Abstract
Objective measurement of walking speed and gait deficits are an important clinical tool in chronic illness management. We previously reported in Parkinson’s disease that different types of gait tests can now be implemented and administered in the clinic or at home using Ambulosono smartphone-sensor technology, whereby movement sensing protocols can be standardized under voice instruction. However, a common challenge that remains for such wearable sensor systems is how meaningful data can be extracted from seemingly “noisy” raw sensor data, and do so with a high level of accuracy and efficiency. Here, we describe a novel pattern recognition algorithm for the automated detection of gait-cycle breakdown and freezing episodes. Ambulosono-gait-cycle-breakdown-and-freezing-detection (Free-D) integrates a nonlinear m-dimensional phase-space data extraction method with machine learning and Monte Carlo analysis for model building and pattern generalization. We first trained Free-D using a small number of data samples obtained from thirty participants during freezing of gait tests. We then tested the accuracy of Free-D via Monte Carlo cross-validation. We found Free-D to be remarkably effective at detecting gait-cycle breakdown, with mode error rates of 0% and mean error rates < 5%. We also demonstrate the utility of Free-D by applying it to continuous holdout traces not used for either training or testing, and found it was able to identify gait-cycle breakdown and freezing events of varying duration. These results suggest that advanced artificial intelligence and automation tools can be developed to enhance the quality, efficiency, and the expansion of wearable sensor data processing capabilities to meet market and industry demand.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Afsar O, Tirnakli U, Marwan N (2018) Recurrence quantification analysis at work: quasi-periodicity based interpretation of gait force profiles for patients with Parkinson disease. Sci Rep 8:9102. https://doi.org/10.1038/s41598-018-27369-2
Ahlrichs C, Samà A, Lawo M et al (2016) Detecting freezing of gait with a tri-axial accelerometer in Parkinson’s disease patients. Med Biol Eng Comput 54:223–233. https://doi.org/10.1007/s11517-015-1395-3
Aich S, Pradhan PM, Park J et al (2018) A validation study of freezing of gait (FoG) detection and machine-learning-based FoG prediction using estimated gait characteristics with a wearable accelerometer. Sensors (Basel) 18:3287. https://doi.org/10.3390/s18103287
Asri H, Mousannif H, Al Moatassime H, Noel T (2016) ScienceDirect the 6th International Symposium on frontiers in ambient and mobile systems using machine learning algorithms for breast cancer risk prediction and diagnosis. Proc Comput Sci 83:1064–1069. https://doi.org/10.1016/j.procs.2016.04.224
Bakhshipour A, Jafari A (2018) Evaluation of support vector machine and artificial neural networks in weed detection using shape features. Comput Electron Agric 145:153–160. https://doi.org/10.1016/J.COMPAG.2017.12.032
Begg R, Kamruzzaman J (2003) A comparison of neural networks and support vector machines for recognizing young-old gait patterns. In: TENCON 2003. Conference on Convergent Technologies for Asia-Pacific Region. Allied Publishers Pvt. Ltd, pp 354–358
Bloem BR, Hausdorff JM, Visser JE, Giladi N (2004) Falls and freezing of gait in Parkinson’s disease: a review of two interconnected, episodic phenomena. Mov Disord 19:871–884
Brognara L, Palumbo P, Grimm B, Palmerini L (2019) Assessing gait in Parkinson’s disease using wearable motion sensors: a systematic review. Diseases (Basel, Switzerland) 7:18. https://doi.org/10.3390/diseases7010018
Camps J, Samà A, Martín M et al (2018) Deep learning for freezing of gait detection in Parkinson’s disease patients in their homes using a waist-worn inertial measurement unit. Knowl-Based Syst 139:119–131. https://doi.org/10.1016/J.KNOSYS.2017.10.017
Chatzimichali EA, Bessant C (2016) Novel application of heuristic optimisation enables the creation and thorough evaluation of robust support vector machine ensembles for machine learning applications. Metabolomics 12:16. https://doi.org/10.1007/s11306-015-0894-4
Chomiak T, Pereira FV, Meyer N et al (2015) A new quantitative method for evaluating freezing of gait and dual-attention task deficits in Parkinson’s disease. J Neural Transm 122:1523–1531. https://doi.org/10.1007/s00702-015-1423-3
