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

Modeling Alzheimer's disease cognitive scores using multi-task sparse group lasso.

Xiaoli Liu1, André R Goncalves2, Peng Cao3

  • 1College of Computer Science and Engineering, Northeastern University, Shenyang, China; Key Laboratory of Medical Image Computing of Ministry of Education, Northeastern University, Shenyang, China; Computing Science & Engineering, University of Minnesota, Twin Cities, USA.

Computerized Medical Imaging and Graphics : the Official Journal of the Computerized Medical Imaging Society
|March 31, 2018
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

Meta2DB: curated shotgun metagenomic feature sets and metadata for health state prediction.

Bioinformatics (Oxford, England)·2026
Same author

C-terminally engineered nucleopeptide-based soft materials exhibiting antibacterial and antifungal efficacy against multi-drug-resistant strains.

Organic & biomolecular chemistry·2026
Same author

DP103 as a critical modulator of Wnt signaling and cancer stemness: implications for precision treatment in triple negative breast cancer.

Cell death & disease·2026
Same author

Lysine containing amphiphilic peptide-based non-cytotoxic soft materials with potential antifungal and antibacterial activities for 3D cell culture.

Soft matter·2026
Same author

Identification of drug repurposing candidates for amyotrophic lateral sclerosis using electronic health records: a retrospective cohort study.

The Lancet. Digital health·2026
Same author

Beyond microbial abundance: metadata integration enhances disease prediction in human microbiome studies.

Frontiers in microbiology·2026

This study introduces a novel multi-task learning framework to predict cognitive decline in Alzheimer's disease (AD) using brain imaging. The proposed method accurately categorizes individuals and identifies key brain regions associated with AD progression.

Area of Science:

  • Neuroimaging
  • Machine Learning
  • Neurology

Background:

  • Alzheimer's disease (AD) is a neurodegenerative disorder causing memory loss and cognitive decline.
  • Accurate prediction of disease progression and identification of affected brain regions are crucial for AD research.
  • Current methods may not fully leverage multi-modal data for simultaneous prediction of various cognitive scores.

Purpose of the Study:

  • To develop and evaluate a multi-task learning framework for predicting cognitive scores in Alzheimer's disease.
  • To identify brain regions critical for characterizing Alzheimer's disease progression using neuroimaging data.
  • To compare the proposed method against existing baseline models for predictive performance.

Main Methods:

  • Utilized features extracted from brain images from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset.
Keywords:
Alzheimer's diseaseMulti-task learningSparse group lasso

Related Experiment Videos

  • Developed a multi-task sparse group lasso (MT-SGL) framework capable of handling Generalized Linear Models.
  • Employed sparse feature estimation coupled across multiple prediction tasks.

    • Main Results:

    • The MT-SGL framework demonstrated promising predictive performance in categorizing subjects (normal, MCI, AD).
    • The model successfully identified specific brain regions associated with Alzheimer's disease progression.
    • MT-SGL outperformed several baseline models across various evaluation metrics.

    Conclusions:

    • The proposed MT-SGL framework offers an effective approach for predicting cognitive status in Alzheimer's disease using neuroimaging.
    • This method enhances the understanding of brain regions implicated in AD progression.
    • MT-SGL provides a valuable tool for multi-task learning in neurodegenerative disease research.