A personalized diet and exercise recommender system in minimizing clinical risk for type 1 diabetes

An in silico study

Jinyu Xie, Qian Wang

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

    2 Citations (Scopus)

    Abstract

    Risk of having hypoglycemia is one of the biggest barriers preventing Type 1 Diabetes (T1D) patients from performing exercise. In addition, management of diet and exercise levels needs to be personalized for each patient to avoid hypoglycemia and to achieve a good glycemic control. In this paper, we developed a model-based diet and exercise recommender system that could be used to provide an (optimal) personalized intervention on diet and exercise for T1D patients. The recommender system makes prediction of blood glucose at each intervention time based on a patient-specific model of glucose dynamics, and then provides the optimal meal sizes, target heart rates during exercise, pre-exercise carbohydrate and bedtime snack by minimizing a clinical risk function under constraints. Patient-specific models of glucose dynamics were identified for 30 virtual subjects generated from a modified UVa/Padova simulator with an added exercise-glucose subsystem. The performance of the recommender system was then compared to two self-management schemes (the Starter and the Skilled). The latter represents an off-line optimal solution providing a lower bound on the risk index. The average clinical risk under the recommender system was reduced by 49% compared to that under the Starter, and it was comparable to the risk of the Skilled. In addition, the recommender system had less number of postexercise/ nocturnal hypoglycemia events occurred than that under the Starter or the Skilled. Such recommender system can be implemented as an "App" patient advisor to improve T1D patients' self-management of glucose control.

    Original languageEnglish (US)
    Title of host publicationAerospace Applications; Advances in Control Design Methods; Bio Engineering Applications; Advances in Non-Linear Control; Adaptive and Intelligent Systems Control; Advances in Wind Energy Systems; Advances in Robotics; Assistive and Rehabilitation Robotics; Biomedical and Neural Systems Modeling, Diagnostics, and Control; Bio-Mechatronics and Physical Human Robot; Advanced Driver Assistance Systems and Autonomous Vehicles; Automotive Systems
    PublisherAmerican Society of Mechanical Engineers
    ISBN (Electronic)9780791858271
    DOIs
    StatePublished - Jan 1 2017
    EventASME 2017 Dynamic Systems and Control Conference, DSCC 2017 - Tysons, United States
    Duration: Oct 11 2017Oct 13 2017

    Publication series

    NameASME 2017 Dynamic Systems and Control Conference, DSCC 2017
    Volume1

    Other

    OtherASME 2017 Dynamic Systems and Control Conference, DSCC 2017
    CountryUnited States
    CityTysons
    Period10/11/1710/13/17

    Fingerprint

    Recommender systems
    Nutrition
    Medical problems
    Glucose
    Starters
    Carbohydrates
    Application programs
    Blood
    Simulators

