Accelerometry-Based Prediction of Energy Expenditure in Preschoolers

in Journal for the Measurement of Physical Behaviour
Restricted access

Purchase article

USD $24.95

Student 1 year subscription

USD $37.00

1 year subscription

USD $50.00

Student 2 year subscription

USD $71.00

2 year subscription

USD $93.00

Purpose: Study purposes were to develop energy expenditure (EE) prediction models from raw accelerometer data and to investigate the performance of three different accelerometers on five different wear positions in preschoolers. Methods: Fourty-one children (54% boys; 3–6.3 years) wore two Actigraph GT3X (left and right hip), three GENEActiv (right hip, left and right wrist), and one activPAL (right thigh) while completing a semi-structured protocol of 10 age-appropriate activities. Participants wore a portable indirect calorimeter to estimate EE. Utilized models to estimate EE included a linear model (LM), a mixed linear model (MLM), a random forest model (RF), and an artificial neural network model (ANN). For each accelerometer, model, and wear position, we assessed prediction accuracy via leave-one-out cross-validation and calculated the root-mean-squared-error (RMSE). Results: Mean RMSE ranged from 2.56–2.76 kJ/min for the RF, 2.72–3.08 kJ/min for the ANN, 2.83–2.94 kJ/min for the LM, and 2.81–2.92 kJ/min for the MLM. The GENEActive obtained mean RMSE of 2.56 kJ/min (left and right wrist) and 2.73 kJ/min (right hip). Predicting EE using the GT3X on the left and right hip obtained mean RMSE of 2.60 and 2.74 kJ/min. The activPAL obtained a mean RMSE of 2.76 kJ/min. Conclusion: These results demonstrate good prediction accuracy for recent accelerometers on different wear positions in preschoolers. The RF and ANN were equally accurate in EE prediction compared with (mixed) linear models. The RF seems to be a viable alternative to linear and ANN models for EE prediction in young children in a semi-structured setting.

Steenbock, Wright, Wirsik, and Brandes are with the Leibniz Institute for Prevention Research and Epidemiology–BIPS, Bremen, Germany. Steenbock is with the Center of Clinical Psychology and Rehabilitation, University of Bremen, Bremen, Germany.

Steenbock (steenbock@leibniz-bips.de) is corresponding author.
Journal for the Measurement of Physical Behaviour

Article Sections

References

  • BatesD.MächlerM.BolkerB. & WalkerS. (2015). Fitting linear mixed-effects models using lme4. Journal of Statistical Software 67(1) 148. doi:10.18637/jss.v067.i01

    • Crossref
    • Search Google Scholar
    • Export Citation
  • BischlB.LangM.KotthoffL.SchiffnerJ.RichterJ.StuderusE.JonesZ.M. (2016). mlr: Machine Learning in R. The Journal of Machine Learning Research 17(170) 15.

    • Search Google Scholar
    • Export Citation
  • BischlB.RichterJ.BossekJ.HornD.ThomasJ. & LangM. (2017). mlrMBO: A Modular Framework for Model-Based Optimization of expensive black-box functions. Retrieved from http://arxiv.org/abs/1703.03373

    • Search Google Scholar
    • Export Citation
  • BorgesJ.H.LangerR.D.CiroliniV.X.PascoaM.A.Guerra-JuniorG. & GoncalvesE.M. (2016). Minimum time to achieve the steady state and optimum abbreviated period to estimate the resting energy expenditure by indirect calorimetry in healthy young adults. Nutrition in Clinical Practice 31(3) 349354. PubMed ID: 26888859

    • Crossref
    • Search Google Scholar
    • Export Citation
  • BorgheseM.M.TremblayM.S.LeBlancA.G.LeducG.BoyerC. & ChaputJ.P. (2017). Comparison of ActiGraph GT3X+ and actical accelerometer data in 9–11-year-old Canadian children. Journal of Sports Sciences 35(6) 517524. PubMed ID: 27103499 doi:10.1080/02640414.2016.1175653

