{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T23:03:21Z","timestamp":1793833401669,"version":"4.6.1"},"reference-count":41,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T00:00:00Z","timestamp":1763596800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neuroinform."],"abstract":"<jats:p>Alzheimer's disease (AD) and frontotemporal dementia (FTD) are major neurodegenerative disorders with characteristic EEG alterations. While most prior studies have focused on eyes-closed (EC) EEG, where stable alpha rhythms support relatively high classification performance, eyes-open (EO) EEG has proven particularly challenging for AD, as low-frequency instability obscures the typical spectral alterations. In contrast, FTD often remains more discriminable under EO conditions, reflecting distinct neurophysiological dynamics between the two disorders. To address this challenge, we propose a CNN-based framework that applies Dynamic Mode Decomposition (DMD) to segment EO EEG into shorter temporal windows and employs a 3D CNN to capture spatio-temporal-spectral representations. This approach outperformed not only the conventional short-epoch spectral ML pipeline but also the same CNN architecture trained on FFT-based features, with particularly pronounced improvements observed in AD classification. Excluding delta yielded small gains in AD-involving contrasts, whereas FTD\/CN was unchanged or slightly better with delta retained\u2014suggesting delta is more perturbative in AD under EO conditions.<\/jats:p>","DOI":"10.3389\/fninf.2025.1706099","type":"journal-article","created":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T13:32:46Z","timestamp":1763645566000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["CNN-based framework for Alzheimer's disease detection from EEG via dynamic mode decomposition"],"prefix":"10.3389","volume":"19","author":[{"given":"Jacob","family":"Kang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hunseok","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jong-Hyeon","family":"Seo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,11,20]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.tins.2019.11.001","article-title":"Gamma entrainment: impact on neurocircuits, glia, and therapeutic opportunities","volume":"43","author":"Adaikkan","year":"2020","journal-title":"Trends Neurosci"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1039496","DOI":"10.3389\/fnagi.2023.1039496","article-title":"Brain network analysis for the discrimination of dementia disorders: a connectivity framework for EEG and MEG data","volume":"15","author":"Adebisi","year":"2023","journal-title":"Front. Aging Neurosci"},{"key":"B3","doi-asserted-by":"publisher","first-page":"949","DOI":"10.1109\/JBHI.2016.2578954","article-title":"Directed functional networks in Alzheimer's disease: disruption of global and local connectivity measures","volume":"21","author":"Afshari","year":"2017","journal-title":"IEEE J. Biomed. Health Inform"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1190203","DOI":"10.3389\/fnhum.2023.1190203","article-title":"EEG-based clinical decision support system for Alzheimer's disease","volume":"17","author":"AlSharabi","year":"2023","journal-title":"Front. Hum. Neurosci"},{"key":"B5","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1016\/j.neurobiolaging.2017.03.030","article-title":"Abnormalities of cortical neural synchronization mechanisms in patients with dementia due to Alzheimer's and lewy body diseases: an EEG study","volume":"55","author":"Babiloni","year":"2017","journal-title":"Neurobiol. Aging"},{"key":"B6","doi-asserted-by":"publisher","first-page":"291","DOI":"10.31887\/DCNS.2013.15.3\/ebasar","article-title":"Brain oscillations in neuropsychiatric disease","volume":"15","author":"Basar","year":"2013","journal-title":"Dialogues Clin. Neurosci"},{"key":"B7","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1016\/j.cortex.2021.05.023","article-title":"Remarks on the analysis of steady-state responses: Spurious artefacts introduced by overlapping epochs","volume":"142","author":"Benjamin","year":"2021","journal-title":"Cortex"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1373515","DOI":"10.3389\/fnins.2024.1373515","article-title":"Data leakage in deep learning studies of translational EEG","volume":"18","author":"Brookshire","year":"2024","journal-title":"Front. Neurosci"},{"key":"B9","doi-asserted-by":"publisher","first-page":"1638922","DOI":"10.3389\/fnins.2025.1638922","article-title":"Olfactory EEG-based Alzheimer disease classification through transformer-based feature fusion with tunable q-factor wavelet coefficient