for Glucose Control Using A Priori Patient Characteristics , 2012, IEEE Transactions on Biomedical Engineering.

[95]  Edgar N. Sánchez,et al.  Inverse optimal neural control of blood glucose level for type 1 diabetes mellitus patients , 2012, J. Frankl. Inst..

[96]  G. P. Rangaiah,et al.  Personalized mechanistic models for exercise, meal and insulin interventions in children and adolescents with type 1 diabetes. , 2014, Journal of theoretical biology.

[97]  L. Magni,et al.  First Use of Model Predictive Control in Outpatient Wearable Artificial Pancreas , 2014, Diabetes Care.

[98]  Henrik Madsen,et al.  Model Identification Using Stochastic Differential Equation Grey-Box Models in Diabetes , 2013, Journal of diabetes science and technology.

[99]  Rolf Johansson,et al.  Bayesian combination of multiple plasma glucose predictors , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[100]  Niels Kjølstad Poulsen,et al.  Model-Based Closed-Loop Glucose Control in Type 1 Diabetes: The DiaCon Experience , 2013, Journal of diabetes science and technology.

[101]  Claudio Cobelli,et al.  A Glucose-Specific Metric to Assess Predictors and Identify Models , 2012, IEEE Transactions on Biomedical Engineering.

[102]  Claudio Cobelli,et al.  Closed loop developments to improve glucose control at home. , 2013, Diabetes research and clinical practice.

[103]  Günter Niemeyer,et al.  A Closed-Loop Artificial Pancreas Based on Risk Management , 2011, Journal of diabetes science and technology.

[104]  Ilknur Atasoy,et al.  Comparison of control algorithms for the blood glucose concentration in a virtual patient with an artificial pancreas , 2012 .

[105]  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.

[106]  Y. Z. Ider,et al.  Quantitative estimation of insulin sensitivity. , 1979, The American journal of physiology.

[107]  Simon Fong,et al.  Evaluation of Stream Mining Classifiers for Real-Time Clinical Decision Support System: A Case Study of Blood Glucose Prediction in Diabetes Therapy , 2013, BioMed research international.

[108]  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.

[109]  M W Percival,et al.  Development of a multi-parametric model predictive control algorithm for insulin delivery in type 1 diabetes mellitus using clinical parameters. , 2011, Journal of process control.

[110]  Lei Yu,et al.  Effect of meal intake on the quality of empirical dynamic models for Type 1 Diabetes , 2014, 2014 IEEE International Symposium on Bioelectronics and Bioinformatics (IEEE ISBB 2014).

[111]  Panagiotis D. Christofides,et al.  Improved postprandial glucose control with a customized Model Predictive Controller , 2015, 2015 American Control Conference (ACC).

[112]  F. Doyle,et al.  Quest for the Artificial Pancreas: Combining Technology with Treatment , 2010, IEEE Engineering in Medicine and Biology Magazine.

[113]  Josep Vehí,et al.  Experimental blood glucose interval identification of patients with type 1 diabetes , 2014 .

[114]  Hsiao-Ping Huang,et al.  Fuzzy-Logic-Based Supervisor of Insulin Bolus Delivery for Patients with Type 1 Diabetes Mellitus , 2013 .

[115]  Youqing Wang,et al.  Hypoglycemia prediction using extreme learning machine (ELM) and regularized ELM , 2013, 2013 25th Chinese Control and Decision Conference (CCDC).

[116]  B. Wayne Bequette,et al.  Extended multiple model prediction with application to blood glucose regulation , 2012 .

[117]  R. Femat,et al.  Theoretical blood glucose control in hyper- and hypoglycemic and exercise scenarios by means of an H(infinity) algorithm. , 2010, Journal of theoretical biology.

[118]  Cheng-Liang Chen,et al.  Modeling the physiological glucose-insulin system on normal and diabetic subjects , 2010, Comput. Methods Programs Biomed..

[119]  D. Dunger,et al.  Unsupervised home use of an overnight closed‐loop system over 3–4 weeks: a pooled analysis of randomized controlled studies in adults and adolescents with type 1 diabetes , 2015, Diabetes, obesity & metabolism.

[120]  Lakshminarayanan Samavedham,et al.  Personalized blood glucose models for exercise, meal and insulin interventions in type 1 diabetic children , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[121]  Roman Hovorka,et al.  Simulation Environment to Evaluate Closed-Loop Insulin Delivery Systems in Type 1 Diabetes , 2010, Journal of diabetes science and technology.

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

[123]  J. Bondia,et al.  El Páncreas Artificial, Control Automático de Infusión de Insulina en Diabetes Mellitus Tipo 1 , 2010 .

[124]  Christoph Ament,et al.  Real-Time State Estimation and Long-Term Model Adaptation: A Two-Sided Approach toward Personalized Diagnosis of Glucose and Insulin Levels , 2012, Journal of diabetes science and technology.

[125]  Youqing Wang,et al.  Predictive-retrospective proportional glycemic control for type 1 diabetes mellitus , 2013, 2013 ICME International Conference on Complex Medical Engineering.

[126]  CapelIsmael,et al.  Artificial pancreas using a personalized rule-based controller achieves overnight normoglycemia in patients with type 1 diabetes. , 2014 .

[127]  Simon Fong,et al.  Using causality modeling and Fuzzy Lattice Reasoning algorithm for predicting blood glucose , 2013, Expert Syst. Appl..

[128]  Mariano De Paula,et al.  Controlling blood glucose variability under uncertainty using reinforcement learning and Gaussian processes , 2015, Appl. Soft Comput..

[129]  Rolf Johansson,et al.  Direct continuous time system identification of MISO transfer function models applied to type 1 diabetes , 2011, IEEE Conference on Decision and Control and European Control Conference.

[130]  Malgorzata E. Wilinska,et al.  Overnight Closed-Loop Insulin Delivery in Young People With Type 1 Diabetes: A Free-Living, Randomized Clinical Trial , 2014, Diabetes Care.

[131]  G. P. Rangaiah,et al.  Review and Analysis of Blood Glucose (BG) Models for Type 1 Diabetic Patients , 2011 .

[132]  Paul Bogdan,et al.  Reducing risk of closed loop control of blood glucose in artificial pancreas using fractional calculus , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[133]  G. Hong,et al.  Physiological analysis on oscillatory behavior of glucose-insulin regulation by model with delays. , 2011, Journal of theoretical biology.

[134]  Eyal Dassau,et al.  Real-Time Hypoglycemia Prediction Suite Using Continuous Glucose Monitoring , 2010, Diabetes Care.

[135]  Chunhui Zhao,et al.  Statistical analysis based online sensor failure detection for continuous glucose monitoring in type I diabetes , 2015 .