Skip to content
DraconiticResearch
Search Sources API
181,686 studies31 sourcesUpdated 7 min ago
Peer-reviewedCC BY-NCAlzheimer's & dementia : the journal of the Alzheimer's Association

EEG-based brain effective and functional connectivity predict PET-defined amyloid positivity in cognitively normal individuals.

  • Boxin Sun1,2
  • Ming Gu1,2
  • Amanda Maher2,3
  • Kelly N DuBois2,4
  • Nicholas M Kanaan2,4
  • Jordan Bross2,3
  • Robert Koeppe2,5
  • Carol C Persad2,3
  • Yi L Murphey6
  • Voyko Kavcic2,7,8
  • Jian Ren1
  • Bruno Giordani2,3
1 more authors
  • Tongtong Li1,2
8 affiliations
  1. 1Department of Electrical and Computer Engineering, Michigan State University, East Lansing, Michigan, USA.
  2. 2Michigan Alzheimer's Disease Research Center, Ann Arbor, Michigan, USA.
  3. 3Department of Psychiatry, University of Michigan, Ann Arbor, Michigan, USA.
  4. 4Department of Translational Neuroscience, Michigan State University, Grand Rapids, Michigan, USA.
  5. 5Department of Radiology, University of Michigan, Ann Arbor, Michigan, USA.
  6. 6Department of Electrical and Computer Engineering, University of Michigan-Dearborn, Dearborn, Michigan, USA.
  7. 7Institute of Gerontology, Wayne State University, Detroit, Michigan, USA.
  8. 8International Institute of Applied Gerontology, Ljubljana, Slovenia.
Read full textPDFDOICite

Abstract

Introduction

Early identification of amyloid-beta (Aβ) pathology is essential for timely intervention in Alzheimer's disease (AD), as Aβ accumulation precedes clinical symptoms by years.Methods

We predicted positron emission tomography (PET) -defined Aβ status in cognitively normal individuals using non-invasive resting-state dry electroencephalography (EEG). Brain effective and functional connectivity were quantified to characterize dynamic information transfer between regions. Features derived from dynamic brain connectivity were used to train machine learning models for Aβ classification.Results

EEG-based models can predict amyloid positivity with accuracy comparable to, or in some cases exceeding, that of plasma p-tau217 and previously reported predictors based on cognitive measures, demographics, and health factors, depending on the model.Discussion

Beyond near real-time Aβ inference, the framework identifies the most affected brain regions and connections associated with neurodegeneration, offering complementary information to blood-based biomarkers and supporting its potential as an affordable tool for early AD detection in primary care and population screening.

Related

  1. Inflammation is associated with altered functional connectivity of the cingulate cortex in individuals with subthreshold depression
    Zhangzhang Qi, Pan Chen, Guanmao Chen +7
    PLOS Digital HealthPeer-reviewedCC BY 4.0Full textImmunologyPhysiologyPLOS
  2. Cerebellar stimulation modulates working memory performance and anterior cerebellum-thalamic-cortical network connectivity in a subgroup of individuals with early course psychosis
    Katherine S. F. Damme, Zach Anderson, Ivanka Ristanovic +4
    Translational PsychiatryPeer-reviewedCC BY-NC-ND 4.0Full textNeurologyCrossref
  3. Altered Cortico-cerebellar effective connectivity of the Visuo-attentional system is associated with READ1 deletion in developmental dyslexia
    Gökçe Korkmaz, Roberta Maria Lorenzi, Valentina Lampis +7
    NeuroImage: ClinicalPeer-reviewedCC BY-NC-ND 4.0Full textGeneral medicinePMC
  4. Directed effective connectivity between the SCN-containing hypothalamus and pineal gland varies by chronotype in bipolar disorder
    I. Mehrdadi, S. Kuster, J. Rohrer +5
    medRxivPreprintCC BYFull textPsychiatry & mental healthmedRxiv
  5. Effective Connectivity and Clinical Correlates in Chronic Obstructive Pulmonary Disease.
    Kyung-Il Han, Jin Ho Bae, Hang Joon Jo +5
    International journal of chronic obstructive pulmonary diseasePeer-reviewedCC BY-NCFull textGeneral medicineEurope PMC

Cite

BibTeXRIS
BibTeX
@article{sun2026eegbased,
  title = {{EEG-based brain effective and functional connectivity predict PET-defined amyloid positivity in cognitively normal individuals.}},
  author = {Boxin Sun and Ming Gu and Amanda Maher and Kelly N DuBois and Nicholas M Kanaan and Jordan Bross and Robert Koeppe and Carol C Persad and Yi L Murphey and Voyko Kavcic and Jian Ren and Bruno Giordani and Tongtong Li},
  journal = {Alzheimer's \& dementia : the journal of the Alzheimer's Association},
  year = {2026},
  month = oct,
  doi = {10.1002/alz.71931},
  url = {https://europepmc.org/article/MED/42952140},
  note = {CC BY-NC},
}
RIS
TY  - JOUR
TI  - EEG-based brain effective and functional connectivity predict PET-defined amyloid positivity in cognitively normal individuals.
AU  - Boxin Sun
AU  - Ming Gu
AU  - Amanda Maher
AU  - Kelly N DuBois
AU  - Nicholas M Kanaan
AU  - Jordan Bross
AU  - Robert Koeppe
AU  - Carol C Persad
AU  - Yi L Murphey
AU  - Voyko Kavcic
AU  - Jian Ren
AU  - Bruno Giordani
AU  - Tongtong Li
PY  - 2026
DA  - 2026/10/01
JO  - Alzheimer's & dementia : the journal of the Alzheimer's Association
DO  - 10.1002/alz.71931
UR  - https://europepmc.org/article/MED/42952140
AB  - Introduction  Early identification of amyloid-beta (Aβ) pathology is essential for timely intervention in Alzheimer's disease (AD), as Aβ accumulation precedes clinical symptoms by years.Methods  We predicted positron emission tomography (PET) -defined Aβ status in cognitively normal individuals using non-invasive resting-state dry electroencephalography (EEG). Brain effective and functional connectivity were quantified to characterize dynamic information transfer between regions. Features derived from dynamic brain connectivity were used to train machine learning models for Aβ classification.Results  EEG-based models can predict amyloid positivity with accuracy comparable to, or in some cases exceeding, that of plasma p-tau217 and previously reported predictors based on cognitive measures, demographics, and health factors, depending on the model.Discussion  Beyond near real-time Aβ inference, the framework identifies the most affected brain regions and connections associated with neurodegeneration, offering complementary information to blood-based biomarkers and supporting its potential as an affordable tool for early AD detection in primary care and population screening.
SN  - 1552-5260
SN  - 1552-5279
ER  -