    • Search Google Scholar
    • Export Citation
  • BrandesM.KleinH.GinselS. & HeitmannA. (2015). Comparability of three mobile respiratory gas analyzers. Sportwissenschaft 45(4) 168172. doi:10.1007/s12662-015-0368-x

    • Crossref
    • Search Google Scholar
    • Export Citation
  • BrandesM.SteenbockB. & WirsikN. (2018). Energy cost of common physical activities in preschoolers. Journal of Physical Activity & Health 15(4) 233238. PubMed ID: 29202634 doi:10.1123/jpah.2017-0348

    • Crossref
    • Search Google Scholar
    • Export Citation
  • ButteN.F.WongW.W.LeeJ.S.AdolphA.L.PuyauM.R. & ZakeriI.F. (2014). Prediction of energy expenditure and physical activity in preschoolers. Medicine & Science in Sports & Exercise 46(6) 12161226. PubMed ID: 24195866 doi:10.1249/mss.0000000000000209

    • Crossref
    • Search Google Scholar
    • Export Citation
  • CaspersenC.J.PowellK.E. & ChristensonG.M. (1985). Physical activity, exercise, and physical fitness: Definitions and distinctions for health-related research. Public Health Rep 100(2) 126131. PubMed ID: 3920711

    • Search Google Scholar
    • Export Citation
  • ChowdhuryA.K.TjondronegoroD.ZhangJ.HagenbuchnerM.CliffD. & TrostS.G. (2018). Deep learning for energy expenditure prediction in pre-school children. Paper presented at the IEEE Conference on Biomedical and Health InformaticsLas Vegas, NA.

    • Search Google Scholar
    • Export Citation
  • DaviesG.ReillyJ.McGowanA.DallP.GranatM. & PatonJ. (2012). Validity, practical utility, and reliability of the activPAL in preschool children. Medicine & Science in Sports & Exercise 44(4) 761768. PubMed ID: 21983077

    • Crossref
    • Search Google Scholar
    • Export Citation
  • De DeckerE.De CraemerM.Santos-LozanoA.Van CauwenbergheE.De BourdeaudhuijI. & CardonG. (2013). Validity of the ActivPAL and the ActiGraph monitors in preschoolers. Medicine & Science in Sports & Exercise 45(10) 20022011. PubMed ID: 23524516 doi:10.1249/MSS.0b013e318292c575

    • Crossref
    • Search Google Scholar
    • Export Citation
  • EvensonK.R.WenF.HerringA.H.DiC.LaMonteM.J.TinkerL.F.BuchnerD.M. (2015). Calibrating physical activity intensity for hip-worn accelerometry in women age 60 to 91 years: The Women’s Health Initiative OPACH Calibration Study. Preventive Medicine Reports 2750756. PubMed ID: 26527313 doi:10.1016/j.pmedr.2015.08.021

    • Crossref
    • Search Google Scholar
    • Export Citation
  • FaircloughS.J.NoonanR.RowlandsA.V.Van HeesV.KnowlesZ. & BoddyL.M. (2016). Wear compliance and activity in children wearing wrist- and hip-mounted accelerometers. Medicine & Science in Sports & Exercise 48(2) 245253. PubMed ID: 26375253 doi:10.1249/mss.0000000000000771

    • Crossref
    • Search Google Scholar
    • Export Citation
  • HagenbuchnerM.CliffD.P.TrostS.G.Van TucN. & PeoplesG.E. (2015). Prediction of activity type in preschool children using machine learning techniques. Journal of Science and Medicine in Sport 18(4) 426431. PubMed ID: 25088983

    • Crossref
    • Search Google Scholar
    • Export Citation
  • HillsA.P.MokhtarN. & ByrneN.M. (2014). Assessment of physical activity and energy expenditure: An overview of objective measures. Frontiers in Nutrition 15. PubMed ID: 25988109 doi:10.3389/fnut.2014.00005

    • Crossref
    • Search Google Scholar
    • Export Citation
  • JanssenX.CliffD.P.ReillyJ.J.HinkleyT.JonesR.A.BatterhamM.OkelyA.D. (2013). Predictive validity and classification accuracy of ActiGraph energy expenditure equations and cut-points in young children. PLoS One 8(11) 79124. PubMed ID: 24244433 doi:10.1371/journal.pone.0079124

