Exploring Machine Learning Models Based on Accelerometer Sensor Alone or Combined With Gyroscope to Classify Home-Based Exercises and Physical Behavior in (Pre)sarcopenic Older Adults

in Journal for the Measurement of Physical Behaviour
View More View Less
  • 1 KU Leuven
  • | 2 UZ Leuven
Restricted access

Purchase article

USD  $24.95

Student 1 year online subscription

USD  $38.00

1 year online subscription

USD  $51.00

Student 2 year online subscription

USD  $73.00

2 year online subscription

USD  $97.00

Tools for objective monitoring of home-based training and physical behavior (PB) in (pre)sarcopenic older adults are needed. The present study explored two approaches with machine learning models, including accelerometer data either with or without additional gyroscope data (in an inertial measurement unit). Twenty-five community-dwelling (pre)sarcopenic adults mean 80.7 [5.5] years) performed the Otago exercise protocol (OEP) and PB modules (e.g., sitting or walking) while wearing an inertial measurement unit on the lower back (Dynaport MoveMonitor; McRoberts, The Hague, The Netherlands). Machine learning (ML) models for classification were developed by two approaches (top-down and bottom-up approaches) and with two levels of classification: general (no wear, OEP, and PB) and detailed (all subclassifications). Classification output was compared with video recordings. For the bottom-up approach, one ML model was developed. For the top-down approach, data were first classified as no wear, OEP, or PB. Thereafter, OEP and PB were subclassified by one ML model each into subclassification. Only classification of the general classification no wear and the subclassification sitting/lying reached the acceptable performance threshold of 80%. This result was independent of the approach used. Moreover, a gyroscope did not improve performance. Despite the progress in ML techniques and monitors, objective compliance registrations remain challenging.

Dedeyne and Wullems shared first authorship. Dedeyne, Dupont, Tournoy, and Gielen are with Gerontology & Geriatrics, Department of Public Health and Primary Care, KU Leuven, Leuven, Belgium. Wullems is with the Department of Electrical Engineering (ESAT) TC, Group T, KU Leuven, Leuven, Belgium. Tournoy, Gielen, and Dupont are also with the Department of Geriatric Medicine, UZ Leuven, Leuven, Belgium. Verschueren is with the Department of Rehabilitation Sciences, KU Leuven, Leuven, Belgium.

Dedeyne (lenore.dedeyne@kuleuven.be) is a corresponding author.

Supplementary Materials

    • Supplementary Figure 1 (PDF 393 KB)
    • Supplementary Table 1 (PDF 195 KB)
    • Supplementary Table 2 (PDF 262 KB)
    • Supplementary Table 3 (PDF 180 KB)
  • American College of Sports Medicine. (1998). American College of Sports Medicine Position Stand. Exercise and physical activity for older adults. Medicine & Science in Sports & Exercise, 30(6), 9921008.

    • Search Google Scholar
    • Export Citation
  • Adams, S.A., Matthews, C.E., Ebbeling, C.B., Moore, C.G., Cunningham, J.E., Fulton, J., & Hebert, J.R. (2005). The effect of social desirability and social approval on self-reports of physical activity. American Journal of Epidemiology, 161(4), 389398. PubMed ID: 15692083 doi:10.1093/aje/kwi054

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Albert, M., Toledo, S., Shapiro, M., & Koerding, K. (2012). Using mobile phones for activity recognition in Parkinson’s patients. Frontiers in Neurology, 3(158). PubMed ID: 23162528 doi:10.3389/fneur.2012.00158

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Allahbakhshi, H., Hinrichs, T., Huang, H., & Weibel, R. (2019). The key factors in physical activity type detection using real-life data: A systematic review. Frontiers in Physiology, 10, 7575. PubMed ID: 30809152 doi:10.3389/fphys.2019.00075

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Bayat, A., Pomplun, M., & Tran, D.A. (2014). A study on human activity recognition using accelerometer data from smartphones. Procedia Computer Science, 34, 450457. doi:10.1016/j.procs.2014.07.009

