{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T23:35:36Z","timestamp":1786664136335,"version":"3.56.0"},"reference-count":39,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T00:00:00Z","timestamp":1755475200000},"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. Comput. Neurosci."],"abstract":"<jats:p>As global life expectancy rises, a growing proportion of the population is affected by dementia, particularly Alzheimer's disease (AD) and Frontotemporal dementia (FTD). Electroencephalography (EEG) based diagnosis presents a non-invasive, cost effective alternative for early detection, yet existing methods are challenged by data scarcity, inter-subject variability, and privacy concerns. This study proposes lightweight and privacy-preserving EEG classification framework combining deep learning and Federated Learning (FL). Five convolutional neural networks (EEGNetv1, EEGNetv4, EEGITNet, EEGInception, EEGInceptionERP) have been evaluated on resting-state EEG dataset comprising 88 subjects. EEG signals are preprocessed using band-pass (1\u201345 Hz) and notch filtering, followed by exponential standardization and 4-second windowing. EEGNetv4 outperformed among other EEG tailored models, and upon utilizing the hybrid fusion techniques it achieves 97.1% accuracy using only 1,609 parameters and less than 1 MB of memory, demonstrating high efficiency. Moreover, FL using FedAvg is implemented across five stratified clients, achieving 96.9% accuracy on the hybrid fused EEGNetV4 model while preserving data privacy. This work establishes a scalable, resource-efficient, and privacy-compliant framework for EEG-based dementia diagnosis, suitable for deployment in real-world clinical and edge-device settings.<\/jats:p>","DOI":"10.3389\/fncom.2025.1617883","type":"journal-article","created":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T05:28:51Z","timestamp":1755494931000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Privacy\u2013preserving dementia classification from EEG via hybrid\u2013fusion EEGNetv4 and federated learning"],"prefix":"10.3389","volume":"19","author":[{"given":"Muhammad","family":"Umair","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad Shahbaz","family":"Khan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad","family":"Hanif","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wad","family":"Ghaban","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ibtehal","family":"Nafea","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sultan Noman","family":"Qasem","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Faisal","family":"Saeed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,8,18]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1016\/j.mejo.2016.08.014","article-title":"Fully differential fifth-order dual-notch powerline interference filter oriented to EEG detection system with low pass feature","volume":"56","author":"Alhammadi","year":"2016","journal-title":"Microelectronics J"},{"key":"B2","doi-asserted-by":"publisher","first-page":"5695","DOI":"10.1002\/alz.13844","article-title":"Sex and gender differences in cognitive resilience to aging and Alzheimer's disease","volume":"20","author":"Arenaza-Urquijo","year":"2024","journal-title":"Alzheimer's Dement"},{"key":"B3","doi-asserted-by":"publisher","first-page":"102324","DOI":"10.1016\/j.jocs.2024.102324","article-title":"Litefusionnet: Boosting the performance for medical image classification with an intelligent and lightweight feature fusion network","volume":"80","author":"Asif","year":"2024","journal-title":"J. Comput. Sci"},{"key":"B4","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1109\/JSAS.2025.3552546","article-title":"Electroencephalogram and event-related potential in mild cognitive impairment: recent developments in signal processing, machine learning, and deep learning","volume":"2","author":"Azami","year":"2025","journal-title":"IEEE J. Selected Areas in Sensors"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1672","DOI":"10.1016\/S0140-6736(15)00461-4","article-title":"Frontotemporal dementia","volume":"386","author":"Bang","year":"2015","journal-title":"Lancet"},{"key":"B6","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1016\/S1474-4422(21)00341-0","article-title":"Advances and controversies in frontotemporal dementia: diagnosis, biomarkers, and therapeutic considerations","volume":"21","author":"Boeve","year":"2022","journal-title":"Lancet Neurol"},{"key":"B7","unstructured":"braindecode.preprocessing.exponential_moving _standardize\n          \n          2022"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-981-96-0462-3_1","author":"Byles","year":"2024","journal-title":"Healthy