A nonlinear data-driven model of glucose dynamics accounting for physical activity for type 1 diabetes: An in silico study

Jinyu Xie, Qian Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Physical activity is an important physiological information which should be taken into account by artificial pancreas to achieve optimal control of blood glucose in Type 1 Diabetes patients. An accurate glucose dynamic model with physical activity as an additional input is highly desirable for the next generation artificial pancreas. In this paper, we present a nonlinear data-driven model that captures both the insulin-independent and -dependent effect of physical activity, especially the prolonged effect of physical activity on insulin sensitivity that can last 24-48 hours post exercise. The model was identified and validated using data sets generated by a physiological glucoseexercise model under a clinical training protocol. Compared to modeling the effect of physical activity as a linear additive term only in a glucose dynamic equation, the proposed nonlinear model showed significant improvement of prediction accuracy in all three metrics, particularly in large prediction horizons (P < 0:05). Further investigation in time-series data indicates that the improvement mainly resulted from the better prediction of glucose around the first meal time after exercise (6 to 8 hours after the meal was taken).

Original languageEnglish (US)
Title of host publicationAdvances in Control Design Methods, Nonlinear and Optimal Control, Robotics, and Wind Energy Systems; Aerospace Applications; Assistive and Rehabilitation Robotics; Assistive Robotics; Battery and Oil and Gas Systems; Bioengineering Applications; Biomedical and Neural Systems Modeling, Diagnostics and Healthcare; Control and Monitoring of Vibratory Systems; Diagnostics and Detection; Energy Harvesting; Estimation and Identification; Fuel Cells/Energy Storage; Intelligent Transportation
PublisherAmerican Society of Mechanical Engineers
ISBN (Electronic)9780791850695
DOIs
StatePublished - Jan 1 2016
EventASME 2016 Dynamic Systems and Control Conference, DSCC 2016 - Minneapolis, United States
Duration: Oct 12 2016Oct 14 2016

Publication series

NameASME 2016 Dynamic Systems and Control Conference, DSCC 2016
Volume1

Other

OtherASME 2016 Dynamic Systems and Control Conference, DSCC 2016
CountryUnited States
CityMinneapolis
Period10/12/1610/14/16

Fingerprint

Medical problems
Glucose
Insulin
Physiological models
Time series
Dynamic models
Blood

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Industrial and Manufacturing Engineering
  • Mechanical Engineering

Cite this

Xie, J., & Wang, Q. (2016). A nonlinear data-driven model of glucose dynamics accounting for physical activity for type 1 diabetes: An in silico study. In Advances in Control Design Methods, Nonlinear and Optimal Control, Robotics, and Wind Energy Systems; Aerospace Applications; Assistive and Rehabilitation Robotics; Assistive Robotics; Battery and Oil and Gas Systems; Bioengineering Applications; Biomedical and Neural Systems Modeling, Diagnostics and Healthcare; Control and Monitoring of Vibratory Systems; Diagnostics and Detection; Energy Harvesting; Estimation and Identification; Fuel Cells/Energy Storage; Intelligent Transportation (ASME 2016 Dynamic Systems and Control Conference, DSCC 2016; Vol. 1). American Society of Mechanical Engineers. https://doi.org/10.1115/DSCC2016-9742
Xie, Jinyu ; Wang, Qian. / A nonlinear data-driven model of glucose dynamics accounting for physical activity for type 1 diabetes : An in silico study. Advances in Control Design Methods, Nonlinear and Optimal Control, Robotics, and Wind Energy Systems; Aerospace Applications; Assistive and Rehabilitation Robotics; Assistive Robotics; Battery and Oil and Gas Systems; Bioengineering Applications; Biomedical and Neural Systems Modeling, Diagnostics and Healthcare; Control and Monitoring of Vibratory Systems; Diagnostics and Detection; Energy Harvesting; Estimation and Identification; Fuel Cells/Energy Storage; Intelligent Transportation. American Society of Mechanical Engineers, 2016. (ASME 2016 Dynamic Systems and Control Conference, DSCC 2016).
@inproceedings{07aecbdfd46e4d36939032bd652347f6,
title = "A nonlinear data-driven model of glucose dynamics accounting for physical activity for type 1 diabetes: An in silico study",
abstract = "Physical activity is an important physiological information which should be taken into account by artificial pancreas to achieve optimal control of blood glucose in Type 1 Diabetes patients. An accurate glucose dynamic model with physical activity as an additional input is highly desirable for the next generation artificial pancreas. In this paper, we present a nonlinear data-driven model that captures both the insulin-independent and -dependent effect of physical activity, especially the prolonged effect of physical activity on insulin sensitivity that can last 24-48 hours post exercise. The model was identified and validated using data sets generated by a physiological glucoseexercise model under a clinical training protocol. Compared to modeling the effect of physical activity as a linear additive term only in a glucose dynamic equation, the proposed nonlinear model showed significant improvement of prediction accuracy in all three metrics, particularly in large prediction horizons (P < 0:05). Further investigation in time-series data indicates that the improvement mainly resulted from the better prediction of glucose around the first meal time after exercise (6 to 8 hours after the meal was taken).",
author = "Jinyu Xie and Qian Wang",
year = "2016",
month = "1",
day = "1",
doi = "10.1115/DSCC2016-9742",
language = "English (US)",
series = "ASME 2016 Dynamic Systems and Control Conference, DSCC 2016",
publisher = "American Society of Mechanical Engineers",
booktitle = "Advances in Control Design Methods, Nonlinear and Optimal Control, Robotics, and Wind Energy Systems; Aerospace Applications; Assistive and Rehabilitation Robotics; Assistive Robotics; Battery and Oil and Gas Systems; Bioengineering Applications; Biomedical and Neural Systems Modeling, Diagnostics and Healthcare; Control and Monitoring of Vibratory Systems; Diagnostics and Detection; Energy Harvesting; Estimation and Identification; Fuel Cells/Energy Storage; Intelligent Transportation",

