Random forest-based classsification and analysis of hemiplegia gait using low-cost depth cameras.

Publisher: Springer Country of Publication: United States NLM ID: 7704869 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1741-0444 (Electronic) Linking ISSN: 01400118 NLM ISO Abbreviation: Med Biol Eng Comput Subsets: MEDLINE

Publication: New York, NY : Springer
Original Publication: Stevenage, Eng., Peregrinus.

Algorithms* ; Costs and Cost Analysis*; Gait Disorders, Neurologic/*diagnosis ; Gait Disorders, Neurologic/*diagnostic imaging ; Hemiplegia/*diagnostic imaging ; Hemiplegia/*physiopathology ; Photography/*economics ; Photography/*instrumentation; Female ; Hemiplegia/economics ; Humans ; Male ; Middle Aged ; ROC Curve

Hemiplegia is a form of paralysis that typically has the symptom of dysbasia. In current clinical rehabilitations, to measure the level of hemiplegia gaits, clinicians often conduct subject evaluations through observations, which is unreliable and inaccurate. The Microsoft Kinect sensor (MS Kinect) is a widely used, low-cost depth sensor that can be used to detect human behaviors in real time. The purpose of this study is to investigate the usage of the Kinect data for the classification and analysis of hemiplegia gait. We first acquire the gait data by using a MS Kinect and extract a set of gait features including the stride length, gait speed, left/right moving distances, and up/down moving distances. With the gait data of 60 subjects including 20 hemiplegia patients and 40 healthy subjects, we employ a random forest-based classification approach to analyze the importances of different gait features for hemiplegia classification. Thanks to the over-fitting avoidance nature of the random forest approach, we do not need to have a careful control over the percentage of patients in the training data. In our experiments, our approach obtained the averaged classification accuracy of 90.65% among all the combinations of the gait features, which substantially outperformed state-of-the-art methods. The best classification accuracy of our approach is 95.45%, which is superior than all existing methods. Additionally, our approach also correctly reveals the importance of different gait features for hemiplegia classification. Our random forest-based approach outperforms support vector machine-based method and the Bayesian-based method, and can effectively extract gait features of subjects with hemiplegia for the classification and analysis of hemiplegia. Graphical Abstract Random Forest based Classsification and Analysis of Hemiplegia Gait using Low-cost Depth Cameras. Left: Motion capture with MS Kinect; Top-right: Random Forest Classsification based on the extracted gait features; Bottom-right: Sensitivity and specificity evaluation of the proposed classification approach.

Arch Phys Med Rehabil. 1995 Jan;76(1):27-32. (PMID: 7811170)
Gait Posture. 2009 Apr;29(3):360-9. (PMID: 19013070)
Gait Posture. 2015 Feb;41(2):402-8. (PMID: 25467429)
J Neurol Neurosurg Psychiatry. 1985 Jul;48(7):650-7. (PMID: 4031909)
Med Eng Phys. 2017 Jun;44:1-7. (PMID: 28408157)
IEEE Trans Biomed Eng. 2005 May;52(5):828-38. (PMID: 15887532)
Gait Posture. 2014 Sep;40(4):532-8. (PMID: 25047828)
Gait Posture. 2012 Jul;36(3):372-7. (PMID: 22633015)
J Neurol Neurosurg Psychiatry. 1983 Jun;46(6):521-4. (PMID: 6875585)
Gait Posture. 2003 Oct;18(2):1-10. (PMID: 14654202)
Med Eng Phys. 2016 Sep;38(9):952-8. (PMID: 27387901)
J Neuroeng Rehabil. 2015 Feb 12;12:15. (PMID: 25884838)
Sensors (Basel). 2012;12(2):2255-83. (PMID: 22438763)
Gait Posture. 2018 May;62:458-462. (PMID: 29665566)
Zh Nevrol Psikhiatr Im S S Korsakova. 2007;107(7):4-9. (PMID: 18379474)
Biomed Eng Online. 2015 Oct 24;14:97. (PMID: 26499251)
Phys Ther. 2013 Dec;93(12):1673-85. (PMID: 23813091)
J Med Eng Technol. 2014 Jul;38(5):274-80. (PMID: 24878252)
J Neuroeng Rehabil. 2005 Jul 31;2:23. (PMID: 16053531)
J Biomech. 2013 Oct 18;46(15):2722-5. (PMID: 24016679)
Gait Posture. 2016 Jul;48:83-88. (PMID: 27477714)
J Neuroeng Rehabil. 2008 Sep 01;5:19. (PMID: 18761735)
J Rehabil Med. 2007 Mar;39(2):170-4. (PMID: 17351701)
Med Eng Phys. 2017 Dec;50:75-82. (PMID: 29102274)
Med Eng Phys. 2015 Feb;37(2):219-25. (PMID: 25619613)
Gait Posture. 2014 Apr;39(4):1062-8. (PMID: 24560691)

Keywords: Depth cameras; Gait analysis; Hemiplegia; Microsoft Kinect; Motion classification; Random forest

Date Created: 20191220 Date Completed: 20201103 Latest Revision: 20201103

20231215

10.1007/s11517-019-02079-7

31853775