Abstract
Spatiotemporal variability during gait is linked to fall risk and could be monitored using wearable sensors. Although many users prefer wrist-worn sensors, most applications position at other sites. We developed and evaluated an application using a consumer-grade smartwatch inertial measurement unit (IMU). Young adults (n = 41) completed seven-minute conditions of treadmill gait at three speeds. Single-stride outcomes (stride time, length, width, and speed) and spatiotemporal variability (coefficient of variation of each single-stride outcome) were recorded using an optoelectronic system, while 232 single- and multi-stride IMU metrics were recorded using an Apple Watch Series 5. These metrics were input to train linear, ridge, support vector machine (SVM), random forest, and extreme gradient boosting (xGB) models of each spatiotemporal outcome. We conducted Model × Condition ANOVAs to explore model sensitivity to speed-related responses. xGB models were best for single-stride outcomes [relative mean absolute error (% error): 7–11%; intraclass correlation coefficient (ICC2,1) 0.60–0.86], and SVM models were best for spatiotemporal variability (% error: 18–22%; ICC2,1 = 0.47–0.64). Spatiotemporal changes with speed were captured by these models (Condition: p < 0.00625). Results support the feasibility of monitoring single-stride and multi-stride spatiotemporal parameters using a smartwatch IMU and machine learning.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10439-023-03290-2/MediaObjects/10439_2023_3290_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10439-023-03290-2/MediaObjects/10439_2023_3290_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10439-023-03290-2/MediaObjects/10439_2023_3290_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10439-023-03290-2/MediaObjects/10439_2023_3290_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10439-023-03290-2/MediaObjects/10439_2023_3290_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10439-023-03290-2/MediaObjects/10439_2023_3290_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10439-023-03290-2/MediaObjects/10439_2023_3290_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10439-023-03290-2/MediaObjects/10439_2023_3290_Fig8_HTML.png)
Similar content being viewed by others
References
Bailey, C. A., M. Porta, G. Pilloni, F. Arippa, J. N. Côté, and M. Pau. Does variability in motor output at individual joints predict stride time variability in gait? Influences of age, sex, and plane of motion. J. Biomech. 99:109574, 2020.
Bailey, C. A., T. K. Uchida, J. Nantel, and R. B. Graham. Validity and sensitivity of an inertial measurement unit-driven biomechanical model of motor variability for gait. Sensors. 21:7690, 2021.
Bamberg, S. J. M., A. Y. Benbasat, D. M. Scarborough, D. E. Krebs, and J. A. Paradiso. Gait analysis using a shoe-integrated wireless sensor system. IEEE Trans. Inf. Technol. Biomed. 12:413–423, 2008.
Beauchet, O., G. Allali, H. Sekhon, J. Verghese, S. Guilain, J.-P. Steinmetz, R. W. Kressig, J. M. Barden, T. Szturm, C. P. Launay, S. Grenier, L. Bherer, T. Liu-Ambrose, V. L. Chester, M. L. Callisaya, V. Srikanth, G. Léonard, A.-M. De Cock, R. Sawa, G. Duque, R. Camicioli, and J. L. Helbostad. Guidelines for assessment of gait and reference values for spatiotemporal gait parameters in older adults: the Biomathics and Canadian Gait Consortiums Initiative. Front. Hum. Neurosci. 11:353, 2017.
Bovi, G., M. Rabuffetti, P. Mazzoleni, and M. Ferrarin. A multiple-task gait analysis approach: kinematic, kinetic and EMG reference data for healthy young and adult subjects. Gait Posture. 33:6–13, 2011.
Brach, J. S., J. E. Berlin, J. M. VanSwearingen, A. B. Newman, and S. A. Studenski. Too much or too little step width variability is associated with a fall history in older persons who walk at or near normal gait speed. J. Neuroeng. Rehabil. 2:21, 2005.
Breiman, L. Random forests. Mach. Learn. 45:5–32, 2001.
Chehab, E. F., T. P. Andriacchi, and J. Favre. Speed, age, sex, and body mass index provide a rigorous basis for comparing the kinematic and kinetic profiles of the lower extremity during walking. J. Biomech. 58:11–20, 2017.
