Laboratory-based and free-living algorithms for energy expenditure estimation in preschool children: A free-living evaluation

Matthew N Ahmadi, Alok Chowdhury, Toby Pavey, Stewart G Trost, Matthew N Ahmadi, Alok Chowdhury, Toby Pavey, Stewart G Trost

Abstract

Purpose: To evaluate the accuracy of LAB EE prediction models in preschool children completing a free-living active play session. Performance was benchmarked against EE prediction models trained on free living (FL) data.

Methods: 25 children (mean age = 4.1±1.0 y) completed a 20-minute active play session while wearing a portable indirect calorimeter and ActiGraph GT3X+ accelerometers on their right hip and non-dominant wrist. EE was predicted using LAB models which included Random Forest (RF) and Support Vector Machine (SVM) models for the wrist, and RF and Artificial Neural Network (ANN) models for the hip. Two variations of the LAB models were evaluated; 1) an "off the shelf" model without additional training; 2) models retrained on free-living data, replicating the methodology used in the original calibration study (retrained LAB). Prediction errors were evaluated in a hold-out sample of 10 children.

Results: Root mean square error (RMSE) for the FL and retrained LAB models ranged from 0.63-0.67 kcals/min. In the hold out sample, RMSE's for the hip LAB (0.62-0.71), retrained LAB (0.58-0.62) and FL models (0.61-0.65) were similar. For the wrist placement, FL SVM had a significantly higher RMSE (0.73 ± 0.29 kcals/min) than the retrained LAB SVM (0.63 ± 0.30 kcals/min) and LAB SVM (0.64 ± 0.18 kcals/min). The LAB (0.64 ± 0.28), retrained LAB (0.64 ± 0.25), and FL (0.62 ± 0.26) RF exhibited comparable accuracy.

Conclusion: Machine learning EE prediction models trained on LAB and FL data had similar accuracy under free-living conditions.

Conflict of interest statement

The authors have declared that no competing interests exist.

Figures

Fig 1. Results for the free-living, retrained…
Fig 1. Results for the free-living, retrained laboratory, and off the shelf laboratory models for the hip placement in the hold-out validation sample.
Error bars represent standard error.
Fig 2. Results for the free-living, retrained…
Fig 2. Results for the free-living, retrained laboratory, and off the shelf laboratory models for the wrist placement in the hold-out validation sample.
*Significantly different from the retrained Support Vector Machine (p

Fig 3. Bland Altman plots depicting regression…

Fig 3. Bland Altman plots depicting regression line and 95% prediction intervals for off the…

Fig 3. Bland Altman plots depicting regression line and 95% prediction intervals for off the shelf laboratory, retrained laboratory, and free-living models for hip placement.
Y-axis values represent percent error (observed–predicted EE). X-axis values represent observed energy expenditure values (kcals).

Fig 4. Bland Altman plots depicting regression…

Fig 4. Bland Altman plots depicting regression line and 95% prediction intervals for off the…

Fig 4. Bland Altman plots depicting regression line and 95% prediction intervals for off the shelf laboratory, retrained laboratory, and free-living models for wrist placement.
Y-axis values represent percent error (observed–predicted EE). X-axis values represent observed energy expenditure values (kcals).
Fig 3. Bland Altman plots depicting regression…
Fig 3. Bland Altman plots depicting regression line and 95% prediction intervals for off the shelf laboratory, retrained laboratory, and free-living models for hip placement.
Y-axis values represent percent error (observed–predicted EE). X-axis values represent observed energy expenditure values (kcals).
Fig 4. Bland Altman plots depicting regression…
Fig 4. Bland Altman plots depicting regression line and 95% prediction intervals for off the shelf laboratory, retrained laboratory, and free-living models for wrist placement.
Y-axis values represent percent error (observed–predicted EE). X-axis values represent observed energy expenditure values (kcals).

