Gait disorders accompany a number of neurological and musculoskeletal disorders that significantly reduce the quality of life. Motion sensors enable high-quality modelling of gait stereotypes. However, they produce large volumes of data, the evaluation of which is a challenge. In this publication, we compare different data reduction methods and classification of reduced data for use in clinical practice. The best accuracy achieved between a group of healthy individuals and patients with ataxic gait extracted from the records of 43 participants (23 ataxic, 20 healthy), forming 418 segments of straight gait pattern, is 98% by random forest classifier preprocessed by t-distributed stochastic neighbour embedding.

Czech Institute of Informatics Robotics and Cybernetics Czech Technical University Prague 160 00 Prague 6 Czech Republic

Department of Chemistry Faculty of Science University of Hradec Králové 500 03 Hradec Králové Czech Republic

Department of Computing and Control Engineering University of Chemistry and Technology Prague 166 28 Praha 6 Czech Republic

Department of Neurology Faculty of Medicine in Hradec Králové Charles University 500 03 Hradec Králové Czech Republic

See more in PubMed

Houlden H., Charlton P., Singh D. Neurology and orthopaedics. J. Neurol. Neurosurg. Psychiatry. 2007;78:224–232. doi: 10.1136/jnnp.2006.092072. PubMed DOI PMC

Möhwald K., Pradhan C., Wuehr M., Dieterich M., Brandt T., Jahn K., Schniepp R. EP 52. PREGAIT study–Pattern recognition and differential diagnosis of neurological gait disorders in instrumental and clinical gait analysis. Clin. Neurophysiol. 2016;127:e260. doi: 10.1016/j.clinph.2016.05.106. DOI

Buckley C., Alcock L., McArdle R., Rehman R.Z.U., Del Din S., Mazzà C., Yarnall A.J., Rochester L. The role of movement analysis in diagnosing and monitoring neurodegenerative conditions: Insights from gait and postural control. Brain Sci. 2019;9:34. doi: 10.3390/brainsci9020034. PubMed DOI PMC

Lim C.H., Vats E., Chan C.S. Fuzzy human motion analysis: A review. Pattern Recognit. 2015;48:1773–1796. doi: 10.1016/j.patcog.2014.11.016. DOI

Terayama K., Sakakibara R., Ogawa A. Wearable gait sensors to measure ataxia due to spinocerebellar degeneration. Neurol. Clin. Neurosci. 2018;6:9–12. doi: 10.1111/ncn3.12174. DOI

Arcuria G., Marcotulli C., Amuso R., Dattilo G., Galasso C., Pierelli F., Casali C. Developing a smartphone application, triaxial accelerometer-based, to quantify static and dynamic balance deficits in patients with cerebellar ataxias. J. Neurol. 2020;267:625–639. doi: 10.1007/s00415-019-09570-z. PubMed DOI

Takayanagi N., Sudo M., Yamashiro Y., Lee S., Kobayashi Y., Niki Y., Shimada H. Relationship between daily and in-laboratory gait speed among healthy community-dwelling older adults. Sci. Rep. 2019;9:3496. doi: 10.1038/s41598-019-39695-0. PubMed DOI PMC

Charvátová H., Procházka A., Vyšata O. Motion Assessment for Accelerometric and Heart Rate Cycling Data Analysis. Sensors. 2020;20:1523. doi: 10.3390/s20051523. PubMed DOI PMC

Procházka A., Vaseghi S., Yadollahi M., Ťupa O., Mareš J., Vyšata O. Remote physiological and GPS data processing in evaluation of physical activities. Med. Biol. Eng. Comput. 2014;52:301–308. doi: 10.1007/s11517-013-1134-6. PubMed DOI

Jarchi D., Pope J., Lee T.K., Tamjidi L., Mirzaei A., Sanei S. A review on accelerometry-based gait analysis and emerging clinical applications. IEEE Rev. Biomed. Eng. 2018;11:177–194. doi: 10.1109/RBME.2018.2807182. PubMed DOI

Hickey A., Gunn E., Alcock L., Del Din S., Godfrey A., Rochester L., Galna B. Validity of a wearable accelerometer to quantify gait in spinocerebellar ataxia type 6. Physiol. Meas. 2016;37:N105. doi: 10.1088/0967-3334/37/11/N105. PubMed DOI