mapping","volume":"19","author":"Cansiz","year":"2025","journal-title":"Front. Neurosci"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1972","DOI":"10.3390\/s18061972","article-title":"Improved dynamic mode decomposition and its application to fault diagnosis of rolling bearing","volume":"18","author":"Dang","year":"2018","journal-title":"Sensors"},{"key":"B11","doi-asserted-by":"publisher","first-page":"1220","DOI":"10.1016\/j.neuroimage.2008.03.050","article-title":"Individual patient diagnosis of ad and ftd via high-dimensional pattern classification of MRI","volume":"41","author":"Davatzikos","year":"2008","journal-title":"Neuroimage"},{"key":"B12","volume-title":"Numerical Methods","author":"Faires","year":"2012"},{"key":"B13","doi-asserted-by":"publisher","first-page":"680200","DOI":"10.3389\/fnagi.2021.680200","article-title":"EEG alpha and beta band functional connectivity in visuospatial memory maintenance in mild cognitive impairment","volume":"13","author":"Fodor","year":"2021","journal-title":"Front. Aging Neurosci"},{"key":"B14","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1177\/155005941104200308","article-title":"EEG theta and alpha reactivity on opening the eyes in the diagnosis of Alzheimer's disease","volume":"42","author":"Fonseca","year":"2011","journal-title":"Clin. EEG Neurosci"},{"key":"B15","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1016\/j.ijpsycho.2013.05.007","article-title":"EEG beta band activity is related to attention and attentional deficits in the visual performance of elderly subjects","volume":"89","author":"Gola","year":"2013","journal-title":"Int. J. Psychophysiol"},{"key":"B16","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1016\/j.jalz.2018.02.018","article-title":"Nia-aa research framework: Toward a biological definition of Alzheimer's disease","volume":"14","author":"Jack","year":"2018","journal-title":"Alzheimer's Dement"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1490","DOI":"10.1016\/j.clinph.2004.01.001","article-title":"EEG dynamics in patients with Alzheimer's disease","volume":"115","author":"Jeong","year":"2004","journal-title":"Clin. Neurophysiol"},{"key":"B18","doi-asserted-by":"publisher","first-page":"713","DOI":"10.54097\/3knv6p63","article-title":"Challenges in early diagnosis and treatment of Alzheimer's disease","volume":"74","author":"Jiang","year":"2023","journal-title":"Highlights Sci. Eng. Technol"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1590201","DOI":"10.3389\/fmed.2025.1590201","article-title":"An explainable and efficient deep learning framework for EEG-based diagnosis of Alzheimer's disease and frontotemporal dementia","volume":"12","author":"Khan","year":"2025","journal-title":"Front. Med"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86993-9_50","article-title":"\u201cThe necessity of leave one subject out (loso) cross validation for EEG disease diagnosis,\u201d","author":"Kunjan","year":"2021","journal-title":"Proceedings of Brain Informatics (BI) 2021"},{"key":"B21","doi-asserted-by":"publisher","first-page":"687","DOI":"10.1001\/archneur.1996.00550070129021","article-title":"Alzheimer disease and frontotemporal dementias. Behavioral distinctions","volume":"53","author":"Levy","year":"1996","journal-title":"Arch. Neurol"},{"key":"B22","doi-asserted-by":"publisher","first-page":"4406","DOI":"10.3390\/math10234406","article-title":"Phase analysis of event-related potentials based on dynamic mode decomposition","volume":"10","author":"Li","year":"2022","journal-title":"Mathematics"},{"key":"B23","doi-asserted-by":"publisher","first-page":"95","DOI":"10.3390\/data8060095","article-title":"A dataset of scalp EEG recordings of Alzheimer's disease, frontotemporal dementia and healthy subjects from routine EEG","volume":"8","author":"Miltiadous","year":"2023","journal-title":"Data"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1359","DOI":"10.3233\/JAD-180300","article-title":"EEG theta power is an early marker of cognitive decline in dementia due to Alzheimer's disease","volume":"64","author":"Musaeus","year":"2018","journal-title":"J. Alzheimers Dis"},{"key":"B25","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1097\/WNP.0000000000000736","article-title":"A primer on EEG spectrograms","volume":"39","author":"Ng","year":"2022","journal-title":"J. Clin. Neurophysiol"},{"key":"B26","doi-asserted-by":"publisher","first-page":"1718","DOI":"10.1016\/j.clinph.2011.02.011","article-title":"Differences in quantitative EEG between frontotemporal dementia and Alzheimer's disease as revealed by loreta","volume":"122","author":"Nishida","year":"2011","journal-title":"Clin. Neurophysiol"},{"key":"B27","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1167\/15.6.4","article-title":"The