References

    1. Corder K, Ekelund U, Steele RM, Wareham NJ, Brage S. Assessment of physical activity in youth. J Appl Physiol. 2008;105:977–87. 10.1152/japplphysiol.00094.2008
    1. Trost SG. Measurement of physical activity in children and adolescents. Am J Lifestyle Med. 2007;1(4):299–314.
    1. Ekblom O, Nyberg G, Bak EE, Ekelund U, Marcus C. Validity and comparability of a wrist-worn accelerometer in children. J Phys Act Heal. 2012;9(3):389–93.
    1. Puyau MR, Adolph AL, Vohra FA, Zakeri I, Butte NF. Prediction of activity energy expenditure using accelerometers in children. Med Sci Sports Exerc. 2004;36(9):1625–31.
    1. Trost SG, Ward DS, Moorehead SM, Watson PD, Riner W, Burke JR. Validity of the computer science and applications (CSA) activity monitor in children. Med Sci Sports Exerc. 1998;30(4):629–33. 10.1097/00005768-199804000-00023
    1. Pate RR, Almeida MJ, McIver KL, Pfeiffer KA, Dowda M. Validation and calibration of an accelerometer in preschool children. Obesity. 2006;14(11):2000–6. 10.1038/oby.2006.234
    1. Phillips LRS, Parfitt G, Rowlands A V. Calibration of the GENEA accelerometer for assessment of physical activity intensity in children. J Sci Med Sport. 2013;16(2):124–8. 10.1016/j.jsams.2012.05.013
    1. Freedson P, Pober D, Janz KF. Calibration of accelerometer output for children. Med Sci Sports Exerc. 2005;37(Suppl 1):523–30.
    1. Trost SG, Way R, Okely AD. Predictive validity of three ActiGraph energy expenditure equations for children. Med Sci Sports Exerc. 2006;38(2):380–7. 10.1249/01.mss.0000183848.25845.e0
    1. Trost SG. Measurement of physical activity in children and adolescents. Am J Lifestyle Med. 2007;1(4):299–314.
    1. Janssen X, Cliff DP, Reilly JJ, Hinkley T, Jones RA, Batterham M, et al. Predictive validity and classification accuracy of actigraph energy expenditure equations and cut-points in young children. PLoS One. 2013;8(11).
    1. Trost SG, Wong W-K, Pfeiffer KA, Zheng Y. Artificial neural networks to predict activity type and energy expenditure in youth. Med Sci Sports Exerc. 2012;44(9):1801–9. 10.1249/MSS.0b013e318258ac11
    1. Bao L, Intille SS. Activity recognition from user-annotated acceleration data. International conference on pervasive computing. Springer-Verlag;2004 Apr 21.
    1. Foerster F, Smeja M, Fahrenberg J. Detection of posture and motion by accelerometry: a validation study in ambulatory monitoring. Comput Human Behav. 1999;15(5):571–83.
    1. Kotsiantis SB, Zaharakis ID, Pintelas PE. Machine learning: a review of classification and combining techniques. Artif Intell Rev. 2006;26(3):159–90.
    1. Wang H, Ma C, Zhou L. A brief review of machine learning and its application. In: 2009 International Conference on Information Engineering and Computer Science, Wuhan;2009 Dec 19–20.
    1. Mjolsness E, DeCoste D. Machine learning for science: State of the art and future prospects. Science. 2001;293:2051–5. 10.1126/science.293.5537.2051
    1. Liu S, Gao RX, John D, Staudenmayer JW, Freedson PS. Multisensor data fusion for physical activity assessment. IEEE Trans Biomed Eng. 2012;59(3):687–96. 10.1109/TBME.2011.2178070
    1. Chowdhury AK, Tjondronegoro D, Zhang J, Hagenbuchner M, Cliff D, Trost SG, Deep learning for energy expenditure prediction in pre-school children. Paper presented at the IEEE Conference on Biomedical and Health Informatics. Las Vegas;2018 Mar 4–7.
    1. Mackintosh KA, Montoye AHK, Pfeiffer KA, McNarry MA. Investigating optimal accelerometer placement for energy expenditure prediction in children using a machine learning approach. Physiol Meas. 2016;37(10):1728–40. 10.1088/0967-3334/37/10/1728
    1. Cliff DP, Reilly JJ, Okely AD. Methodological considerations in using accelerometers to assess habitual physical activity in children aged 0–5 years. J Sci Med Sport. 2009;12(5):557–67. 10.1016/j.jsams.2008.10.008
    1. Zakeri IF, Adolph AL, Puyau MR, Vohra FA, Butte NF. Multivariate adaptive regression splines models for the prediction of energy expenditure in children and adolescents. J Appl Physiol. 2010;108(1):128–36. 10.1152/japplphysiol.00729.2009
    1. Zakeri IF, Adolph AL, Puyau MR, Vohra FA, Butte NF. Cross-sectional time series and multivariate adaptive regression splines models using accelerometry and heart rate predict energy expenditure of preschoolers. J Nutr. 2013;143(1):114–22. 10.3945/jn.112.168542
    1. Butte NF, Wong WW, Lee JS, Adolph AL, Puyau MR, Zakeri IF. Prediction of energy expenditure and physical activity in preschoolers. Med Sci Sports Exerc. 2014;46(6):1216–26. 10.1249/MSS.0000000000000209