Ageing and Healthy Life Expectancy"},{"key":"B9","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1111\/1468-2354.t01-1-00076","article-title":"The band pass filter","volume":"44","author":"Christiano","year":"2003","journal-title":"Int. Econ. Rev"},{"key":"B10","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":"B11","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1186\/s13024-019-0333-5","article-title":"The neuropathological diagnosis of Alzheimer's disease","volume":"14","author":"DeTure","year":"2019","journal-title":"Mol. Neurodegener"},{"key":"B12","doi-asserted-by":"publisher","first-page":"e14337","DOI":"10.1002\/alz.14337","article-title":"The Alzheimer's association clinical practice guideline for the diagnostic evaluation, testing, counseling, and disclosure of suspected Alzheimer's disease and related disorders (detecd-adrd): executive summary of recommendations for specialty care","volume":"21","author":"Dickerson","year":"2025","journal-title":"Alzheimer's Dement"},{"key":"B13","doi-asserted-by":"publisher","first-page":"3873","DOI":"10.1093\/bioinformatics\/bty440","article-title":"deepnf: deep network fusion for protein function prediction","volume":"34","author":"Gligorijevi\u0107","year":"2018","journal-title":"Bioinformatics"},{"key":"B14","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1007\/s11571-025-10232-2","article-title":"Classification for alzheimer's disease and frontotemporal dementia via resting-state electroencephalography-based coherence and convolutional neural network","volume":"19","author":"Jiang","year":"2025","journal-title":"Cogn. Neurodyn"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCA62237.2024.10927984","article-title":"\u201cEEG signatures in alzheimer and ftd's diseases using gnn deep learning technique,\u201d","author":"Kassem","year":"2024","journal-title":"2024 International Conference on Computer and Applications (ICCA)"},{"key":"B16","doi-asserted-by":"publisher","first-page":"120833","DOI":"10.1016\/j.ins.2024.120833","article-title":"FDCNN-as: Federated deep convolutional neural network alzheimer detection schemes for different age groups","volume":"677","author":"Lakhan","year":"2024","journal-title":"Inf. Sci"},{"key":"B17","doi-asserted-by":"publisher","first-page":"335","DOI":"10.3390\/brainsci14040335","article-title":"A comparative study on feature extraction techniques for the discrimination of frontotemporal dementia and alzheimer's disease with electroencephalography in resting-state adults","volume":"14","author":"Lal","year":"2024","journal-title":"Brain Sci"},{"key":"B18","doi-asserted-by":"publisher","first-page":"056013","DOI":"10.1088\/1741-2552\/aace8c","article-title":"EEGnet: a compact convolutional neural network for EEG-based brain\u2013computer interfaces","volume":"15","author":"Lawhern","year":"2018","journal-title":"J. Neural Eng"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1374","DOI":"10.1111\/epi.18282","article-title":"The role of electroencephalography in epilepsy research\u2013from seizures to interictal activity and comorbidities","volume":"66","author":"Lisgaras","year":"2025","journal-title":"Epilepsia"},{"key":"B20","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1111\/joim.13244","article-title":"Practical recommendations for timely, accurate diagnosis of symptomatic Alzheimer's disease (MCI and dementia) in primary care: a review and synthesis","volume":"290","author":"Liss","year":"2021","journal-title":"J. Intern. Med"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1156372","DOI":"10.3389\/fbioe.2023.1156372","article-title":"Prediction of drug sensitivity based on multi-omics data using deep learning and similarity network fusion approaches","volume":"11","author":"Liu","year":"2023","journal-title":"Front. Bioeng. Biotechnol"},{"key":"B22","first-page":"1273","article-title":"\u201cCommunication-efficient learning of deep networks from decentralized data,\u201d","volume-title":"Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, volume 54 of Proceedings of Machine Learning Research","author":"McMahan","year":"2017"},{"key":"B23","doi-asserted-by":"publisher","first-page":"88","DOI":"10.3390\/data8060095","article-title":"A dataset of 88 EEG recordings from: Alzheimer's disease, frontotemporal dementia and healthy subjects","volume":"1","author":"Miltiadous","year":"","journal-title":"OpenNeuro"},{"key":"B24","doi-asserted-by":"crossref","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":"","journal-title":"Data"},{"key":"B25","unstructured":"Ministry of health protocol for the prevention of cognitive impairment\n          \n          2024"},{"key":"B26","doi-asserted-by":"publisher","first-page":"2727","DOI":"10.1007\/s11276-025-03902-w","article-title":"Optimizing healthcare big data privacy with scalable subtree-based l-anonymization in cloud environments","volume":"31","author":"Natarajan","year":"2025","journal-title":"Wirel. Netw"},{"key":"B27","doi-asserted-by":"publisher","first-page":"3447","DOI":"10.1007\/s11571-024-10152-7","article-title":"EEG-based classification of alzheimer's disease and frontotemporal dementia: a comprehensive analysis of discriminative features","volume":"18","author":"Rostamikia","year":"2024","journal-title":"Cogn. Neurodyn"},{"key":"B28","doi-asserted-by":"publisher","first-page":"e16","DOI":"10.34172\/ija.2023.e16","article-title":"The global burden of diseases and injuries among older adults","volume":"1","author":"Safiri","year":"2023","journal-title":"Int. J. Aging"},{"key":"B29","doi-asserted-by":"publisher","first-page":"20552076241295577","DOI":"10.1177\/20552076241295577","article-title":"Towards privacy-preserving alzheimer's disease classification: federated learning on t1-weighted magnetic resonance imaging data","volume":"10","author":"Sahid","year":"2024","journal-title":"Digital Health"},{"key":"B30","doi-asserted-by":"publisher","first-page":"36672","DOI":"10.1109\/ACCESS.2022.3161489","article-title":"EEG-itnet: an explainable inception temporal convolutional network for motor imagery classification","volume":"10","author":"Salami","year":"2022","journal-title":"IEEE Access"},{"key":"B31","doi-asserted-by":"publisher","first-page":"2773","DOI":"10.1109\/TNSRE.2020.3048106","article-title":"EEG-inception: a novel deep convolutional neural network for assistive erp-based brain-computer interfaces","volume":"28","author":"Santamar\u00eda-V\u00e1zquez","year":"2020","journal-title":"IEEE Trans. Neural Syst. Rehabilit. Eng"},{"key":"B32","doi-asserted-by":"publisher","first-page":"5391","DOI":"10.1002\/hbm.23730","article-title":"Deep learning with convolutional neural networks for EEG decoding and visualization","volume":"38","author":"Schirrmeister","year":"2017","journal-title":"Hum. Brain Mapp"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1105","DOI":"10.3233\/JAD-161088","article-title":"Oxidative stress, synaptic dysfunction, and Alzheimer's disease","volume":"57","author":"T\u00f6nnies","year":"2017","journal-title":"J. Alzheimer's Dis"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2025.1569828","article-title":"Decentralized EEG-based detection of major depressive disorder via transformer architectures and split learning","author":"Umair","year":"2025","journal-title":"Front. Comput. Neurosci"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1109\/ICAIIC60209.2024.10463247","article-title":"\u201cDynamic federated learning aggregation for enhanced intrusion detection in iot attacks,\u201d","author":"Umair","year":"2024","journal-title":"2024 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)"},{"key":"B36","doi-asserted-by":"publisher","first-page":"263","DOI":"10.3233\/JAD-220397","article-title":"Mini-mental state examination and montreal cognitive assessment as tools for following cognitive changes in alzheimer's disease neuroimaging initiative participants","volume":"90","author":"Wang","year":"2022","journal-title":"J. Alzheimer's Dis"},{"key":"B37","unstructured":"Dementia\n          \n          2025"},{"key":"B38","doi-asserted-by":"publisher","first-page":"1361","DOI":"10.1016\/j.jagp.2024.06.009","article-title":"Beta-to-theta entropy ratio of EEG in aging, frontotemporal dementia, and Alzheimer's dementia","volume":"32","author":"Zandbagleh","year":"2024","journal-title":"Am. J. Geriatr. Psychiat"},{"key":"B39","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1016\/j.clinph.2024.12.008","article-title":"Time-frequency functional connectivity alterations in Alzheimer's disease and frontotemporal dementia: an EEG analysis using machine learning","volume":"170","author":"Zheng","year":"2025","journal-title":"Clin. Neurophysiol"}],"container-title":["Frontiers in Computational Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2025.1617883\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T05:28:53Z","timestamp":1755494933000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2025.1617883\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,18]]},"references-count":39,"alternative-id":["10.3389\/fncom.2025.1617883"],"URL":"https:\/\/doi.org\/10.3389\/fncom.2025.1617883","relation":{},"ISSN":["1662-5188"],"issn-type":[{"value":"1662-5188","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,18]]},"article-number":"1617883"}}