Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

Predicting physical activity intensity using raw accelerometer signals in manual wheelchair users with spinal cord injury

Abstract

Study design

Cross-sectional validation study.

Objectives

The performance of previously published physical activity (PA) intensity cutoff thresholds based on proprietary ActiGraph counts for manual wheelchair users (MWUs) with spinal cord injury (SCI) was initially evaluated using an out-of-sample dataset of 60 individuals with SCI. Two types of PA intensity classification models based on raw accelerometer signals were developed and evaluated.

Setting

Research institutions in Pittsburgh PA, Birmingham AL, and Bronx NY.

Methods

Data were collected from 60 MWUs with SCI who followed a structured activity protocol while wearing an ActiGraph activity monitor on their dominant wrist and portable metabolic cart which measured criterion PA intensity. Data was used to assess published models as well as develop and assess custom models using recall, specificity, precision, as well as normalized Mathew’s correlation coefficient (nMCC).

Results

All the models performed well for predicting sedentary vs non-sedentary activity, yielding an nMCC of 0.87–0.90. However, all models demonstrated inadequate performance for predicting moderate to vigorous PA (MVPA) with an nMCC of 0.76–0.82.

Conclusions

The mean absolute deviation (MAD) cutoff threshold yielded the best performance for predicting sedentary vs non-sedentary PA and may be used for tracking daily sedentary activity. None of the models displayed strong performance for MVPA vs non-MVPA. Future studies should investigate combining physiological measures with accelerometry to yield better prediction accuracies for MVPA.

This is a preview of subscription content

Access options

Rent or Buy article

Get time limited or full article access on ReadCube.

from$8.99

All prices are NET prices.

Fig. 1: ROC analysis of the ENMO feature for both sedentary vs non-sedentary, and MVPA vs non-MVPA cutoff thresholds.
Fig. 2: ROC analysis of the MAD feature for both sedentary vs non-sedentary, and MVPA vs non-MVPA cutoff thresholds.

Data availability

The datasets supporting this study are available on reasonable request from the corresponding author.

References

  1. 1.

    McColl MA, Walker J, Stirling P, Wilkins R, Corey P. Expectations of life and health among spinal cord injured adults. Spinal Cord. 1997;35:818–28.

    CAS  Article  Google Scholar 

  2. 2.

    Myers J, Lee M, Kiratli J. Cardiovascular disease in spinal cord injury: an overview of prevalence, risk, evaluation, and management. Am J Phys Med Rehabil. 2007;86:142–52.

    Article  Google Scholar 

  3. 3.

    Buchholz AC, Martin Ginis KA, Bray SR, Craven BC, Hicks AL, Hayes KC, et al. Greater daily leisure time physical activity is associated with lower chronic disease risk in adults with spinal cord injury. Appl Physiol Nutr Metab. 2009;34:640–7.

    Article  Google Scholar 

  4. 4.

    Warburton DER, Nicol CW, Bredin SSD. Health benefits of physical activity: the evidence. CMAJ 2006;174:801–9.

    Article  Google Scholar 

  5. 5.

    Phillips WT, Kiratli BJ, Sarkarati M, Weraarchakul G, Myers J, Franklin BA, et al. Effect of spinal cord injury on the heart and cardiovascular fitness. Curr Probl Cardiol. 1998;23:641–716.

    CAS  Article  Google Scholar 

  6. 6.

    Martin Ginis KA, van der Scheer JW, Latimer-Cheung AE, Barrow A, Bourne C, Carruthers P, et al. Evidence-based scientific exercise guidelines for adults with spinal cord injury: an update and a new guideline. Spinal Cord. 2018;56:308–21.

    Article  Google Scholar 

  7. 7.

    Verschuren O, Dekker B, van Koppenhagen C, Post M. Sedentary behavior in people with spinal cord injury. Arch Phys Med Rehabil. 2016;97:173.

    Article  Google Scholar 

  8. 8.

    Nightingale TE, Williams S, Thompson D, Bilzon JL. Energy balance components in persons with paraplegia: daily variation and appropriate measurement duration. Int J of Behav Nutr and Phys. 2017;14:132.

    Article  Google Scholar 

  9. 9.

    Manns PJ, Dunstan DW, Owen N, Healy GN. Addressing the nonexercise part of the activity continuum: a more realistic and achievable approach to activity programming for adults with mobility disability? Phys Ther. 2012;92:614–25.

    Article  Google Scholar 

  10. 10.

    Burr JF, Shephard RJ, Zehr EP. Physical activity after stroke and spinal cord injury: evidence-based recommendations on clearance for physical activity and exercise. Can Fam Physician. 2012;58:1236–9.

    PubMed  PubMed Central  Google Scholar 

  11. 11.

    Vissers M, van den Berg-Emons R, Sluis T, Bergen M, Stam H, Bussmann H. Barriers to and facilitators of everyday physical activity in persons with a spinal cord injury after discharge from the rehabilitation centre. J Rehabil Med. 2008;40:461–7.

    Article  Google Scholar 

  12. 12.

