Machine Learning-Based Classification of Dependence in Ambulation in Stroke Patients Using Smartphone Video Data
The goal of this study was to develop a framework to classify dependence in ambulation by employing a deep model in a 3D convolutional neural network (3D-CNN) using video data recorded by a smartphone during inpatient rehabilitation therapy in stroke patients. Among 2311 video clips, 1218 walk actio...
Gespeichert in:
Veröffentlicht in: | Journal of personalized medicine 2021-10, Vol.11 (11), p.1080 |
---|---|
Hauptverfasser: | , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | 11 |
container_start_page | 1080 |
container_title | Journal of personalized medicine |
container_volume | 11 |
creator | Lee, Jong Taek Park, Eunhee Jung, Tae-Du |
description | The goal of this study was to develop a framework to classify dependence in ambulation by employing a deep model in a 3D convolutional neural network (3D-CNN) using video data recorded by a smartphone during inpatient rehabilitation therapy in stroke patients. Among 2311 video clips, 1218 walk action cases were collected from 206 stroke patients receiving inpatient rehabilitation therapy (63.24 ± 14.36 years old). As ground truth, the dependence in ambulation was assessed and labeled using the functional ambulatory categories (FACs) and Berg balance scale (BBS). The dependent ambulation was defined as a FAC score less than 4 or a BBS score less than 45. We extracted patient-centered video and patient-centered pose of the target from the tracked target’s posture keypoint location information. Then, the extracted patient-centered video was input in the 3D-CNN, and the extracted patient-centered pose was used to measure swing time asymmetry. Finally, we evaluated the classification of dependence in ambulation using video data via fivefold cross-validation. When training the 3D-CNN based on FACs and BBS, the model performed with 86.3% accuracy, 87.4% precision, 94.0% recall, and 90.5% F1 score. When the 3D-CNN based on FACs and BBS was combined with swing time asymmetry, the model exhibited improved performance (88.7% accuracy, 89.1% precision, 95.7% recall, and 92.2% F1 score). The proposed framework for dependence in ambulation can be useful, as it alerts clinicians or caregivers when stroke patients with dependent ambulatory move alone without assistance. In addition, monitoring dependence in ambulation can facilitate the design of individualized rehabilitation strategies for stroke patients with impaired mobility and balance function. |
doi_str_mv | 10.3390/jpm11111080 |
format | Article |
fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_8623599</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2602084364</sourcerecordid><originalsourceid>FETCH-LOGICAL-c386t-92bfaefd4ff195bc1e813786eecb779fe3906edb9e5869b97db7ea63e187be1c3</originalsourceid><addsrcrecordid>eNpdkVFrFDEQx4MottQ--QUCvgiyNdlks8mLUK9WhROFWl9Dkp30cu4m22RX8Nub44pU52UmmR9__jOD0EtKLhhT5O1-nughiCRP0GlL-q7hvBVPH9Un6LyUPakhu7YV5Dk6YVwyzll7iuYvxu1CBLwFk2OId817U2DAm9GUEnxwZgkp4uTxFcwQB4gOcIj4crLreOzV182S00_A3-oHxKXg21KV8M1k8jLvUlX_EQZI-Mos5gV65s1Y4Pwhn6Hb6w_fN5-a7dePnzeX28YxKZZGtdYb8AP3nqrOOgqSsl4KAGf7XnmowwsYrIJOCmVVP9gejGBAZW-BOnaG3h1159VOMLjqK5tRzzlUV791MkH_24lhp-_SLy1FyzqlqsDrB4Gc7lcoi55CcTCOJkJai66b5IeV0q6ir_5D92nNsY53oFoiORO8Um-OlMuplAz-rxlK9OGY-tEx2R96yJJa</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2602084364</pqid></control><display><type>article</type><title>Machine Learning-Based Classification of Dependence in Ambulation in Stroke Patients Using Smartphone Video Data</title><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><source>PubMed Central Open Access</source><source>MDPI - Multidisciplinary Digital Publishing Institute</source><source>PubMed Central</source><creator>Lee, Jong Taek ; Park, Eunhee ; Jung, Tae-Du</creator><creatorcontrib>Lee, Jong Taek ; Park, Eunhee ; Jung, Tae-Du</creatorcontrib><description>The goal of this study was to develop a framework to classify