Chomiak T, Watts A, Meyer N et al (2017) A training approach to improve stepping automaticity while dual-tasking in Parkinson’s disease: a prospective pilot study. Medicine (United States) 96:e5934. https://doi.org/10.1097/MD.0000000000005934
Chomiak T, Watts A, Burt J et al (2018) Differentiating cognitive or motor dimensions associated with the perception of fall-related self-efficacy in Parkinson’s Disease. NPJ Parkinsons Dis 4:26. https://doi.org/10.1038/s41531-018-0059-z
Chomiak T, Sidhu A, Watts A et al (2019) Development and validation of ambulosono: a wearable sensor for bio-feedback rehabilitation training. Sensors 19:686. https://doi.org/10.3390/s19030686
Chui K, Alhalabi W, Pang S et al (2017) Disease diagnosis in smart healthcare: innovation, technologies and applications. Sustainability 9:2309. https://doi.org/10.3390/su9122309
Ganz M, Konukoglu E (2017) Permutation tests for classification: revisited. In: 2017 International Workshop on Pattern Recognition in Neuroimaging (PRNI). IEEE, pp 1–4
Golland P, Fischl B (2003) Permutation tests for classification: towards statistical significance in image-based studies. Inf Process Med Imaging 18:330–341
Guo Y, De Jong K, Liu F et al (2012) A comparison of artificial neural networks and support vector machines on land cover classification. In: Li Z, Li X, Liu Y, Cai Z (eds) Computational intelligence and intelligent systems. ISICA 2012. Communications in computer and information science, vol 316. Springer, Berlin, pp 531–539
Guosheng H, Guohong Z (2008) Comparison on neural networks and support vector machines in suppliers’ selection. J Syst Eng Electron 19:316–320. https://doi.org/10.1016/S1004-4132(08)60085-7
Jodas DS, Marranghello N, Pereira AS, Guido RC (2013) Comparing support vector machines and artificial neural networks in the recognition of steering angle for driving of mobile robots through paths in plantations. Proc Comput Sci 18:240–249. https://doi.org/10.1016/J.PROCS.2013.05.187
Kavakiotis I, Tsave O, Salifoglou A et al (2017) Machine learning and data mining methods in diabetes research. Comput Struct Biotechnol J 15:104–116. https://doi.org/10.1016/J.CSBJ.2016.12.005
Konvalinka I, Xygalatas D, Bulbulia J et al (2011) Synchronized arousal between performers and related spectators in a fire-walking ritual. Proc Natl Acad Sci USA 108:8514–8519. https://doi.org/10.1073/pnas.1016955108
Koutsouleris N, Meisenzahl EM, Davatzikos C et al (2009) Use of neuroanatomical pattern classification to identify subjects in at-risk mental states of psychosis and predict disease transition. Arch Gen Psychiatry 66:700–712. https://doi.org/10.1001/archgenpsychiatry.2009.62
Kumar P, Gupta DK, Mishra VN, Prasad R (2015) Comparison of support vector machine, artificial neural network, and spectral angle mapper algorithms for crop classification using LISS IV data. Int J Remote Sens 36:1604–1617. https://doi.org/10.1080/2150704X.2015.1019015
Marwan N, Kurths J (2002) Nonlinear analysis of bivariate data with cross recurrence plots. Phys Lett A 302:299–307. https://doi.org/10.1016/S0375-9601(02)01170-2
Mazzetta I, Zampogna A, Suppa A et al (2019) Wearable sensors system for an improved analysis of freezing of gait in Parkinson’s disease using electromyography and inertial signals. Sensors (Basel) 19:948. https://doi.org/10.3390/s19040948
Merola A, Sturchio A, Hacker S et al (2018) Technology-based assessment of motor and nonmotor phenomena in Parkinson disease. Expert Rev Neurother 18:825–845. https://doi.org/10.1080/14737175.2018.1530593
Moore ST, MacDougall HG, Ondo WG (2008) Ambulatory monitoring of freezing of gait in Parkinson’s disease. J Neurosci Methods 167:340–348. https://doi.org/10.1016/j.jneumeth.2007.08.023
Moore ST, Yungher DA, Morris TR et al (2013) Autonomous identification of freezing of gait in Parkinson’s disease from lower-body segmental accelerometry. J Neuroeng Rehabil 10:19. https://doi.org/10.1186/1743-0003-10-19
Nantel J, de Solages C, Bronte-Stewart H (2011) Repetitive stepping in place identifies and measures freezing episodes in subjects with Parkinson’s disease. Gait Posture 34:329–333
Nieuwboer A, Giladi N (2013) Characterizing freezing of gait in Parkinson’s disease: models of an episodic phenomenon. Mov Disord 28:1509–1519
Odin P, Chaudhuri KR, Volkmann J et al (2018) Viewpoint and practical recommendations from a movement disorder specialist panel on objective measurement in the clinical management of Parkinson’s disease. NPJ Parkinsons Dis 4:14. https://doi.org/10.1038/s41531-018-0051-7
