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: Jan 9, 2026

An Objective and Child-friendly Assessment of Arm Function by Using a 3-D Sensor
07:25

An Objective and Child-friendly Assessment of Arm Function by Using a 3-D Sensor

Published on: February 12, 2018

7.2K

Attention-Based Deep Sequential Models for Adhesive Capsulitis Classification Using a Single Azure Kinect-D Camera.

Konki Sravan Kumar, Hyeon Hong, Kyuwon Lee

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
    |December 3, 2025
    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

    A machine learning-based screening tool for classifying post-traumatic stress disorder in firefighters: Firefighter Latent Risk Evaluation (FLARE).

    BMC psychiatry·2026
    Same author

    Adhesion-Dependent Receding Contact Line Dynamics of Water Droplets and Residual Droplet Deposition on Inclined Grooved Hydrophobic Surfaces.

    Langmuir : the ACS journal of surfaces and colloids·2026
    Same author

    Improved upper limb functionality after Abdominal Drawing-in maneuver in chronic stroke survivors: a crossover study.

    Physiotherapy theory and practice·2026
    Same author

    Longitudinal trajectories of allergen sensitization in children with different transcriptome profiles from COCOA study.

    Allergology international : official journal of the Japanese Society of Allergology·2026
    Same author

    Influence of social determinants of health on post-acute use and outcome: a scoping review.

    Health affairs scholar·2026
    Same author

    Ligand-Driven Tuning of Adsorption Energy in Nanocrystals for High-Performance H<sub>2</sub>O<sub>2</sub> Electrosynthesis.

    Journal of the American Chemical Society·2026

    This study introduces an AI framework using an Azure Kinect-D camera to diagnose adhesive capsulitis (frozen shoulder) by analyzing shoulder movements. The Att-GRU model achieved over 98% accuracy, offering a reliable, non-invasive diagnostic tool.

    Area of Science:

    • Medical Imaging
    • Artificial Intelligence
    • Biomechanics

    Background:

    • Adhesive capsulitis (AC), or frozen shoulder, causes severe shoulder pain and stiffness.
    • Accurate diagnosis is crucial for effective treatment and management.
    • Current diagnostic methods can be subjective and time-consuming.

    Purpose of the Study:

    • To develop and validate a novel attention-based deep sequential framework for classifying adhesive capsulitis.
    • To utilize shoulder abduction movements captured by an Azure Kinect-D camera for AC diagnosis.
    • To assess the diagnostic performance of recurrent neural networks integrated with attention mechanisms.

    Main Methods:

    • A deep sequential framework incorporating attention mechanisms into LSTM, BiLSTM, and GRU models was proposed.

    More Related Videos

    Rat Model of Adhesive Capsulitis of the Shoulder
    04:46

    Rat Model of Adhesive Capsulitis of the Shoulder

    Published on: September 28, 2018

    7.8K

    Related Experiment Videos

    Last Updated: Jan 9, 2026

    An Objective and Child-friendly Assessment of Arm Function by Using a 3-D Sensor
    07:25

    An Objective and Child-friendly Assessment of Arm Function by Using a 3-D Sensor

    Published on: February 12, 2018

    7.2K
    Rat Model of Adhesive Capsulitis of the Shoulder
    04:46

    Rat Model of Adhesive Capsulitis of the Shoulder

    Published on: September 28, 2018

    7.8K
  • Shoulder abduction movements were captured using a single Azure Kinect-D camera.
  • The Att-GRU model was evaluated for its classification accuracy, precision, specificity, recall, F1-score, and AUC.

    • Main Results:

    • The Att-GRU model demonstrated superior performance with 98.51% accuracy, 98.28% precision, 100% specificity, 98.26% recall, 98.85% F1-score, and an AUC of 0.992.
    • Attention weight analysis identified distinct movement patterns differentiating healthy individuals from those with AC.
    • The framework proved to be a reliable and objective tool for identifying disease-specific movement dynamics.

    Conclusions:

    • The proposed attention-based deep sequential framework offers a highly accurate and reliable method for diagnosing adhesive capsulitis.
    • This non-invasive approach using readily available camera technology has significant potential for clinical application in frozen shoulder diagnosis.
    • The model's ability to focus on clinically relevant movement patterns enhances diagnostic objectivity.