dependence in ambulation by employing a deep model in a 3D convolutional neural network (3D-CNN) using video data recorded by a smartphone during inpatient rehabilitation therapy in stroke patients. Among 2311 video clips, 1218 walk action cases were collected from 206 stroke patients receiving inpatient rehabilitation therapy (63.24 ± 14.36 years old). As ground truth, the dependence in ambulation was assessed and labeled using the functional ambulatory categories (FACs) and Berg balance scale (BBS). The dependent ambulation was defined as a FAC score less than 4 or a BBS score less than 45. We extracted patient-centered video and patient-centered pose of the target from the tracked target’s posture keypoint location information. Then, the extracted patient-centered video was input in the 3D-CNN, and the extracted patient-centered pose was used to measure swing time asymmetry. Finally, we evaluated the classification of dependence in ambulation using video data via fivefold cross-validation. When training the 3D-CNN based on FACs and BBS, the model performed with 86.3% accuracy, 87.4% precision, 94.0% recall, and 90.5% F1 score. When the 3D-CNN based on FACs and BBS was combined with swing time asymmetry, the model exhibited improved performance (88.7% accuracy, 89.1% precision, 95.7% recall, and 92.2% F1 score). The proposed framework for dependence in ambulation can be useful, as it alerts clinicians or caregivers when stroke patients with dependent ambulatory move alone without assistance. In addition, monitoring dependence in ambulation can facilitate the design of individualized rehabilitation strategies for stroke patients with impaired mobility and balance function.</description><identifier>ISSN: 2075-4426</identifier><identifier>EISSN: 2075-4426</identifier><identifier>DOI: 10.3390/jpm11111080</identifier><identifier>PMID: 34834432</identifier><language>eng</language><publisher>Basel: MDPI AG</publisher><subject>Asymmetry ; Caregivers ; Classification ; Falls ; Learning algorithms ; Machine learning ; Mobility ; Neural networks ; Patients ; Posture ; Precision medicine ; Rehabilitation ; Smartphones ; Stroke ; Walking</subject><ispartof>Journal of personalized medicine, 2021-10, Vol.11 (11), p.1080</ispartof><rights>2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>2021 by the authors. 2021</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c386t-92bfaefd4ff195bc1e813786eecb779fe3906edb9e5869b97db7ea63e187be1c3</citedby><cites>FETCH-LOGICAL-c386t-92bfaefd4ff195bc1e813786eecb779fe3906edb9e5869b97db7ea63e187be1c3</cites><orcidid>0000-0002-1636-8665 ; 0000-0002-6962-3148</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC8623599/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC8623599/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,314,727,780,784,885,27924,27925,53791,53793</link.rule.ids></links><search><creatorcontrib>Lee, Jong Taek</creatorcontrib><creatorcontrib>Park, Eunhee</creatorcontrib><creatorcontrib>Jung, Tae-Du</creatorcontrib><title>Machine Learning-Based Classification of Dependence in Ambulation in Stroke Patients Using Smartphone Video Data</title><title>Journal of personalized medicine</title><description>The goal of this study was to develop a framework to classify dependence in ambulation by employing a deep model in a 3D convolutional neural network (3D-CNN) using video data recorded by a smartphone during inpatient rehabilitation therapy in stroke patients. Among 2311 video clips, 1218 walk action cases were collected from 206 stroke patients receiving inpatient rehabilitation therapy (63.24 ± 14.36 years old). As ground truth, the dependence in ambulation was assessed and labeled using the functional ambulatory categories (FACs) and Berg balance scale (BBS). The dependent ambulation was defined as a FAC score less than 4 or a BBS score less than 45. We extracted patient-centered video and patient-centered pose of the target from the tracked target’s posture keypoint location