Field evaluation of a random forest activity classifier for wrist-worn accelerometer data.

Objectives: Wrist-worn accelerometers are convenient to wear and associated with greater wear-time compliance. Previous work has generally relied on choreographed activity trials to train and test classification models. However, validity in free-living contexts is starting to emerge. Study aims were...

Descripción completa

Detalles Bibliográficos
Publicado en:Journal of Science & Medicine in Sport Vol. 20; no. 1; pp. 75 - 81
Autores principales: Pavey, Toby G., Gilson, Nicholas D., Gomersall, Sjaan R., Clark, Bronwyn, Trost, Stewart G.
Formato: clinical trial research Journal Article
Publicado: Elsevier B.V. Jan2017
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=120347142&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 120347142
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        14402440
        1FKA
      jtl: Journal of Science & Medicine in Sport
      issn: 14402440
      maglogo: N
    pubinfo:
      dt: Jan2017
      vid: 20
      iid: 1
      pid: 467
      pub: Elsevier B.V.
      place: New York, New York
    artinfo:
      ui:
        120347142
        120347142
        NLM27372275
        120347142
        10.1016/j.jsams.2016.06.003
        NLM27372275
        120347142
      ppf: 75
      ppct: 6
      formats:
      tig:
        atl: Field evaluation of a random forest activity classifier for wrist-worn accelerometer data.
      aug:
        au:
          Pavey, Toby G.
          Gilson, Nicholas D.
          Gomersall, Sjaan R.
          Clark, Bronwyn
          Trost, Stewart G.
        affil: School of Exercise and Nutrition Sciences, Queensland University of Technology, Australia
      sug:
        subj:
          Monitoring, Physiologic Methods
          Accelerometry Methods
          Exercise
          Algorithms
          Human
          Adult
          Sensitivity and Specificity
          Wrist
          Young Adult
          Walking
          Running
          Male
          Random Assignment
          Sedentary Behavior
          Female
          Validation Studies
          Comparative Studies
          Evaluation Research
          Multicenter Studies
          Arthritis Impact Measurement Scales
          Scales
          Clinical Trials
          Adult: 19-44 years
          Male
          Female
      ab: Objectives: Wrist-worn accelerometers are convenient to wear and associated with greater wear-time compliance. Previous work has generally relied on choreographed activity trials to train and test classification models. However, validity in free-living contexts is starting to emerge. Study aims were: (1) train and test a random forest activity classifier for wrist accelerometer data; and (2) determine if models trained on laboratory data perform well under free-living conditions.Design: Twenty-one participants (mean age=27.6±6.2) completed seven lab-based activity trials and a 24h free-living trial (N=16).Methods: Participants wore a GENEActiv monitor on the non-dominant wrist. Classification models recognising four activity classes (sedentary, stationary+, walking, and running) were trained using time and frequency domain features extracted from 10-s non-overlapping windows. Model performance was evaluated using leave-one-out-cross-validation. Models were implemented using the randomForest package within R. Classifier accuracy during the 24h free living trial was evaluated by calculating agreement with concurrently worn activPAL monitors.Results: Overall classification accuracy for the random forest algorithm was 92.7%. Recognition accuracy for sedentary, stationary+, walking, and running was 80.1%, 95.7%, 91.7%, and 93.7%, respectively for the laboratory protocol. Agreement with the activPAL data (stepping vs. non-stepping) during the 24h free-living trial was excellent and, on average, exceeded 90%. The ICC for stepping time was 0.92 (95% CI=0.75-0.97). However, sensitivity and positive predictive values were modest. Mean bias was 10.3min/d (95% LOA=-46.0 to 25.4min/d).Conclusions: The random forest classifier for wrist accelerometer data yielded accurate group-level predictions under controlled conditions, but was less accurate at identifying stepping verse non-stepping behaviour in free living conditions Future studies should conduct more rigorous field-based evaluations using observation as a criterion measure.
      pubtype: Academic Journal
      doctype:
        clinical trial
        research
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N