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 21, 2026

Use of a Foot-Induced Digitally Controlled Resistance Device for Functional Magnetic Resonance Imaging Evaluation in Patients with Foot Paresis
08:55

Use of a Foot-Induced Digitally Controlled Resistance Device for Functional Magnetic Resonance Imaging Evaluation in Patients with Foot Paresis

Published on: July 7, 2023

Minimum Foot Clearance Prediction in Stroke Survivors: A Transformer-Based Approach.

Nandini Sengupta, Rezaul Begg, Aravinda S Rao

    IEEE Transactions on Neural Systems and Rehabilitation Engineering : a Publication of the IEEE Engineering in Medicine and Biology Society
    |May 19, 2026
    PubMed
    Summary

    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

    Engaging With Hospital Staff to Develop Implementation Strategies For Delivering a Patient Falls Prevention Education Program Using a World Café.

    Western journal of nursing research·2026
    Same author

    Appraisal of Clinical Practice Guideline: A core set of outcome measures to assess physical function for adults participating in physical therapy treatment in the hospital: a clinical practice guideline.

    Journal of physiotherapy·2026
    Same author

    Task-Dependent Reorganization of Ankle-Knee Mechanical Coordination Revealed by Moment-Moment Phase Space Analysis.

    Journal of functional morphology and kinesiology·2026
    Same author

    Exploring the utility of artificial intelligence in identifying progression of prostate cancer during active surveillance: A systematic review.

    Prostate cancer and prostatic diseases·2026
    Same author

    Use of gaming as an occupation in adults with upper limb impairment: a scoping review.

    Disability and rehabilitation. Assistive technology·2026
    Same author

    Remote assessment and management of physical function in older adults (RAMP): An international expert Delphi process.

    Archives of gerontology and geriatrics·2026

    Researchers developed a Transformer model to predict Minimum Foot Clearance (MFC) in stroke survivors, aiding in early fall risk assessment. This model helps identify individuals at higher risk of tripping due to reduced foot clearance.

    Area of Science:

    • Biomedical Engineering
    • Rehabilitation Science
    • Artificial Intelligence in Healthcare

    Background:

    • Decreased Minimum Foot Clearance (MFC) during walking is a primary cause of tripping-related falls in stroke survivors.
    • Accurate prediction of MFC is essential for early fall risk assessment in this population.

    Purpose of the Study:

    • To propose a novel Transformer model for multistep MFC prediction in stroke survivors.
    • To enhance the prediction performance using a data-driven conditional post-normalization projection.
    • To improve model robustness by incorporating a statistical moment-matching loss function for data variability.

    Main Methods:

    • Utilized a Transformer model with a two-head self-attention mechanism for MFC prediction.
    • Implemented a data-driven conditional post-normalization projection for enhanced multistep prediction.

    More Related Videos

    A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation
    11:06

    A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation

    Published on: April 12, 2016

    Related Experiment Videos

    Last Updated: May 21, 2026

    Use of a Foot-Induced Digitally Controlled Resistance Device for Functional Magnetic Resonance Imaging Evaluation in Patients with Foot Paresis
    08:55

    Use of a Foot-Induced Digitally Controlled Resistance Device for Functional Magnetic Resonance Imaging Evaluation in Patients with Foot Paresis

    Published on: July 7, 2023

    A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation
    11:06

    A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation

    Published on: April 12, 2016

  • Employed a statistical moment-matching loss function to address data variability in stroke survivors.
  • Compared the Transformer model against two other deep learning models.

    • Main Results:

    • The Transformer model demonstrated faster training times compared to other models.
    • Achieved an average Mean Absolute Error (MAE) of ~0.0035, Maximum Absolute Error (MaxAE) of ~0.0085, and Root Mean Square Error (RMSE) of ~0.0043.
    • The self-attention LSTM model achieved the highest prediction within the upper bound (PWUB) at approximately 89%.

    Conclusions:

    • The developed Transformer model offers a promising approach for predicting MFC in stroke survivors.
    • The study identifies specific instances when stroke survivors are at increased risk of tripping due to lower MFC.
    • Findings contribute to improved fall prevention strategies for individuals post-stroke.