information. Then, the extracted patient-centered video was input in the 3D-CNN, and the extracted patient-centered pose was used to measure swing time asymmetry. Finally, we evaluated the classification of dependence in ambulation using video data via fivefold cross-validation. When training the 3D-CNN based on FACs and BBS, the model performed with 86.3% accuracy, 87.4% precision, 94.0% recall, and 90.5% F1 score. When the 3D-CNN based on FACs and BBS was combined with swing time asymmetry, the model exhibited improved performance (88.7% accuracy, 89.1% precision, 95.7% recall, and 92.2% F1 score). The proposed framework for dependence in ambulation can be useful, as it alerts clinicians or caregivers when stroke patients with dependent ambulatory move alone without assistance. In addition, monitoring dependence in ambulation can facilitate the design of individualized rehabilitation strategies for stroke patients with impaired mobility and balance function.</description><subject>Asymmetry</subject><subject>Caregivers</subject><subject>Classification</subject><subject>Falls</subject><subject>Learning algorithms</subject><subject>Machine learning</subject><subject>Mobility</subject><subject>Neural networks</subject><subject>Patients</subject><subject>Posture</subject><subject>Precision medicine</subject><subject>Rehabilitation</subject><subject>Smartphones</subject><subject>Stroke</subject><subject>Walking</subject><issn>2075-4426</issn><issn>2075-4426</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GNUQQ</sourceid><recordid>eNpdkVFrFDEQx4MottQ--QUCvgiyNdlks8mLUK9WhROFWl9Dkp30cu4m22RX8Nub44pU52UmmR9__jOD0EtKLhhT5O1-nughiCRP0GlL-q7hvBVPH9Un6LyUPakhu7YV5Dk6YVwyzll7iuYvxu1CBLwFk2OId817U2DAm9GUEnxwZgkp4uTxFcwQB4gOcIj4crLreOzV182S00_A3-oHxKXg21KV8M1k8jLvUlX_EQZI-Mos5gV65s1Y4Pwhn6Hb6w_fN5-a7dePnzeX28YxKZZGtdYb8AP3nqrOOgqSsl4KAGf7XnmowwsYrIJOCmVVP9gejGBAZW-BOnaG3h1159VOMLjqK5tRzzlUV791MkH_24lhp-_SLy1FyzqlqsDrB4Gc7lcoi55CcTCOJkJai66b5IeV0q6ir_5D92nNsY53oFoiORO8Um-OlMuplAz-rxlK9OGY-tEx2R96yJJa</recordid><startdate>20211025</startdate><enddate>20211025</enddate><creator>Lee, Jong Taek</creator><creator>Park, Eunhee</creator><creator>Jung, Tae-Du</creator><general>MDPI AG</general><general>MDPI</general><scope>AAYXX</scope><scope>CITATION</scope><scope>8FE</scope><scope>8FH</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BBNVY</scope><scope>BENPR</scope><scope>BHPHI</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>LK8</scope><scope>M7P</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>7X8</scope><scope>5PM</scope><orcidid>https://orcid.org/0000-0002-1636-8665</orcidid><orcidid>https://orcid.org/0000-0002-6962-3148</orcidid></search><sort><creationdate>20211025</creationdate><title>Machine Learning-Based Classification of Dependence in Ambulation in Stroke Patients Using Smartphone Video Data</title><author>Lee, Jong Taek ; Park, Eunhee ; Jung, Tae-Du</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c386t-92bfaefd4ff195bc1e813786eecb779fe3906edb9e5869b97db7ea63e187be1c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Asymmetry</topic><topic>Caregivers</topic><topic>Classification</topic><topic>Falls</topic><topic>Learning algorithms</topic><topic>Machine learning</topic><topic>Mobility</topic><topic>Neural networks</topic><topic>Patients</topic><topic>Posture</topic><topic>Precision medicine</topic><topic>Rehabilitation</topic><topic>Smartphones</topic><topic>Stroke</topic><topic>Walking</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Lee, Jong Taek</creatorcontrib><creatorcontrib>Park, Eunhee</creatorcontrib><creatorcontrib>Jung, Tae-Du</creatorcontrib><collection>CrossRef</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Natural Science Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>Biological Science Collection</collection><collection>ProQuest Central</collection><collection>Natural Science Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Biological Science Collection</collection><collection>Biological