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 Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Localized gold nanoparticles-mediated photothermal therapy for head and neck cancer: in vivo proof-of-concept.

International journal of pharmaceutics·2026
Same author

Cognitive performance in youth football players: Evidence from spectral and temporal EEG analyses.

Psychology of sport and exercise·2026
Same author

Healthy Life Years After 65: Building on Portugal's Progress with Stronger Geriatric Medicine.

Acta medica portuguesa·2025
Same author

Fourier Transforms the way we see B-lines in Lung Ultrasound.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

Towards a Less Invasive Treatment for Head and Neck Cancer: Initial Evaluation of Gold Nanoparticle-Mediated Photothermal Therapy.

Pharmaceutics·2025
Same author

Multidisciplinary co-creation, design and clinical evaluation of a two-material 3D printed ankle-foot orthosis: Preliminary clinical findings in a case report of fibular hemimelia.

Assistive technology : the official journal of RESNA·2025

Related Experiment Video

Updated: Jun 25, 2026

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

Real-World Generalizability of Alzheimer's Volumetric MRI Machine-Learning Models: External Validation with British

Helena Rico Pereira1,2, Vasco Sá Diogo1,3, José Manuel Fonseca2

  • 1Institute of Biophysics and Biomedical Engineering, Faculty of Sciences, University of Lisbon, University of Lisbon, Lisbon, Portugal.

Clinical Neuroradiology
|June 24, 2026
PubMed
Summary

Machine learning models for Alzheimer's disease (AD) diagnosis show varied performance. Brain volume normalization impacts accuracy, while magnetic field strength has minimal effect. Model robustness is key for real-world clinical application.

Keywords:
Artificial intelligenceBiomarkersDementiaExternal validationMild cognitive impairment

More Related Videos

Basics of Multivariate Analysis in Neuroimaging Data
06:35

Basics of Multivariate Analysis in Neuroimaging Data

Published on: July 24, 2010

Generalized Psychophysiological Interaction (PPI) Analysis of Memory Related Connectivity in Individuals at Genetic Risk for Alzheimer's Disease
09:38

Generalized Psychophysiological Interaction (PPI) Analysis of Memory Related Connectivity in Individuals at Genetic Risk for Alzheimer's Disease

Published on: November 14, 2017

Related Experiment Videos

Last Updated: Jun 25, 2026

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

Basics of Multivariate Analysis in Neuroimaging Data
06:35

Basics of Multivariate Analysis in Neuroimaging Data

Published on: July 24, 2010

Generalized Psychophysiological Interaction (PPI) Analysis of Memory Related Connectivity in Individuals at Genetic Risk for Alzheimer's Disease
09:38

Generalized Psychophysiological Interaction (PPI) Analysis of Memory Related Connectivity in Individuals at Genetic Risk for Alzheimer's Disease

Published on: November 14, 2017

Area of Science:

  • Neuroimaging
  • Machine Learning
  • Clinical Diagnostics

Background:

  • Machine learning models are increasingly used for diagnosing neurological conditions like Alzheimer's disease (AD).
  • Assessing the generalizability and performance of these models in real-world clinical settings is critical for their reliable deployment.
  • Factors such as magnetic field strength and brain volume normalization can influence model outcomes.

Purpose of the Study:

  • To test the performance of previously developed machine learning models on an external, real-world clinical dataset.
  • To evaluate the impact of magnetic field strength (1.5T vs. 3.0T) on model classification accuracy.
  • To assess the effect of brain volume normalization on the generalizability of machine learning models for AD diagnosis.

Main Methods:

  • Two machine learning models, previously trained on public datasets for differentiating cognitively normal (CN), mild cognitive impairment (MCI), and AD subjects, were validated.
  • The models were tested on a UK memory clinic dataset (SLaM-BRC) comprising 255 non-AD, 281 MCI, and 711 AD subjects.
  • Performance was evaluated using balanced accuracy (BAC) and class assignment consistency across different magnetic field strengths and normalization methods.

Main Results:

  • The 'CN vs. AD' model demonstrated similar performance across different magnetic field strengths (1.5T vs. 3.0T), with 87.1% class assignment consistency.
  • Volume normalization in the 'CN vs. AD' model decreased performance in the external dataset (81.5% BAC) compared to the internal dataset (87.7% BAC).
  • The non-normalized 'CN vs. MCI vs. AD' model showed robust performance, with similar balanced accuracy in the external dataset (54.6% BAC) as in the internal dataset.

Conclusions:

  • Brain volume normalization to estimated total intracranial volume reduced performance discrepancies between internal and external datasets.
  • The 'CN vs. MCI vs. AD' model exhibited consistent performance, indicating robustness across different datasets.
  • Dataset heterogeneity, disease variability, magnetic field strength, and brain volume normalization are significant factors influencing machine learning model performance in clinical settings.