Evaluation of functional tests performance using a camera-based and machine learning approach.
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 function...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2023-01-01
|
Series: | PLoS ONE |
Online Access: | https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0288279&type=printable |
_version_ | 1797633310278549504 |
---|---|
author | Jindřich Adolf Yoram Segal Matyáš Turna Tereza Nováková Jaromír Doležal Patrik Kutílek Jan Hejda Ofer Hadar Lenka Lhotská |
author_facet | Jindřich Adolf Yoram Segal Matyáš Turna Tereza Nováková Jaromír Doležal Patrik Kutílek Jan Hejda Ofer Hadar Lenka Lhotská |
author_sort | Jindřich Adolf |
collection | DOAJ |
description | 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. |
first_indexed | 2024-03-11T11:52:18Z |
format | Article |
id | doaj.art-d31b87b4e28d4be7a8484f14686acfbe |
institution | Directory Open Access Journal |
issn | 1932-6203 |
language | English |
last_indexed | 2024-03-11T11:52:18Z |
publishDate | 2023-01-01 |
publisher | Public Library of Science (PLoS) |
record_format | Article |
series | PLoS ONE |
spelling | doaj.art-d31b87b4e28d4be7a8484f14686acfbe2023-11-09T05:32:12ZengPublic Library of Science (PLoS)PLoS ONE1932-62032023-01-011811e028827910.1371/journal.pone.0288279Evaluation of functional tests performance using a camera-based and machine learning approach.Jindřich AdolfYoram SegalMatyáš TurnaTereza NovákováJaromír DoležalPatrik KutílekJan HejdaOfer HadarLenka LhotskáThe 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.https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0288279&type=printable |
spellingShingle | Jindřich Adolf Yoram Segal Matyáš Turna Tereza Nováková Jaromír Doležal Patrik Kutílek Jan Hejda Ofer Hadar Lenka Lhotská Evaluation of functional tests performance using a camera-based and machine learning approach. PLoS ONE |
title | Evaluation of functional tests performance using a camera-based and machine learning approach. |
title_full | Evaluation of functional tests performance using a camera-based and machine learning approach. |
title_fullStr | Evaluation of functional tests performance using a camera-based and machine learning approach. |
title_full_unstemmed | Evaluation of functional tests performance using a camera-based and machine learning approach. |
title_short | Evaluation of functional tests performance using a camera-based and machine learning approach. |
title_sort | evaluation of functional tests performance using a camera based and machine learning approach |
url | https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0288279&type=printable |
work_keys_str_mv | AT jindrichadolf evaluationoffunctionaltestsperformanceusingacamerabasedandmachinelearningapproach AT yoramsegal evaluationoffunctionaltestsperformanceusingacamerabasedandmachinelearningapproach AT matyasturna evaluationoffunctionaltestsperformanceusingacamerabasedandmachinelearningapproach AT terezanovakova evaluationoffunctionaltestsperformanceusingacamerabasedandmachinelearningapproach AT jaromirdolezal evaluationoffunctionaltestsperformanceusingacamerabasedandmachinelearningapproach AT patrikkutilek evaluationoffunctionaltestsperformanceusingacamerabasedandmachinelearningapproach AT janhejda evaluationoffunctionaltestsperformanceusingacamerabasedandmachinelearningapproach AT oferhadar evaluationoffunctionaltestsperformanceusingacamerabasedandmachinelearningapproach AT lenkalhotska evaluationoffunctionaltestsperformanceusingacamerabasedandmachinelearningapproach |