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 Videos

Simple models for estimating dementia severity using machine learning.

W R Shankle1, S Mania, M B Dick

  • 1University of California at Irvine 62967, USA.

Studies in Health Technology and Informatics
|June 29, 1999
PubMed
Summary
This summary is machine-generated.

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

Anatomical and radiological description of ligament insertions on the radial aspect of the scaphoid bone.

Hand surgery & rehabilitation·2022
Same author

Application of Digital Cognitive Biomarkers for Alzheimer's Disease: Identifying Cognitive Process Changes and Impending Cognitive Decline.

The journal of prevention of Alzheimer's disease·2021
Same author

Novel Therapy of Hyperhomocysteinemia in Mild Cognitive Impairment, Alzheimer's Disease, and Other Dementing Disorders.

The journal of nutrition, health & aging·2016
Same author

Walking stabilizes cognitive functioning in Alzheimer's disease (AD) across one year.

Archives of gerontology and geriatrics·2012
Same author

Word-meaning selection in multiprocess language understanding programs.

IEEE transactions on pattern analysis and machine intelligence·2011
Same author

The development of structure and function in the postnatal human cerebral cortex from birth to 72 months: changes in thickness of layers II and III co-relate to the onset of new age-specific behaviors.

Pediatric pathology & molecular medicine·2002
Same journal

A GenAI Pipeline for Violinist Kinematic Data Management.

Studies in health technology and informatics·2026
Same journal

AMAL-For-Qatar: A Comprehensive AI Ecosystem for Fetal Ultrasound Analysis - Project Overview and Achievements.

Studies in health technology and informatics·2026
Same journal

Longitudinal Treatment-Aware Multimodal AI for Dermatology: A Scoping Review.

Studies in health technology and informatics·2026
Same journal

Predicting Postpartum Depression Using Imbalance-Aware Machine Learning.

Studies in health technology and informatics·2026
Same journal

Validation of Deep-Learning Models for Autosegmentation of Brain Metastases.

Studies in health technology and informatics·2026
Same journal

Delay-Dependent Gating in Modular RNNs.

Studies in health technology and informatics·2026
See all related articles

Machine learning models simplify dementia severity estimation using Electronic Medical Records (EMR). These models accurately classify dementia stages in community settings, overcoming current cost and time barriers.

Area of Science:

  • Neurology
  • Medical Informatics
  • Artificial Intelligence

Background:

  • Estimating dementia severity via the Clinical Dementia Rating (CDR) Scale is complex, costly, and impractical for community settings.
  • Current CDR Scale staging has limitations in interrater reliability, reaching only 80% at best.
  • Accurate dementia severity staging is crucial for both economic and clinical management.

Purpose of the Study:

  • To develop simplified Machine Learning (ML) models for estimating total CDR scores using Electronic Medical Records (EMR).
  • To identify a reduced set of attributes for accurate dementia severity classification.
  • To assess the clinical utility of ML-derived CDR scores in community-based healthcare.

Main Methods:

  • Utilized Machine Learning (ML) algorithms applied to Electronic Medical Record (EMR) data.

Related Experiment Videos

  • Developed models to estimate total CDR scores using a significantly reduced number of attributes compared to the gold standard.
  • Evaluated classification accuracy across different ML algorithms and dementia severity groupings.

    • Main Results:

    • ML models identified dementia severity with as few as seven attributes, a substantial reduction from the 34 attributes of the gold standard.
    • Naïve Bayes algorithm achieved the highest classification accuracy at 76%.
    • Grouping severity classes (normal, mild, moderate-to-severe) resulted in clinically acceptable accuracies of 85%.

    Conclusions:

    • Simplified ML models derived from EMR data offer a practical solution for estimating dementia severity in community settings.
    • These models address the current limitations of time and cost associated with traditional CDR Scale assessments.
    • The developed approach enhances the feasibility of dementia severity staging, improving patient care and resource allocation.