steady-state visual evoked potential in vision research","volume":"15","author":"Norcia","year":"2015","journal-title":"J. Vis"},{"key":"B28","doi-asserted-by":"publisher","first-page":"64","DOI":"10.3390\/data10050064","article-title":"A complementary dataset of scalp EEG recordings featuring participants with Alzheimer's disease, frontotemporal dementia, and healthy controls, obtained from photostimulation EEG","volume":"10","author":"Ntetska","year":"2025","journal-title":"Data"},{"key":"B29","doi-asserted-by":"publisher","first-page":"2019","DOI":"10.1016\/j.clinph.2021.05.012","article-title":"Resting-state EEG alpha\/theta power ratio discriminates early-onset Alzheimer's disease from healthy controls","volume":"132","author":"\u00d6zbek","year":"2021","journal-title":"Clin. Neurophysiol"},{"key":"B30","doi-asserted-by":"publisher","first-page":"2277","DOI":"10.1212\/WNL.54.12.2277","article-title":"Differentiating frontal and temporal variant frontotemporal dementia from Alzheimer's disease","volume":"54","author":"Perry","year":"2000","journal-title":"Neurology"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1287","DOI":"10.1016\/j.clinph.2020.03.003","article-title":"Early diagnosis of Alzheimer's disease: the role of biomarkers including advanced EEG signal analysis. Report from the IFCN-sponsored panel of experts","volume":"131","author":"Rossini","year":"2020","journal-title":"Clin. Neurophysiol"},{"key":"B32","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1017\/S0022112010001217","article-title":"Dynamic mode decomposition of numerical and experimental data","volume":"656","author":"Schmid","year":"2010","journal-title":"J. Fluid Mech"},{"key":"B33","doi-asserted-by":"publisher","first-page":"60","DOI":"10.3389\/fnagi.2013.00060","article-title":"Index of alpha\/theta ratio of the electroencephalogram: a new marker for alzheimer's disease","volume":"5","author":"Schmidt","year":"2013","journal-title":"Front. Aging Neurosci"},{"key":"B34","doi-asserted-by":"publisher","first-page":"481","DOI":"10.3390\/math8040481","article-title":"Pattern recognition in epileptic EEG signals via dynamic mode decomposition","volume":"8","author":"Seo","year":"2020","journal-title":"Mathematics"},{"key":"B35","doi-asserted-by":"publisher","first-page":"2266","DOI":"10.1016\/j.clinph.2005.06.011","article-title":"Nonlinear dynamical analysis of EEG and MEG: review of an emerging field","volume":"116","author":"Stam","year":"2005","journal-title":"Clin. Neurophysiol"},{"key":"B36","doi-asserted-by":"publisher","first-page":"27","DOI":"10.3390\/jpm15010027","article-title":"A novel CNN-based framework for Alzheimer's disease detection using EEG spectrogram representations","volume":"15","author":"Stefanou","year":"2025","journal-title":"J. Pers. Med"},{"key":"B37","doi-asserted-by":"publisher","first-page":"1648","DOI":"10.1038\/s41598-021-83795-9","article-title":"Ssvep phase synchronies and propagation during repetitive visual stimulation at high frequencies","volume":"11","author":"Tsoneva","year":"2021","journal-title":"Sci. Rep"},{"key":"B38","doi-asserted-by":"publisher","first-page":"391","DOI":"10.3934\/jcd.2014.1.391","article-title":"On dynamic mode decomposition: theory and applications","volume":"1","author":"Tu","year":"2014","journal-title":"J. Comput. Dyn"},{"key":"B39","article-title":"xEEGnet: towards explainable AI in EEG dementia classification","author":"Zanola","year":"2025","journal-title":"arXiv preprint arXiv:2504.21457"},{"key":"B40","doi-asserted-by":"publisher","first-page":"23319","DOI":"10.1038\/s41598-025-06519-3","article-title":"A dual path graph neural network framework for dementia diagnosis","volume":"15","author":"Zhang","year":"2025","journal-title":"Sci. Rep"},{"key":"B41","doi-asserted-by":"publisher","first-page":"e6068","DOI":"10.1002\/gps.6068","article-title":"Variability in Alzheimer's disease mortality from European vital statistics, 2012\u20132020","volume":"39","author":"Zuin","year":"2024","journal-title":"Int. J. Geriatr. Psychiatry"}],"container-title":["Frontiers in Neuroinformatics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fninf.2025.1706099\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T13:32:47Z","timestamp":1763645567000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fninf.2025.1706099\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,20]]},"references-count":41,"alternative-id":["10.3389\/fninf.2025.1706099"],"URL":"https:\/\/doi.org\/10.3389\/fninf.2025.1706099","relation":{},"ISSN":["1662-5196"],"issn-type":[{"value":"1662-5196","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,20]]},"article-number":"1706099"}}