    All Science Journal Classification (ASJC) codes

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

    Cite this

    Xie, J., & Wang, Q. (2017). A personalized diet and exercise recommender system in minimizing clinical risk for type 1 diabetes: An in silico study. In Aerospace Applications; Advances in Control Design Methods; Bio Engineering Applications; Advances in Non-Linear Control; Adaptive and Intelligent Systems Control; Advances in Wind Energy Systems; Advances in Robotics; Assistive and Rehabilitation Robotics; Biomedical and Neural Systems Modeling, Diagnostics, and Control; Bio-Mechatronics and Physical Human Robot; Advanced Driver Assistance Systems and Autonomous Vehicles; Automotive Systems (ASME 2017 Dynamic Systems and Control Conference, DSCC 2017; Vol. 1). American Society of Mechanical Engineers. https://doi.org/10.1115/DSCC2017-5136
    Xie, Jinyu ; Wang, Qian. / A personalized diet and exercise recommender system in minimizing clinical risk for type 1 diabetes : An in silico study. Aerospace Applications; Advances in Control Design Methods; Bio Engineering Applications; Advances in Non-Linear Control; Adaptive and Intelligent Systems Control; Advances in Wind Energy Systems; Advances in Robotics; Assistive and Rehabilitation Robotics; Biomedical and Neural Systems Modeling, Diagnostics, and Control; Bio-Mechatronics and Physical Human Robot; Advanced Driver Assistance Systems and Autonomous Vehicles; Automotive Systems. American Society of Mechanical Engineers, 2017. (ASME 2017 Dynamic Systems and Control Conference, DSCC 2017).
    @inproceedings{0192e9701ec3488d9c94102d113fad24,
    title = "A personalized diet and exercise recommender system in minimizing clinical risk for type 1 diabetes: An in silico study",
    abstract = "Risk of having hypoglycemia is one of the biggest barriers preventing Type 1 Diabetes (T1D) patients from performing exercise. In addition, management of diet and exercise levels needs to be personalized for each patient to avoid hypoglycemia and to achieve a good glycemic control. In this paper, we developed a model-based diet and exercise recommender system that could be used to provide an (optimal) personalized intervention on diet and exercise for T1D patients. The recommender system makes prediction of blood glucose at each intervention time based on a patient-specific model of glucose dynamics, and then provides the optimal meal sizes, target heart rates during exercise, pre-exercise carbohydrate and bedtime snack by minimizing a clinical risk function under constraints. Patient-specific models of glucose dynamics were identified for 30 virtual subjects generated from a modified UVa/Padova simulator with an added exercise-glucose subsystem. The performance of the recommender system was then compared to two self-management schemes (the Starter and the Skilled). The latter represents an off-line optimal solution providing a lower bound on the risk index. The average clinical risk under the recommender system was reduced by 49{\%} compared to that under the Starter, and it was comparable to the risk of the Skilled. In addition, the recommender system had less number of postexercise/ nocturnal hypoglycemia events occurred than that under the Starter or the Skilled. Such recommender system can be implemented as an {"}App{"} patient advisor to improve T1D patients' self-management of glucose control.",
    author = "Jinyu Xie and Qian Wang",
    year = "2017",
    month = "1",
    day = "1",
    doi = "10.1115/DSCC2017-5136",
    language = "English (US)",
    series = "ASME 2017 Dynamic Systems and Control Conference, DSCC 2017",
    publisher = "American Society of Mechanical Engineers",
    booktitle = "Aerospace Applications; Advances in Control Design Methods; Bio Engineering Applications; Advances in Non-Linear Control; Adaptive and Intelligent Systems Control; Advances in Wind Energy Systems; Advances in Robotics; Assistive and Rehabilitation Robotics; Biomedical and Neural Systems Modeling, Diagnostics, and Control; Bio-Mechatronics and Physical Human Robot; Advanced Driver Assistance Systems and Autonomous Vehicles; Automotive Systems",

    }

    Xie, J & Wang, Q 2017, A personalized diet and exercise recommender system in minimizing clinical risk for type 1 diabetes: An in silico study. in Aerospace Applications; Advances in Control Design Methods; Bio Engineering Applications; Advances in Non-Linear Control; Adaptive and Intelligent Systems Control; Advances in Wind Energy Systems; Advances in Robotics; Assistive and Rehabilitation Robotics; Biomedical and Neural Systems Modeling, Diagnostics, and Control; Bio-Mechatronics and Physical Human Robot; Advanced Driver Assistance Systems and Autonomous Vehicles; Automotive Systems. ASME 2017 Dynamic Systems and Control Conference, DSCC 2017, vol. 1, American Society of Mechanical Engineers, ASME 2017 Dynamic Systems and Control Conference, DSCC 2017, Tysons, United States, 10/11/17. https://doi.org/10.1115/DSCC2017-5136

    A personalized diet and exercise recommender system in minimizing clinical risk for type 1 diabetes : An in silico study. / Xie, Jinyu; Wang, Qian.

    Aerospace Applications; Advances in Control Design Methods; Bio Engineering Applications; Advances in Non-Linear Control; Adaptive and Intelligent Systems Control; Advances in Wind Energy Systems; Advances in Robotics; Assistive and Rehabilitation Robotics; Biomedical and Neural Systems Modeling, Diagnostics, and Control; Bio-Mechatronics and Physical Human Robot; Advanced Driver Assistance Systems and Autonomous Vehicles; Automotive Systems. American Society of Mechanical Engineers, 2017. (ASME 2017 Dynamic Systems and Control Conference, DSCC 2017; Vol. 1).

