Multimedia Tools and Applications

, Volume 78, Issue 14, pp 19697–19734 | Cite as

Statistical methods for analysis of Parkinson’s disease gait pattern and classification

  • Anup NandyEmail author


Understanding the human gait and extracting intrinsic feature helps to classify walking patterns of Parkinson disease patients. The measurement of time series gait pattern is required to detect gait disturbances observed in medical gait data. An attempt is taken to compute Normalized Auto Correlation (NAC) along the temporal axis which calculates the degree of gait fluctuation in control subjects (CO) and Parkinson patient’s (PD) gait. In this paper, an underlying statistical analysis is addressed to understand the statistical nature of data. Identifying the proper distribution of these data in advance discards the unwanted information which helps to preserve more informative features. Four different normality testing methods (i.e. W/S, Kolmogorov-Smirnov, Shapiro Wilk and Anderson Darling) are applied to ensure whether the acquired gait data are modelled by a normal distribution. It precludes the costly error during feature analysis to produce the accurate results. A feature selection method, Fisher Discriminant Ratio (FDR) is applied to select most discriminative feature among all the statistical features (i.e. Mean, Median, Mode, Standard Deviation, Variance, Skewness and Kurtosis) derived from both the classes. A probabilistic classifier based on Bayes’ theorem demonstrates its efficiency in the classification of Parkinson gait with illustrating statistical error metrics (i.e. MAE, RMSE, MCE, MSE, SEM, SSE etc.).


Human gait Normalized auto correlation Parkinson disease Statistical normality testing Fisher discriminant ratio Probabilistic classifier Error metrics 



We are extremely thankful to PhysioNet people for sharing their medical gait data with us for completing this research work. I would also extend my thanks to pervious B.Tech. Students, Monika and Kamnee, Upharika and Nurzin in my previous Institute for their contribution to this research work.