Science 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>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Journal of personalized medicine</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Lee, Jong Taek</au><au>Park, Eunhee</au><au>Jung, Tae-Du</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Machine Learning-Based Classification of Dependence in Ambulation in Stroke Patients Using Smartphone Video Data</atitle><jtitle>Journal of personalized medicine</jtitle><date>2021-10-25</date><risdate>2021</risdate><volume>11</volume><issue>11</issue><spage>1080</spage><pages>1080-</pages><issn>2075-4426</issn><eissn>2075-4426</eissn><abstract>The goal of this study was to develop a framework to classify dependence in ambulation by employing a deep model in a 3D convolutional neural network (3D-CNN) using video data recorded by a smartphone during inpatient rehabilitation therapy in stroke patients. Among 2311 video clips, 1218 walk action cases were collected from 206 stroke patients receiving inpatient rehabilitation therapy (63.24 ± 14.36 years old). As ground truth, the dependence in ambulation was assessed and labeled using the functional ambulatory categories (FACs) and Berg balance scale (BBS). The dependent ambulation was defined as a FAC score less than 4 or a BBS score less than 45. We extracted patient-centered video and patient-centered pose of the target from the tracked target’s posture keypoint location information. Then, the extracted patient-centered video was input in the 3D-CNN, and the extracted patient-centered pose was used to measure swing time asymmetry. Finally, we evaluated the classification of dependence in ambulation using video data via fivefold cross-validation. When training the 3D-CNN based on FACs and BBS, the model performed with 86.3% accuracy, 87.4% precision, 94.0% recall, and 90.5% F1 score. When the 3D-CNN based on FACs and BBS was combined with swing time asymmetry, the model exhibited improved performance (88.7% accuracy, 89.1% precision, 95.7% recall, and 92.2% F1 score). The proposed framework for dependence in ambulation can be useful, as it alerts clinicians or caregivers when stroke patients with dependent ambulatory move alone without assistance. In addition, monitoring dependence in ambulation can facilitate the design of individualized rehabilitation strategies for stroke patients with impaired mobility and balance function.</abstract><cop>Basel</cop><pub>MDPI AG</pub><pmid>34834432</pmid><doi>10.3390/jpm11111080</doi><orcidid>https://orcid.org/0000-0002-1636-8665</orcidid><orcidid>https://orcid.org/0000-0002-6962-3148</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 2075-4426 |
ispartof | Journal of personalized medicine, 2021-10, Vol.11 (11), p.1080 |
issn | 2075-4426 2075-4426 |
language | eng |
recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_8623599 |
source | Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals; PubMed Central Open Access; MDPI - Multidisciplinary Digital Publishing Institute; PubMed Central |
subjects | Asymmetry Caregivers Classification Falls Learning algorithms Machine learning Mobility Neural networks Patients Posture Precision medicine Rehabilitation Smartphones Stroke Walking |
title | Machine Learning-Based Classification of Dependence in Ambulation in Stroke Patients Using Smartphone Video Data |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T10%3A36%3A49IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Machine%20Learning-Based%20Classification%20of%20Dependence%20in%20Ambulation%20in%20Stroke%20Patients%20Using%20Smartphone%20Video%20Data&rft.jtitle=Journal%20of%20personalized%20medicine&rft.au=Lee,%20Jong%20Taek&rft.date=2021-10-25&rft.volume=11&rft.issue=11&rft.spage=1080&rft.pages=1080-&rft.issn=2075-4426&rft.eissn=2075-4426&rft_id=info:doi/10.3390/jpm11111080&rft_dat=%3Cproquest_pubme%3E2602084364%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2602084364&rft_id=info:pmid/34834432&rfr_iscdi=true |