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

Multimodal Machine Learning to Personalize Transcutaneous Spinal Cord Stimulation for Stroke Rehabilitation.

Digital biomarkers·2026
Same author

Rest-activity rhythmicity as digital biomarkers of postoperative recovery and complications in children.

Digital health·2026
Same author

Identifying unique gait phenotypes across neuromotor conditions using wearable inertial sensors and topological data analysis.

NPJ digital medicine·2026
Same author

Beyond microprocessor knees: exploring the potential of fully powered prosthetic legs.

Journal of neuroengineering and rehabilitation·2026
Same author

Scalable networks of multimodal haptic arrays for plantar sensory substitution.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

The effects of electrode configuration and location on motor thresholds, tolerance, and muscle selectivity of transcutaneous spinal cord stimulation in stroke.

Journal of neurophysiology·2026

Related Experiment Video

Updated: Aug 23, 2025

A Structured Rehabilitation Protocol for Improved Multifunctional Prosthetic Control: A Case Study
06:58

A Structured Rehabilitation Protocol for Improved Multifunctional Prosthetic Control: A Case Study

Published on: November 6, 2015

9.6K

Autoencoder Composite Scoring to Evaluate Prosthetic Performance in Individuals with Lower Limb Amputation.

Thasina Tabashum1, Ting Xiao1,2, Chandrasekaran Jayaraman3,4

  • 1Department of Computer Science and Engineering, University of North Texas, Denton, TX 76203, USA.

Bioengineering (Basel, Switzerland)
|October 27, 2022
PubMed
Summary

A deep learning autoencoder created a single metric to assess lower limb amputee outcomes with prosthetic knees. Microprocessor-controlled knees significantly improved this metric compared to mechanical knees.

Keywords:
autoencoderlower limb amputationprincipal component analysis

More Related Videos

Engineering Platform and Experimental Protocol for Design and Evaluation of a Neurally-controlled Powered Transfemoral Prosthesis
11:16

Engineering Platform and Experimental Protocol for Design and Evaluation of a Neurally-controlled Powered Transfemoral Prosthesis

Published on: July 22, 2014

16.3K
Characterization of the Sense of Agency over the Actions of Neural-machine Interface-operated Prostheses
05:21

Characterization of the Sense of Agency over the Actions of Neural-machine Interface-operated Prostheses

Published on: January 7, 2019

8.0K

Related Experiment Videos

Last Updated: Aug 23, 2025

A Structured Rehabilitation Protocol for Improved Multifunctional Prosthetic Control: A Case Study
06:58

A Structured Rehabilitation Protocol for Improved Multifunctional Prosthetic Control: A Case Study

Published on: November 6, 2015

9.6K
Engineering Platform and Experimental Protocol for Design and Evaluation of a Neurally-controlled Powered Transfemoral Prosthesis
11:16

Engineering Platform and Experimental Protocol for Design and Evaluation of a Neurally-controlled Powered Transfemoral Prosthesis

Published on: July 22, 2014

16.3K
Characterization of the Sense of Agency over the Actions of Neural-machine Interface-operated Prostheses
05:21

Characterization of the Sense of Agency over the Actions of Neural-machine Interface-operated Prostheses

Published on: January 7, 2019

8.0K

Area of Science:

  • Biomedical Engineering
  • Rehabilitation Science
  • Artificial Intelligence in Medicine

Background:

  • Assessing prosthetic device effectiveness involves analyzing multiple clinical outcomes.
  • Lower limb amputees utilize diverse prosthetic knees, including mechanical and microprocessor-controlled types.
  • Synthesizing varied clinical scores into a single metric aids comparative analysis.

Purpose of the Study:

  • To develop a novel assessment metric using deep learning for comparing prosthetic knee outcomes.
  • To evaluate the efficacy of a microprocessor-controlled knee against a mechanical knee in transfemoral amputees.
  • To establish a succinct, holistic measure for variable clinical data in prosthetic research.

Main Methods:

  • A seven-layer deep autoencoder was employed to distill eight clinical outcomes into a single composite score.
  • The autoencoder-derived metric was compared against principal component analysis (PCA) for variance explanation.
  • Data from ten dysvascular transfemoral amputees using two prosthetic knee types were analyzed.

Main Results:

  • The autoencoder metric successfully reconstructed eight clinical scores, explaining 83.29% of the variance.
  • A statistically significant improvement (p < 0.001) was observed in the autoencoder metric with microprocessor-controlled knees.
  • The autoencoder metric demonstrated a positive correlation with overall functional ability in the study population.
  • The autoencoder approach captured substantially more variance (83.29%) compared to PCA (67.3%).

Conclusions:

  • A deep learning autoencoder can generate a reliable, single-valued metric for assessing prosthetic outcomes in lower limb amputees.
  • The autoencoder-based metric offers a succinct and holistic assessment tool, particularly for limited clinical datasets.
  • Microprocessor-controlled prosthetic knees show superior performance compared to mechanical knees, as indicated by the autoencoder metric.