  1. 1.
    Aqmar MR, Fujihara Y, Makihara Y, Yagi Y (2014) Gait recognition by fluctuations. Comput Vis Image Underst 126:38–52Google Scholar
  2. 2.
    Chen SW, Lin SH, Liao LD, Lai HY, Pei YC, Kuo TS, Tsang S (2011) Quantification and recognition of parkinsonian gait from monocular video imaging using kernel-based principal component analysis. Biomed Eng Online 10(1):1–21Google Scholar
  3. 3.
    Chen YY, Cho CW, Lin SH, Lai HY, Lo YC, Chen SY, Tsai ST, Tsang S (2012) A vision-based regression model to evaluate parkinsonian gait from monocular image sequences. Expert Syst Appl 39(1):520–526Google Scholar
  4. 4.
    Chen P-H, Wang R-L, Liou D-J, Shaw J-S (2013) Gait disorders in Parkinson’s disease: assessment and management. International Journal of Gerontology 7(4):189–193Google Scholar
  5. 5.
    Das KR, Rahmatullah Imon AHM (2016) A brief review of tests for normality. Am J Theor Appl Stat 5(1):5–12Google Scholar
  6. 6.
    Dekker MHP (2009) Zero-moment point method for stable biped walking. Eindhoven University of TechnologyGoogle Scholar
  7. 7.
    Djuric-Jovicic M, Jovicic NS, Milovanovic I, Radovanovic S, Kresojevic N, Popovic MB (2010) Classification of walking patterns in Parkinson's disease patients based on inertial sensor data. In: 10th Symposium on Neural Network Applications in Electrical Engineering (NEUREL), p 3–6Google Scholar
  8. 8.
    Eltoukhy M, Kuenze C, Andersen MS, Oh J, Signorile J (2017) Prediction of ground reaction forces for Parkinson’s disease patients using a kinect-driven musculoskeletal gait analysis model. Med Eng Phys 50:75–82Google Scholar
  9. 9.
    Filion M, Tremblay L (1991) Abnormal spontaneous activity of globus pallidus neurons in monkeys with MPTP-induced parkinsonism. Brain Res 547(1):140–144Google Scholar
  10. 10.
    Filion M, Tremblay L, Bédard PJ (1988) Abnormal influences of passive limb movement on the activity of globus pallidus neurons in parkinsonian monkeys. Brain Res 444(1):165–176Google Scholar
  11. 11.
    Gait in Parkinson’s disease (2004). Available from:
  12. 12.
    Hoehn and Yahr (HAY) score (1967). Available from: <>
  13. 13.
    Koh S-B, Park K-W, Lee D-H, Kim SJ, Yoon J-S (2008) Gait analysis in patients with Parkinson’s disease: relationship to clinical features and freezing. Journal of Movement Disorders 1(2):59–64Google Scholar
  14. 14.
    Lang AE, Lozano AM (1998) Parkinson's disease. N Engl J Med 339(15):1044–1053Google Scholar
  15. 15.
    Lei H, Zhang J, Yang Z., Tan El, Lei B, Luo Q (2017) Joint detection and clinical score prediction in Parkinson's disease via multi-modal sparse learning. 14th IEEE International Symposium on Biomedical Imaging (ISBI 2017), Melbourne, VIC, p 1231–1234Google Scholar
  16. 16.
    Liu Y, Nie L, Han L, Zhang L, Rosenblum DS (2015) Action2Activity: recognizing complex activities from sensor data. In: Proceedings of the 24th International Conference on Artificial Intelligence, series = IJCAI'15, publisher = AAAI Press, Buenos Aires, Argentina, p 1617–1623Google Scholar
  17. 17.
    Liu Y, Zhang L, Nie L, Yan Y, Rosenblum DS (2016) Fortune teller: predicting your career path, Proc AAAI, p 201–207Google Scholar
  18. 18.
    Liu Y, Nie L, Liu L, Rosenblum DS (2016) From action to activity: sensor-based activity recognition. Neurocomputing 181:108–115Google Scholar
  19. 19.
    Makihara Y, Sagawa R, Mukaigawa Y, Echigo T, Yagi Y (2006) Gait recognition using a view transformation model in the frequency domain. In: Computer Vision–ECCV, p 151–163Google Scholar
  20. 20.
    Makihara Y, Aqmar MR, Ngo TT, Nagahara H, Sagawa R, Mukaigawa Y, Yagi Y (2014) Phase estimation of a single quasi-periodic signal. IEEE Trans Signal Process 62(8):2066–2079MathSciNetzbMATHGoogle Scholar
  21. 21.
    Manap HH, Tahir NM, Yassin AIM, M AI (2011) Statistical analysis of parkinson disease gait classification using Artificial Neural Network. In: IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), p 060–065Google Scholar
  22. 22.
    Martinez Martin P, Gil Nagel A, Gracia LM, Gómez JB, Martinez Sarriés J, Bermejo F (1994) Unified Parkinson's disease rating scale characteristics and structure. Mov Disord 9(1):76–83Google Scholar
  23. 23.
    Medeiros L, Almeida H, Dias L, Perkusich M, Fischer R (2016) A gait analysis approach to track parkinson's disease evolution using principal component analysis. 29th IEEE International Symposium on Computer-Based Medical Systems (CBMS), Dublin, p 48–53Google Scholar
  24. 24.
    Mori A, Makihara Y, Yagi Y (2010) Gait recognition using period-based phase synchronization for low frame-rate videos. In: International Conference on Pattern Recognition (ICPR), p 2194–2197Google Scholar
  25. 25.
    Nilashi M, Ibrahim O, Ahani A (2016) Accuracy improvement for predicting Parkinson’s disease progression. Sci RepGoogle Scholar
  26. 26.
    Nilashi M, brahim OI, Ahmadi H, Shahmoradi L, Farahmand M (2018) A hybrid intelligent system for the prediction of Parkinson's disease progression using machine learning techniques. Biocybernetics and Biomedical Engineering 38:1–15Google Scholar
  27. 27.
    Okuda S, Takano S, Ueno M, Hara Y, Chida Y, Ikkaku T, Kanda F, Toda T (2016) Gait analysis of patients with Parkinson's disease using a portable triaxial accelerometer. Neurology and Clinical Neuroscience 4(3):93–97Google Scholar
  28. 28.
    Parkinson J (2002) An essay on the shaking palsy. J Neuropsychiatry Clin Neurosci 14(2):223–236Google Scholar
  29. 29.
    Perumal SV, Sankar R (2016) Gait monitoring system for patients with Parkinson's disease using wearable sensors, 2016 IEEE Healthcare Innovation Point-Of-Care Technologies Conference (HI-POCT), Cancun, p 21–24Google Scholar
  30. 30.
    Roiz R, Cacho EWA, Pazinatto MM, Reis JG, Cliquet A, Barasnevicius-Quagliato EMA (2010) Gait analysis comparing Parkinson's disease with healthy elderly subjects. Arq Neuropsiquiatr 68(1):81–86Google Scholar
  31. 31.
    Rosin R, Topka H, Dichgans J (1997) Gait initiation in Parkinson’s disease. Mov Disord 12(5):682–690Google Scholar
  32. 32.
    Rostami M, Bessonnet MG (2009) Impactless sagittal gait of a biped robot during the single support phase. In: IEEE International Conference on Robotics and Automation, Proceedings, Vol. 2, p 1385–139Google Scholar
  33. 33.
  34. 34.
    Salarian A, Russmann H, Vingerhoets FJ, Dehollaini C, Blanc Y, Burkhard PR, Aminian K (2004) Gait assessment in Parkinson's disease: toward an ambulatory system for long-term monitoring. IEEE Trans Biomed Eng 51(8):1434–1443Google Scholar
  35. 35.
    Scheiner A, Ferencz DC, Chizeck HJ (1995) Quantitative measurement of stability in human gait through computer simulation and Floquet analysis. In: IEEE 17th Annual Conference on Engineering in Medicine and Biology Society Vol. 2, p 1489–1490Google Scholar
  36. 36.
    Stam CJ (2005) Nonlinear dynamical analysis of EEG and MEG: review of an emerging field. Clin Neurophysiol 116(10):2266–2301Google Scholar
  37. 37.
    Wu Y, Krishnan S (2010) Statistical analysis of gait rhythm in patients with Parkinson's disease. IEEE Trans Neural Syst Rehabil Eng 18(2):150–158Google Scholar
  38. 38.
    Ye Q, Xia Y, Yao Z (2018) Classification of gait patterns in patients with neurodegenerative disease using adaptive neuro-fuzzy inference system. In: , p 1–8Google Scholar
  39. 39.
    Zhang Y, Ogunbona PO, Li W, Munro B, Wallace GG (2013) Pathological gait detection of Parkinson's disease using sparse representation, 2013 International Conference on Digital Image Computing: Techniques and Applications (DICTA), Hobart, TAS, p 1–8Google Scholar
  40. 40.
    Zheng YF, Shen J (1990) Gait synthesis for the SD-2 biped robot to climb sloping surface. IEEE Trans Robot Autom 6(1):86–96Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Computer Science and Engineering Department, Machine Intelligence and Bio-Motion Research LaboratoryNational Institute of Technology, RourkelaRourkelaIndia

Personalised recommendations