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

Molecular and Lifestyle Determinants of Oral Squamous Cell Carcinoma in Bangladesh: Dietary Patterns Independent of HPV and TERT Promoter Mutations.

Asian Pacific journal of cancer prevention : APJCP·2026
Same author

Telehealth utilization among adults with cognitive difficulty: Evidence from the National Health Interview Survey, 2020-2023.

International journal of medical informatics·2026
Same author

Tumor CTR1 Expression and Systemic Copper Dynamics Converge on a Copper Axis in High-Grade Triple-Negative Breast Cancer.

Cancer research communications·2026
Same author

Digital Phenotyping via Passive Network Traffic Monitoring: Prospective Observational Study in University Students.

JMIR formative research·2026
Same author

Longitudinal datasets of health app reviews for privacy and trust modeling.

Data in brief·2026
Same author

Machine learning-driven optimization of monolithic gold plasmonic sensors: Achieving ultrahigh sensitivity with interpretable linear models.

PloS one·2026

Related Experiment Video

Updated: Jun 9, 2025

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.5K

Feasibility of Using a Novel, Multimodal Motor Function Assessment Platform With Machine Learning to Identify

Jamie B Hall1, Sonia Akter2, Praveen Rao2,3

  • 1Department of Physical Therapy.

Alzheimer Disease and Associated Disorders
|October 25, 2024
PubMed
Summary

Machine learning models can identify mild cognitive impairment (MCI) using motor function data from a portable device. This pilot study shows promising results for early ADRD detection through gait and balance assessments.

More Related Videos

Dual-Task Stroop Paradigm for Detecting Cognitive Deficits in High-Functioning Stroke Patients
07:42

Dual-Task Stroop Paradigm for Detecting Cognitive Deficits in High-Functioning Stroke Patients

Published on: December 16, 2022

2.9K
Motor Dual-Tasks for Gait Analysis and Evaluation in Post-Stroke Patients
05:23

Motor Dual-Tasks for Gait Analysis and Evaluation in Post-Stroke Patients

Published on: March 11, 2021

2.3K

Related Experiment Videos

Last Updated: Jun 9, 2025

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.5K
Dual-Task Stroop Paradigm for Detecting Cognitive Deficits in High-Functioning Stroke Patients
07:42

Dual-Task Stroop Paradigm for Detecting Cognitive Deficits in High-Functioning Stroke Patients

Published on: December 16, 2022

2.9K
Motor Dual-Tasks for Gait Analysis and Evaluation in Post-Stroke Patients
05:23

Motor Dual-Tasks for Gait Analysis and Evaluation in Post-Stroke Patients

Published on: March 11, 2021

2.3K

Area of Science:

  • Neurology
  • Biomedical Engineering
  • Data Science

Background:

  • Early identification of Alzheimer disease and related dementias (ADRD) is crucial for effective intervention.
  • Subtle motor declines associated with ADRD can be detected using instrumented assessments.
  • This study explores the feasibility of using motor function data for early MCI detection.

Purpose of the Study:

  • To establish the feasibility of a machine learning model for identifying mild cognitive impairment (MCI).
  • To utilize motor function data from an inexpensive, portable device for MCI classification.
  • To assess the potential of multimodal motor function assessment for early ADRD detection.

Main Methods:

  • A novel, multimodal motor function assessment platform was developed, integrating a depth camera, forceplate, and interface board.
  • Healthy older adults (n=28) and older adults with MCI (n=19) performed static balance, gait, and sit-to-stand tasks under single- and dual-task conditions.
  • Three machine learning models (support vector machine, decision trees, logistic regression) were trained and tested for MCI classification.

Main Results:

  • The decision trees model achieved the highest performance, with 83% accuracy, 0.83 sensitivity, 1.00 specificity, and an 0.83 F1 score.
  • Key motor function features contributing to MCI classification were identified and ranked by importance.
  • The study demonstrated the potential of specific motor tasks and machine learning for distinguishing MCI from healthy controls.

Conclusions:

  • Building a machine learning model to identify individuals with MCI using motor function data from a portable device is feasible.
  • The findings support the use of inexpensive, portable multimodal devices for objective motor assessments in clinical settings.
  • This approach holds promise for early detection and monitoring of cognitive decline associated with ADRD.