Accurate deep-learning model to differentiate dementia severity and diagnosis using a portable electroencephalography device

Abstract Mild cognitive impairment (MCI) and dementia pose significant health challenges in aging societies, emphasizing the need for accessible, cost-effective, and noninvasive diagnostic tools. Electroencephalography (EEG) is a promising biomarker, but traditional systems are limited by size, cost...

Full description

Saved in:
Bibliographic Details
Main Authors: Masahiro Hata, Takufumi Yanagisawa, Yuki Miyazaki, Hisaki Omori, Atsuya Hirashima, Yuta Nakagawa, Mitsuhiro Eto, Kenji Yoshiyama, Hideki Kanemoto, Byambadorj Nyamradnaa, Shusuke Yoshimoto, Kotaro Ezure, Shun Takahashi, Manabu Ikeda
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-12526-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849333128264417280
author Masahiro Hata
Takufumi Yanagisawa
Yuki Miyazaki
Hisaki Omori
Atsuya Hirashima
Yuta Nakagawa
Mitsuhiro Eto
Kenji Yoshiyama
Hideki Kanemoto
Byambadorj Nyamradnaa
Shusuke Yoshimoto
Kotaro Ezure
Shun Takahashi
Manabu Ikeda
author_facet Masahiro Hata
Takufumi Yanagisawa
Yuki Miyazaki
Hisaki Omori
Atsuya Hirashima
Yuta Nakagawa
Mitsuhiro Eto
Kenji Yoshiyama
Hideki Kanemoto
Byambadorj Nyamradnaa
Shusuke Yoshimoto
Kotaro Ezure
Shun Takahashi
Manabu Ikeda
author_sort Masahiro Hata
collection DOAJ
description Abstract Mild cognitive impairment (MCI) and dementia pose significant health challenges in aging societies, emphasizing the need for accessible, cost-effective, and noninvasive diagnostic tools. Electroencephalography (EEG) is a promising biomarker, but traditional systems are limited by size, cost, and the need for skilled technicians. This study proposes a deep-learning-based approach using data from a portable EEG device to distinguish healthy volunteers (HVs) from patients with dementia-related conditions. We analyzed EEG data from 233 participants, including 119 HVs and 114 patients, and transformed the signals into frequency-domain features using a short-time Fourier transform. A customized transformer-based model was trained and evaluated using 10-fold cross-validation and a holdout dataset. In the cross-validation, the model achieved an area under the curve (AUC) of 0.872 and a balanced accuracy (bACC) of 80.8% in distinguishing HVs from patients. Subgroup analyses were conducted for HVs versus patients stratified by dementia severity and by clinical diagnosis, yielding AUCs ranging from 0.812 to 0.898 and bACCs from 74.9 to 86.4%. Comparable results were obtained in the holdout dataset. These findings suggest that portable EEG data combined with deep learning may serve as a practical tool for the early detection and classification of dementia-related conditions.
format Article
id doaj-art-9cf6d4d97a264ea69194db42f5dec4bb
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-9cf6d4d97a264ea69194db42f5dec4bb2025-08-20T03:45:59ZengNature PortfolioScientific Reports2045-23222025-07-0115111110.1038/s41598-025-12526-1Accurate deep-learning model to differentiate dementia severity and diagnosis using a portable electroencephalography deviceMasahiro Hata0Takufumi Yanagisawa1Yuki Miyazaki2Hisaki Omori3Atsuya Hirashima4Yuta Nakagawa5Mitsuhiro Eto6Kenji Yoshiyama7Hideki Kanemoto8Byambadorj Nyamradnaa9Shusuke Yoshimoto10Kotaro Ezure11Shun Takahashi12Manabu Ikeda13Department of Psychiatry, Osaka University Graduate School of MedicineInstitute for Advanced Co-creation Studies, Osaka UniversityDepartment of Psychiatry, Osaka University Graduate School of MedicineDepartment of Psychiatry, Osaka University Graduate School of MedicineDepartment of Psychiatry, Osaka University Graduate School of MedicineDepartment of Psychiatry, Osaka University Graduate School of MedicineDepartment of Psychiatry, Osaka University Graduate School of MedicineDepartment of Psychiatry, Osaka University Graduate School of MedicineDepartment of Psychiatry, Osaka University Graduate School of MedicinePGV IncPGV IncPGV IncDepartment of Psychiatry, Osaka University Graduate School of MedicineDepartment of Psychiatry, Osaka University Graduate School of MedicineAbstract Mild cognitive impairment (MCI) and dementia pose significant health challenges in aging societies, emphasizing the need for accessible, cost-effective, and noninvasive diagnostic tools. Electroencephalography (EEG) is a promising biomarker, but traditional systems are limited by