Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Associations of Chronic Low Back Pain with Disability and Health-Related Quality of Life Outcomes in People with Multiple Sclerosis: A Cross-Sectional Survey Study.

The journal of pain·2026
Same author

Preventing frailty in multiple sclerosis is a realistic goal: Yes.

Multiple sclerosis (Houndmills, Basingstoke, England)·2026
Same author

Validity of multiple human pose estimation tools for measuring knee impact angles in video-captured falls of older adults.

PloS one·2026
Same author

Energy dissipation strategy in backward falls in at-risk older adults: evidence and implications for head injury prevention.

Journal of biomechanics·2026
Same author

Reducing frailty in frail people with multiple sclerosis: Feasibility of a 6-week multimodal exercise training program.

PloS one·2026
Same author

Fall Injury Avoidance Strategy Scale (FIAS)-Validation of a Scale to Quantify Fall-Related Protective Movements.

Archives of physical medicine and rehabilitation·2026

Related Experiment Video

Updated: Jan 4, 2026

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

11.1K

Fall Risk Prediction in Multiple Sclerosis Using Postural Sway Measures: A Machine Learning Approach.

Ruopeng Sun1,2, Katherine L Hsieh3, Jacob J Sosnoff3

  • 1Department of Kinesiology and Community Health, University of Illinois at Urbana-Champaign, Champaign, USA. rusun@stanford.edu.

Scientific Reports
|November 8, 2019
PubMed
Summary

Machine learning identified key postural sway metrics for differentiating multiple sclerosis (MS) patients from healthy individuals. Mediolateral sway amplitude and sway sample entropy are crucial for assessing fall risk in MS.

More Related Videos

Computerized Dynamic Posturography for Postural Control Assessment in Patients with Intermittent Claudication
14:52

Computerized Dynamic Posturography for Postural Control Assessment in Patients with Intermittent Claudication

Published on: December 11, 2013

11.9K
Author Spotlight: Innovations in iTUG Test for Enhanced Risk Assessment and Cognitive Insights
05:26

Author Spotlight: Innovations in iTUG Test for Enhanced Risk Assessment and Cognitive Insights

Published on: October 25, 2024

1.7K

Related Experiment Videos

Last Updated: Jan 4, 2026

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

11.1K
Computerized Dynamic Posturography for Postural Control Assessment in Patients with Intermittent Claudication
14:52

Computerized Dynamic Posturography for Postural Control Assessment in Patients with Intermittent Claudication

Published on: December 11, 2013

11.9K
Author Spotlight: Innovations in iTUG Test for Enhanced Risk Assessment and Cognitive Insights
05:26

Author Spotlight: Innovations in iTUG Test for Enhanced Risk Assessment and Cognitive Insights

Published on: October 25, 2024

1.7K

Area of Science:

  • Neurology
  • Biomedical Engineering
  • Rehabilitation Science

Background:

  • Postural sway metrics are sensitive to balance impairment and fall risk in individuals with Multiple Sclerosis (MS).
  • Lack of guidelines exists for selecting optimal postural sway metrics for monitoring MS-related impairment.
  • Machine learning (ML) offers a novel approach to analyze complex physiological data for improved diagnostic and prognostic capabilities.

Purpose of the Study:

  • To employ an ML approach to evaluate the accuracy and feature importance of various postural sway metrics.
  • To differentiate individuals with MS from healthy controls based on physiological fall risk.
  • To identify the most effective sway metrics for classifying MS fall risk subgroups.

Main Methods:

  • A cohort of 153 participants (103 with MS, 50 controls) underwent static posturography and fall risk assessments.
  • Participants were categorized into four fall risk groups: controls, low-risk MS, moderate-risk MS, and high-risk MS.
  • A random forest (RF) ML algorithm with 10-fold cross-validation was trained using 20 sway metrics to predict fall risk grouping.

Main Results:

  • The RF classifier demonstrated high accuracy (>86%) in distinguishing individuals with MS from healthy controls.
  • Sway sample entropy was the most significant feature for classifying low-risk MS individuals compared to healthy controls.
  • Mediolateral sway amplitude emerged as the strongest predictor for differentiating between all other fall risk groupings in MS.

Conclusions:

  • ML analysis effectively utilizes postural sway metrics to identify individuals with MS and stratify their fall risk.
  • Specific sway metrics, namely sway sample entropy and mediolateral sway amplitude, hold significant predictive power for MS-related balance impairment.
  • These findings can inform the development of standardized guidelines for using postural sway analysis in MS clinical practice and research.