Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Monday, March 11, 2019 at 4:00 PM to 4:30 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Advertisement

Currently submitted to: JMIR Formative Research

Date Submitted: Oct 17, 2019
Open Peer Review Period: Oct 17, 2019 - Dec 12, 2019
(currently open for review)

Machine Learning Approaches to Calibrate Wrist-Worn Accelerometry for Physical Activity Assessment in Preschoolers

  • Shiyu Li; 
  • Zenong Yin; 
  • Jeffrey Howard; 
  • Erica Sosa; 
  • Alberto Cordova; 
  • Deborah Parra-Medina; 

ABSTRACT

Background:

Physical activity (PA) level is associated with multiple health benefits during early childhood. However, inconsistency remains in the quantification of PA levels in preschoolers.

Objective:

The present study used machine learning (ML) approaches to develop PA intensity cut-points for wrist-worn accelerometry to assess PA in preschoolers.

Methods:

Wrist- and hip-worn accelerometer data were collected simultaneously from 34 preschoolers for three consecutive preschool days. Two supervised ML models, receiver operating characteristic curve (ROC) and ordinal logistic regression (OLR), and one unsupervised ML model, k-means cluster analysis, were applied to establish wrist-worn accelerometer vector magnitude (VM) cut-points to classify accelerometer counts into sedentary behavior (SED), light PA (LPA), moderate PA (MPA), and vigorous PA (VPA). PA intensity levels identified by hip-worn accelerometer VM cut-points were used as the reference to train the supervised ML models. VM counts were classified by intensity based on three newly established wrist methods and the hip reference to examine classification accuracy. Estimates of PA were compared to the hip reference at daily level.

Results:

3600 epochs with matched hip- and wrist-worn accelerometer VM counts were analyzed. All ML approaches performed differently on developing PA intensity cut-points for wrist-worn accelerometers. Among the three ML models, K-means cluster analysis derived cut-points, which were: ≤ 2556 cpm for SED, 2557-7064 cpm for LPA, 7065-14532 for MPA, and ≥ 14533 cpm for VPA, had the highest classification accuracy, with more than 70% of the total epochs being classified into the correct PA categories as examined by the hip reference. K-means cut-points also exhibited the most accurate estimates on SED, LPA, and VPA as the hip reference, whereas none of the three wrist methods were able to accurately assess MPA.

Conclusions:

This study demonstrates the potential of ML approaches on establishing cut-points for wrist-worn accelerometry to assess PA in preschoolers. Based on the findings from this study, warrant additional validation studies of wrist-worn accelerometry for PA assessment in preschoolers, and the feasibility of using the k-means cluster analysis derived cut-points to assess PA in a larger sample. Clinical Trial: ClinicalTrials.Gov (NCT03590834) July 18, 2018 https://clinicaltrials.gov/ct2/show/NCT03590834


 Citation

Please cite as:

Li S, Yin Z, Howard J, Sosa E, Cordova A, Parra-Medina D

Machine Learning Approaches to Calibrate Wrist-Worn Accelerometry for Physical Activity Assessment in Preschoolers

JMIR Preprints. 17/10/2019:16727

DOI: 10.2196/preprints.16727

URL: https://preprints.jmir.org/preprint/16727


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.