size, cost, and the need for skilled technicians. This study proposes a deep-learning-based approach using data from a portable EEG device to distinguish healthy volunteers (HVs) from patients with dementia-related conditions. We analyzed EEG data from 233 participants, including 119 HVs and 114 patients, and transformed the signals into frequency-domain features using a short-time Fourier transform. A customized transformer-based model was trained and evaluated using 10-fold cross-validation and a holdout dataset. In the cross-validation, the model achieved an area under the curve (AUC) of 0.872 and a balanced accuracy (bACC) of 80.8% in distinguishing HVs from patients. Subgroup analyses were conducted for HVs versus patients stratified by dementia severity and by clinical diagnosis, yielding AUCs ranging from 0.812 to 0.898 and bACCs from 74.9 to 86.4%. Comparable results were obtained in the holdout dataset. These findings suggest that portable EEG data combined with deep learning may serve as a practical tool for the early detection and classification of dementia-related conditions.https://doi.org/10.1038/s41598-025-12526-1DementiaMild cognitive impairmentAlzheimer’s diseaseDLBEEGDeep learning
spellingShingle Masahiro Hata
Takufumi Yanagisawa
Yuki Miyazaki
Hisaki Omori
Atsuya Hirashima
Yuta Nakagawa
Mitsuhiro Eto
Kenji Yoshiyama
Hideki Kanemoto
Byambadorj Nyamradnaa
Shusuke Yoshimoto
Kotaro Ezure
Shun Takahashi
Manabu Ikeda
Accurate deep-learning model to differentiate dementia severity and diagnosis using a portable electroencephalography device
Scientific Reports
Dementia
Mild cognitive impairment
Alzheimer’s disease
DLB
EEG
Deep learning
title Accurate deep-learning model to differentiate dementia severity and diagnosis using a portable electroencephalography device
title_full Accurate deep-learning model to differentiate dementia severity and diagnosis using a portable electroencephalography device
title_fullStr Accurate deep-learning model to differentiate dementia severity and diagnosis using a portable electroencephalography device
title_full_unstemmed Accurate deep-learning model to differentiate dementia severity and diagnosis using a portable electroencephalography device
title_short Accurate deep-learning model to differentiate dementia severity and diagnosis using a portable electroencephalography device
title_sort accurate deep learning model to differentiate dementia severity and diagnosis using a portable electroencephalography device
topic Dementia
Mild cognitive impairment
Alzheimer’s disease
DLB
EEG
Deep learning
url https://doi.org/10.1038/s41598-025-12526-1
work_keys_str_mv AT masahirohata accuratedeeplearningmodeltodifferentiatedementiaseverityanddiagnosisusingaportableelectroencephalographydevice
AT takufumiyanagisawa accuratedeeplearningmodeltodifferentiatedementiaseverityanddiagnosisusingaportableelectroencephalographydevice
AT yukimiyazaki accuratedeeplearningmodeltodifferentiatedementiaseverityanddiagnosisusingaportableelectroencephalographydevice
AT hisakiomori accuratedeeplearningmodeltodifferentiatedementiaseverityanddiagnosisusingaportableelectroencephalographydevice
AT atsuyahirashima accuratedeeplearningmodeltodifferentiatedementiaseverityanddiagnosisusingaportableelectroencephalographydevice
AT yutanakagawa accuratedeeplearningmodeltodifferentiatedementiaseverityanddiagnosisusingaportableelectroencephalographydevice
AT mitsuhiroeto accuratedeeplearningmodeltodifferentiatedementiaseverityanddiagnosisusingaportableelectroencephalographydevice
AT kenjiyoshiyama accuratedeeplearningmodeltodifferentiatedementiaseverityanddiagnosisusingaportableelectroencephalographydevice
AT hidekikanemoto accuratedeeplearningmodeltodifferentiatedementiaseverityanddiagnosisusingaportableelectroencephalographydevice
AT byambadorjnyamradnaa accuratedeeplearningmodeltodifferentiatedementiaseverityanddiagnosisusingaportableelectroencephalographydevice
AT shusukeyoshimoto accuratedeeplearningmodeltodifferentiatedementiaseverityanddiagnosisusingaportableelectroencephalographydevice
AT kotaroezure accuratedeeplearningmodeltodifferentiatedementiaseverityanddiagnosisusingaportableelectroencephalographydevice
AT shuntakahashi accuratedeeplearningmodeltodifferentiatedementiaseverityanddiagnosisusingaportableelectroencephalographydevice
AT manabuikeda accuratedeeplearningmodeltodifferentiatedementiaseverityanddiagnosisusingaportableelectroencephalographydevice