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

Optimizing Machine Learning Methods to Improve Predictive Models of Alzheimer's Disease.

Ali Ezzati1,2, Andrea R Zammit1, Danielle J Harvey3

  • 1Department of Neurology, Albert Einstein College of Medicine, Bronx, NY, USA.

Journal of Alzheimer'S Disease : JAD
|September 3, 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

Neuroticism is linked to cognitive decline and increased risk of Alzheimer's disease through dysregulation of excitatory neurons.

bioRxiv : the preprint server for biology·2026
Same author

Hippocampal asymmetry captures non-amyloid-related risk of memory decline and clinical progression.

The journal of prevention of Alzheimer's disease·2026
Same author

Associations of stable psychological traits with multi-omic subtypes of Alzheimer's dementia.

Translational psychiatry·2026
Same author

APOE and amyloid-tau pathology in cognitively unimpaired older adults.

medRxiv : the preprint server for health sciences·2026
Same author

Scalable markers for early cognitive decline: Plasma p-tau217, subjective cognitive concerns, and digital testing: Results from the A4/LEARN studies.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2026
Same author

Suicide mortality in United States urban career firefighters and emergency medical service providers.

Preventive medicine·2026

Machine learning models accurately classify individuals with Alzheimer's disease (AD) and predict mild cognitive impairment (MCI) to AD conversion. This aids clinical trials and decision-making for cognitive decline.

Area of Science:

  • Neuroscience
  • Artificial Intelligence
  • Medical Imaging

Background:

  • Predicting cognitive decline is crucial for clinical trials and decision-making.
  • Machine learning (ML) offers predictive capabilities, but optimal features and algorithms remain a challenge.

Purpose of the Study:

  • To evaluate ML methods for classifying cognitively normal (CN) individuals from Alzheimer's disease (AD).
  • To assess ML's accuracy in predicting longitudinal outcomes for individuals with mild cognitive impairment (MCI).

Main Methods:

  • Utilized 1,329 participants from the Alzheimer's Disease Neuroimaging Initiative (ADNI).
  • Employed four baseline feature sets (including neuroimaging and demographics) and six ML algorithms.
  • Classified CN vs. AD and predicted MCI to AD conversion using the best-performing model.
Keywords:
Alzheimer’s diseaseclassificationearly diagnosismachine learningmagnetic resonance imagingmild cognitive impairmentpredictive analytics

Related Experiment Videos

Main Results:

  • Ensemble linear discriminant models with demographics and volumetric MRI data achieved 92.8% accuracy in classifying CN vs. AD.
  • Prediction accuracy for MCI to AD conversion at 48 months reached 77.0%.

Conclusions:

  • ML models trained for CN vs. AD classification enhance the prediction of MCI conversion to AD.
  • These findings support the use of ML in predicting cognitive decline trajectories.