Show simple item record

dc.contributor.authorAhmadi, Matthew N
dc.contributor.authorO'Neil, Margaret E
dc.contributor.authorBaque, Emmah
dc.contributor.authorBoyd, Roslyn N
dc.contributor.authorTrost, Stewart G
dc.date.accessioned2020-08-03T23:16:34Z
dc.date.available2020-08-03T23:16:34Z
dc.date.issued2020
dc.identifier.issn1424-8220
dc.identifier.doi10.3390/s20143976
dc.identifier.urihttp://hdl.handle.net/10072/396111
dc.description.abstractPattern recognition methodologies, such as those utilizing machine learning (ML) approaches, have the potential to improve the accuracy and versatility of accelerometer-based assessments of physical activity (PA). Children with cerebral palsy (CP) exhibit significant heterogeneity in relation to impairment and activity limitations; however, studies conducted to date have implemented "one-size fits all" group (G) models. Group-personalized (GP) models specific to the Gross Motor Function Classification (GMFCS) level and fully-personalized (FP) models trained on individual data may provide more accurate assessments of PA; however, these approaches have not been investigated in children with CP. In this study, 38 children classified at GMFCS I to III completed laboratory trials and a simulated free-living protocol while wearing an ActiGraph GT3X+ on the wrist, hip, and ankle. Activities were classified as sedentary, standing utilitarian movements, or walking. In the cross-validation, FP random forest classifiers (99.0-99.3%) exhibited a significantly higher accuracy than G (80.9-94.7%) and GP classifiers (78.7-94.1%), with the largest differential observed in children at GMFCS III. When evaluated under free-living conditions, all model types exhibited significant declines in accuracy, with FP models outperforming G and GP models in GMFCS levels I and II, but not III. Future studies should evaluate the comparative accuracy of personalized models trained on free-living accelerometer data.
dc.description.peerreviewedYes
dc.languageeng
dc.publisherMDPI AG
dc.relation.ispartofpagefrom3976
dc.relation.ispartofissue14
dc.relation.ispartofjournalSensors
dc.relation.ispartofvolume20
dc.subject.fieldofresearchAnalytical Chemistry
dc.subject.fieldofresearchDistributed Computing
dc.subject.fieldofresearchElectrical and Electronic Engineering
dc.subject.fieldofresearchEnvironmental Science and Management
dc.subject.fieldofresearchEcology
dc.subject.fieldofresearchcode0301
dc.subject.fieldofresearchcode0805
dc.subject.fieldofresearchcode0906
dc.subject.fieldofresearchcode0502
dc.subject.fieldofresearchcode0602
dc.subject.keywordsGMFCS level
dc.subject.keywordsaccelerometers
dc.subject.keywordsexercise
dc.subject.keywordsmeasurement
dc.subject.keywordswearable sensors
dc.titleMachine Learning to Quantify Physical Activity in Children with Cerebral Palsy: Comparison of Group, Group-Personalized, and Fully-Personalized Activity Classification Models.
dc.typeJournal article
dc.type.descriptionC1 - Articles
dcterms.bibliographicCitationAhmadi, MN; O'Neil, ME; Baque, E; Boyd, RN; Trost, SG, Machine Learning to Quantify Physical Activity in Children with Cerebral Palsy: Comparison of Group, Group-Personalized, and Fully-Personalized Activity Classification Models., Sensors, 2020, 20 (14), pp. 3976
dcterms.dateAccepted2020-07-16
dcterms.licensehttp://creativecommons.org/licenses/by/4.0/
dc.date.updated2020-08-03T05:15:52Z
dc.description.versionPublished
gro.rights.copyright© 2020 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 (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
gro.hasfulltextFull Text
gro.griffith.authorBaque, Emmah


Files in this item

This item appears in the following Collection(s)

  • Journal articles
    Contains articles published by Griffith authors in scholarly journals.

Show simple item record