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: Sep 26, 2025

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.8K

Fall risk assessment through a synergistic multi-source DNN learning model.

Olga Andreeva1, Wei Ding1, Suzanne G Leveille2

  • 1Department of Computer Science, College of Science and Mathematics, United States of America; University of Massachusetts Boston, Boston, MA, United States of America.

Artificial Intelligence in Medicine
|April 17, 2022
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

Implementation of School Nutrition Policies to Address Noncommunicable Diseases in Uzbekistan and Kyrgyzstan.

Global health, science and practice·2024
Same author

Design and Implementation of Brief Interventions to Address Noncommunicable Diseases in Uzbekistan.

Global health, science and practice·2024
Same author

Assessing and Forecasting Fatigue Strength of Metals and Alloys under Cyclic Loads.

Materials (Basel, Switzerland)·2024
Same author

Application of the Concept of Land Degradation Neutrality for Remote Monitoring of Agricultural Sustainability of Irrigated Areas in Uzbekistan.

Sensors (Basel, Switzerland)·2023
Same author

Characterizing Fall Circumstances in Community-Dwelling Older Adults: A Mixed Methods Approach.

The journals of gerontology. Series A, Biological sciences and medical sciences·2023
Same author

Discovery of highly potent proapoptotic antiestrogens in a series of androst-5,16-dienes D-modified with imidazole-annulated pendants.

The Journal of steroid biochemistry and molecular biology·2023
This summary is machine-generated.

This study introduces the Synergy LSTM model to predict falls in older adults by combining text descriptions and physical data. The model effectively identifies fall risk factors, improving prediction accuracy.

Area of Science:

  • Gerontology
  • Biomedical Engineering
  • Data Science

Background:

  • Falls are a major cause of disability in the elderly population.
  • Fall detection is important, but fall prevention strategies offer greater impact.
  • Identifying novel risk factors for falls in community-dwelling older adults is crucial.

Purpose of the Study:

  • To explore novel risk factors for falls in community-living older adults.
  • To develop a multi-source learning approach for fall risk assessment.
  • To evaluate the Synergy LSTM model's effectiveness in identifying fall risk factors.

Main Methods:

  • A prospective cohort study was conducted with community-living older adults.
  • Multiple data sources were acquired, including textual fall descriptions and physical characteristics.
Keywords:
AttentionDeep learningFall risk factorsMulti-label classificationMulti-source learning

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

661

Related Experiment Videos

Last Updated: Sep 26, 2025

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.8K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

661
  • A novel multi-source learning model, Synergy LSTM, was proposed to exploit data complementarity.

    • Main Results:

    • The Synergy LSTM model significantly improved classification performance for fall risk.
    • The model effectively captured meaningful relations between disparate data sources.
    • Learned complementarities were used to evaluate fall risk factors.

    Conclusions:

    • The Synergy LSTM model offers a powerful approach for multi-source learning in fall risk assessment.
    • Exploiting complementarity in diverse data sources enhances the identification of fall risk factors.
    • This approach holds promise for developing more effective fall preventive strategies in the elderly.