Personalized state-space modeling of glucose dynamics for type 1 diabetes using continuously monitored glucose, insulin dose, and meal intake: An extended Kalman filter approach

Qian Wang, Peter Molenaar, Saurabh Harsh, Kenneth Allan Freeman, Jinyu Xie, Carol Gold, Mike Rovine, Jan Ulbrecht

Research output: Contribution to journalArticle

37 Citations (Scopus)

Abstract

An essential component of any artificial pancreas is on the prediction of blood glucose levels as a function of exogenous and endogenous perturbations such as insulin dose, meal intake, and physical activity and emotional tone under natural living conditions. In this article, we present a new data-driven state-space dynamic model with time-varying coefficients that are used to explicitly quantify the time-varying patient-specific effects of insulin dose and meal intake on blood glucose fluctuations. Using the 3-variate time series of glucose level, insulin dose, and meal intake of an individual type 1 diabetic subject, we apply an extended Kalman filter (EKF) to estimate time-varying coefficients of the patient-specific state-space model. We evaluate our empirical modeling using (1) the FDA-approved UVa/Padova simulator with 30 virtual patients and (2) clinical data of 5 type 1 diabetic patients under natural living conditions. Compared to a forgetting-factor-based recursive ARX model of the same order, the EKF model predictions have higher fit, and significantly better temporal gain and J index and thus are superior in early detection of upward and downward trends in glucose. The EKF based state-space model developed in this article is particularly suitable for model-based state-feedback control designs since the Kalman filter estimates the state variable of the glucose dynamics based on the measured glucose time series. In addition, since the model parameters are estimated in real time, this model is also suitable for adaptive control.

Original languageEnglish (US)
Pages (from-to)331-345
Number of pages15
JournalJournal of Diabetes Science and Technology
Volume8
Issue number2
DOIs
StatePublished - Jan 1 2014

Fingerprint

Insulin
Extended Kalman filters
Medical problems
Type 1 Diabetes Mellitus
Glucose
Meals
Space Simulation
Social Conditions
Blood Glucose
Time series
Blood
Artificial Pancreas
State feedback
Kalman filters
Feedback control
Dynamic models
Simulators
Exercise

All Science Journal Classification (ASJC) codes

  • Internal Medicine
  • Endocrinology, Diabetes and Metabolism
  • Bioengineering
  • Biomedical Engineering

Cite this

@article{7730708908904fbab7b3fb935d281ef5,
title = "Personalized state-space modeling of glucose dynamics for type 1 diabetes using continuously monitored glucose, insulin dose, and meal intake: An extended Kalman filter approach",
abstract = "An essential component of any artificial pancreas is on the prediction of blood glucose levels as a function of exogenous and endogenous perturbations such as insulin dose, meal intake, and physical activity and emotional tone under natural living conditions. In this article, we present a new data-driven state-space dynamic model with time-varying coefficients that are used to explicitly quantify the time-varying patient-specific effects of insulin dose and meal intake on blood glucose fluctuations. Using the 3-variate time series of glucose level, insulin dose, and meal intake of an individual type 1 diabetic subject, we apply an extended Kalman filter (EKF) to estimate time-varying coefficients of the patient-specific state-space model. We evaluate our empirical modeling using (1) the FDA-approved UVa/Padova simulator with 30 virtual patients and (2) clinical data of 5 type 1 diabetic patients under natural living conditions. Compared to a forgetting-factor-based recursive ARX model of the same order, the EKF model predictions have higher fit, and significantly better temporal gain and J index and thus are superior in early detection of upward and downward trends in glucose. The EKF based state-space model developed in this article is particularly suitable for model-based state-feedback control designs since the Kalman filter estimates the state variable of the glucose dynamics based on the measured glucose time series. In addition, since the model parameters are estimated in real time, this model is also suitable for adaptive control.",
author = "Qian Wang and Peter Molenaar and Saurabh Harsh and Freeman, {Kenneth Allan} and Jinyu Xie and Carol Gold and Mike Rovine and Jan Ulbrecht",
year = "2014",
month = "1",
day = "1",
doi = "10.1177/1932296814524080",
language = "English (US)",
volume = "8",
pages = "331--345",
journal = "Journal of diabetes science and technology",
issn = "1932-2968",
publisher = "Diabetes Technology Society",
number = "2",

}

TY - JOUR

T1 - Personalized state-space modeling of glucose dynamics for type 1 diabetes using continuously monitored glucose, insulin dose, and meal intake

T2 - An extended Kalman filter approach

AU - Wang, Qian

AU - Molenaar, Peter

AU - Harsh, Saurabh

AU - Freeman, Kenneth Allan

AU - Xie, Jinyu

AU - Gold, Carol

AU - Rovine, Mike

AU - Ulbrecht, Jan

PY - 2014/1/1

Y1 - 2014/1/1

N2 - An essential component of any artificial pancreas is on the prediction of blood glucose levels as a function of exogenous and endogenous perturbations such as insulin dose, meal intake, and physical activity and emotional tone under natural living conditions. In this article, we present a new data-driven state-space dynamic model with time-varying coefficients that are used to explicitly quantify the time-varying patient-specific effects of insulin dose and meal intake on blood glucose fluctuations. Using the 3-variate time series of glucose level, insulin dose, and meal intake of an individual type 1 diabetic subject, we apply an extended Kalman filter (EKF) to estimate time-varying coefficients of the patient-specific state-space model. We evaluate our empirical modeling using (1) the FDA-approved UVa/Padova simulator with 30 virtual patients and (2) clinical data of 5 type 1 diabetic patients under natural living conditions. Compared to a forgetting-factor-based recursive ARX model of the same order, the EKF model predictions have higher fit, and significantly better temporal gain and J index and thus are superior in early detection of upward and downward trends in glucose. The EKF based state-space model developed in this article is particularly suitable for model-based state-feedback control designs since the Kalman filter estimates the state variable of the glucose dynamics based on the measured glucose time series. In addition, since the model parameters are estimated in real time, this model is also suitable for adaptive control.

AB - An essential component of any artificial pancreas is on the prediction of blood glucose levels as a function of exogenous and endogenous perturbations such as insulin dose, meal intake, and physical activity and emotional tone under natural living conditions. In this article, we present a new data-driven state-space dynamic model with time-varying coefficients that are used to explicitly quantify the time-varying patient-specific effects of insulin dose and meal intake on blood glucose fluctuations. Using the 3-variate time series of glucose level, insulin dose, and meal intake of an individual type 1 diabetic subject, we apply an extended Kalman filter (EKF) to estimate time-varying coefficients of the patient-specific state-space model. We evaluate our empirical modeling using (1) the FDA-approved UVa/Padova simulator with 30 virtual patients and (2) clinical data of 5 type 1 diabetic patients under natural living conditions. Compared to a forgetting-factor-based recursive ARX model of the same order, the EKF model predictions have higher fit, and significantly better temporal gain and J index and thus are superior in early detection of upward and downward trends in glucose. The EKF based state-space model developed in this article is particularly suitable for model-based state-feedback control designs since the Kalman filter estimates the state variable of the glucose dynamics based on the measured glucose time series. In addition, since the model parameters are estimated in real time, this model is also suitable for adaptive control.

UR - http://www.scopus.com/inward/record.url?scp=84900792152&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84900792152&partnerID=8YFLogxK

U2 - 10.1177/1932296814524080

DO - 10.1177/1932296814524080

M3 - Article

C2 - 24876585

AN - SCOPUS:84900792152

VL - 8

SP - 331

EP - 345

JO - Journal of diabetes science and technology

JF - Journal of diabetes science and technology

SN - 1932-2968

IS - 2

ER -