Automated insulin delivery for type 1 diabetes mellitus patients using gaussian process-based model predictive control

Lukas Ortmann; Dawei Shi; Eyal Dassau; Francis J. Doyle; Berno J.E. Misgeld; Steffen Leonhardt

doi:10.23919/acc.2019.8815258

Automated insulin delivery for type 1 diabetes mellitus patients using gaussian process-based model predictive control

Lukas Ortmann
, Dawei Shi
, Eyal Dassau
, Francis J. Doyle
, Berno J.E. Misgeld
, Steffen Leonhardt

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

14 Citations (Scopus)

Abstract

The human insulin-glucose metabolism is a time-varying process, which is partly caused by the changing insulin sensitivity of the body. This insulin sensitivity follows a circadian rhythm and its effects should be anticipated by any automated insulin delivery system. This paper presents an extension of our previous work on automated insulin delivery by developing a controller suitable for humans with Type 1 Diabetes Mellitus. Furthermore, we enhance the controller with a new kernel function for the Gaussian Process and deal with noisy measurements, as well as, the noisy training data for the Gaussian Process, arising therefrom. This enables us to move the proposed control algorithm, a combination of Model Predictive Controller and a Gaussian Process, closer towards clinical application. Simulation results on the University of Virginia/Padova FDA-accepted metabolic simulator are presented for a meal schedule with random carbohydrate sizes and random times of carbohydrate uptake to show the performance of the proposed control scheme.

Original language	English
Title of host publication	2019 American Control Conference, ACC 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	4118-4123
Number of pages	6
ISBN (Electronic)	9781538679265
DOIs	https://doi.org/10.23919/acc.2019.8815258
Publication status	Published - Jul 2019
Externally published	Yes
Event	2019 American Control Conference, ACC 2019 - Philadelphia, United States Duration: 10 Jul 2019 → 12 Jul 2019

Publication series

Name	Proceedings of the American Control Conference
Volume	2019-July
ISSN (Print)	0743-1619

Conference

Conference	2019 American Control Conference, ACC 2019
Country/Territory	United States
City	Philadelphia
Period	10/07/19 → 12/07/19

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Artificial pancreas
Gaussian process
Insulin sensitivity
Model predictive control

Access to Document

10.23919/acc.2019.8815258

Cite this

Ortmann, L., Shi, D., Dassau, E., Doyle, F. J., Misgeld, B. J. E., & Leonhardt, S. (2019). Automated insulin delivery for type 1 diabetes mellitus patients using gaussian process-based model predictive control. In 2019 American Control Conference, ACC 2019 (pp. 4118-4123). Article 8815258 (Proceedings of the American Control Conference; Vol. 2019-July). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/acc.2019.8815258

@inproceedings{a9e2cb1bc6a7483489f8d3f2573f5112,

title = "Automated insulin delivery for type 1 diabetes mellitus patients using gaussian process-based model predictive control",

abstract = "The human insulin-glucose metabolism is a time-varying process, which is partly caused by the changing insulin sensitivity of the body. This insulin sensitivity follows a circadian rhythm and its effects should be anticipated by any automated insulin delivery system. This paper presents an extension of our previous work on automated insulin delivery by developing a controller suitable for humans with Type 1 Diabetes Mellitus. Furthermore, we enhance the controller with a new kernel function for the Gaussian Process and deal with noisy measurements, as well as, the noisy training data for the Gaussian Process, arising therefrom. This enables us to move the proposed control algorithm, a combination of Model Predictive Controller and a Gaussian Process, closer towards clinical application. Simulation results on the University of Virginia/Padova FDA-accepted metabolic simulator are presented for a meal schedule with random carbohydrate sizes and random times of carbohydrate uptake to show the performance of the proposed control scheme.",

keywords = "Artificial pancreas, Gaussian process, Insulin sensitivity, Model predictive control",

author = "Lukas Ortmann and Dawei Shi and Eyal Dassau and Doyle, \{Francis J.\} and Misgeld, \{Berno J.E.\} and Steffen Leonhardt",

note = "Publisher Copyright: {\textcopyright} 2019 American Automatic Control Council.; 2019 American Control Conference, ACC 2019 ; Conference date: 10-07-2019 Through 12-07-2019",