Ahmad N., Ghazilla R.A.R., Khairi N.M., Kasi V. Reviews on various inertial measurement unit (IMU) sensor applications. Int. J. Signal Process. Syst. 2013;1:256–262. doi: 10.12720/ijsps.1.2.256-262. DOI

Sers R., Forrester S., Moss E., Ward S., Ma J., Zecca M. Validity of the Perception Neuron inertial motion capture system for upper body motion analysis. Measurement. 2020;149:107024. doi: 10.1016/j.measurement.2019.107024. DOI

Taylor C.R., von Konsky B.R., Kirtley C. Polynomial approximations of gait for human motion analysis and visualization; Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol. 20 Biomedical Engineering Towards the Year 2000 and Beyond (Cat. No. 98CH36286); Hong Kong, China. 1 November 1998; pp. 2490–2493.

Karahoca A., Nurullahoglu M. WSEAS International Conference, Proceedings of the Mathematics and Computers in Science and Engineering, Heraklion Greece, 23–25 July 2008. Volume 7 World Scientific and Engineering Academy and Society; Singapore: 2008. Human motion analysis and action recognition.

Lewandowski M. Ph.D. Thesis. Kingston University; London, UK: 2011. Advanced Nonlinear Dimensionality Reduction Methods for Multidimensional Time Series Application to Human Motion Analysis.

Mandery C., Plappert M., Borras J., Asfour T. Dimensionality reduction for whole-body human motion recognition; Proceedings of the 2016 19th International Conference on Information Fusion (FUSION); Heidelberg, Germany. 5–8 July 2016; pp. 355–362.

Potluri S., Ravuri S., Diedrich C., Schega L. Deep Learning based Gait Abnormality Detection using Wearable Sensor System; Proceedings of the 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC); Berlin, Germany. 23–27 July 2019; pp. 3613–3619. PubMed

Phinyomark A., Petri G., Ibáñez-Marcelo E., Osis S.T., Ferber R. Analysis of big data in gait biomechanics: Current trends and future directions. J. Med. Biol. Eng. 2018;38:244–260. doi: 10.1007/s40846-017-0297-2. PubMed DOI PMC

Shirai S., Yabe I., Matsushima M., Ito Y.M., Yoneyama M., Sasaki H. Quantitative evaluation of gait ataxia by accelerometers. J. Neurol. Sci. 2015;358:253–258. doi: 10.1016/j.jns.2015.09.004. PubMed DOI

Fazio P., Granieri G., Casetta I., Cesnik E., Mazzacane S., Caliandro P., Pedrielli F., Granieri E. Gait measures with a triaxial accelerometer among patients with neurological impairment. Neurol. Sci. 2013;34:435–440. doi: 10.1007/s10072-012-1017-x. PubMed DOI

LeMoyne R., Heerinckx F., Aranca T., De Jager R., Zesiewicz T., Saal H.J. Wearable body and wireless inertial sensors for machine learning classification of gait for people with Friedreich’s ataxia; Proceedings of the 2016 IEEE 13th International Conference on Wearable and Implantable Body Sensor Networks (BSN); San Francisco, CA, USA. 14–17 June 2016; pp. 147–151.

Mannini A., Martinez-Manzanera O., Lawerman T.F., Trojaniello D., Della Croce U., Sival D.A., Maurits N.M., Sabatini A.M. Automatic classification of gait in children with early-onset ataxia or developmental coordination disorder and controls using inertial sensors. Gait Posture. 2017;52:287–292. doi: 10.1016/j.gaitpost.2016.12.002. PubMed DOI

Matsushima A., Yoshida K., Genno H., Ikeda S.I. Principal component analysis for ataxic gait using a triaxial accelerometer. J. Neuroeng. Rehabil. 2017;14:37. doi: 10.1186/s12984-017-0249-7. PubMed DOI PMC

Dostál O., Procházka A., Vyšata O., Ťupa O., Cejnar P., Vališ M. Recognition of motion patterns using accelerometers for ataxic gait assessment. Neural Comput. Appl. 2020;33:2207–2215. doi: 10.1007/s00521-020-05103-2. DOI

Matsushima A., Yoshida K., Genno H., Murata A., Matsuzawa S., Nakamura K., Nakamura A., Ikeda S. Clinical assessment of standing and gait in ataxic patients using a triaxial accelerometer. Cerebellum Ataxias. 2015;2:1–7. doi: 10.1186/s40673-015-0028-9. PubMed DOI PMC

