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 Video

Updated: Jun 12, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

Boosting power for clinical trials using classifiers based on multiple biomarkers.

Omid Kohannim1, Xue Hua, Derrek P Hibar

  • 1Laboratory of Neuro Imaging, Department of Neurology, UCLA School of Medicine, Los Angeles, CA 90095-1769, USA.

Neurobiology of Aging
|June 15, 2010
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

Genetic studies of quantitative MCI and AD phenotypes in ADNI: Progress, opportunities, and plans.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2015
Same author

Development of the human fetal hippocampal formation during early second trimester.

NeuroImage·2015
Same author

2014 Update of the Alzheimer's Disease Neuroimaging Initiative: A review of papers published since its inception.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2015
Same author

Sharing data in the global alzheimer's association interactive network.

NeuroImage·2015
Same author

Imaging in StrokeNet: Realizing the Potential of Big Data.

Stroke·2015
Same author

The Image and Data Archive at the Laboratory of Neuro Imaging.

NeuroImage·2015

This study introduces a machine learning approach to enhance clinical trial power for Alzheimer's disease (AD) and mild cognitive impairment (MCI) by identifying individuals most likely to progress. The method significantly reduces the number of participants needed to detect treatment effects.

Area of Science:

  • Neuroimaging
  • Biomarkers
  • Machine Learning

Background:

  • Machine learning aids in computer-assisted diagnosis and predicting clinical decline.
  • Clinical trials require robust methods to detect treatment efficacy.
  • Alzheimer's disease (AD) and mild cognitive impairment (MCI) diagnosis and progression prediction are critical research areas.

Purpose of the Study:

  • To introduce a machine learning method to boost statistical power in clinical trials for Alzheimer's disease (AD) and mild cognitive impairment (MCI).
  • To develop a Support Vector Machine (SVM) algorithm integrating multimodal biomarkers for subject classification.
  • To identify a subsample of subjects most likely to experience clinical decline for enhanced trial efficiency.

Main Methods:

  • A Support Vector Machine (SVM) algorithm was developed using data from 737 Alzheimer's Disease Neuroimaging Initiative (ADNI) subjects.

Related Experiment Videos

Last Updated: Jun 12, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

  • Classifiers were trained on multimodal data: MRI volumes (hippocampal, ventricular, temporal lobe), PET-FDG, CSF biomarkers (t-tau, p-tau, Abeta(42)), ApoE genotype, age, sex, and BMI.
  • The SVM classifier was used to select the one-third of subjects with the highest likelihood of decline.

    • Main Results:

    • MRI measures were most influential for classifying Alzheimer's disease (AD).
    • PET-FDG and CSF biomarkers, especially Abeta(42), were more critical for classifying mild cognitive impairment (MCI).
    • In the selected subsample, detecting a 25% slowing in temporal lobe atrophy required fewer than 40 AD and MCI subjects with 80% power, significantly boosting trial power.

    Conclusions:

    • A machine learning approach integrating multimodal biomarkers can effectively classify individuals with AD, MCI, and normal cognition.
    • This method significantly enhances statistical power in clinical trials by enriching the sample with individuals likely to progress.
    • The developed classifier offers a promising tool for optimizing clinical trial design and participant selection in neurodegenerative disease research.