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: May 29, 2026

A Methodological Protocol and Considerations for Transcranial Ultrasonic Stimulation in Exploratory Clinical Human Studies
09:47

A Methodological Protocol and Considerations for Transcranial Ultrasonic Stimulation in Exploratory Clinical Human Studies

Published on: December 12, 2025

BiLSTM Segmentation of TUG Subtasks Across Healthy and Pathological Populations Using a Single IMU.

S Loreto Rojas, Paulina Ortega-Bastidas, Pedro Pinacho-Davidson

    IEEE Transactions on Neural Systems and Rehabilitation Engineering : a Publication of the IEEE Engineering in Medicine and Biology Society
    |May 27, 2026
    PubMed
    Summary

    This study introduces an AI model for detailed Timed Up and Go (TUG) test analysis using a single sensor. The automated segmentation of TUG subtasks enhances mobility assessment for clinical insights.

    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

    Modular and programmable breathing phantom station for accelerated degradation testing of industrial respirator filters.

    HardwareX·2026
    Same author

    Burnout in health students and its relationship with demographic and academic characteristics: a survey-based study.

    BMC medical education·2026
    Same author

    Step-Length Estimation in Asymmetric Gait Using a Single Lower-Back IMU Data and a Biomechanical Model Inspired by a Double Inverted Pendulum.

    Bioengineering (Basel, Switzerland)·2026
    Same author

    A Breathing Phantom Station for Assessing Filter Clogging in Industrial Respirators.

    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

    Real-Time Detection of Industrial Respirator Fit Using Embedded Breath Sensors and Machine Learning Algorithms.

    Biosensors·2025
    Same author

    Finite Element Modelling for Biophysical Models of Nervous System Stimulation: Best Practices for Multiscale Adaptive Meshing.

    IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2025

    Area of Science:

    • Biomedical Engineering
    • Rehabilitation Technology
    • Artificial Intelligence in Healthcare

    Background:

    • The Timed Up and Go (TUG) test is a standard mobility assessment tool.
    • Current TUG analysis relies solely on total time, limiting detailed functional impairment insights.
    • Instrumented TUG (iTUG) with wearable sensors offers potential for richer data but requires robust activity segmentation.

    Purpose of the Study:

    • To develop and validate an automated method for segmenting subtasks within the Instrumented TUG (iTUG) test.
    • To utilize a Bidirectional Long Short-Term Memory (BiLSTM) network for accurate activity recognition.
    • To enhance the clinical utility of the iTUG test through detailed subtask analysis.

    Main Methods:

    • A Bidirectional Long Short-Term Memory (BiLSTM) network with multilabel classification was employed.

    More Related Videos

    Localizing Function-specific Targets for Transcranial Magnetic Stimulation in the Absence of Navigation Equipment
    09:30

    Localizing Function-specific Targets for Transcranial Magnetic Stimulation in the Absence of Navigation Equipment

    Published on: May 23, 2025

    Related Experiment Videos

    Last Updated: May 29, 2026

    A Methodological Protocol and Considerations for Transcranial Ultrasonic Stimulation in Exploratory Clinical Human Studies
    09:47

    A Methodological Protocol and Considerations for Transcranial Ultrasonic Stimulation in Exploratory Clinical Human Studies

    Published on: December 12, 2025

    Localizing Function-specific Targets for Transcranial Magnetic Stimulation in the Absence of Navigation Equipment
    09:30

    Localizing Function-specific Targets for Transcranial Magnetic Stimulation in the Absence of Navigation Equipment

    Published on: May 23, 2025

  • Data from 105 participants (healthy and with gait pathologies) were collected using a single lumbar-mounted IMU.
  • The model was trained to segment iTUG subtasks: sit-to-stand, walking, turns, and stand-to-sit.

    • Main Results:

    • The BiLSTM model achieved a high macroaverage F1-score of 0.94 across all segmented subtasks.
    • Clinical validation demonstrated strong agreement with manual annotations, with Mean Absolute Errors (MAE) between 0.28-0.40 seconds.
    • Significant differences in subtask durations were observed between healthy participants and those with gait pathologies, with the clinical group showing prolonged times.

    Conclusions:

    • An automated and clinically validated method for iTUG subtask segmentation using a single IMU was successfully developed.
    • This approach provides detailed mobility insights beyond total TUG completion time.
    • The findings support the use of this technology for enhanced clinical mobility assessment and understanding of functional impairments.