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Beaudart, C., Reginster, J.Y., Petermans, J., Gillain, S., Quabron, A., Locquet, M., . . . Bruyere, O. (2015). Quality of life and physical components linked to sarcopenia: The SarcoPhAge study. Experimental gerontology, 69, 103110. PubMed ID: 25979160 doi:10.1016/j.exger.2015.05.003

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Beaudart, C., Zaaria, M., Pasleau, F., Reginster, J., & Bruyère, O. (2017). Health outcomes of sarcopenia: A systematic review and meta-analysis. PLoS One, 12(1), e0169548. doi:10.1371/journal.pone.0169548

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Borson, S., Scanlan, J., Brush, M., Vitaliano, P., & Dokmak, A. (2000). The mini-cog: A cognitive ‘vital signs’ measure for dementia screening in multi-lingual elderly. The International Journal of Geriatric Psychiatry, 15(11), 10211027. PubMed ID: 11113982 doi:10.1002/1099-1166(200011)15:11%2C1021::AID-GPS234%2E3.0.CO;2-6

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Campbell, A.J., Robertson, M.C., Gardner, M.M., Norton, R.N., Tilyard, M.W., & Buchner, D.M. (1997). Randomised controlled trial of a general practice programme of home based exercise to prevent falls in elderly women. The BMJ, 315(7115), 10651069. PubMed ID: 9366737 doi:10.1136/bmj.315.7115.1065.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Caspersen, C.J., Powell, K.E., & Christenson, G.M. (1985). Physical activity, exercise, and physical fitness: Definitions and distinctions for health-related research. Public Health Reports, 100(2), 126131.

    • Search Google Scholar
    • Export Citation
  • Chang, K.-H., Chen, M., & Canny, J. (2007). Tracking free-weight exercises. LNCS, 4717, 1937.

  • Chawla, N.V., Bowyer, K.W., Hall, L.O., & Kegelmeyer, W.P. (2002). SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 16, 321357. doi:10.1613/jair.953.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Cruz-Jentoft, A.J., Baeyens, J.P., Bauer, J.M., Boirie, Y., Cederholm, T., Landi, F., . . . European Working Group on Sarcopenia in Older, P. (2010). Sarcopenia: European consensus on definition and diagnosis: Report of the European Working Group on Sarcopenia in older people. Age and Ageing, 39(4), 412423. PubMed ID: 30312372 20392703 doi:10.1093/ageing/afq034

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Cruz-Jentoft, A.J., Bahat, G., Bauer, J., Boirie, Y., Bruyere, O., Cederholm, T., . . . Zamboni, M. (2019). Writing Group for the European Working Group on Sarcopenia in Older People 2 (EWGSOP2), and the Extended Group for EWGSOP2. Sarcopenia: revised European consensus on definition and diagnosis. Age Ageing, 48(1), 1631. PubMed ID: doi:10.1093/ageing/afy169

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Dedeyne, L., Deschodt, M., Verschueren, S., Tournoy, J., & Gielen, E. (2017). Effects of multi-domain interventions in (pre)frail elderly on frailty, functional, and cognitive status: A systematic review. Clinical Interventions in Aging, 12, 873896. PubMed ID: 28579766 doi:10.2147/CIA.S130794

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Dedeyne, L., Dewinter, L., Lovik, A., Verschueren, S., Tournoy, J., & Gielen, E. (2018). Nutritional and physical exercise programs for older people: Program format preferences and (dis)incentives to participate. Clinical Interventions in Aging, 13, 12591266. doi:10.2147/CIA.S159819

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Dijkstra, B., Kamsma, Y., & Zijlstra, W. (2010). Detection of gait and postures using a miniaturised triaxial accelerometer-based system: Accuracy in community-dwelling older adults. Age and Ageing, 39(2), 259262. doi:10.1093/ageing/afp249

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Dijkstra, B., Zijlstra, W., Scherder, E., & Kamsma, Y. (2008). Detection of walking periods and number of steps in older adults and patients with Parkinson’s disease. Age and Aging, 37(4), 436441. doi:10.1093/ageing/afn097

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Ellis, K., Kerr, J., Godbole, S., Staudenmayer, J., & Lanckriet, G. (2016). Hip and wrist accelerometer algorithms for free-living behavior classification. Medicine & Science in Sports & Exercise, 48(5), 933940. PubMed ID: 26673126 doi:10.1249/MSS.0000000000000840