Patrício M, Pereira J, Crisóstomo J et al (2018) Using resistin, glucose, age and BMI to predict the presence of breast cancer. BMC Cancer 18:29. https://doi.org/10.1186/s12885-017-3877-1
Prateek GV, Skog I, McNeely ME et al (2018) Modeling, detecting, and tracking freezing of gait in Parkinson disease using inertial sensors. IEEE Trans Biomed Eng 65:2152–2161. https://doi.org/10.1109/TBME.2017.2785625
Punin C, Barzallo B, Clotet R et al (2019) A non-invasive medical device for Parkinson’s patients with episodes of freezing of gait. Sensors 19:737. https://doi.org/10.3390/s19030737
Rodríguez-Martín D, Samà A, Pérez-López C et al (2017) Home detection of freezing of gait using support vector machines through a single waist-worn triaxial accelerometer. PLoS One 12:e0171764. https://doi.org/10.1371/journal.pone.0171764
Sakr G, Mokbel M, Darwich A (2016) Comparing deep learning and support vector machines for autonomous waste sorting. IEEE Int Multidiscip Conf Eng Technol 2016:1–6
Silva de Lima AL, Evers LJW, Hahn T et al (2017) Freezing of gait and fall detection in Parkinson’s disease using wearable sensors: a systematic review. J Neurol 264:1642–1654. https://doi.org/10.1007/s00415-017-8424-0
Takens F (1981) Detecting strange attractors in turbulence. Dynamical systems and turbulence. Springer, Berlin, pp 366–381
Vandenbossche J, Deroost N, Soetens E et al (2012) Freezing of gait in Parkinson’s disease: disturbances in automaticity and control. Front Hum Neurosci 6:356
Vercruysse S, Devos H, Munks L et al (2012) Explaining freezing of gait in Parkinson’s disease: motor and cognitive determinants. Mov Disord 27:1644–1651
Wallot S, Roepstorff A, Mønster D (2016) Multidimensional recurrence quantification analysis (MdRQA) for the analysis of multidimensional time-series: a software implementation in MATLAB and its application to group-level data in joint action. Front Psychol 7:1835. https://doi.org/10.3389/fpsyg.2016.01835
Walton CC, Shine JM, Hall JM et al (2015) The major impact of freezing of gait on quality of life in Parkinson’s disease. J Neurol 262:108–115
Walton CC, Mowszowski L, Gilat M et al (2018) Cognitive training for freezing of gait in Parkinson’s disease: a randomized controlled trial. NPJ Parkinsons Dis 4:15. https://doi.org/10.1038/s41531-018-0052-6
Webber CL, Zbilut JP (2005) Recurrence quantification analysis of nonlinear dynamical systems. In: Riley M, Van Orden G (eds) Tutorials in contemporary nonlinear methods for the behavioural sciences. National Science Foundation, Arlington, pp 26–95
Wu T, Hallett M, Chan P (2015) Motor automaticity in Parkinson’s disease. Neurobiol Dis 82:226–234
Wu W, Li A-D, He X-H et al (2018) A comparison of support vector machines, artificial neural network and classification tree for identifying soil texture classes in southwest China. Comput Electron Agric 144:86–93. https://doi.org/10.1016/J.COMPAG.2017.11.037
Xu SS, Mak MW, Cheung CC (2017) Deep neural networks versus support vector machines for ECG arrhythmia classification. In: 2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017. IEEE, pp 127–132
Xu C, He J, Zhang X et al (2018) Template-matching-based detection of freezing of gait using wearable sensors. Proc Comput Sci 129:21–27. https://doi.org/10.1016/J.PROCS.2018.03.038
Acknowledgements
This research was funded by the University of Calgary Suter Professorship for Parkinson’s Research, and SonoStep Inc., Canada. We would also like to thank Abhijot Singh Sidhu and Dr. Fernando Vieira Pereira for their involvement with data collection, as well as support from Canadian Institutes of Health Research, Alberta Innovates-Health Solutions, MITACs, Parkinson Alberta Society, and the Hotchkiss Brain Institute. TC was previously funded by MITACs.
Author information
Authors and Affiliations
Contributions
Conceptualization, TC; experimental methodology, all authors; sensor development, BH; algorithm development, TC; writing—original draft preparation, TC drafted the initial version, and all other authors critically reviewed it.
Corresponding authors
Ethics declarations
Conflict of interest
BH invented the Ambulosono data system and GaitReminder App which is under investigational use, and is the founder of SonoStep Inc.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Chomiak, T., Xian, W., Pei, Z. et al. A novel single-sensor-based method for the detection of gait-cycle breakdown and freezing of gait in Parkinson’s disease. J Neural Transm 126, 1029–1036 (2019). https://doi.org/10.1007/s00702-019-02020-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00702-019-02020-0