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

Alzheimer's Disease: Overview01:26

Alzheimer's Disease: Overview

454
Alzheimer's Disease (AD) is a continually advancing neurodegenerative disorder, distinguished by escalating memory loss, cognitive dysfunction, and dementia. The disease unfolds in three stages: preclinical, mild cognitive impairment (MCI), and dementia. Its onset is insidious, and the progression gradual, with the cause not well explained by other disorders.
The clinical diagnosis of AD hinges on the presence of memory and other cognitive impairments. Biomarkers, such as changes in Aβ...
454

You might also read

Related Articles

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

Sort by
Same author

The Exchangeable Copper-Zinc Ratio Links Sex Hormones, Tumor Burden, and Epithelial Remodeling in Colorectal Cancer.

Biomolecules·2026
Same author

Toward a Neurobiological Model of Gestalt Confluence: Thalamocortical Integration as a Hypothetical Framework for Contact Interruption.

Brain sciences·2026
Same author

FlowLet: Conditional 3D brain MRI synthesis using wavelet flow matching.

Medical image analysis·2026
Same author

Association of blood group B and of rare variants affecting immune system with multisystem inflammatory syndrome in children in an Italian cohort.

Frontiers in immunology·2026
Same author

Iron to Cobalt Swapping in a Bioinspired Heme-Peroxidase: Structural Characterization and Functional Implications.

Inorganic chemistry·2026
Same author

Monocyte distribution width in breast cancer: Results from a retrospective exploratory pilot study.

Molecular and clinical oncology·2026

Related Experiment Video

Updated: Jun 15, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

989

Detecting label noise in longitudinal Alzheimer's data with explainable artificial intelligence.

Paolo Sorino1, Angela Lombardi2, Domenico Lofù1

  • 1Department of Electrical and Information Engineering (DEI), Polytechnic University of Bari, Via E. Orabona 4, 70125, BA, Bari, Italy.

Brain Informatics
|June 10, 2025
PubMed
Summary

This study uses explainable AI to identify potential mislabeling in Alzheimer's Disease (AD) cognitive data. The approach flags inconsistencies, improving the reliability of machine learning models in AD research.

Keywords:
Alzheimer’s diseaseExplainable artificial intelligenceLongitudinal studiesMachine learningNoisy labelsSHAP

More Related Videos

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.5K
Automated, Long-term Behavioral Assay for Cognitive Functions in Multiple Genetic Models of Alzheimer's Disease, Using IntelliCage
06:46

Automated, Long-term Behavioral Assay for Cognitive Functions in Multiple Genetic Models of Alzheimer's Disease, Using IntelliCage

Published on: August 4, 2018

12.1K

Related Experiment Videos

Last Updated: Jun 15, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

989
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.5K
Automated, Long-term Behavioral Assay for Cognitive Functions in Multiple Genetic Models of Alzheimer's Disease, Using IntelliCage
06:46

Automated, Long-term Behavioral Assay for Cognitive Functions in Multiple Genetic Models of Alzheimer's Disease, Using IntelliCage

Published on: August 4, 2018

12.1K

Area of Science:

  • Neuroscience
  • Artificial Intelligence
  • Medical Informatics

Background:

  • Accurate classification of cognitive states in longitudinal Alzheimer's Disease (AD) studies is crucial for early diagnosis and intervention.
  • Noisy diagnostic labels in AD research, due to subjective assessments and variability, can compromise machine learning (ML) model performance.
  • Explainable artificial intelligence (XAI) offers potential for identifying and characterizing label inconsistencies in complex medical datasets.

Purpose of the Study:

  • To explore the utility of XAI in detecting and characterizing noisy labels within longitudinal AD datasets.
  • To develop a framework for identifying potential misclassifications without altering existing clinical diagnoses.
  • To enhance the reliability of ML models used in AD research by addressing label noise.

Main Methods:

  • A predictive model was trained using a Leave-One-Subject-Out validation strategy for subject-level interpretability.
  • SHapley Additive exPlanations (SHAP) values were employed to analyze temporal feature importance variations across patient visits.
  • Statistical thresholds derived from stable individuals were used to flag potential labeling inconsistencies.

Main Results:

  • The study demonstrated the capability of XAI to identify temporal transitions potentially indicative of noisy labels in longitudinal AD data.
  • A method was proposed to flag subjects with potential misclassifications, aiding in diagnostic reassessment.
  • The framework successfully highlighted cases warranting further review without altering primary diagnoses.

Conclusions:

  • Integrating XAI into the analysis of cognitive state transitions can significantly enhance the reliability of longitudinal AD studies.
  • This approach supports a more robust application of ML in Alzheimer's Disease research by providing insights into data quality.
  • The findings suggest a structured method for identifying and addressing label noise, potentially improving diagnostic accuracy and intervention strategies.