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Fokkenrood, H.J., Verhofstad, N., van den Houten, M.M., Lauret, G.J., Wittens, C., Scheltinga, M.R., & Teijink, J.A. (2014). Physical activity monitoring in patients with peripheral arterial disease: Validation of an activity monitor. The European Journal of Vascular and Endovascular Surgery, 48(2), 194200. PubMed ID: 24880631 doi:10.1016/j.ejvs.2014.04.003

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Fried, L.P., Tangen, C.M., Walston, J., Newman, A.B., Hirsch, C., Gottdiener, J., . . . McBurnie, M.A. (2001). Frailty in older adultsevidence for a phenotype. The Journals of Gerontology: Series A, 56(3), M146M157. doi:10.1093/gerona/56.3.M146

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Gallego, J.A., Rocon, E., Roa, J.O., Moreno, J.C., & Pons, J.L. (2010). Real-time estimation of pathological tremor parameters from gyroscope data. Sensors, 10(3), 21292149. doi:10.3390/s100302129

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Galloza, J., Castillo, B., & Micheo, W. (2017). Benefits of exercise in the older population. Physical Medicine and Rehabilitation Clinics of North America, 28(4), 659669. PubMed ID: 29031333 doi:10.1016/j.pmr.2017.06.001

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Garber, C.E., Blissmer, B., Deschenes, M. R., Franklin, B.A., Lamonte, M.J., Lee, I. M., . . . Swain, D.P. (2011). American College of Sports Medicine position stand. Quantity and quality of exercise for developing and maintaining cardiorespiratory, musculoskeletal, and neuromotor fitness in apparently healthy adults: guidance for prescribing exercise. Medicine & Science in Sports & Exercise, 43(7), 13341359. PubMed ID: 21694556 doi:10.1249/MSS.0b013e318213fefb

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Gielen, E., Verschueren, S., O’Neill, T.W., Pye, S.R., O’Connell, M.D., Lee, D.M., . . . Boonen, S. (2012). Musculoskeletal frailty: A geriatric syndrome at the core of fracture occurrence in older age. Calcified Tissue International, 91(3), 161177. PubMed ID: 22797855 doi:10.1007/s00223-012-9622-5

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Győrbíró, N., Fábián, Á., & Hományi, G. (2009). An activity recognition system for mobile phones. Mobile Networks and Applications, 14(1), 8291. doi:10.1007/s11036-008-0112-y

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Kursa, M.B., & Rudnicki, W.R. (2010). Feature selection with the Boruta package. Journal of Statistical Software, 36(11). doi:10.18637/jss.v036.i11

  • Lambrecht, S., Gallego, J.A., Rocon, E., & Pons, J.L. (2014). Automatic real-time monitoring and assessment of tremor parameters in the upper limb from orientation data. Frontiers in Neuroscience, 8(221). PubMed ID: 25120424 doi:10.3389/fnins.2014.00221

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Lang, T., Streeper, T., Cawthon, P., Baldwin, K., Taaffe, D.R., & Harris, T.B. (2010). Sarcopenia: Etiology, clinical consequences, intervention, and assessment. Osteoporosis International, 21(4), 543559. PubMed ID: 19779761 doi:10.1007/s00198-009-1059-y

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Langhammer, B., Bergland, A., & Rydwik, E. (2018). The importance of physical activity exercise among older people. BioMed Research International, 2018, 78568237856823. PubMed ID: 30627571 doi:10.1155/2018/7856823

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Liaw, A., & Wiener, M. (2002). Classification and regression by randomForest. R News, 2(3), 1822.

