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 Experiment Video

Updated: Jun 6, 2025

3D Kinematic Gait Analysis for Preclinical Studies in Rodents
10:19

3D Kinematic Gait Analysis for Preclinical Studies in Rodents

Published on: August 3, 2019

10.6K

Deep learning-based screening for locomotive syndrome using single-camera walking video: Development and validation

Junichi Kushioka1,2,3, Satoru Tada1,4,5, Noriko Takemura1,6

  • 1ayumo Inc., Osaka, Japan.

PLOS Digital Health
|November 26, 2024
PubMed

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

A single-camera video-based assessment of locomotive syndrome using pose-silhouette fusion model.

PLOS digital health·2026
Same author

Semantic Segmentation for Pixel-Wise Visualization of Breast Cancer in Deep Ultraviolet-Excited Fluorescence Images.

Acta histochemica et cytochemica·2026
Same author

Temporal Patterns of Wearable Accelerometer-Measured Physical Activity and Symptom Worsening in Knee Osteoarthritis: A 2-Year Longitudinal Study from the Osteoarthritis Initiative.

Sensors (Basel, Switzerland)·2026
Same author

Impact of Experimental Design in Age Prediction from Retinal Fundus Images<sup></sup>.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

E-InMeMo: Enhanced Prompting for Visual In-Context Learning.

Journal of imaging·2025
Same author

Selective identification of polyploid hepatocellular carcinomas with poor prognosis by artificial intelligence-based pathological image recognition.

Communications medicine·2025
Summary

A new deep learning model uses computer vision to diagnose Locomotive Syndrome (LS), a condition affecting walking and standing. This non-invasive tool offers efficient LS detection, improving patient outcomes.

Area of Science:

  • Digital Health
  • Computer Vision
  • Musculoskeletal Health

Background:

  • Locomotive Syndrome (LS) is characterized by reduced walking and standing abilities.
  • Early LS diagnosis is crucial for effective intervention and management.
  • Current diagnostic methods are labor-intensive and time-consuming, limiting widespread adoption.

Purpose of the Study:

  • To develop and validate a Deep Learning (DL)-based computer vision model for objective LS assessment.
  • To provide an efficient and accessible tool for early LS detection and analysis.
  • To streamline the diagnostic process and expedite treatment initiation for LS patients.

Main Methods:

  • Utilized a DL model integrating OpenPose for pose estimation and MS-G3D for spatial-temporal graph analysis.

More Related Videos

Comprehensive Understanding of Inactivity-Induced Gait Alteration in Rodents
04:37

Comprehensive Understanding of Inactivity-Induced Gait Alteration in Rodents

Published on: July 6, 2022

2.3K
Mouse Short- and Long-term Locomotor Activity Analyzed by Video Tracking Software
10:15

Mouse Short- and Long-term Locomotor Activity Analyzed by Video Tracking Software

Published on: June 20, 2013

20.2K

Related Experiment Videos

Last Updated: Jun 6, 2025

3D Kinematic Gait Analysis for Preclinical Studies in Rodents
10:19

3D Kinematic Gait Analysis for Preclinical Studies in Rodents

Published on: August 3, 2019

10.6K
Comprehensive Understanding of Inactivity-Induced Gait Alteration in Rodents
04:37

Comprehensive Understanding of Inactivity-Induced Gait Alteration in Rodents

Published on: July 6, 2022

2.3K
Mouse Short- and Long-term Locomotor Activity Analyzed by Video Tracking Software
10:15

Mouse Short- and Long-term Locomotor Activity Analyzed by Video Tracking Software

Published on: June 20, 2013

20.2K
  • Trained and validated the model on a dataset of 186 walking videos, with external validation on 65 additional videos.
  • Employed single-camera video captures for non-invasive gait pattern analysis.

    • Main Results:

    • The model achieved an average sensitivity of 0.86 and a positive predictive value of 0.85 for LS detection.
    • Overall accuracy was 0.77, with strong generalizability confirmed by an Area Under the Curve of 0.75 on external validation.
    • The model demonstrated higher precision in diagnosing LS cases compared to non-LS cases.

    Conclusions:

    • This study introduces a pioneering computer vision model for diagnosing LS through pose estimation.
    • The developed model offers an accessible, non-invasive, and efficient alternative to traditional labor-intensive LS diagnostic tests.
    • This advancement in digital health can significantly improve patient outcomes by facilitating timely LS detection and treatment.