Literature DB >> 35354470

Machine learning classification of multiple sclerosis patients based on raw data from an instrumented walkway.

Wenting Hu1, Owen Combden1, Xianta Jiang2, Syamala Buragadda3, Caitlin J Newell3, Maria C Williams3, Amber L Critch3, Michelle Ploughman3.   

Abstract

BACKGROUND: Using embedded sensors, instrumented walkways provide clinicians with important information regarding gait disturbances. However, because raw data are summarized into standard gait variables, there may be some salient features and patterns that are ignored. Multiple sclerosis (MS) is an inflammatory neurodegenerative disease which predominantly impacts young to middle-aged adults. People with MS may experience varying degrees of gait impairments, making it a reasonable model to test contemporary machine leaning algorithms. In this study, we employ machine learning techniques applied to raw walkway data to discern MS patients from healthy controls. We achieve this goal by constructing a range of new features which supplement standard parameters to improve machine learning model performance.
RESULTS: Eleven variables from the standard gait feature set achieved the highest accuracy of 81%, precision of 95%, recall of 81%, and F1-score of 87%, using support vector machine (SVM). The inclusion of the novel features (toe direction, hull area, base of support area, foot length, foot width and foot area) increased classification accuracy by 7%, recall by 9%, and F1-score by 6%.
CONCLUSIONS: The use of an instrumented walkway can generate rich data that is generally unseen by clinicians and researchers. Machine learning applied to standard gait variables can discern MS patients from healthy controls with excellent accuracy. Noteworthy, classifications are made stronger by including novel gait features (toe direction, hull area, base of support area, foot length and foot area).
© 2022. The Author(s).

Entities:  

Keywords:  Artificial intelligence; Gait analysis; Machine learning; Multiple sclerosis; Rehabilitation; Walkway

Mesh:

Year:  2022        PMID: 35354470      PMCID: PMC8969278          DOI: 10.1186/s12938-022-00992-x

Source DB:  PubMed          Journal:  Biomed Eng Online        ISSN: 1475-925X            Impact factor:   2.819


  29 in total

1.  Gait pattern in myotonic dystrophy (Steinert disease): a kinematic, kinetic and EMG evaluation using 3D gait analysis.

Authors:  Manuela Galli; Veronica Cimolin; Veronica Crugnola; Lorenzo Priano; Francesco Menegoni; Claudio Trotti; Eva Milano; Alessandro Mauro
Journal:  J Neurol Sci       Date:  2011-11-25       Impact factor: 3.181

2.  Multiple sclerosis; earning a living.

Authors:  L Scheinberg; N Holland; N Larocca; P Laitin; A Bennett; H Hall
Journal:  N Y State J Med       Date:  1980-08

Review 3.  Multiple Sclerosis.

Authors:  Daniel S Reich; Claudia F Lucchinetti; Peter A Calabresi
Journal:  N Engl J Med       Date:  2018-01-11       Impact factor: 91.245

4.  miR-223 promotes regenerative myeloid cell phenotype and function in the demyelinated central nervous system.

Authors:  Dylan A Galloway; Stephanie N Blandford; Tangyne Berry; John B Williams; Mark Stefanelli; Michelle Ploughman; Craig S Moore
Journal:  Glia       Date:  2018-12-11       Impact factor: 7.452

5.  Reliability of gait and dual-task measures in multiple sclerosis.

Authors:  Alice Chen; Megan C Kirkland; Katie P Wadden; Elizabeth M Wallack; Michelle Ploughman
Journal:  Gait Posture       Date:  2020-03-05       Impact factor: 2.840

6.  Validity of the timed 25-foot walk as an ambulatory performance outcome measure for multiple sclerosis.

Authors:  Robert W Motl; Jeffrey A Cohen; Ralph Benedict; Glenn Phillips; Nicholas LaRocca; Lynn D Hudson; Richard Rudick
Journal:  Mult Scler       Date:  2017-02-16       Impact factor: 6.312

7.  Use of a Single Wireless IMU for the Segmentation and Automatic Analysis of Activities Performed in the 3-m Timed Up & Go Test.

Authors:  Paulina Ortega-Bastidas; Pablo Aqueveque; Britam Gómez; Francisco Saavedra; Roberto Cano-de-la-Cuerda
Journal:  Sensors (Basel)       Date:  2019-04-06       Impact factor: 3.576

8.  IMU-based joint angle measurement for gait analysis.

Authors:  Thomas Seel; Jörg Raisch; Thomas Schauer
Journal:  Sensors (Basel)       Date:  2014-04-16       Impact factor: 3.576

9.  Responder definition of the Multiple Sclerosis Impact Scale physical impact subscale for patients with physical worsening.

Authors:  Glenn A Phillips; Kathleen W Wyrwich; Shien Guo; Rossella Medori; Arman Altincatal; Linda Wagner; Jacob Elkins
Journal:  Mult Scler       Date:  2014-04-16       Impact factor: 6.312

10.  Selecting Clinically Relevant Gait Characteristics for Classification of Early Parkinson's Disease: A Comprehensive Machine Learning Approach.

Authors:  Rana Zia Ur Rehman; Silvia Del Din; Yu Guan; Alison J Yarnall; Jian Qing Shi; Lynn Rochester
Journal:  Sci Rep       Date:  2019-11-21       Impact factor: 4.996

View more
  1 in total

1.  Machine learning corroborates subjective ratings of walking and balance difficulty in multiple sclerosis.

Authors:  Wenting Hu; Owen Combden; Xianta Jiang; Syamala Buragadda; Caitlin J Newell; Maria C Williams; Amber L Critch; Michelle Ploughman
Journal:  Front Artif Intell       Date:  2022-09-29
  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.