Chen, S., J. Lach, B. Lo, and G. Z. Yang. Toward pervasive gait analysis with wearable sensors: a systematic review. IEEE J. Biomed. Health Inform. 20:1521–1537, 2016.
Chen, T., and C. Guestrin. XGBoost: a scalable tree boosting system. Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., pp. 785–794, 2016.
Cicchetti, D. V. Guidelines, criteria, and rules of thumb for evaluating normed and standardized assessment instruments in psychology. Psychol. Assess. 6:284–290, 1994.
Costa, M., C.-K. Peng, A. L. Goldberger, and J. M. Hausdorff. Multiscale entropy analysis of human gait dynamics. Phys. A: Stat. Mech. Appl. 330:53–60, 2003.
Crea, S., M. Donati, S. M. M. De Rossi, C. Maria Oddo, and N. Vitiello. A wireless flexible sensorized insole for gait analysis. Sensors. 14:1073–1093, 2014.
Dingwell, J. B., and L. C. Marin. Kinematic variability and local dynamic stability of upper body motions when walking at different speeds. J. Biomech. 39:444–452, 2006.
Erdem, N. S., C. Ersoy, and C. Tunca. Gait analysis using smartwatches. Proc. IEEE 30th Int. Sympos. Person. Indoor Mob. Radio Commun., pp. 1–6, 2019.
Ferrari, A., P. Ginis, M. Hardegger, F. Casamassima, L. Rocchi, and L. Chiari. A mobile Kalman-filter based solution for the real-time estimation of spatio-temporal gait parameters. IEEE Trans. Neural Syst. Rehabil. Eng. 24:764–773, 2016.
Fusca, M., F. Negrini, P. Perego, L. Magoni, F. Molteni, and G. Andreoni. Validation of a wearable IMU system for gait analysis: protocol and application to a new system. Appl. Sci. 8:1167, 2018.
Hannink, J., T. Kautz, C. F. Pasluosta, J. Barth, S. Schulein, K.-G. Gassmann, J. Klucken, and B. M. Eskofier. Mobile stride length estimation with deep convolutional neural networks. IEEE J. Biomed. Health Inform. 22:354–362, 2018.
Hausdorff, J. M. Gait variability: methods, modeling and meaning. J. Neuroeng. Rehabil. 2:19, 2005.
Hausdorff, J. M., D. A. Rios, and H. K. Edelberg. Gait variability and fall risk in community-living older adults: a 1-year prospective study. Arch. Phys. Med. Rehabil. 82:1050–1056, 2001.
Hicks, J. L., T. K. Uchida, A. Seth, A. Rajagopal, and S. L. Delp. Is my model good enough? Best practices for verification and validation of musculoskeletal models and simulations of movement. J. Biomech. Eng. 137:020905, 2015.
Hoerl, A. E., and R. W. Kennard. Ridge regression: biased estimation for nonorthogonal problems. Technometrics. 12:55–67, 1970.
Hofmann, T., B. Schölkopf, and A. J. Smola. Kernel methods in machine learning. Ann. Stat. 36:1171–1220, 2008.
Hollman, J. H., M. K. Watkins, A. C. Imhoff, C. E. Braun, K. A. Akervik, and D. K. Ness. A comparison of variability in spatiotemporal gait parameters between treadmill and overground walking conditions. Gait Posture. 43:204–209, 2016.
Holmes, H. H., R. T. Fawcett, and J. A. Roper. Changes in spatiotemporal measures and variability during user-driven treadmill, fixed-speed treadmill, and overground walking in young adults: a pilot study. J. Appl. Biomech. 37:277–281, 2021.
Johnston, A. H., and G. M. Weiss. Smartwatch-based biometric gait recognition. Proc. IEEE 7th Int. Conf. Biom. Theory Appl. Syst. (BTAS), pp. 1–6, 2015.
Kang, H. G., and J. B. Dingwell. Separating the effects of age and walking speed on gait variability. Gait Posture. 27:572–577, 2008.
