Machine Learning Based Walking Aid Detection in Timed Up-and-Go Test Recordings of Elderly Patients

Andreas Ziegl; Dieter Hayn; Peter Kastner; Kerstin Loffler; Lisa Weidinger; Bianca Brix; Nandu Goswami; Gunter Schreier

doi:10.1109/EMBC44109.2020.9176574

Machine Learning Based Walking Aid Detection in Timed Up-and-Go Test Recordings of Elderly Patients

Andreas Ziegl, Dieter Hayn, Peter Kastner, Kerstin Loffler, Lisa Weidinger, Bianca Brix, Nandu Goswami, Gunter Schreier

Institute of Neural Engineering (7090)

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

Abstract

Frailty and falls are the main causes of morbidity and disability in elderly people. The Timed Up-and-Go (TUG) test has been proposed as an appropriate method for evaluating elderly individuals' risk of falling. To analyze the TUG's potential for falls prediction, we conducted a clinical study with participants aged ≥ 65 years, living in nursing homes. We harvested 138 TUG recordings with the information, if patients used a walking aid or not and developed a method to predict the use of walking aids using a Random Forest Classifier for ultrasonic based TUG test recordings. We achieved a high accuracy with an Area Under the Curve (AUC) of 96,9% using a 20% leave out evaluation strategy. Automated collection of structured data from TUG recordings - like the use of a walking aid - may help to improve fall risk tools in future.

Original language	English
Title of host publication	42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society
Subtitle of host publication	Enabling Innovative Technologies for Global Healthcare, EMBC 2020
Publisher	Institute of Electrical and Electronics Engineers
Pages	808-811
Number of pages	4
ISBN (Electronic)	9781728119908
DOIs	https://doi.org/10.1109/EMBC44109.2020.9176574
Publication status	Published - Jul 2020
Event	42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society: EMBC 2020 - Virtuell, Montreal, Canada Duration: 20 Jul 2020 → 24 Jul 2020

Publication series

Name	Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
Volume	2020-July
ISSN (Print)	1557-170X

Conference

Conference	42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society
Abbreviated title	EMBC 2020
Country/Territory	Canada
City	Virtuell, Montreal
Period	20/07/20 → 24/07/20

ASJC Scopus subject areas

Signal Processing
Biomedical Engineering
Computer Vision and Pattern Recognition
Health Informatics

UN SDGs

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

Access to Document

10.1109/EMBC44109.2020.9176574

Cite this

Ziegl, A., Hayn, D., Kastner, P., Loffler, K., Weidinger, L., Brix, B., Goswami, N., & Schreier, G. (2020). Machine Learning Based Walking Aid Detection in Timed Up-and-Go Test Recordings of Elderly Patients. In 42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society: Enabling Innovative Technologies for Global Healthcare, EMBC 2020 (pp. 808-811). Article 9176574 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS; Vol. 2020-July). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/EMBC44109.2020.9176574

Machine Learning Based Walking Aid Detection in Timed Up-and-Go Test Recordings of Elderly Patients. / Ziegl, Andreas; Hayn, Dieter; Kastner, Peter et al.
42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society: Enabling Innovative Technologies for Global Healthcare, EMBC 2020. Institute of Electrical and Electronics Engineers, 2020. p. 808-811 9176574 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS; Vol. 2020-July).

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

Ziegl, A, Hayn, D, Kastner, P, Loffler, K, Weidinger, L, Brix, B, Goswami, N & Schreier, G 2020, Machine Learning Based Walking Aid Detection in Timed Up-and-Go Test Recordings of Elderly Patients. in 42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society: Enabling Innovative Technologies for Global Healthcare, EMBC 2020., 9176574, Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, vol. 2020-July, Institute of Electrical and Electronics Engineers, pp. 808-811, 42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society, Virtuell, Montreal, Quebec, Canada, 20/07/20. https://doi.org/10.1109/EMBC44109.2020.9176574

Ziegl A, Hayn D, Kastner P, Loffler K, Weidinger L, Brix B et al. Machine Learning Based Walking Aid Detection in Timed Up-and-Go Test Recordings of Elderly Patients. In 42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society: Enabling Innovative Technologies for Global Healthcare, EMBC 2020. Institute of Electrical and Electronics Engineers. 2020. p. 808-811. 9176574. (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS). doi: 10.1109/EMBC44109.2020.9176574

Ziegl, Andreas ; Hayn, Dieter ; Kastner, Peter et al. / Machine Learning Based Walking Aid Detection in Timed Up-and-Go Test Recordings of Elderly Patients. 42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society: Enabling Innovative Technologies for Global Healthcare, EMBC 2020. Institute of Electrical and Electronics Engineers, 2020. pp. 808-811 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS).