  • Liu, S., Gao, R.X., & Freedson, P.S. (2012). Computational methods for estimating energy expenditure in human physical activities. Medicine & Science in Sports & Exercise, 44(11), 21382146. PubMed ID: 22617402 doi:10.1249/MSS.0b013e31825e825a

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Liu-Ambrose, T., Donaldson, M.G., Ahamed, Y., Graf, P., Cook, W.L., Close, J., . . . Khan, K.M. (2008). Otago home-based strength and balance retraining improves executive functioning in older fallers: A randomized controlled trial. Journal of the American Geriatrics Society, 56(10), 18211830. PubMed ID: 18795987 doi:10.1111/j.1532-5415.2008.01931.x

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Mannini, A., & Sabatini, A.M. (2010). Machine learning methods for classifying human physical activity from on-body accelerometers. Sensors, 10(2), 11541175. PubMed ID: 22205862 doi:10.3390/s100201154

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Minnen, D., Starner, T., Essa, I., & Isbel, C. (2006, October). Discovering characteristics actions from onbody sensor data. Paper presented at the International Symposium on Wearable Computing (ISWC), Montreux, CH.

    • Search Google Scholar
    • Export Citation
  • Nelson, M.E., Rejeski, W.J., Blair, S.N., Duncan, P.W., Judge, J.O., King, A.C., . . . Castaneda-Sceppa, C. (2007). Physical activity and public health in older adults: Recommendation from the American College of Sports Medicine and the American Heart Association. Circulation, 116(9), 10941105. PubMed ID: 17671236 doi:10.1161/CIRCULATIONAHA.107.185650

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Nicolson, P.J.A., Hinman, R.S., Wrigley, T.V., Stratford, P.W., & Bennell, K.L. (2018). Self-reported home exercise adherence: A validity and reliability study using concealed accelerometers. The Journal of Orthopaedic & Sports Physical Therapy, 48(12), 943950. PubMed ID: 30053792 doi:10.2519/jospt.2018.8275

    • Crossref
    • Search Google Scholar
    • Export Citation
  • R Core Team. (2013). R: A language and environment for statistical computing. Vienna, Austria: R Core Team. Retrieved from http://www.R-project.org/

    • Search Google Scholar
    • Export Citation
  • Rabinovich, R.A., Louvaris, Z., Raste, Y., Langer, D., Van Remoortel, H., Giavedoni, S., . . . Consortium, P.R. (2013). Validity of physical activity monitors during daily life in patients with COPD. The European Respiratory Journal, 42(5), 12051215. PubMed ID: 23397303 doi:10.1183/09031936.00134312

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Rezende, L.F.M.d., Rodrigues Lopes, M., Rey-López, J.P., Matsudo, V.K.R., & Luiz, O.d.C. (2014). Sedentary behavior and health outcomes: An overview of systematic reviews. PLoS One, 9(8), e105620. doi:10.1371/journal.pone.0105620

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Robertson, M.C., Devlin, N., Gardner, M.M., & Campbell, A.J. (2001). Effectiveness and economic evaluation of a nurse delivered home exercise programme to prevent falls. 1: Randomised controlled trial. The BMJ, 322(7288), 697697. doi:10.1136/bmj.322.7288.697

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Sasaki, J.E., Hickey, A.M., Staudenmayer, J.W., John, D., Kent, J.A., & Freedson, P.S. (2016). Performance of activity classification algorithms in free-living older adults. Medicine & Science in Sports & Exercise, 48(5), 941950. PubMed ID: 26673129 doi:10.1249/MSS.0000000000000844

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Scott, B.R., Duthie, G.M., Thornton, H.R., & Dascombe, B.J. (2016). Training monitoring for resistance exercise: Theory and applications. Sports medicine, 46(5), 687698. PubMed ID: 26780346 doi:10.1007/s40279-015-0454-0

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Seeger, C., Buchman, A., & Van Laerhoven, K. (2012). myHealthAssistant: A phone-based body sensor network that captures the wearer’s exercises throughout the day. Paper presented at the Bodynets, Beijing, People’s Republic of China.