    Nightingale TE, Rouse PC, Thompson D, Bilzon JLJ. Measurement of physical activity and energy expenditure in wheelchair users: methods, considerations and future directions. Sports Med Open. 2017;3:10.

    Article  Google Scholar 

  13. 13.

    Collins EG, Gater D, Kiratli J, Butler J, Hanson K, Langbein WE. Energy cost of physical activities in persons with spinal cord injury. Med Sci Sports Exerc. 2010;42:691–700.

    Article  Google Scholar 

  14. 14.

    Mendes M, de A, da Silva I, Ramires V, Reichert F, Martins R, et al. Metabolic equivalent of task (METs) thresholds as an indicator of physical activity intensity. PLoS One. 2018;13:e0200701.

    Article  Google Scholar 

  15. 15.

    Martin Ginis KA, Latimer AE, Buchholz AC, Bray SR, Craven BC, Hayes KC, et al. Establishing evidence-based physical activity guidelines: methods for the Study of Health and Activity in People with Spinal Cord Injury (SHAPE SCI). Spinal Cord. 2008;46:216–21.

    CAS  Article  Google Scholar 

  16. 16.

    Ginis KAM, Latimer AE, Hicks AL, Craven BC. Development and evaluation of an activity measure for people with spinal cord injury. Med Sci Sports Exerc. 2005;37:1099–111.

    Article  Google Scholar 

  17. 17.

    Martin Ginis KA, Phang SH, Latimer AE, Arbour-Nicitopoulos KP. Reliability and validity tests of the leisure time physical activity questionnaire for people with spinal cord injury. Arch Phys Med Rehabil. 2012;93:677–82.

    Article  Google Scholar 

  18. 18.

    Washburn RA, Zhu W, McAuley E, Frogley M, Figoni SF. The physical activity scale for individuals with physical disabilities: development and evaluation. Arch Phys Med Rehabil. 2002;83:193–200.

    Article  Google Scholar 

  19. 19.

    Glasheen E, Domingo A, Kressler J. Accuracy of Apple Watch fitness tracker for wheelchair use varies according to movement frequency and task. Ann Phys Rehabil Med. 2021;64:101382.

    Article  Google Scholar 

  20. 20.

    Sushames A, Edwards A, Thompson F, McDermott R, Gebel K. Validity and reliability of Fitbit Flex for step count, moderate to vigorous physical activity and activity energy expenditure. PLoS One. 2016;11:e0161224.

    Article  Google Scholar 

  21. 21.

    Learmonth YC, Kinnett-Hopkins D, Rice IM, Dysterheft JL, Motl RW. Accelerometer output and its association with energy expenditure during manual wheelchair propulsion. Spinal Cord. 2016;54:110–4.

    CAS  Article  Google Scholar 

  22. 22.

    McCracken LA, Ma JK, Voss C, Chan FH, Martin Ginis KA, West CR. Wrist accelerometry for physical activity measurement in individuals with spinal cord injury-A need for individually calibrated cut-points. Arch Phys Med Rehabil. 2018;99:684–9.

    Article  Google Scholar 

  23. 23.

    Veerubhotla A, Hong E, Knezevic S, Spungen A, Ding D. Estimation of physical activity intensity in spinal cord injury using a wrist-worn ActiGraph monitor. Arch Phys Med Rehabil. 2020;101:1563–9.

    Article  Google Scholar 

  24. 24.

    Bourassa S, Best KL, Racine M, Borisoff J, Leblond J, Routhier F. Use of actigraphy to measure real-world physical activities in manual wheelchair users. J Rehabil Assist Technol Eng. 2020;7:2055668320907814.

    PubMed  PubMed Central  Google Scholar 

  25. 25.

    Holmlund T, Ekblom-Bak E, Franzén E, Hultling C, Wahman K. Defining accelerometer cut-points for different intensity levels in motor-complete spinal cord injury. Spinal Cord. 2020;58:116–24.

    Article  Google Scholar 

  26. 26.

    Ried-Larsen M, Brønd JC, Brage S, Hansen BH, Grydeland M, Andersen LB, et al. Mechanical and free living comparisons of four generations of the Actigraph activity monitor. Int J Behav Nutr Phys Act. 2012;9:113.

    Article  Google Scholar 

  27. 27.

    Nightingale TE, Walhin J-P, Thompson D, Bilzon JLJ. Influence of accelerometer type and placement on physical activity energy expenditure prediction in manual wheelchair users. PLoS One. 2015;10:e0126086.

    Article  Google Scholar 

  28. 28.

    Tsang K. Using wearable sensors for physical activity measurement and promotion in manual wheelchair users. University of Pittsburgh; 2018.

  29. 29.

    Compher C, Frankenfield D, Keim N, Roth-Yousey L, Evidence Analysis Working Group. Best practice methods to apply to measurement of resting metabolic rate in adults: a systematic review. J Am Diet Assoc. 2006;106:881–903.

    Article  Google Scholar 

  30. 30.

    McClave SA, Spain DA, Skolnick JL, Lowen CC, Kieber MJ, Wickerham PS, et al. Achievement of steady state optimizes results when performing indirect calorimetry. JPEN J Parenter Enter Nutr. 2003;27:16–20.