Kanko, R. M., E. K. Laende, G. Strutzenberger, M. Brown, W. S. Selbie, V. DePaul, S. H. Scott, and K. J. Deluzio. Assessment of spatiotemporal gait parameters using a deep learning algorithm-based markerless motion capture system. J. Biomech. 122:110414, 2021.
König, N., N. B. Singh, J. von Beckerath, L. Janke, and W. R. Taylor. Is gait variability reliable? An assessment of spatio-temporal parameters of gait variability during continuous overground walking. Gait Posture. 39:615–617, 2014.
Liu, J., T. Lockhart, and S. Kim. Prediction of the spatio-temporal gait parameters using inertial sensor. J. Mech. Med. Biol. 18:1840002, 2018.
Maki, B. E. Gait changes in older adults: predictors of falls or indicators of fear? J. Am. Geriatr. Soc. 45:313–320, 1997.
Mao, Y., T. Ogata, H. Ora, N. Tanaka, and Y. Miyake. Estimation of stride-by-stride spatial gait parameters using inertial measurement unit attached to the shank with inverted pendulum model. Sci. Rep. 11:1391, 2021.
Mazilu, S., U. Blanke, A. Calatroni, E. Gazit, J. M. Hausdorff, and G. Tröster. The role of wrist-mounted inertial sensors in detecting gait freeze episodes in Parkinson’s disease. Pervasive Mob. Comput. 33:1–16, 2016.
Mirelman, A., H. Bernad-Elazari, T. Nobel, A. Thaler, A. Peruzzi, M. Plotnik, N. Giladi, and J. M. Hausdorff. Effects of aging on arm swing during gait: the role of gait speed and dual tasking. PLoS ONE. 10:e0136043, 2015.
Ngueleu, A. M., A. K. Blanchette, L. Bouyer, D. Maltais, B. J. McFadyen, H. Moffet, and C. S. Batcho. Design and accuracy of an instrumented insole using pressure sensors for step count. Sensors. 19:984, 2019.
Niknejad, N., W. B. Ismail, A. Mardani, H. Liao, and I. Ghani. A comprehensive overview of smart wearables: the state of the art literature, recent advances, and future challenges. Eng. Appl. Artif. Intell. 90:103529, 2020.
O’Day, J., M. Lee, K. Seagers, S. Hoffman, A. Jih-Schiff, Ł Kidziński, S. Delp, and H. Bronte-Stewart. Assessing inertial measurement unit locations for freezing of gait detection and patient preference. J. Neuroeng. Rehabil. 19:20, 2022.
Pacini Panebianco, G., M. C. Bisi, R. Stagni, and S. Fantozzi. Analysis of the performance of 17 algorithms from a systematic review: influence of sensor position, analysed variable and computational approach in gait timing estimation from IMU measurements. Gait Posture. 66:76–82, 2018.
Postuma, R. B., D. Berg, M. Stern, W. Poewe, C. W. Olanow, W. Oertel, J. Obeso, K. Marek, I. Litvan, A. E. Lang, G. Halliday, C. G. Goetz, T. Gasser, B. Dubois, P. Chan, B. R. Bloem, C. H. Adler, and G. Deuschl. MDS clinical diagnostic criteria for Parkinson’s disease. Mov. Disord. 30:1591–1601, 2015.
Rajagopal, A., C. L. Dembia, M. S. DeMers, D. D. Delp, J. L. Hicks, and S. L. Delp. Full-body musculoskeletal model for muscle-driven simulation of human gait. IEEE Trans. Biomed. Eng. 63:2068–2079, 2016.
Rebula, J. R., L. V. Ojeda, P. G. Adamczyk, and A. D. Kuo. Measurement of foot placement and its variability with inertial sensors. Gait Posture. 38:974–980, 2013.
De Ridder, R., J. Lebleu, T. Willems, C. De Blaiser, C. Detrembleur, and P. Roosen. Concurrent validity of a commercial wireless trunk triaxial accelerometer system for gait analysis. J. Sport Rehabil. 28:1–4, 2019.
Riva, F., M. C. Bisi, and R. Stagni. Gait variability and stability measures: minimum number of strides and within-session reliability. Comput. Biol. Med. 50:9–13, 2014.