Caliandro P., Conte C., Iacovelli C., Tatarelli A., Castiglia S.F., Reale G., Serrao M. Exploring risk of falls and dynamic unbalance in cerebellar ataxia by inertial sensor assessment. Sensors. 2019;19:5571. doi: 10.3390/s19245571. PubMed DOI PMC

Procházka A., Vyšata O., Charvátová H., Vališ M. Motion Symmetry Evaluation Using Accelerometers and Energy Distribution. Symmetry. 2019;11:871. doi: 10.3390/sym11070871. DOI

Wold S., Esbensen K., Geladi P. Principal component analysis. Chemom. Intell. Lab. Syst. 1987;2:37–52. doi: 10.1016/0169-7439(87)80084-9. DOI

Maaten L.V.D., Hinton G. Visualizing data using t-SNE. J. Mach. Learn. Res. 2008;9:2579–2605.

McInnes L., Healy J., Melville J. Umap: Uniform manifold approximation and projection for dimension reduction. arXiv. 20181802.03426

Hosmer D.W., Jr., Lemeshow S., Sturdivant R.X. Applied Logistic Regression. Volume 398 John Wiley & Sons; Hoboken, NJ, USA: 2013.

Suykens J.A., Vandewalle J. Least squares support vector machine classifiers. Neural Process. Lett. 1999;9:293–300. doi: 10.1023/A:1018628609742. DOI

Howley T., Madden M.G. The genetic kernel support vector machine: Description and evaluation. Artif. Intell. Rev. 2005;24:379–395. doi: 10.1007/s10462-005-9009-3. DOI

Rish I. An empirical study of the naive Bayes classifier; Proceedings of the IJCAI 2001 Workshop on Empirical Methods in Artificial Intelligence; Seattle, WA, USA. 4–6 August 2001; pp. 41–46.

Thomaz C.E., Gillies D.F., Feitosa R.Q. International Workshop on Biometric Authentication. Springer; Berlin/Heidelberg, Germany: 2002. A new quadratic classifier applied to biometric recognition; pp. 186–196.

Seidl T., Kriegel H.P. Optimal multi-step k-nearest neighbor search; Proceedings of the 1998 ACM SIGMOD International Conference on Management of Data; Seattle, WA, USA. 2–4 June 1998; pp. 154–165.

Vens C., Struyf J., Schietgat L., Džeroski S., Blockeel H. Decision trees for hierarchical multi-label classification. Mach. Learn. 2008;73:185. doi: 10.1007/s10994-008-5077-3. DOI

Liaw A., Wiener M. Classification and regression by randomForest. R News. 2002;2:18–22.

Lippmann R.P. Pattern classification using neural networks. IEEE Commun. Mag. 1989;27:47–50. doi: 10.1109/35.41401. DOI

Hastie T., Rosset S., Zhu J., Zou H. Multi-class adaboost. Stat. Interface. 2009;2:349–360. doi: 10.4310/SII.2009.v2.n3.a8. DOI

Figueiredo J., Santos C.P., Moreno J.C. Automatic recognition of gait patterns in human motor disorders using machine learning: A review. Med. Eng. Phys. 2018;53:1–12. doi: 10.1016/j.medengphy.2017.12.006. PubMed DOI

McGinnis R.S., Mahadevan N., Moon Y., Seagers K., Sheth N., Wright J.A., Jr., DiCristofaro S., Silva I., Jortberg E., Ceruolo M., et al. A machine learning approach for gait speed estimation using skin-mounted wearable sensors: From healthy controls to individuals with multiple sclerosis. PLoS ONE. 2017;12:e0178366. doi: 10.1371/journal.pone.0178366. PubMed DOI PMC

Alotaibi M., Mahmood A. Improved gait recognition based on specialized deep convolutional neural network. Comput. Vis. Image Underst. 2017;164:103–110. doi: 10.1016/j.cviu.2017.10.004. DOI

Phan D., Nguyen N., Pathirana P.N., Horne M., Power L., Szmulewicz D. A random forest approach for quantifying gait ataxia with truncal and peripheral measurements using multiple wearable sensors. IEEE Sens. J. 2019;20:723–734. doi: 10.1109/JSEN.2019.2943879. DOI

Reynard F., Terrier P. Determinants of gait stability while walking on a treadmill: A machine learning approach. J. Biomech. 2017;65:212–215. doi: 10.1016/j.jbiomech.2017.10.020. PubMed DOI