year = "2019",

month = jul,

doi = "10.23919/acc.2019.8815258",

language = "English",

series = "Proceedings of the American Control Conference",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "4118--4123",

booktitle = "2019 American Control Conference, ACC 2019",

address = "United States",

}

Ortmann, L, Shi, D, Dassau, E, Doyle, FJ, Misgeld, BJE & Leonhardt, S 2019, Automated insulin delivery for type 1 diabetes mellitus patients using gaussian process-based model predictive control. in 2019 American Control Conference, ACC 2019., 8815258, Proceedings of the American Control Conference, vol. 2019-July, Institute of Electrical and Electronics Engineers Inc., pp. 4118-4123, 2019 American Control Conference, ACC 2019, Philadelphia, United States, 10/07/19. https://doi.org/10.23919/acc.2019.8815258

Automated insulin delivery for type 1 diabetes mellitus patients using gaussian process-based model predictive control. / Ortmann, Lukas; Shi, Dawei; Dassau, Eyal et al.
2019 American Control Conference, ACC 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 4118-4123 8815258 (Proceedings of the American Control Conference; Vol. 2019-July).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Automated insulin delivery for type 1 diabetes mellitus patients using gaussian process-based model predictive control

AU - Ortmann, Lukas

AU - Shi, Dawei

AU - Dassau, Eyal

AU - Doyle, Francis J.

AU - Misgeld, Berno J.E.

AU - Leonhardt, Steffen

PY - 2019/7

Y1 - 2019/7

N2 - The human insulin-glucose metabolism is a time-varying process, which is partly caused by the changing insulin sensitivity of the body. This insulin sensitivity follows a circadian rhythm and its effects should be anticipated by any automated insulin delivery system. This paper presents an extension of our previous work on automated insulin delivery by developing a controller suitable for humans with Type 1 Diabetes Mellitus. Furthermore, we enhance the controller with a new kernel function for the Gaussian Process and deal with noisy measurements, as well as, the noisy training data for the Gaussian Process, arising therefrom. This enables us to move the proposed control algorithm, a combination of Model Predictive Controller and a Gaussian Process, closer towards clinical application. Simulation results on the University of Virginia/Padova FDA-accepted metabolic simulator are presented for a meal schedule with random carbohydrate sizes and random times of carbohydrate uptake to show the performance of the proposed control scheme.

AB - The human insulin-glucose metabolism is a time-varying process, which is partly caused by the changing insulin sensitivity of the body. This insulin sensitivity follows a circadian rhythm and its effects should be anticipated by any automated insulin delivery system. This paper presents an extension of our previous work on automated insulin delivery by developing a controller suitable for humans with Type 1 Diabetes Mellitus. Furthermore, we enhance the controller with a new kernel function for the Gaussian Process and deal with noisy measurements, as well as, the noisy training data for the Gaussian Process, arising therefrom. This enables us to move the proposed control algorithm, a combination of Model Predictive Controller and a Gaussian Process, closer towards clinical application. Simulation results on the University of Virginia/Padova FDA-accepted metabolic simulator are presented for a meal schedule with random carbohydrate sizes and random times of carbohydrate uptake to show the performance of the proposed control scheme.

KW - Artificial pancreas

KW - Gaussian process

KW - Insulin sensitivity

KW - Model predictive control

UR - https://www.scopus.com/pages/publications/85072284078

U2 - 10.23919/acc.2019.8815258

DO - 10.23919/acc.2019.8815258

M3 - Conference contribution

AN - SCOPUS:85072284078

T3 - Proceedings of the American Control Conference

SP - 4118

EP - 4123

BT - 2019 American Control Conference, ACC 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 American Control Conference, ACC 2019

Y2 - 10 July 2019 through 12 July 2019

ER -

Ortmann L, Shi D, Dassau E, Doyle FJ, Misgeld BJE, Leonhardt S. Automated insulin delivery for type 1 diabetes mellitus patients using gaussian process-based model predictive control. In 2019 American Control Conference, ACC 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 4118-4123. 8815258. (Proceedings of the American Control Conference). doi: 10.23919/acc.2019.8815258

Automated insulin delivery for type 1 diabetes mellitus patients using gaussian process-based model predictive control

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this