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

Predicting Alzheimer's disease progression using multi-modal deep learning approach.

Garam Lee1,2, Kwangsik Nho3,4, Byungkon Kang1

  • 1Department of Software and Computer Engineering, Ajou University, Suwon, South Korea.

Scientific Reports
|February 15, 2019
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

Development of Virtual Reality Health Literacy: Delphi Expert Consensus Study.

Journal of medical Internet research·2026
Same author

Predicting post-hepatectomy liver failure after hemi-hepatectomy using a combined model based on age, ALBI score, and the future liver remnant-to-spleen volume ratio.

Updates in surgery·2026
Same author

Quantifying the Independent and Combined Contributions of Clinical, Genetic, Proteomic, and Metabolomic Signals to ASCVD Prediction.

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science·2026
Same author

Cellular immunology data enable clinical severity prediction via supervised machine learning.

iScience·2026
Same author

Genetic proxies of GLP1R expression are associated with lower risk of psoriasis and psoriatic arthritis.

The British journal of dermatology·2026
Same author

A conserved translational repression module buffers sugar-inducible root vascular proliferation.

Molecular plant·2026
This summary is machine-generated.

This study developed a deep learning model to predict Alzheimer's disease (AD) progression from mild cognitive impairment (MCI). Integrating multiple data types improved prediction accuracy, aiding early detection and clinical trial stratification.

Area of Science:

  • Neuroscience
  • Artificial Intelligence
  • Biomarker Discovery

Background:

  • Alzheimer's disease (AD) is a progressive neurodegenerative disorder lacking disease-modifying treatments.
  • Early detection of AD, particularly predicting conversion from Mild Cognitive Impairment (MCI) to AD, is crucial for timely intervention.
  • Current diagnostic approaches require improvement for accurate and early prediction of AD progression.

Purpose of the Study:

  • To develop and validate a deep learning framework for predicting MCI to probable AD conversion.
  • To investigate the efficacy of integrating multimodal, longitudinal data for enhanced prediction accuracy.
  • To assess the potential of a multimodal deep learning approach for identifying individuals at high risk of AD.

Main Methods:

Related Experiment Videos

  • A multimodal recurrent neural network deep learning approach was employed.
  • The framework integrated cross-sectional neuroimaging, longitudinal cerebrospinal fluid (CSF) biomarkers, and cognitive performance data.
  • Data was sourced from the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort.

    • Main Results:

    • Individual data modalities achieved up to 75% accuracy (AUC=0.83) in predicting MCI to AD conversion.
    • The integrated multimodal, longitudinal framework achieved the highest performance with 81% accuracy (AUC=0.86).
    • The model demonstrated significant potential in identifying individuals at risk for AD progression.

    Conclusions:

    • Multimodal deep learning frameworks integrating longitudinal data significantly improve the prediction of MCI to AD conversion.
    • This approach offers a promising tool for early identification of at-risk individuals for clinical trials or as a stratification strategy.
    • Further development and validation of such models are warranted for clinical application in Alzheimer's disease management.