    Article  Google Scholar 

  31. 31.

    Schlein KM, Coulter SP. Best practices for determining resting energy expenditure in critically ill adults. Nutr Clin Pr. 2014;29:44–55.

    Article  Google Scholar 

  32. 32.

    Reeves MM, Davies PSW, Bauer J, Battistutta D. Reducing the time period of steady state does not affect the accuracy of energy expenditure measurements by indirect calorimetry. J Appl Physiol. 2004;97:130–4.

    Article  Google Scholar 

  33. 33.

    Kirasich K, Smith T, Sadler B. Random forest vs logistic regression: binary classification for heterogeneous datasets. SMU Data Sci Rev. 2018;1:9.

    Google Scholar 

  34. 34.

    Bakrania K, Yates T, Rowlands AV, Esliger DW, Bunnewell S, Sanders J, et al. Intensity thresholds on raw acceleration data: Euclidean Norm Minus One (ENMO) and Mean Amplitude Deviation (MAD) approaches. PLoS One. 2016;11:e0164045.

    Article  Google Scholar 

  35. 35.

    Vähä-Ypyä H, Vasankari T, Husu P, Suni J, Sievänen H. A universal, accurate intensity-based classification of different physical activities using raw data of accelerometer. Clin Physiol Funct Imaging. 2015;35:64–70.

    Article  Google Scholar 

  36. 36.

    Aittasalo M, Vähä-Ypyä H, Vasankari T, Husu P, Jussila A-M, Sievänen H. Mean amplitude deviation calculated from raw acceleration data: a novel method for classifying the intensity of adolescents’ physical activity irrespective of accelerometer brand. BMC Sports Sci Med Rehabil. 2015;7:18.

    Article  Google Scholar 

  37. 37.

    Zhou X-H, Obuchowski NA, McClish DK. Statistical methods in diagnostic medicine: Zhou/statistical. Hoboken, NJ, USA: John Wiley & Sons, Inc.; 2011.

  38. 38.

    Brieuc MSO, Waters CD, Drinan DP, Naish KA. A practical introduction to Random Forest for genetic association studies in ecology and evolution. Mol Ecol Resour. 2018;18:755–66.

    Article  Google Scholar 

  39. 39.

    Chicco D, Jurman G. The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics. 2020;21:6.

    Article  Google Scholar 

  40. 40.

    Shwetar YJ, Veerubhotla AL, Huang Z, Ding D. Comparative validity of energy expenditure prediction algorithms using wearable devices for people with spinal cord injury. Spinal Cord. 2020;58:821–30.

    Article  Google Scholar 

  41. 41.

    Ma JK, McCracken LA, Voss C, Chan FHN, West CR, Martin Ginis KA. Physical activity measurement in people with spinal cord injury: comparison of accelerometry and self-report (the Physical Activity Recall Assessment for People with Spinal Cord Injury). Disabil Rehabil. 2020;42:240–6.

    Article  Google Scholar 

  42. 42.

    Sui W, Sui A, Prapavessis H. Relationships between indices of sedentary behavior and hedonic well-being: A scoping review. Psychol Sport Exerc. 2021;54:101920.

    Article  Google Scholar 

  43. 43.

    Nightingale TE, Walhin JP, Thompson D, Bilzon JLJ. Predicting physical activity energy expenditure in wheelchair users with a multisensor device. BMJ Open Sport Exerc Med. 2015;1:bmjsem-2015-000008.

Download references

Funding

This study was funded by the VA Rehabilitation Research & Development under Grant #1I01RX000971-01A. The content is solely the responsibility of the authors and does not represent the official views of the VA.

Author information

Affiliations

Authors

Contributions

YJS was responsible for conducting data analysis, obtaining results, and writing the manuscript in its entirety. ALV was responsible for designing the protocol, screening potential participants, and performing data collection. ZH conducted feature development for the random forest machine learning model. Also assisted with model tuning and development. SK was responsible for designing the protocol, screening potential participants, and performing data collection. EH was responsible for designing the protocol, screening potential participants, and performing data collection. AS oversaw a subset of data collection, which included screening participants, initializing equipment, and organizing patient visits. Also provided guidance for manuscript development. DD provided guidance throughout the study including formulating the manuscript plan, supervising the literature search, data collection, data analysis, and result interpretation, as well as editing the manuscript.

Corresponding author

Correspondence to Dan Ding.

Ethics declarations

Competing interests

The authors declare no competing interests.

Ethics approval

This study was approved by the US Department of Veterans Affairs (VA) Central Institutional Review Board and the local Institutional Review Boards at the VA Pittsburgh Healthcare System and the James J. Peters VA Medical Center, respectively. We certify that all applicable institutional and governmental regulations concerning the ethical use of human volunteers were followed during the course of this research.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Shwetar, Y., Huang, Z., Veerubhotla, A. et al. Predicting physical activity intensity using raw accelerometer signals in manual wheelchair users with spinal cord injury. Spinal Cord (2021). https://doi.org/10.1038/s41393-021-00728-z

Download citation

Search

Quick links