}

Xie, J & Wang, Q 2016, A nonlinear data-driven model of glucose dynamics accounting for physical activity for type 1 diabetes: An in silico study. in Advances in Control Design Methods, Nonlinear and Optimal Control, Robotics, and Wind Energy Systems; Aerospace Applications; Assistive and Rehabilitation Robotics; Assistive Robotics; Battery and Oil and Gas Systems; Bioengineering Applications; Biomedical and Neural Systems Modeling, Diagnostics and Healthcare; Control and Monitoring of Vibratory Systems; Diagnostics and Detection; Energy Harvesting; Estimation and Identification; Fuel Cells/Energy Storage; Intelligent Transportation. ASME 2016 Dynamic Systems and Control Conference, DSCC 2016, vol. 1, American Society of Mechanical Engineers, ASME 2016 Dynamic Systems and Control Conference, DSCC 2016, Minneapolis, United States, 10/12/16. https://doi.org/10.1115/DSCC2016-9742

A nonlinear data-driven model of glucose dynamics accounting for physical activity for type 1 diabetes : An in silico study. / Xie, Jinyu; Wang, Qian.

Advances in Control Design Methods, Nonlinear and Optimal Control, Robotics, and Wind Energy Systems; Aerospace Applications; Assistive and Rehabilitation Robotics; Assistive Robotics; Battery and Oil and Gas Systems; Bioengineering Applications; Biomedical and Neural Systems Modeling, Diagnostics and Healthcare; Control and Monitoring of Vibratory Systems; Diagnostics and Detection; Energy Harvesting; Estimation and Identification; Fuel Cells/Energy Storage; Intelligent Transportation. American Society of Mechanical Engineers, 2016. (ASME 2016 Dynamic Systems and Control Conference, DSCC 2016; Vol. 1).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A nonlinear data-driven model of glucose dynamics accounting for physical activity for type 1 diabetes

T2 - An in silico study

AU - Xie, Jinyu

AU - Wang, Qian

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Physical activity is an important physiological information which should be taken into account by artificial pancreas to achieve optimal control of blood glucose in Type 1 Diabetes patients. An accurate glucose dynamic model with physical activity as an additional input is highly desirable for the next generation artificial pancreas. In this paper, we present a nonlinear data-driven model that captures both the insulin-independent and -dependent effect of physical activity, especially the prolonged effect of physical activity on insulin sensitivity that can last 24-48 hours post exercise. The model was identified and validated using data sets generated by a physiological glucoseexercise model under a clinical training protocol. Compared to modeling the effect of physical activity as a linear additive term only in a glucose dynamic equation, the proposed nonlinear model showed significant improvement of prediction accuracy in all three metrics, particularly in large prediction horizons (P < 0:05). Further investigation in time-series data indicates that the improvement mainly resulted from the better prediction of glucose around the first meal time after exercise (6 to 8 hours after the meal was taken).

AB - Physical activity is an important physiological information which should be taken into account by artificial pancreas to achieve optimal control of blood glucose in Type 1 Diabetes patients. An accurate glucose dynamic model with physical activity as an additional input is highly desirable for the next generation artificial pancreas. In this paper, we present a nonlinear data-driven model that captures both the insulin-independent and -dependent effect of physical activity, especially the prolonged effect of physical activity on insulin sensitivity that can last 24-48 hours post exercise. The model was identified and validated using data sets generated by a physiological glucoseexercise model under a clinical training protocol. Compared to modeling the effect of physical activity as a linear additive term only in a glucose dynamic equation, the proposed nonlinear model showed significant improvement of prediction accuracy in all three metrics, particularly in large prediction horizons (P < 0:05). Further investigation in time-series data indicates that the improvement mainly resulted from the better prediction of glucose around the first meal time after exercise (6 to 8 hours after the meal was taken).

UR - http://www.scopus.com/inward/record.url?scp=85015942690&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015942690&partnerID=8YFLogxK

U2 - 10.1115/DSCC2016-9742

DO - 10.1115/DSCC2016-9742

M3 - Conference contribution

AN - SCOPUS:85015942690

T3 - ASME 2016 Dynamic Systems and Control Conference, DSCC 2016

BT - Advances in Control Design Methods, Nonlinear and Optimal Control, Robotics, and Wind Energy Systems; Aerospace Applications; Assistive and Rehabilitation Robotics; Assistive Robotics; Battery and Oil and Gas Systems; Bioengineering Applications; Biomedical and Neural Systems Modeling, Diagnostics and Healthcare; Control and Monitoring of Vibratory Systems; Diagnostics and Detection; Energy Harvesting; Estimation and Identification; Fuel Cells/Energy Storage; Intelligent Transportation

PB - American Society of Mechanical Engineers

ER -

Xie J, Wang Q. A nonlinear data-driven model of glucose dynamics accounting for physical activity for type 1 diabetes: An in silico study. In Advances in Control Design Methods, Nonlinear and Optimal Control, Robotics, and Wind Energy Systems; Aerospace Applications; Assistive and Rehabilitation Robotics; Assistive Robotics; Battery and Oil and Gas Systems; Bioengineering Applications; Biomedical and Neural Systems Modeling, Diagnostics and Healthcare; Control and Monitoring of Vibratory Systems; Diagnostics and Detection; Energy Harvesting; Estimation and Identification; Fuel Cells/Energy Storage; Intelligent Transportation. American Society of Mechanical Engineers. 2016. (ASME 2016 Dynamic Systems and Control Conference, DSCC 2016). https://doi.org/10.1115/DSCC2016-9742