Seth, A., J. L. Hicks, T. K. Uchida, A. Habib, C. L. Dembia, J. J. Dunne, C. F. Ong, M. S. DeMers, A. Rajagopal, M. Millard, S. R. Hamner, E. M. Arnold, J. R. Yong, S. K. Lakshmikanth, M. A. Sherman, J. P. Ku, and S. L. Delp. OpenSim: simulating musculoskeletal dynamics and neuromuscular control to study human and animal movement. PLoS Comput. Biol. 14:e1006223, 2018.
Springer, S., and G. Yogev Seligmann. Validity of the kinect for gait assessment: a focused review. Sensors. 16:194, 2016.
Subramaniam, S., S. Majumder, A. I. Faisal, and M. J. Deen. Insole-based systems for health monitoring: current solutions and research challenges. Sensors. 22:438, 2022.
Teufl, W., M. Miezal, B. Taetz, M. Fröhlich, and G. Bleser. Validity of inertial sensor based 3D joint kinematics of static and dynamic sport and physiotherapy specific movements. PLoS ONE. 14:e0213064, 2019.
Tunca, C., N. Pehlivan, N. Ak, B. Arnrich, G. Salur, and C. Ersoy. Inertial sensor-based robust gait analysis in non-hospital settings for neurological disorders. Sensors. 17:825, 2017.
Usmani, S., A. Saboor, M. Haris, M. A. Khan, and H. Park. Latest research trends in fall detection and prevention using machine learning: a systematic review. Sensors. 21:5134, 2021.
Washabaugh, E. P., T. Kalyanaraman, P. G. Adamczyk, E. S. Claflin, and C. Krishnan. Validity and repeatability of inertial measurement units for measuring gait parameters. Gait Posture. 55:87–93, 2017.
Woltring, H. J. A Fortran package for generalized, cross-validatory spline smoothing and differentiation. Adv. Eng. Softw. 8:104–113, 1986.
Wren, T. A. L., G. E. Gorton, S. Õunpuu, and C. A. Tucker. Efficacy of clinical gait analysis: a systematic review. Gait Posture. 34:149–153, 2011.
Wu, Y., Y. Li, A.-M. Liu, F. **ao, Y.-Z. Wang, F. Hu, J.-L. Chen, K.-R. Dai, and D.-Y. Gu. Effect of active arm swing to local dynamic stability during walking. Hum. Mov. Sci. 45:102–109, 2016.
Zhang, H., Y. Guo, and D. Zanotto. Accurate ambulatory gait analysis in walking and running using machine learning models. IEEE Trans. Neural Syst. Rehabil. Eng. 28:191–202, 2020.
Zhou, L., C. Tunca, E. Fischer, C. M. Brahms, C. Ersoy, U. Granacher, and B. Arnrich. Validation of an IMU gait analysis algorithm for gait monitoring in daily life situations. Proc. 42nd Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. (EMBC), pp. 4229–4232, 2020.
Acknowledgements
The authors thank the participants for volunteering their time.
Funding
This work was supported by grants from the Natural Sciences and Engineering Research Council of Canada (NSERC), by the Ontario Ministry of Research, Innovation and Science Early Researcher Award, by postdoctoral fellowships from NSERC and the uOttawa-Children’s Hospital of Eastern Ontario Research Institute, and by the Apple Investigator Support Program.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
Apple Inc. supplied the smartwatches used in this study as part of the Investigator Support Program. Apple Inc. and funding sources had no involvement in study design, data collection, analysis, and interpretation, or writing of the manuscript. The authors have no other conflicts of interest to declare.
Additional information
Associate Editor Jillian Urban oversaw the review of this article.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Bailey, C.A., Mir-Orefice, A., Uchida, T.K. et al. Smartwatch-Based Prediction of Single-Stride and Stride-to-Stride Gait Outcomes Using Regression-Based Machine Learning. Ann Biomed Eng 51, 2504–2517 (2023). https://doi.org/10.1007/s10439-023-03290-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10439-023-03290-2