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

Two-Stage Machine Learning model for guideline development.

S Mani1, W R Shankle, M B Dick

  • 1Department of Information and Computer Science, University of California, Irvine, USA. mani@cbmi.upmc.edu

Artificial Intelligence in Medicine
|May 4, 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

Hormonal stimulation reduces numbers and impairs function of human uterine natural killer cells during implantation.

Human reproduction (Oxford, England)·2023
Same author

Potential antiviral effects of pantethine against SARS-CoV-2.

Scientific reports·2023
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

Urinary Ascites and Transient Intestinal Obstruction in a Preterm Infant: An Interesting Case of Posterior Urethral Valve.

AJP reports·2019
Same author

<i>REPLY</i>.

AJNR. American journal of neuroradiology·2018
Same author

Brain Imaging in Cases with Positive Serology for Dengue with Neurologic Symptoms: A Clinicoradiologic Correlation.

AJNR. American journal of neuroradiology·2018
Same journal

Real-time EEG-based epileptic seizure prediction using artificial intelligence: A systematic review.

Artificial intelligence in medicine·2026
Same journal

R-peak detection and ECG data compression scheme based on empirical mode decomposition and wavelet transform.

Artificial intelligence in medicine·2026
Same journal

CastNet: A three-channel EEG-based deep learning model for cross-subject depression detection.

Artificial intelligence in medicine·2026
Same journal

State-of-the-art TinyML approaches for colorectal cancer detection: Current advances, challenges, and future directions.

Artificial intelligence in medicine·2026
Same journal

JRadiEvo: A Japanese radiology report generation model enhanced by evolutionary optimization of model merging.

Artificial intelligence in medicine·2026
Same journal

Causally-informed deep learning towards explainable and generalizable outcome prediction in critical care.

Artificial intelligence in medicine·2026
See all related articles

A novel Two-Stage Machine Learning (ML) model improves dementia staging accuracy. This data mining approach mimics physician reasoning, outperforming experts in classifying dementia severity, especially in early stages.

Area of Science:

  • Artificial Intelligence
  • Neurology
  • Data Mining

Background:

  • Dementia staging is complex and subjective, relying on ambiguous clinical guidelines.
  • Existing methods for dementia staging lack consistent objectivity.

Purpose of the Study:

  • To develop and validate a Two-Stage Machine Learning (ML) model for objective dementia staging.
  • To improve the accuracy of the Clinical Dementia Rating Scale (CDRS) scoring.

Main Methods:

  • A Two-Stage ML model was developed, learning intermediate CDRS category scores before predicting the global CDRS score.
  • Decision tree learners and rule inducers (C4.5, Cart, C4.5 rules) were employed, with Naive Bayes as a baseline.
  • The model utilized demographic, functional, and cognitive data from 678 patients.

Related Experiment Videos

Main Results:

  • The Two-Stage ML model achieved classification accuracy comparable to or exceeding expert inter-rater agreement for CDRS scores.
  • The model demonstrated superior accuracy in distinguishing normal from very mildly impaired dementia (28.1% and 6.6% improvement).
  • The 'Judgment and Problem Solving' category was identified as a key area for potential improvement in dementia staging accuracy.

Conclusions:

  • The Two-Stage ML model offers a robust and accurate method for dementia staging.
  • This approach can enhance the objectivity and reliability of clinical dementia assessments.
  • Further research into specific CDRS categories could further refine ML-based dementia staging.