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

Andreas Ziegl; Dieter Hayn; Peter Kastner; Kerstin Löffler; Lisa Weidinger; Bianca Brix; Nandu Goswami; Günter Schreier; Günter 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 (Speaker), Dieter Hayn, Peter Kastner, Kerstin Löffler, Lisa Weidinger, Bianca Brix, Nandu Goswami, Günter Schreier, Günter Schreier

Digital Health Information Systems

Research output: Chapter in Book or Conference Proceedings › Conference Proceedings with Oral Presentation › 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	2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
Pages	808-811
Number of pages	4
DOIs	https://doi.org/10.1109/EMBC44109.2020.9176574
Publication status	Published - 2020
Event	Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) - Duration: 20 Jul 2020 → 24 Jul 2020

Conference

Conference	Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
Period	20/07/20 → 24/07/20

Research Field

Exploration of Digital Health

UN SDGs

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

Access to Document

10.1109/EMBC44109.2020.9176574Licence: Unspecified

Cite this

Ziegl, A., Hayn, D., Kastner, P., Löffler, K., Weidinger, L., Brix, B., Goswami, N., Schreier, G., & Schreier, G. (2020). Machine Learning Based Walking Aid Detection in Timed Up-and-Go Test Recordings of Elderly Patients. In 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) (pp. 808-811) https://doi.org/10.1109/EMBC44109.2020.9176574

@inproceedings{8c61ea37c66147ffa5a87c836b3516b3,

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 L{\"o}ffler and Lisa Weidinger and Bianca Brix and Nandu Goswami and G{\"u}nter Schreier and G{\"u}nter Schreier",

year = "2020",

doi = "10.1109/EMBC44109.2020.9176574",

language = "English",

pages = "808--811",

booktitle = "2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)",

note = "Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) ; Conference date: 20-07-2020 Through 24-07-2020",

}

Ziegl, A, Hayn, D, Kastner, P, Löffler, K, Weidinger, L, Brix, B, Goswami, N, Schreier, G & Schreier, G 2020, Machine Learning Based Walking Aid Detection in Timed Up-and-Go Test Recordings of Elderly Patients. in 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). pp. 808-811, Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 20/07/20. 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 (Speaker); Hayn, Dieter; Kastner, Peter et al.
2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). 2020. p. 808-811.

Research output: Chapter in Book or Conference Proceedings › Conference Proceedings with Oral Presentation › peer-review

TY - GEN

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

AU - Hayn, Dieter

AU - Kastner, Peter

AU - Löffler, Kerstin

AU - Weidinger, Lisa

AU - Brix, Bianca

AU - Goswami, Nandu

AU - Schreier, Günter

A2 - Ziegl, Andreas

PY - 2020

Y1 - 2020

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.

U2 - 10.1109/EMBC44109.2020.9176574

DO - 10.1109/EMBC44109.2020.9176574

M3 - Conference Proceedings with Oral Presentation

SP - 808

EP - 811

BT - 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)

T2 - Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)

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

Conference

Research Field

UN SDGs

Access to Document

Fingerprint

Cite this