Task-Related EEG as a Biomarker for Preclinical Alzheimer’s Disease: An Explainable Deep Learning Approach

The early detection of Alzheimer’s disease (AD) in cognitively healthy individuals remains a major preclinical challenge. EEG is a promising tool that has shown effectiveness in detecting AD risk. Task-related EEG has been rarely used in Alzheimer’s disease research, as most studies have focused on...

Volledige beschrijving

Bewaard in:
Bibliografische gegevens
Hoofdauteurs: Ziyang Li, Hong Wang, Lei Li
Formaat: Artikel
Taal:Engels
Gepubliceerd in: MDPI AG 2025-07-01
Reeks:Biomimetics
Onderwerpen:
Online toegang:https://www.mdpi.com/2313-7673/10/7/468
Tags: Voeg label toe
Geen labels, Wees de eerste die dit record labelt!
_version_ 1839616407108583424
author Ziyang Li
Hong Wang
Lei Li
author_facet Ziyang Li
Hong Wang
Lei Li
author_sort Ziyang Li
collection DOAJ
description The early detection of Alzheimer’s disease (AD) in cognitively healthy individuals remains a major preclinical challenge. EEG is a promising tool that has shown effectiveness in detecting AD risk. Task-related EEG has been rarely used in Alzheimer’s disease research, as most studies have focused on resting-state EEG. An interpretable deep learning framework—Interpretable Convolutional Neural Network (InterpretableCNN)—was utilized to identify AD-related EEG features. EEG data were recorded during three cognitive task conditions, and samples were labeled based on APOE genotype and polygenic risk scores. A 100-fold leave-p%-subjects-out cross-validation (LPSO-CV) was used to evaluate model performance and generalizability. The model achieved an ROC AUC of 60.84% across the tasks and subjects, with a Kappa value of 0.22, indicating fair agreement. Interpretation revealed a consistent focus on theta and alpha activity in the parietal and temporal regions—areas commonly associated with AD pathology. Task-related EEG combined with interpretable deep learning can reveal early AD risk signatures in healthy individuals. InterpretableCNN enhances transparency in feature identification, offering a valuable tool for preclinical screening.
format Article
id doaj-art-b943fdfb0fba480e91ff3bed53bcdfb9
institution Matheson Library
issn 2313-7673
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Biomimetics
spelling doaj-art-b943fdfb0fba480e91ff3bed53bcdfb92025-07-25T13:16:15ZengMDPI AGBiomimetics2313-76732025-07-0110746810.3390/biomimetics10070468Task-Related EEG as a Biomarker for Preclinical Alzheimer’s Disease: An Explainable Deep Learning ApproachZiyang Li0Hong Wang1Lei Li2Department of Mechanical Engineering and Automation, Northeastern University, Wenhua Street, Shenyang 110819, ChinaDepartment of Mechanical Engineering and Automation, Northeastern University, Wenhua Street, Shenyang 110819, ChinaDepartment of Mechanical Engineering and Automation, Northeastern University, Wenhua Street, Shenyang 110819, ChinaThe early detection of Alzheimer’s disease (AD) in cognitively healthy individuals remains a major preclinical challenge. EEG is a promising tool that has shown effectiveness in detecting AD risk. Task-related EEG has been rarely used in Alzheimer’s disease research, as most studies have focused on resting-state EEG. An interpretable deep learning framework—Interpretable Convolutional Neural Network (InterpretableCNN)—was utilized to identify AD-related EEG features. EEG data were recorded during three cognitive task conditions, and samples were labeled based on APOE genotype and polygenic risk scores. A 100-fold leave-p%-subjects-out cross-validation (LPSO-CV) was used to evaluate model performance and generalizability. The model achieved an ROC AUC of 60.84% across the tasks and subjects, with a Kappa value of 0.22, indicating fair agreement. Interpretation revealed a consistent focus on theta and alpha activity in the parietal and temporal regions—areas commonly associated with AD pathology. Task-related EEG combined with interpretable deep learning can reveal early AD risk signatures in healthy individuals. InterpretableCNN enhances transparency in feature identification, offering a valuable tool for preclinical screening.https://www.mdpi.com/2313-7673/10/7/468task-related EEGAlzheimer’s disease riskinterpretable deep learningearly screeningbiomarker
spellingShingle Ziyang Li
Hong Wang
Lei Li
Task-Related EEG as a Biomarker for Preclinical Alzheimer’s Disease: An Explainable Deep Learning Approach
Biomimetics
task-related EEG
Alzheimer’s disease risk
interpretable deep learning
early screening
biomarker
title Task-Related EEG as a Biomarker for Preclinical Alzheimer’s Disease: An Explainable Deep Learning Approach
title_full Task-Related EEG as a Biomarker for Preclinical Alzheimer’s Disease: An Explainable Deep Learning Approach
title_fullStr Task-Related EEG as a Biomarker for Preclinical Alzheimer’s Disease: An Explainable Deep Learning Approach
title_full_unstemmed Task-Related EEG as a Biomarker for Preclinical Alzheimer’s Disease: An Explainable Deep Learning Approach
title_short Task-Related EEG as a Biomarker for Preclinical Alzheimer’s Disease: An Explainable Deep Learning Approach
title_sort task related eeg as a biomarker for preclinical alzheimer s disease an explainable deep learning approach
topic task-related EEG
Alzheimer’s disease risk
interpretable deep learning
early screening
biomarker
url https://www.mdpi.com/2313-7673/10/7/468
work_keys_str_mv AT ziyangli taskrelatedeegasabiomarkerforpreclinicalalzheimersdiseaseanexplainabledeeplearningapproach
AT hongwang taskrelatedeegasabiomarkerforpreclinicalalzheimersdiseaseanexplainabledeeplearningapproach
AT leili taskrelatedeegasabiomarkerforpreclinicalalzheimersdiseaseanexplainabledeeplearningapproach