Automatically Evaluating Balance: A Machine Learning Approach

Compared to in-clinic balance training, in-home training is not as effective. This is, in part, due to the lack of feedback from physical therapists (PTs). Here, we analyze the feasibility of using trunk sway data and machine learning (ML) techniques to automatically evaluate balance, providing accu...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2019-06
Hauptverfasser: Tian Bao, Klatt, Brooke N, Whitney, Susan L, Sienko, Kathleen H, Wiens, Jenna
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Tian Bao
Klatt, Brooke N
Whitney, Susan L
Sienko, Kathleen H
Wiens, Jenna
description Compared to in-clinic balance training, in-home training is not as effective. This is, in part, due to the lack of feedback from physical therapists (PTs). Here, we analyze the feasibility of using trunk sway data and machine learning (ML) techniques to automatically evaluate balance, providing accurate assessments outside of the clinic. We recruited sixteen participants to perform standing balance exercises. For each exercise, we recorded trunk sway data and had a PT rate balance performance on a scale of 1 to 5. The rating scale was adapted from the Functional Independence Measure. From the trunk sway data, we extracted a 61-dimensional feature vector representing performance of each exercise. Given these labeled data, we trained a multi-class support vector machine (SVM) to map trunk sway features to PT ratings. Evaluated in a leave-one-participant-out scheme, the model achieved a classification accuracy of 82%. Compared to participant self-assessment ratings, the SVM outputs were significantly closer to PT ratings. The results of this pilot study suggest that in the absence of PTs, ML techniques can provide accurate assessments during standing balance exercises. Such automated assessments could reduce PT consultation time and increase user compliance outside of the clinic.
doi_str_mv 10.48550/arxiv.1906.05657
format Article
fullrecord <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_1906_05657</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2239956439</sourcerecordid><originalsourceid>FETCH-LOGICAL-a529-d471b30bc02f3fc7cf0636c3d797824915e1534e14778a6a1eb0b64b35e162883</originalsourceid><addsrcrecordid>eNotj09Lw0AUxBdBsNR-AE8GPCfu7tu_godYWhUiXnoPL9uNpqRJ3CTFfnvT1tPw5g3D_Ai5YzQRRkr6iOG3OiTMUpVQqaS-IjMOwGIjOL8hi77fUUq50lxKmJHndBzaPQ6Vw7o-RqsD1uN0NV_RC9bYOP8UpdEHuu-q8VHmMTSnX9p1oZ3MW3JdYt37xb_OyWa92izf4uzz9X2ZZjFKbuOt0KwAWjjKSyiddiVVoBxstdWGC8ukZxKEZ0JrgwqZL2ihRAGTr7gxMCf3l9ozW96Fao_hmJ8Y8zPjlHi4JKZdP6Pvh3zXjqGZNuWcg7VSCbDwBx-FUlw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2239956439</pqid></control><display><type>article</type><title>Automatically Evaluating Balance: A Machine Learning Approach</title><source>arXiv.org</source><source>Free E- Journals</source><creator>Tian Bao ; Klatt, Brooke N ; Whitney, Susan L ; Sienko, Kathleen H ; Wiens, Jenna</creator><creatorcontrib>Tian Bao ; Klatt, Brooke N ; Whitney, Susan L ; Sienko, Kathleen H ; Wiens, Jenna</creatorcontrib><description>Compared to in-clinic balance training, in-home training is not as effective. This is, in part, due to the lack of feedback from physical therapists (PTs). Here, we analyze the feasibility of using trunk sway data and machine learning (ML) techniques to automatically evaluate balance, providing accurate assessments outside of the clinic. We recruited sixteen participants to perform standing balance exercises. For each exercise, we recorded trunk sway data and had a PT rate balance performance on a scale of 1 to 5. The rating scale was adapted from the Functional Independence Measure. From the trunk sway data, we extracted a 61-dimensional feature vector representing performance of each exercise. Given these labeled data, we trained a multi-class support vector machine (SVM) to map trunk sway features to PT ratings. Evaluated in a leave-one-participant-out scheme, the model achieved a classification accuracy of 82%. Compared to participant self-assessment ratings, the SVM outputs were significantly closer to PT ratings. The results of this pilot study suggest that in the absence of PTs, ML techniques can provide accurate assessments during standing balance exercises. Such automated assessments could reduce PT consultation time and increase user compliance outside of the clinic.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.1906.05657</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Artificial intelligence ; Balance ; Computer Science - Computers and Society ; Computer Science - Learning ; Consultation ; Feasibility studies ; Feature extraction ; Machine learning ; Model accuracy ; Ratings ; Self assessment ; Statistics - Machine Learning ; Support vector machines ; Training</subject><ispartof>arXiv.org, 2019-06</ispartof><rights>2019. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,784,885,27923</link.rule.ids><backlink>$$Uhttps://doi.org/10.1109/TNSRE.2019.2891000$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.48550/arXiv.1906.05657$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Tian Bao</creatorcontrib><creatorcontrib>Klatt, Brooke N</creatorcontrib><creatorcontrib>Whitney, Susan L</creatorcontrib><creatorcontrib>Sienko, Kathleen H</creatorcontrib><creatorcontrib>Wiens, Jenna</creatorcontrib><title>Automatically Evaluating Balance: A Machine Learning Approach</title><title>arXiv.org</title><description>Compared to in-clinic balance training, in-home training is not as effective. This is, in part, due to the lack of feedback from physical therapists (PTs). Here, we analyze the feasibility of using trunk sway data and machine learning (ML) techniques to automatically evaluate balance, providing accurate assessments outside of the clinic. We recruited sixteen participants to perform standing balance exercises. For each exercise, we recorded trunk sway data and had a PT rate balance performance on a scale of 1 to 5. The rating scale was adapted from the Functional Independence Measure. From the trunk sway data, we extracted a 61-dimensional feature vector representing performance of each exercise. Given these labeled data, we trained a multi-class support vector machine (SVM) to map trunk sway features to PT ratings. Evaluated in a leave-one-participant-out scheme, the model achieved a classification accuracy of 82%. Compared to participant self-assessment ratings, the SVM outputs were significantly closer to PT ratings. The results of this pilot study suggest that in the absence of PTs, ML techniques can provide accurate assessments during standing balance exercises. Such automated assessments could reduce PT consultation time and increase user compliance outside of the clinic.