    • Crossref
    • Search Google Scholar
    • Export Citation
  • JimmyG.SeilerR. & MaederU. (2013). Development and validation of energy expenditure prediction models based on GT3X accelerometer data in 5- to 9-year-old children. Journal of Physical Activity & Health 10(7) 10571067. PubMed ID: 23136371

    • Crossref
    • Search Google Scholar
    • Export Citation
  • JohanssonE.LarischL.M.MarcusC. & HagstromerM. (2016). Calibration and validation of a wrist- and hip-worn actigraph accelerometer in 4-year-old children. PLoS One 11(9) e0162436. PubMed ID: 27617962 doi:10.1371/journal.pone.0162436

    • Crossref
    • Search Google Scholar
    • Export Citation
  • KnaepsS.BourgoisJ.G.CharlierR.MertensE.LefevreJ. & WijndaeleK. (2018). Ten-year change in sedentary behaviour, moderate-to-vigorous physical activity, cardiorespiratory fitness and cardiometabolic risk: Independent associations and mediation analysis. British Journal of Sports Medicine 52(16) 10631068. PubMed ID: 27491779 doi:10.1136/bjsports-2016-096083

    • Crossref
    • Search Google Scholar
    • Export Citation
  • LamonteM.J. & AinsworthB.E. (2001). Quantifying energy expenditure and physical activity in the context of dose response. Medicine & Science in Sports & Exercise 33(Suppl. 6) S370378. discussion S419–S320. PubMed ID: 11427762

    • Crossref
    • Search Google Scholar
    • Export Citation
  • MacfarlaneD.J. & WongP. (2012). Validity, reliability and stability of the portable cortex metamax 3B gas analysis system. European Journal of Applied Physiology 112(7) 25392547. PubMed ID: 22075643 doi:10.1007/s00421-011-2230-7

    • Crossref
    • Search Google Scholar
    • Export Citation
  • MackintoshK.A.MontoyeA.H.PfeifferK.A. & McNarryM.A. (2016). Investigating optimal accelerometer placement for energy expenditure prediction in children using a machine learning approach. Physiological Measurement 37(10) 17281740. PubMed ID: 27653339 doi:10.1088/0967-3334/37/10/1728

    • Crossref
    • Search Google Scholar
    • Export Citation
  • MiguelesJ.H.Cadenas-SanchezC.EkelundU.Delisle NystromC.Mora-GonzalezJ.LofM.OrtegaF.B. (2017). Accelerometer data collection and processing criteria to assess physical activity and other outcomes: A systematic review and practical considerations. Sports Medicine 47(9) 18211845. PubMed ID: 28303543 doi:10.1007/s40279-017-0716-0

    • Crossref
    • Search Google Scholar
    • Export Citation
  • MontoyeA.H.BegumM.HenningZ. & PfeifferK.A. (2017). Comparison of linear and non-linear models for predicting energy expenditure from raw accelerometer data. Physiological Measurement 38(2) 343357. PubMed ID: 28107205 doi:10.1088/1361-6579/38/2/343

    • Crossref
    • Search Google Scholar
    • Export Citation
  • MontoyeA.H.MuddL.M.BiswasS. & PfeifferK.A. (2015). Energy expenditure prediction using raw accelerometer data in simulated free living. Medicine & Science in Sports & Exercise 47(8) 17351746. PubMed ID: 25494392 doi:10.1249/mss.0000000000000597

    • Crossref
    • Search Google Scholar
    • Export Citation
  • NilssonA.BrageS.RiddochC.AnderssenS.A.SardinhaL.B.WedderkoppN.EkelundU. (2008). Comparison of equations for predicting energy expenditure from accelerometer counts in children. Scandinavian Journal of Medicine & Science in Sports 18(5) 643650. PubMed ID: 18208433 doi:10.1111/j.1600-0838.2007.00694.x