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

    TY - GEN

    T1 - A personalized diet and exercise recommender system in minimizing clinical risk for type 1 diabetes

    T2 - An in silico study

    AU - Xie, Jinyu

    AU - Wang, Qian

    PY - 2017/1/1

    Y1 - 2017/1/1

    N2 - Risk of having hypoglycemia is one of the biggest barriers preventing Type 1 Diabetes (T1D) patients from performing exercise. In addition, management of diet and exercise levels needs to be personalized for each patient to avoid hypoglycemia and to achieve a good glycemic control. In this paper, we developed a model-based diet and exercise recommender system that could be used to provide an (optimal) personalized intervention on diet and exercise for T1D patients. The recommender system makes prediction of blood glucose at each intervention time based on a patient-specific model of glucose dynamics, and then provides the optimal meal sizes, target heart rates during exercise, pre-exercise carbohydrate and bedtime snack by minimizing a clinical risk function under constraints. Patient-specific models of glucose dynamics were identified for 30 virtual subjects generated from a modified UVa/Padova simulator with an added exercise-glucose subsystem. The performance of the recommender system was then compared to two self-management schemes (the Starter and the Skilled). The latter represents an off-line optimal solution providing a lower bound on the risk index. The average clinical risk under the recommender system was reduced by 49% compared to that under the Starter, and it was comparable to the risk of the Skilled. In addition, the recommender system had less number of postexercise/ nocturnal hypoglycemia events occurred than that under the Starter or the Skilled. Such recommender system can be implemented as an "App" patient advisor to improve T1D patients' self-management of glucose control.

    AB - Risk of having hypoglycemia is one of the biggest barriers preventing Type 1 Diabetes (T1D) patients from performing exercise. In addition, management of diet and exercise levels needs to be personalized for each patient to avoid hypoglycemia and to achieve a good glycemic control. In this paper, we developed a model-based diet and exercise recommender system that could be used to provide an (optimal) personalized intervention on diet and exercise for T1D patients. The recommender system makes prediction of blood glucose at each intervention time based on a patient-specific model of glucose dynamics, and then provides the optimal meal sizes, target heart rates during exercise, pre-exercise carbohydrate and bedtime snack by minimizing a clinical risk function under constraints. Patient-specific models of glucose dynamics were identified for 30 virtual subjects generated from a modified UVa/Padova simulator with an added exercise-glucose subsystem. The performance of the recommender system was then compared to two self-management schemes (the Starter and the Skilled). The latter represents an off-line optimal solution providing a lower bound on the risk index. The average clinical risk under the recommender system was reduced by 49% compared to that under the Starter, and it was comparable to the risk of the Skilled. In addition, the recommender system had less number of postexercise/ nocturnal hypoglycemia events occurred than that under the Starter or the Skilled. Such recommender system can be implemented as an "App" patient advisor to improve T1D patients' self-management of glucose control.

    UR - http://www.scopus.com/inward/record.url?scp=85036649630&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85036649630&partnerID=8YFLogxK

    U2 - 10.1115/DSCC2017-5136

    DO - 10.1115/DSCC2017-5136

    M3 - Conference contribution

    T3 - ASME 2017 Dynamic Systems and Control Conference, DSCC 2017

    BT - Aerospace Applications; Advances in Control Design Methods; Bio Engineering Applications; Advances in Non-Linear Control; Adaptive and Intelligent Systems Control; Advances in Wind Energy Systems; Advances in Robotics; Assistive and Rehabilitation Robotics; Biomedical and Neural Systems Modeling, Diagnostics, and Control; Bio-Mechatronics and Physical Human Robot; Advanced Driver Assistance Systems and Autonomous Vehicles; Automotive Systems

    PB - American Society of Mechanical Engineers

    ER -

    Xie J, Wang Q. A personalized diet and exercise recommender system in minimizing clinical risk for type 1 diabetes: An in silico study. In Aerospace Applications; Advances in Control Design Methods; Bio Engineering Applications; Advances in Non-Linear Control; Adaptive and Intelligent Systems Control; Advances in Wind Energy Systems; Advances in Robotics; Assistive and Rehabilitation Robotics; Biomedical and Neural Systems Modeling, Diagnostics, and Control; Bio-Mechatronics and Physical Human Robot; Advanced Driver Assistance Systems and Autonomous Vehicles; Automotive Systems. American Society of Mechanical Engineers. 2017. (ASME 2017 Dynamic Systems and Control Conference, DSCC 2017). https://doi.org/10.1115/DSCC2017-5136