</description><subject>Artificial intelligence</subject><subject>Balance</subject><subject>Computer Science - Computers and Society</subject><subject>Computer Science - Learning</subject><subject>Consultation</subject><subject>Feasibility studies</subject><subject>Feature extraction</subject><subject>Machine learning</subject><subject>Model accuracy</subject><subject>Ratings</subject><subject>Self assessment</subject><subject>Statistics - Machine Learning</subject><subject>Support vector machines</subject><subject>Training</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GOX</sourceid><recordid>eNotj09Lw0AUxBdBsNR-AE8GPCfu7tu_godYWhUiXnoPL9uNpqRJ3CTFfnvT1tPw5g3D_Ai5YzQRRkr6iOG3OiTMUpVQqaS-IjMOwGIjOL8hi77fUUq50lxKmJHndBzaPQ6Vw7o-RqsD1uN0NV_RC9bYOP8UpdEHuu-q8VHmMTSnX9p1oZ3MW3JdYt37xb_OyWa92izf4uzz9X2ZZjFKbuOt0KwAWjjKSyiddiVVoBxstdWGC8ukZxKEZ0JrgwqZL2ihRAGTr7gxMCf3l9ozW96Fao_hmJ8Y8zPjlHi4JKZdP6Pvh3zXjqGZNuWcg7VSCbDwBx-FUlw</recordid><startdate>20190607</startdate><enddate>20190607</enddate><creator>Tian Bao</creator><creator>Klatt, Brooke N</creator><creator>Whitney, Susan L</creator><creator>Sienko, Kathleen H</creator><creator>Wiens, Jenna</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><scope>AKY</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20190607</creationdate><title>Automatically Evaluating Balance: A Machine Learning Approach</title><author>Tian Bao ; Klatt, Brooke N ; Whitney, Susan L ; Sienko, Kathleen H ; Wiens, Jenna</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a529-d471b30bc02f3fc7cf0636c3d797824915e1534e14778a6a1eb0b64b35e162883</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Artificial intelligence</topic><topic>Balance</topic><topic>Computer Science - Computers and Society</topic><topic>Computer Science - Learning</topic><topic>Consultation</topic><topic>Feasibility studies</topic><topic>Feature extraction</topic><topic>Machine learning</topic><topic>Model accuracy</topic><topic>Ratings</topic><topic>Self assessment</topic><topic>Statistics - Machine Learning</topic><topic>Support vector machines</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Tian Bao</creatorcontrib><creatorcontrib>Klatt, Brooke N</creatorcontrib><creatorcontrib>Whitney, Susan L</creatorcontrib><creatorcontrib>Sienko, Kathleen H</creatorcontrib><creatorcontrib>Wiens, Jenna</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><collection>arXiv Computer Science</collection><collection>arXiv Statistics</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Tian Bao</au><au>Klatt, Brooke N</au><au>Whitney, Susan L</au><au>Sienko, Kathleen H</au><au>Wiens, Jenna</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Automatically Evaluating Balance: A Machine Learning Approach</atitle><jtitle>arXiv.org</jtitle><date>2019-06-07</date><risdate>2019</risdate><eissn>2331-8422</eissn><abstract>Compared to in-clinic balance training, in-home training is not as effective. This is, in part, due to the lack of feedback from physical therapists (PTs). Here, we analyze the feasibility of using trunk sway data and machine learning (ML) techniques to automatically evaluate balance, providing accurate assessments outside of the clinic. We recruited sixteen participants to perform standing balance exercises. For each exercise, we recorded trunk sway data and had a PT rate balance performance on a scale of 1 to 5. The rating scale was adapted from the Functional Independence Measure. From the trunk sway data, we extracted a 61-dimensional feature vector representing performance of each exercise. Given these labeled data, we trained a multi-class support vector machine (SVM) to map trunk sway features to PT ratings. Evaluated in a leave-one-participant-out scheme, the model achieved a classification accuracy of 82%. Compared to participant self-assessment ratings, the SVM outputs were significantly closer to PT ratings. The results of this pilot study suggest that in the absence of PTs, ML techniques can provide accurate assessments during standing balance exercises. Such automated assessments could reduce PT consultation time and increase user compliance outside of the clinic.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.1906.05657</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2019-06
issn 2331-8422
language eng
recordid cdi_arxiv_primary_1906_05657
source arXiv.org; Free E- Journals
subjects Artificial intelligence
Balance
Computer Science - Computers and Society
Computer Science - Learning
Consultation
Feasibility studies
Feature extraction
Machine learning
Model accuracy
Ratings
Self assessment
Statistics - Machine Learning
Support vector machines
Training
title Automatically Evaluating Balance: A Machine Learning Approach
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-09T18%3A48%3A07IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Automatically%20Evaluating%20Balance:%20A%20Machine%20Learning%20Approach&rft.jtitle=arXiv.org&rft.au=Tian%20Bao&rft.date=2019-06-07&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.1906.05657&rft_dat=%3Cproquest_arxiv%3E2239956439%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2239956439&rft_id=info:pmid/&rfr_iscdi=true