Evaluation of functional tests performance using a camera-based and machine learning approach

Jindřich Adolf; Yoram Segal; Matyáš Turna; Tereza Nováková; Jaromír Doležal; Patrik Kutílek; Jan Hejda; Ofer Hadar; Lenka Lhotská

doi:10.1371/journal.pone.0288279

Evaluation of functional tests performance using a camera-based and machine learning approach

Jindřich Adolf, Yoram Segal, Matyáš Turna, Tereza Nováková, Jaromír Doležal, Patrik Kutílek, Jan Hejda, Ofer Hadar, Lenka Lhotská

Research output: Contribution to journal › Article › peer-review

Abstract

The objective of this study is to evaluate the performance of functional tests using a camera-based system and machine learning techniques. Specifically, we investigate whether OpenPose and any standard camera can be used to assess the quality of the Single Leg Squat Test and Step Down Test functional tests. We recorded these exercises performed by forty-six healthy subjects, extract motion data, and classify them to expert assessments by three independent physiotherapists using 15 binary parameters. We calculated ranges of movement in Keypoint-pair orientations, joint angles, and relative distances of the monitored segments and used machine learning algorithms to predict the physiotherapists’ assessments. Our results show that the AdaBoost classifier achieved a specificity of 0.8, a sensitivity of 0.68, and an accuracy of 0.7. Our findings suggest that a camera-based system combined with machine learning algorithms can be a simple and inexpensive tool to assess the performance quality of functional tests.

Original language	English
Article number	e0288279
Journal	PLoS ONE
Volume	18
Issue number	11 NOVEMBER
DOIs	https://doi.org/10.1371/journal.pone.0288279
State	Published - Nov 2023
Externally published	Yes

Bibliographical note

Publisher Copyright:
© 2023 Adolf et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Funding

This research was supported by a grant from the Ministry of Science & Technology, Israel, and the Ministry of Education, Youth and Sports of the Czech Republic. The described research was supported by the project No. LTAIZ19008 (Czech - supported authors: JA, LL, JD, PK, JH), and No. 8773451 (Israel - supported authors: YS, OH) Enhancing Robotic Physiotherapeutic Treatment

Funders	Funder number
Ministerstvo Školství, Mládeže a Tělovýchovy	LTAIZ19008, 8773451
Ministry of science and technology, Israel

Access to Document

10.1371/journal.pone.0288279

Cite this

@article{55e7d09a8e834b83b02fe2cdbd28b9b7,

title = "Evaluation of functional tests performance using a camera-based and machine learning approach",

abstract = "The objective of this study is to evaluate the performance of functional tests using a camera-based system and machine learning techniques. Specifically, we investigate whether OpenPose and any standard camera can be used to assess the quality of the Single Leg Squat Test and Step Down Test functional tests. We recorded these exercises performed by forty-six healthy subjects, extract motion data, and classify them to expert assessments by three independent physiotherapists using 15 binary parameters. We calculated ranges of movement in Keypoint-pair orientations, joint angles, and relative distances of the monitored segments and used machine learning algorithms to predict the physiotherapists{\textquoteright} assessments. Our results show that the AdaBoost classifier achieved a specificity of 0.8, a sensitivity of 0.68, and an accuracy of 0.7. Our findings suggest that a camera-based system combined with machine learning algorithms can be a simple and inexpensive tool to assess the performance quality of functional tests.",

author = "Jind{\v r}ich Adolf and Yoram Segal and Maty{\'a}{\v s} Turna and Tereza Nov{\'a}kov{\'a} and Jarom{\'i}r Dole{\v z}al and Patrik Kut{\'i}lek and Jan Hejda and Ofer Hadar and Lenka Lhotsk{\'a}",

note = "Publisher Copyright: {\textcopyright} 2023 Adolf et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.",

year = "2023",

month = nov,

doi = "10.1371/journal.pone.0288279",

language = "אנגלית",

volume = "18",

journal = "PLoS ONE",

issn = "1932-6203",

publisher = "Public Library of Science",

number = "11 NOVEMBER",

}

TY - JOUR

T1 - Evaluation of functional tests performance using a camera-based and machine learning approach

AU - Adolf, Jindřich

AU - Segal, Yoram

AU - Turna, Matyáš

AU - Nováková, Tereza

AU - Doležal, Jaromír

AU - Kutílek, Patrik

AU - Hejda, Jan

AU - Hadar, Ofer

AU - Lhotská, Lenka

N1 - Publisher Copyright: © 2023 Adolf et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

PY - 2023/11

Y1 - 2023/11

N2 - The objective of this study is to evaluate the performance of functional tests using a camera-based system and machine learning techniques. Specifically, we investigate whether OpenPose and any standard camera can be used to assess the quality of the Single Leg Squat Test and Step Down Test functional tests. We recorded these exercises performed by forty-six healthy subjects, extract motion data, and classify them to expert assessments by three independent physiotherapists using 15 binary parameters. We calculated ranges of movement in Keypoint-pair orientations, joint angles, and relative distances of the monitored segments and used machine learning algorithms to predict the physiotherapists’ assessments. Our results show that the AdaBoost classifier achieved a specificity of 0.8, a sensitivity of 0.68, and an accuracy of 0.7. Our findings suggest that a camera-based system combined with machine learning algorithms can be a simple and inexpensive tool to assess the performance quality of functional tests.

AB - The objective of this study is to evaluate the performance of functional tests using a camera-based system and machine learning techniques. Specifically, we investigate whether OpenPose and any standard camera can be used to assess the quality of the Single Leg Squat Test and Step Down Test functional tests. We recorded these exercises performed by forty-six healthy subjects, extract motion data, and classify them to expert assessments by three independent physiotherapists using 15 binary parameters. We calculated ranges of movement in Keypoint-pair orientations, joint angles, and relative distances of the monitored segments and used machine learning algorithms to predict the physiotherapists’ assessments. Our results show that the AdaBoost classifier achieved a specificity of 0.8, a sensitivity of 0.68, and an accuracy of 0.7. Our findings suggest that a camera-based system combined with machine learning algorithms can be a simple and inexpensive tool to assess the performance quality of functional tests.

UR - http://www.scopus.com/inward/record.url?scp=85175968582&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0288279

DO - 10.1371/journal.pone.0288279

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

C2 - 37922293

AN - SCOPUS:85175968582

SN - 1932-6203

VL - 18

JO - PLoS ONE

JF - PLoS ONE

IS - 11 NOVEMBER

M1 - e0288279

ER -

Evaluation of functional tests performance using a camera-based and machine learning approach

Abstract

Bibliographical note

Funding

Access to Document

Other files and links

Fingerprint

Cite this