Skip to main content
Elsevier
View Cart

Personalized Predictive Modeling in Type 1 Diabetes

  • 1st Edition - November 29, 2017
  • Latest edition
  • Authors: Eleni I. Georga, Dimitrios I Fotiadis, Stelios K. Tigas
  • Language: English

Personalized Predictive Modeling in Diabetes features state-of-the-art methodologies and algorithmic approaches which have been applied to predictive modeling of glucose concentra… Read more

World Book Day celebration

Where learning shapes lives

Up to 25% off trusted resources that support research, study, and discovery.

Explore resources

Description

Personalized Predictive Modeling in Diabetes features state-of-the-art methodologies and algorithmic approaches which have been applied to predictive modeling of glucose concentration, ranging from simple autoregressive models of the CGM time series to multivariate nonlinear regression techniques of machine learning. Developments in the field have been analyzed with respect to: (i) feature set (univariate or multivariate), (ii) regression technique (linear or non-linear), (iii) learning mechanism (batch or sequential), (iv) development and testing procedure and (v) scaling properties. In addition, simulation models of meal-derived glucose absorption and insulin dynamics and kinetics are covered, as an integral part of glucose predictive models.

This book will help engineers and clinicians to: select a regression technique which can capture both linear and non-linear dynamics in glucose metabolism in diabetes, and which exhibits good generalization performance under stationary and non-stationary conditions; ensure the scalability of the optimization algorithm (learning mechanism) with respect to the size of the dataset, provided that multiple days of patient monitoring are needed to obtain a reliable predictive model; select a features set which efficiently represents both spatial and temporal dependencies between the input variables and the glucose concentration; select simulation models of subcutaneous insulin absorption and meal absorption; identify an appropriate validation procedure, and identify realistic performance measures.

Key features

  • Describes fundamentals of modeling techniques as applied to glucose control
  • Covers model selection process and model validation
  • Offers computer code on a companion website to show implementation of models and algorithms
  • Features the latest developments in the field of diabetes predictive modeling

Readership

Bioengineers, Clinicians, graduate and undergraduate students in the field of medicine and biomedical engineering

Table of contents

Chapter 1 Introduction1.1 The Glucose-Insulin Regulatory System1.2 Pathophysiology of Diabetes Mellitus1.3 Assessment of Glycemic Control1.4 Management of Diabetes1.5 Predictive Modelling of Glucose Concentration1.6 The Artificial Pancreas SystemChapter 2 Data-Driven Prediction of Glucose Concentration in Type 1 Diabetes2.1 Dataset Construction2.1.1 Data Pre-processing2.1.2 Feature Extraction2.2 The Glucose Prediction Model2.2.1 Regression Models2.2.2 Models of Subcutaneous Insulin Absorption2.2.3 Models of Meal Absorption2.3 Training and Evaluation of the Glucose Prediction Model2.4 Assessing the Performance of the Glucose Prediction ModelChapter 3 Linear Models of Glucose Concentration3.1 Polynomial Models3.2 Autoregressive and Autoregressive Moving Average Models3.3 Autoregressive and Autoregressive Moving Average Models with Exogenous InputsChapter 4 Non-linear Models of Glucose Concentration4.1 Nonlinear Autoregressive and Autoregressive Moving Average Models with Exogenous Inputs4.2 Neural Networks4.3 Kernel-based Regression Models4.4 Extreme Learning Machines4.5 Hybrid ApproachesChapter 5 Prediction Models of Hypoglycaemia5.1 Detection of Hypoglycaemic Events in Continuous Glucose Monitoring Data5.2 Predictors of Hypoglycaemia5.3 Statistical Methods5.4 Methods based on Time series Analysis5.5 Methods based on Machine Learning Chapter 6 Adaptive Glucose Prediction Models6.1 The Stationarity Hypothesis in Glucose Prediction Problem6.2 Linear Models6.2.1 Least-Mean-Square Algorithm6.2.2 Recursive Least-Squares Algorithm6.2.3 The Latent Variable Model6.3 Kalman Filters6.4 Neural Networks6.4.1 Recurrent Neural Networks6.4.2 Sequential Extreme Learning Machines6.5 Kernel Adaptive Filtering6.5.1 Kernel Least-Mean-Square Algorithm6.5.2 Kernel Recursive Least-Squares Algorithm6.5.3 Sparse Kernel Adaptive Filters6.6 Hybrid ApproachesChapter 7 Anticipatory Mobile Systems in Diabetes7.1 Architecture of Anticipatory Mobile Systems7.1.1 Context Sensing7.1.2 Context Inference7.1.3 Context Prediction7.1.4 Intelligent Actioning7.2 Integration of Glucose Prediction Models into Anticipatory Mobile Systems7.3 Use of Reinforcement Learning in Diabetes ManagementChapter 8 Conclusions and Future Trends8.1 Towards Personalised Diabetes Management Systems

Product details

  • Edition: 1
  • Latest edition
  • Published: December 11, 2017
  • Language: English

About the authors

EG

Eleni I. Georga

Ph.D. candidate at the Department of Materials Science and Engineering, University of Ioannina, Greece
Affiliations and expertise
Ph.D. candidate, Department of Materials Science and Engineering, University of Ioannina, Greece

DF

Dimitrios I Fotiadis

Dimitrios I. Fotiadis received his Diploma degree in chemical engineering from National Technical University of Athens, Athens, Greece, in 1985 and the Ph.D. degree in chemical engineering from the University of Minnesota, Minneapolis, MN, in 1990. He is currently Professor at the Department of Materials Science and Engineering, University of Ioannina, Greece, and affiliated researcher at the Biomedical Research Dept. of the Institute of Molecular Biology and Biotechnology - FORTH. He is the Director of the Unit of Medical Technology and Intelligent Information Systems, Greece. He is the member of the board of Michailideion Cardiology Center. His research interests include modeling of human tissues and organs, intelligent wearable devices for automated diagnosis and processing/analysis of biomedical data.
Affiliations and expertise
Professor of Biomedical Engineering, Department of Materials Science and Engineering, University of Ioannina, Greece

ST

Stelios K. Tigas

Stelios Tigas is awarded PhD in Endocrinology from the University of Ioannina. Stelios Tigas international experience includes various programs, contributions and participation in different countries for diverse fields of study. Stelios Tigas research interests as an Associate Professor reflect in wide range of publications in various national and international journals
Affiliations and expertise
Assistant Professor of Endocrinology, Department of Endocrinology and Diabetes, University of Ioannina, Greece

View book on ScienceDirect

Read Personalized Predictive Modeling in Type 1 Diabetes on ScienceDirect