@inproceedings{e630a1ca96714c878ebc6e4e038cc1ee,

title = "Machine Learning Based Walking Aid Detection in Timed Up-and-Go Test Recordings of Elderly Patients",

abstract = "Frailty and falls are the main causes of morbidity and disability in elderly people. The Timed Up-and-Go (TUG) test has been proposed as an appropriate method for evaluating elderly individuals' risk of falling. To analyze the TUG's potential for falls prediction, we conducted a clinical study with participants aged ≥ 65 years, living in nursing homes. We harvested 138 TUG recordings with the information, if patients used a walking aid or not and developed a method to predict the use of walking aids using a Random Forest Classifier for ultrasonic based TUG test recordings. We achieved a high accuracy with an Area Under the Curve (AUC) of 96,9% using a 20% leave out evaluation strategy. Automated collection of structured data from TUG recordings - like the use of a walking aid - may help to improve fall risk tools in future.",

author = "Andreas Ziegl and Dieter Hayn and Peter Kastner and Kerstin Loffler and Lisa Weidinger and Bianca Brix and Nandu Goswami and Gunter Schreier",

year = "2020",

month = jul,

doi = "10.1109/EMBC44109.2020.9176574",

language = "English",

series = "Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS",

publisher = "Institute of Electrical and Electronics Engineers",

pages = "808--811",

booktitle = "42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society",

address = "United States",

note = "42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society : EMBC 2020, EMBC 2020 ; Conference date: 20-07-2020 Through 24-07-2020",

}

TY - GEN

T1 - Machine Learning Based Walking Aid Detection in Timed Up-and-Go Test Recordings of Elderly Patients

AU - Ziegl, Andreas

AU - Hayn, Dieter

AU - Kastner, Peter

AU - Loffler, Kerstin

AU - Weidinger, Lisa

AU - Brix, Bianca

AU - Goswami, Nandu

AU - Schreier, Gunter

PY - 2020/7

Y1 - 2020/7

N2 - Frailty and falls are the main causes of morbidity and disability in elderly people. The Timed Up-and-Go (TUG) test has been proposed as an appropriate method for evaluating elderly individuals' risk of falling. To analyze the TUG's potential for falls prediction, we conducted a clinical study with participants aged ≥ 65 years, living in nursing homes. We harvested 138 TUG recordings with the information, if patients used a walking aid or not and developed a method to predict the use of walking aids using a Random Forest Classifier for ultrasonic based TUG test recordings. We achieved a high accuracy with an Area Under the Curve (AUC) of 96,9% using a 20% leave out evaluation strategy. Automated collection of structured data from TUG recordings - like the use of a walking aid - may help to improve fall risk tools in future.

AB - Frailty and falls are the main causes of morbidity and disability in elderly people. The Timed Up-and-Go (TUG) test has been proposed as an appropriate method for evaluating elderly individuals' risk of falling. To analyze the TUG's potential for falls prediction, we conducted a clinical study with participants aged ≥ 65 years, living in nursing homes. We harvested 138 TUG recordings with the information, if patients used a walking aid or not and developed a method to predict the use of walking aids using a Random Forest Classifier for ultrasonic based TUG test recordings. We achieved a high accuracy with an Area Under the Curve (AUC) of 96,9% using a 20% leave out evaluation strategy. Automated collection of structured data from TUG recordings - like the use of a walking aid - may help to improve fall risk tools in future.

UR - http://www.scopus.com/inward/record.url?scp=85091012902&partnerID=8YFLogxK

U2 - 10.1109/EMBC44109.2020.9176574

DO - 10.1109/EMBC44109.2020.9176574

M3 - Conference paper

AN - SCOPUS:85091012902

T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

SP - 808

EP - 811

BT - 42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society

PB - Institute of Electrical and Electronics Engineers

T2 - 42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society

Y2 - 20 July 2020 through 24 July 2020

ER -

Machine Learning Based Walking Aid Detection in Timed Up-and-Go Test Recordings of Elderly Patients

Abstract

Publication series

Conference

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this