A deep learning approach to adherence detection for type 2 diabetics

Ali Mohebbi; Tinna Björk Aradóttir; Alexander Rosenberg Johansen; Henrik Bengtsson; Marco Fraccaro; Morten Mørup

doi:10.1109/EMBC.2017.8037462

A deep learning approach to adherence detection for type 2 diabetics

Ali Mohebbi
, Tinna Björk Aradóttir
, Alexander Rosenberg Johansen
, Henrik Bengtsson
, Marco Fraccaro
, Morten Mørup

Novo Nordisk Foundation

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

Abstract

Diabetes has become one of the biggest health problems in the world. In this context, adherence to insulin treatment is essential in order to avoid life-threatening complications. In this pilot study, a novel adherence detection algorithm using Deep Learning (DL) approaches was developed for type 2 diabetes (T2D) patients, based on simulated Continuous Glucose Monitoring (CGM) signals. A large and diverse amount of CGM signals were simulated for T2D patients using a T2D adapted version of the Medtronic Virtual Patient (MVP) model for T1D. By using these signals, different classification algorithms were compared using a comprehensive grid search. We contrast a standard logistic regression baseline to Multi- Layer Perceptrons (MLPs) and Convolutional Neural Networks (CNNs). The best classification performance with an average accuracy of 77:5% was achieved with CNN. Hence, this indicates the potential of DL, when considering adherence detection systems for T2D patients.

Original language	English
Title of host publication	Proceedings of 2017 39th Annual International Conference of the Ieee Engineering in Medicine and Biology Society
Publisher	IEEE
Publication date	2017
Pages	2896-9
ISBN (Print)	978-1-5090-2809-2
DOIs	https://doi.org/10.1109/EMBC.2017.8037462
Publication status	Published - 2017
Event	39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society - International Convention Center, Jeju Island, Jeju, Korea, Republic of Duration: 11 Jul 2017 → 15 Jul 2017 Conference number: 39

Conference

Conference	39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Number	39
Location	International Convention Center, Jeju Island
Country/Territory	Korea, Republic of
City	Jeju
Period	11/07/2017 → 15/07/2017

UN SDGs

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

SDG 3 Good Health and Well-being

Access to Document

10.1109/EMBC.2017.8037462

OpenUrl availability

Full text

Cite this

@inproceedings{da3de830602548f080277179d09c32c4,

title = "A deep learning approach to adherence detection for type 2 diabetics",

abstract = "Diabetes has become one of the biggest health problems in the world. In this context, adherence to insulin treatment is essential in order to avoid life-threatening complications. In this pilot study, a novel adherence detection algorithm using Deep Learning (DL) approaches was developed for type 2 diabetes (T2D) patients, based on simulated Continuous Glucose Monitoring (CGM) signals. A large and diverse amount of CGM signals were simulated for T2D patients using a T2D adapted version of the Medtronic Virtual Patient (MVP) model for T1D. By using these signals, different classification algorithms were compared using a comprehensive grid search. We contrast a standard logistic regression baseline to Multi- Layer Perceptrons (MLPs) and Convolutional Neural Networks (CNNs). The best classification performance with an average accuracy of 77:5\% was achieved with CNN. Hence, this indicates the potential of DL, when considering adherence detection systems for T2D patients.",

author = "Ali Mohebbi and Arad{\'o}ttir, \{Tinna Bj{\"o}rk\} and Johansen, \{Alexander Rosenberg\} and Henrik Bengtsson and Marco Fraccaro and Morten M{\o}rup",

year = "2017",

doi = "10.1109/EMBC.2017.8037462",

language = "English",

isbn = "978-1-5090-2809-2",

pages = "2896--9",

booktitle = "Proceedings of 2017 39th Annual International Conference of the Ieee Engineering in Medicine and Biology Society",

publisher = "IEEE",

address = "United States",

note = "39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2017 ; Conference date: 11-07-2017 Through 15-07-2017",

}

Mohebbi, A, Aradóttir, TB, Johansen, AR, Bengtsson, H, Fraccaro, M & Mørup, M 2017, A deep learning approach to adherence detection for type 2 diabetics. in Proceedings of 2017 39th Annual International Conference of the Ieee Engineering in Medicine and Biology Society. IEEE, pp. 2896-9, 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Jeju, Korea, Republic of, 11/07/2017. https://doi.org/10.1109/EMBC.2017.8037462

A deep learning approach to adherence detection for type 2 diabetics. / Mohebbi, Ali; Aradóttir, Tinna Björk; Johansen, Alexander Rosenberg et al.
Proceedings of 2017 39th Annual International Conference of the Ieee Engineering in Medicine and Biology Society. IEEE, 2017. p. 2896-9.

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

TY - GEN

T1 - A deep learning approach to adherence detection for type 2 diabetics

AU - Mohebbi, Ali

AU - Aradóttir, Tinna Björk

AU - Johansen, Alexander Rosenberg

AU - Bengtsson, Henrik

AU - Fraccaro, Marco

AU - Mørup, Morten

N1 - Conference code: 39

PY - 2017

Y1 - 2017

N2 - Diabetes has become one of the biggest health problems in the world. In this context, adherence to insulin treatment is essential in order to avoid life-threatening complications. In this pilot study, a novel adherence detection algorithm using Deep Learning (DL) approaches was developed for type 2 diabetes (T2D) patients, based on simulated Continuous Glucose Monitoring (CGM) signals. A large and diverse amount of CGM signals were simulated for T2D patients using a T2D adapted version of the Medtronic Virtual Patient (MVP) model for T1D. By using these signals, different classification algorithms were compared using a comprehensive grid search. We contrast a standard logistic regression baseline to Multi- Layer Perceptrons (MLPs) and Convolutional Neural Networks (CNNs). The best classification performance with an average accuracy of 77:5% was achieved with CNN. Hence, this indicates the potential of DL, when considering adherence detection systems for T2D patients.

AB - Diabetes has become one of the biggest health problems in the world. In this context, adherence to insulin treatment is essential in order to avoid life-threatening complications. In this pilot study, a novel adherence detection algorithm using Deep Learning (DL) approaches was developed for type 2 diabetes (T2D) patients, based on simulated Continuous Glucose Monitoring (CGM) signals. A large and diverse amount of CGM signals were simulated for T2D patients using a T2D adapted version of the Medtronic Virtual Patient (MVP) model for T1D. By using these signals, different classification algorithms were compared using a comprehensive grid search. We contrast a standard logistic regression baseline to Multi- Layer Perceptrons (MLPs) and Convolutional Neural Networks (CNNs). The best classification performance with an average accuracy of 77:5% was achieved with CNN. Hence, this indicates the potential of DL, when considering adherence detection systems for T2D patients.

U2 - 10.1109/EMBC.2017.8037462

DO - 10.1109/EMBC.2017.8037462

M3 - Article in proceedings

C2 - 29060503

SN - 978-1-5090-2809-2

SP - 2896

EP - 2899

BT - Proceedings of 2017 39th Annual International Conference of the Ieee Engineering in Medicine and Biology Society

PB - IEEE

T2 - 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society

Y2 - 11 July 2017 through 15 July 2017

ER -

A deep learning approach to adherence detection for type 2 diabetics

Abstract

Conference

UN SDGs

Access to Document

OpenUrl availability

Fingerprint

Cite this