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: Jul 4, 2026

A Fine Motor Task to Study Joint Kinematics in a Preclinical Model of Neurodegenerative Disease
05:39

A Fine Motor Task to Study Joint Kinematics in a Preclinical Model of Neurodegenerative Disease

Published on: June 13, 2025

Multimodal Contrastive Spatiotemporal Self-Organizing Neural Networks for In-Home Activity Learning of Mild Cognitive

Seng-Khoon Teh, Ah-Hwee Tan, Kar-Way Tan

    IEEE Journal of Biomedical and Health Informatics
    |July 2, 2026
    PubMed
    Summary

    This study introduces a novel machine learning model using in-home movement data to detect Mild Cognitive Impairment (MCI). The multimodal approach effectively integrates diverse spatiotemporal data for early geriatric condition detection.

    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

    Can Sensor Technologies Accurately Detect and Monitor Behavioural and Psychological Symptoms of Dementia? A Systematic Review.

    Dementia and geriatric cognitive disorders extra·2026
    Same author

    Development and Validation of Machine Learning Models for Predicting Early Cognitive Decline Using Home Sensor-Derived Behavioral Data: Sensors in-Home for Elder Wellbeing (SINEW) Cohort Study.

    JMIR research protocols·2026
    Same author

    Gender-focused mental health services in Singapore: A brief history and future directions.

    Annals of the Academy of Medicine, Singapore·2026
    Same author

    Curcumin-Rich Curry Consumption Is Associated with Lower Risk of Cognitive Decline and Incidence of Mild Cognitive Impairment or Dementia: An Asian Population-Based Study.

    Nutrients·2025
    Same author

    Managing Psychosis in Acute Intermittent Porphyria: A Case Report on Olanzapine Use.

    Cureus·2025
    Same author

    Relation prediction in knowledge graphs: A self-organizing neural network approach.

    Neural networks : the official journal of the International Neural Network Society·2025

    Area of Science:

    • Artificial Intelligence
    • Gerontology
    • Machine Learning

    Background:

    • In-home spatiotemporal data offers predictive value for geriatric conditions like Mild Cognitive Impairment (MCI).
    • Existing models struggle to integrate disparate spatiotemporal data types for comprehensive analysis.
    • A generalized machine learning model is needed to jointly model various in-home spatiotemporal data.

    Purpose of the Study:

    • To develop and evaluate a multimodal spatiotemporal machine learning model for MCI detection.
    • To integrate movement trajectory and spatial time-series data for enhanced predictive utility.
    • To assess the model's performance against state-of-the-art methods in early geriatric condition detection.

    Main Methods:

    • A multimodal spatiotemporal machine learning model based on self-organizing neural networks was developed.

    More Related Videos

    Soft Pneumatic Robot Modulates Graph Theory Metrics of Brain Network for Hand Rehabilitation After Stroke
    05:30

    Soft Pneumatic Robot Modulates Graph Theory Metrics of Brain Network for Hand Rehabilitation After Stroke

    Published on: October 10, 2025

    Related Experiment Videos

    Last Updated: Jul 4, 2026

    A Fine Motor Task to Study Joint Kinematics in a Preclinical Model of Neurodegenerative Disease
    05:39

    A Fine Motor Task to Study Joint Kinematics in a Preclinical Model of Neurodegenerative Disease

    Published on: June 13, 2025

    Soft Pneumatic Robot Modulates Graph Theory Metrics of Brain Network for Hand Rehabilitation After Stroke
    05:30

    Soft Pneumatic Robot Modulates Graph Theory Metrics of Brain Network for Hand Rehabilitation After Stroke

    Published on: October 10, 2025

  • Episodic Memory Adaptive Resonance Theory (EM-ART) and SpatioTemporal Episodic Memory (STEM) were employed for different data types.
  • A contrastive layer normalized features, and a Fusion ART layer integrated them for MCI classification.

    • Main Results:

    • Individual EM-ART and STEM models achieved a ROC-AUC of 0.6-0.7 for MCI detection.
    • The integrated multimodal contrastive model demonstrated 84.2% predictive accuracy and 66.7% F1 rate.
    • The proposed model outperformed SVM and LSTM in specificity and accuracy for MCI detection.

    Conclusions:

    • The developed multimodal spatiotemporal model effectively integrates diverse in-home data for MCI detection.
    • This approach shows significant potential for the early detection of geriatric conditions in clinical settings.
    • The model paves the way for utilizing passive sensing data in geriatric healthcare.