    • Crossref
    • Search Google Scholar
    • Export Citation
  • R Core Team. (2017). R: A language and environment for statistical computing. Vienna, Austria: R Foundation for Statistical Computing. Retrieved from https://www.R-project.org/

    • Search Google Scholar
    • Export Citation
  • ReddonH.MeyreD. & CairneyJ. (2017). Physical activity and global self-worth in a longitudinal study of children. Medicine & Science in Sports & Exercise 49(8) 16061613. PubMed ID: 28319588 doi:10.1249/mss.0000000000001275

    • Crossref
    • Search Google Scholar
    • Export Citation
  • ReillyJ.J.KellyL.A.MontgomeryC.JacksonD.M.SlaterC.GrantS. & PatonJ.Y. (2006). Validation of Actigraph accelerometer estimates of total energy expenditure in young children. International Journal of Pediatric Obesity 1(3) 161167. PubMed ID: 17899634

    • Crossref
    • Search Google Scholar
    • Export Citation
  • RoscoeC.M.P.JamesR.S. & DuncanM.J. (2017). Calibration of GENEActiv accelerometer wrist cut-points for the assessment of physical activity intensity of preschool aged children. European Journal of Pediatrics 176(8) 10931098. PubMed ID: 28674825 doi:10.1007/s00431-017-2948-2

    • Crossref
    • Search Google Scholar
    • Export Citation
  • ShoupJ.A.GattshallM.DandamudiP. & EstabrooksP. (2008). Physical activity, quality of life, and weight status in overweight children. Quality of Life Research 17(3) 407412. PubMed ID: 18293100 doi:10.1007/s11136-008-9312-y

    • Crossref
    • Search Google Scholar
    • Export Citation
  • SkotteJ.KorshojM.KristiansenJ.HanischC. & HoltermannA. (2014). Detection of physical activity types using triaxial accelerometers. Journal of Physical Activity & Health 11(1) 7684. PubMed ID: 23249722 doi:10.1123/jpah.2011-0347

    • Crossref
    • Search Google Scholar
    • Export Citation
  • SkredeT.StavnsboM.AadlandE.AadlandK.N.AnderssenS.A.ResalandG.K. & EkelundU. (2017). Moderate-to-vigorous physical activity, but not sedentary time, predicts changes in cardiometabolic risk factors in 10-y-old children: The active smarter kids study. The American Journal of Clinical Nutrition 105(6) 13911398. PubMed ID: 28381476 doi:10.3945/ajcn.116.150540

    • Search Google Scholar
    • Export Citation
  • VenablesW.N. & RipleyB.D. (2002). Modern Applied Statistics with S (4th ed.). New York, NY: Springer.

  • WafaS.W.ShahrilM.R.AhmadA.B.ZainuddinL.R.IsmailK.F.AungM.M. & Mohd YusoffN.A. (2016). Association between physical activity and health-related quality of life in children: A cross-sectional study. Health and Quality of Life Outcomes 1471. PubMed ID: 27146199 doi:10.1186/s12955-016-0474-y

    • Crossref
    • Search Google Scholar
    • Export Citation
  • WeirJ.B. (1949). New methods for calculating metabolic rate with special reference to protein metabolism. The Journal of Physiology 109(1–2) 19. PubMed ID: 15394301

    • Crossref
    • Search Google Scholar
    • Export Citation
  • WelkG.J. (2005). Principles of design and analyses for the calibration of accelerometry-based activity monitors. Medicine & Science in Sports & Exercise 37(Suppl. 11) S501S511. PubMed ID: 16294113

    • Crossref
    • Search Google Scholar
    • Export Citation
  • WrightM.N. & ZieglerA. (2017). Ranger: A fast implementation of random forests for high dimensional data in C++ and R. Journal of Statistical Software 77(1) 117. doi:10.18637/jss.v077.i01

    • Crossref
    • Search Google Scholar
    • Export Citation

Article Metrics

All Time Past Year Past 30 Days
Abstract Views 38 38 28
Full Text Views 2 2 2
PDF Downloads 3 3 3

Altmetric Badge

PubMed

Google Scholar