Transforming Brainwaves into Language: EEG Microstates Meet Text Embedding Models for Dementia Detection

Nguyen, QT; Le, L; Tran, XT; Bai, D; Duong-Trung, N; Do, T; Lin, CT

Transforming Brainwaves into Language: EEG Microstates Meet Text Embedding Models for Dementia Detection

Nguyen, QT Le, L Tran, XT Bai, D Duong-Trung, N Do, T Lin, CT

Permalink

Publisher:: ASSOC COMPUTATIONAL LINGUISTICS-ACL
Publication Type:: Conference Proceeding
Citation:: Proceedings of the Annual Meeting of the Association for Computational Linguistics, 2025, 4, pp. 186-202
Issue Date:: 2025-01-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (870.91 kB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Nguyen, QT
dc.contributor.author	Le, L
dc.contributor.author	Tran, XT
dc.contributor.author	Bai, D
dc.contributor.author	Duong-Trung, N
dc.contributor.author	Do, T
dc.contributor.author	Lin, CT
dc.contributor.editor	Wang, M
dc.contributor.editor	Zhao, J
dc.contributor.editor	Liu, Z
dc.date	2025-07-27
dc.date.accessioned	2026-01-30T02:19:43Z
dc.date.available	2026-01-30T02:19:43Z
dc.date.issued	2025-01-01
dc.identifier.citation	Proceedings of the Annual Meeting of the Association for Computational Linguistics, 2025, 4, pp. 186-202
dc.identifier.issn	0736-587X
dc.identifier.uri	http://hdl.handle.net/10453/192599
dc.description.abstract	This study proposes a novel, scalable, noninvasive and channel-independent approach for early dementia detection, particularly Alzheimer’s Disease (AD), by representing Electroencephalography (EEG) microstates as symbolic, language-like sequences. These representations are processed via text embedding and time-series deep learning models for classification. Developed on EEG data from 1001 participants across multiple countries, the proposed method achieves a high accuracy of 94.31% for AD detection. By eliminating the need for fixed EEG configurations and costly/invasive modalities, the introduced approach improves generalisability and enables cost-effective deployment without requiring separate AI models or specific devices. It facilitates scalable and accessible dementia screening, supporting timely interventions and enhancing AD detection in resource-limited communities.
dc.language	en
dc.publisher	ASSOC COMPUTATIONAL LINGUISTICS-ACL
dc.relation.ispartof	Proceedings of the Annual Meeting of the Association for Computational Linguistics
dc.relation.ispartof	63rd Association for Computational Linguistics Meeting-ACL-Annual
dc.relation.isbasedon	10.18653/v1/2025.acl-srw.12
dc.rights	info:eu-repo/semantics/openAccess
dc.title	Transforming Brainwaves into Language: EEG Microstates Meet Text Embedding Models for Dementia Detection
dc.type	Conference Proceeding
utslib.citation.volume	4
utslib.location.activity	AUSTRIA, Vienna
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
pubs.organisational-group	University of Technology Sydney/UTS Groups
pubs.organisational-group	University of Technology Sydney/UTS Groups/Australian Artificial Intelligence Institute (AAII)
pubs.organisational-group	University of Technology Sydney/UTS Groups/Stroke Research Collaborative
utslib.copyright.status	open_access	*
dc.rights.license	This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0). To view a copy of this license, visit https://creativecommons.org/licenses/by/4.0/
dc.date.updated	2026-01-30T02:19:42Z
pubs.finish-date	2025-08-01
pubs.publication-status	Published
pubs.start-date	2025-07-27
pubs.volume	4

Abstract:

This study proposes a novel, scalable, noninvasive and channel-independent approach for early dementia detection, particularly Alzheimer’s Disease (AD), by representing Electroencephalography (EEG) microstates as symbolic, language-like sequences. These representations are processed via text embedding and time-series deep learning models for classification. Developed on EEG data from 1001 participants across multiple countries, the proposed method achieves a high accuracy of 94.31% for AD detection. By eliminating the need for fixed EEG configurations and costly/invasive modalities, the introduced approach improves generalisability and enables cost-effective deployment without requiring separate AI models or specific devices. It facilitates scalable and accessible dementia screening, supporting timely interventions and enhancing AD detection in resource-limited communities.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/192599