    1. Wijndaele K, Westgate K, Stephens SK, Blair SN, Bull FC, Chastin SFM, et al. Utilization and harmonization of adult accelerometry data: review and expert consensus. Med Sci Sports Exerc. 2015;47(10):2129–39. 10.1249/MSS.0000000000000661
    1. Liu S, Gao RX, Freedson PS. Computational methods for estimating energy expenditure in human physical activities. Med Sci Sports Exerc. 2012;44(11):2138–46. 10.1249/MSS.0b013e31825e825a
    1. Bassett DR Jr, Rowlands A V, Trost SG. Calibration and validation of wearable monitors. Med Sci Sports Exerc. 2012;44(Suppl 1):S32.
    1. Steenbock B, Wright MN, Wirsik N, Brandes M. Accelerometry-based prediction of energy expenditure in preschoolers. J Meas Phys Behav. 2019;2(2):94–102.
    1. Sasaki JE, Hickey AM, Staudenmayer JW, John D, Kent JA, Freedson PS. Performance of activity classification algorithms in free-living older adults. Med Sci Sports Exerc. 2016;48(5):941–9. 10.1249/MSS.0000000000000844
    1. Bastian T, Maire A, Dugas J, Ataya A, Villars C, Gris F, et al. Automatic identification of physical activity types and sedentary behaviors from triaxial accelerometer: laboratory-based calibrations are not enough. J Appl Physiol. 2015;118(6):716–22. 10.1152/japplphysiol.01189.2013
    1. Ross RM, Beck KC, Casaburi R, Johnson BD, Marciniuk DD, Wagner PD, et al. ATS/ACCP statement on cardiopulmonary exercise testing (multiple letters). Am J Respir Crit Care Med. 2003;167(10):1451 10.1164/ajrccm.167.10.950
    1. Potter CR, Childs DJ, Houghton W, Armstrong N. Breath-to-breath “noise” in the ventilatory and gas exchange responses of children to exercise. Eur J Appl Physiol Occup Physiol. 1999;80(2):118–24. 10.1007/s004210050567
    1. Weir JB New methods for calculating metabolic rate with special reference to protein metabolism. J Physiol. 1949;109:1–9. 10.1113/jphysiol.1949.sp004363
    1. Schofield WN. Predicting basal metabolic rate, new standards and review of previous work. Hum Nutr Clin Nutr. 1985;39:5–41.
    1. Chowdhury AK, Tjondronegoro D, Chandran V, et al. Physical activity recognition using posterior-adapted class-based fusion of multiaccelerometer data. IEEE J. Biomed. Health Inform. 2018;22:678–85. 10.1109/JBHI.2017.2705036
    1. Pavey TG, Gilson ND, Gomersall SR, Clark B, Trost SG. Field evaluation of a random forest activity classifier for wrist-worn accelerometer data. J Sci Med Sport. 2017;20(1):75–80. 10.1016/j.jsams.2016.06.003
    1. Peng H, Long F, Ding C. Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell. 2005;27(8):1226–38. 10.1109/TPAMI.2005.159
    1. Liaw A, Wiener M. Classification and regression by randomForest. R News. 2002;2(3):18–22.
    1. Karatzoglou A, Smola A, Hornik K, Zeileis A. kernlab-an S4 package for kernel methods in R. J Stat Softw. 2004;11(9):1–20.
    1. Ripley B, Venables W, Ripley MB. Package ‘nnet.’ R Packag version. 2016;7:3–12.
    1. Kuhn M. Building predictive models in R using the Caret package. J Stat Softw. 2008;28(5):1–26.
    1. Core R. R: A Language and Environment for Statistical Computing. Vienna, Austria: 2018.
    1. Mannini A, Intille SS, Rosenberger M, Sabatini AM, Haskell W. Activity recognition In youth using a single accelerometer placed at the wrist or ankle. Med Sci Sport Exerc. 2017;49(4):801–12.
    1. Connor P, Ross A. Biometric recognition by gait: A survey of modalities and features. Computer Vision and Image Understanding. 2018;167(January):1–27.
    1. Butte NF, Watson KB, Ridley K, Zakeri IF, McMurray RG, Pfeiffer KA, et al. A youth compendium of physical activities: Activity codes and metabolic intensities. Med Sci Sports Exerc. 2018;50(2):246–56. 10.1249/MSS.0000000000001430
    1. Trost SG, Drovandi CC, Pfeiffer K. Developmental trends in the energy cost of physical activities performed by youth. J Phys Act Health. 2016;13(6 Suppl 1):S35–40.
    1. Troiano RP, Mcclain JJ, Brychta RJ, Chen KY. Evolution of accelerometer methods for physical activity research. Br J Sports Med. 2014;100(2):130–4.
    1. Rowlands A V., Fraysse F, Catt M, Stiles VH, Stanley RM, Eston RG, et al. Comparability of measured acceleration from accelerometry-based activity monitors. Med Sci Sports Exerc. 2015;47(1):201–10. 10.1249/MSS.0000000000000394
    1. John D, Freedson P. ActiGraph and Actical physical activity monitors: a peek under the hood. Med Sci Sports Exerc. 2012;44(Suppl 1):S86–S89.

Source: PubMed

Sponsors et collaborateurs

Les conditions médicales

Interventions en matière de drogue

3
S'abonner