A machine learning approach to distinguish Parkinson’s disease (PD) patient’s with shuffling gait from older adults based on gait signals using 3D motion analysis

  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract

    In recent times the adverse impact of Parkinson’s disease (PD) getting worse and worse with the increasing rate of old age population through out the world. This disease is the second common neurological disorder and has a tremendous economical and social impact because the cost associated with the healthcare as well as service is extremely high. The diagnosis process of this disease mostly done by closely observing the patient in the clinic as well as using the rating scale. However, this kind of diagnosis is subjective in nature and usually takes long time and assessment of this disease is complicated and cannot replicated in other patients. This kind of diagnosis method is also not suitable for the early detection of the PD. So, with this shortcoming it is necessary to find a suitable method that can automate the process as well as useful in the initial phase of diagnosis of PD. Recently with the invention of motion capture equipment’s and artificial intelligent technique, the feasibility of the objective nature-based diagnosis is getting lot of attention, especially the objective quantification of gait parameters. Shuffling of gait is one of the important characteristics of PD patients and it is usually defined y shorter stride length and low foot clearance. In this study a novel method is proposed to quantify the gait parameters using 3D motion captures and then various feature selection algorithm have used to select the effective features and finally machine learning based techniques were implemented to automate the classification process of two groups composed of PD patients as well as older adults. We have found maximum accuracy of 98.54 %by using support vector machine (SVM) classifier with radial basis function coupled with minimum redundancy and maximum relevance (MRMR) algorithm-based feature set. Our result showed that the proposed method can help the clinicians to distinguish PD patients from the older adults. This method helps to detect the PD at early stage.



  • Keywords

    Shuffling Gait; Feature Selection; Machine Learning; Parkinson’s disease; Wearable Sensor

  • References

      [1] M.Hermanns, “Weathering the storm: living with Parkinson's disease,” Journal of Christian Nursing, vol. 28, no. 2, pp.76-82,2011.

      [2] J.M. Beitz, “Parkinson disease: a review” Frontiers in Bioscience, S6, pp.65-74, 2014.

      [3] A. Schrag, Y. Ben-Shlomo, N. Quinn, “How valid is the clinical diagnosis of Parkinson's disease in the community?,” Journal of Neurology, Neurosurgery & Psychiatry, vol. 73, no. 5, pp. 529-534, 2002.

      [4] R. Das, “A comparison of multiple classification methods for diagnosis of Parkinson disease,” Expert Systems with Applications, vol. 37, no. 2, pp.1568-1572, 2010.

      [5] P.H. Chen, R.L. Wang, D.J. Liou, J.S. Shaw, “Gait disorders in Parkinson’s disease: assessment and management,” International Journal of Gerontology, vol. 57, no. 4, pp.189-193, 2013.

      [6] S. Hou, L. Li, R. Bo, W. Wang, T. Wang, “Feature generation using recurrence quantification analysis with application to fault classification,” In System Science, Engineering Design and Manufacturing Informatization (ICSEM), 2011 International Conference on, Vol. 2, pp. 43-46, IEEE, October 2011.

      [7] D.Jain, V. Singh, “Feature selection and classification systems for chronic disease prediction: A review,” Egyptian Informatics Journal, 2018.

      [8] J. Han, J. Pei, M. Kamber, “Data mining: concepts and techniques,” Elsevier, 2011.

      [9] P.N. Tan, “Introduction to data mining,” Pearson Education India, 2006.

      [10] M.H. Dunham, “Data mining: introductory and advanced topics,” Pearson Education India, 2006.

      [11] B. Sijobert, M. Benoussaad, J. Denys, R. Pissard-Gibollet, C. Geny, and C.A. Coste, “Implementation and Validation of a Stride Length Estimation Algorithm, Using a Single Basic Inertial Sensor on Healthy Subjects and Patients Suffering from Parkinson's Disease,” Health,7, pp.704-714,2015.

      [12] L.Carcreff, C.N. Gerber, A. Paraschiv-Ionescu, G. De Coulon, C.J. Newman, S. Armand, and K. Aminian, “What is the Best Configuration of Wearable Sensors to Measure Spatiotemporal Gait Parameters in Children with Cerebral Palsy?,” Sensors” vol.18, no. 2, p.394,2018.

      [13] N.M. Tahir, H.H. Manap, “Parkinson Disease Gait classification based on Machine Learning Approach,” Journal of Applied Sciences, vol. 12, no. 2, pp. 180–185, 2012.

      [14] B. Pogorelc, Z. Bosnić, M. Gams, “Automatic recognition of gait-related health problems in the elderly using machine learning,” Multimedia Tools and Applications, vol. 58, no.2, pp.333–354, 2012.

      [15] W. Froelich, K. Wrobel, and P. Porwik, “Diagnosis of Parkinson's disease using speech samples and threshold-based classification,” Journal of Medical Imaging and Health Informatics, vol. 5, no.6, pp. 1358-1363, 2015.

      [16] K. Polat, “Classification of Parkinson’s disease using feature weighting method on the basis of fuzzy c-means clustering,” International Journal of Systems Science, vol. 43, no. 4, pp.597–609,2012.

      [17] W.L. Zuo, Z.Y. Wang, T. Liu, H.L. Chen, “Effective detection of Parkinson’s disease using an adaptive fuzzy k-nearest neighbor approach,” Biomedical Signal Processing and Control, vol. 8, no. 4, pp.364-373,2013.




Article ID: 18547
DOI: 10.14419/ijet.v7i3.29.18547

Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.