    • Search Google Scholar
    • Export Citation
  • Seon-Woo, L., & Mase, K. (2002). Activity and location recognition using wearable sensors. IEEE Pervasive Computing, 1(3), 2432. doi:10.1109/MPRV.2002.1037719

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Shoaib, M., Bosch, S., Incel, O.D., Scholten, H., & Havinga, P.J. (2014). Fusion of smartphone motion sensors for physical activity recognition. Sensors, 14(6), 1014610176. PubMed ID: 24919015 doi:10.3390/s140610146

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Sousa Lima, W., Souto, E., El-Khatib, K., Jalali, R., & Gama, J. (2019). Human activity recognition using inertial sensors in a smartphone: An overview. Sensors, 19(14), 3213. PubMed ID: 31330919 doi:10.3390/s19143213

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Staudenmayer, J., Pober, D., Crouter, S., Bassett, D., & Freedson, P. (2009). An artificial neural network to estimate physical activity energy expenditure and identify physical activity type from an accelerometer. Journal of Applied Physiology, 107(4), 13001307. PubMed ID: 19644028 doi:10.1152/japplphysiol.00465.2009

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Tahavori, F., Stack, E., Agarwal, V., Burnett, M., Ashburn, A., Hoseinitabatabaei, S.A., & Harwin, W. (2017, Sept. 14–17). Physical activity recognition of elderly people and people with Parkinson’s (PwP) during standard mobility tests using wearable sensors. Paper presented at the 2017 International Smart Cities Conference (ISC2).

    • Search Google Scholar
    • Export Citation
  • Torgo, L. (2010). Data Mining using R: Learning with case studies. Boca Raton, FL: CRC Press.

  • Touillet, A., Guesdon, H., Bosser, G., Beis, J.M., & Paysant, J. (2010). Assessment of compliance with prescribed activity by hemiplegic stroke patients after an exercise programme and physical activity education. The Annals of Physical and Rehabilitation Medicine, 53(4), 250265. PubMed ID: 20399174 doi:10.1016/j.rehab.2010.03.005

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Tremblay, M.S., Aubert, S., Barnes, J.D., Saunders, T.J., Carson, V., Latimer-Cheung, A. E., . . . Chinapaw, M.J.M. (2017). Sedentary Behavior Research Network (SBRN)—Terminology Consensus Project process and outcome. The International Journal of Behavioral Nutrition and Physical Activity, 14(1), 75. PubMed ID: 28599680 doi:10.1186/s12966-017-0525-8

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Trost, S.G., Zheng, Y., & Wong, W.-K. (2014). Machine learning for activity recognition: Hip versus wrist data. Physiological Measurement, 35(11), 21832189. doi:10.1088/0967-3334/35/11/2183

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Van Lummel, R.C., Walgaard, S., Pijnappels, M., Elders, P.J., Garcia-Aymerich, J., van Dieen, J.H., & Beek, P.J. (2015). Physical performance and physical activity in older adults: Associated but separate domains of physical function in old age. PLoS One, 10(12), e0144048. PubMed ID: 26630268 doi:10.1371/journal.pone.0144048

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Welch, W.A., Bassett, D.R., Thompson, D.L., Freedson, P.S., Staudenmayer, J.W., John, D., . . . Fitzhugh, E. C. (2013). Classification accuracy of the wrist-worn gravity estimator of normal everyday activity accelerometer. Medicine & Science in Sports & Exercise, 45(10), 20122019. PubMed ID: 23584403 doi:10.1249/MSS.0b013e3182965249

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Wu, W., Dasgupta, S., Ramirez, E.E., Peterson, C., & Norman, G.J. (2012). Classification accuracies of physical activities using smartphone motion sensors. Journal of Medical Internet Research, 14(5), e130. PubMed ID: 23041431 doi:10.2196/jmir.2208

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Wullems, J.A., Verschueren, S.M.P., Degens, H., Morse, C.I., & Onambele, G.L. (2017). Performance of thigh-mounted triaxial accelerometer algorithms in objective quantification of sedentary behaviour and physical activity in older adults. PLoS One, 12(11), e0188215. doi:10.1371/journal.pone.0188215

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Zhang, S., Rowlands, A.V., Murray, P., & Hurst, T.L. (2012). Physical activity classification using the GENEA wrist-worn accelerometer. Medicine & Science in Sports & Exercise, 44(4), 742748. PubMed ID: 21988935

    • Crossref
    • Search Google Scholar
    • Export Citation
All Time Past Year Past 30 Days
Abstract Views 136 136 38
Full Text Views 7 7 0
PDF Downloads 2 2 0