{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T04:49:56Z","timestamp":1791521396211,"version":"4.3.4"},"reference-count":29,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:00:00Z","timestamp":1790640000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Electroencephalography (EEG) is widely used to study cognitive states and clinical biomarkers, yet the contribution of stable between-subject differences to common EEG feature representations is rarely quantified directly or incorporated into evaluation design. Here, we examine subject-linked structure in spectral EEG features using a longitudinal four-session dataset spanning 199 days and replicate key findings across four public datasets covering 39 to 395 participants, multiple paradigms, and recording systems ranging from low-channel consumer devices to research-grade EEG. In spectral band-power representations, subject identity accounted for substantially more variance than session-related drift and supported extremely strong individual discriminability under subject-wise held-out protocols, with high verification performance and robust cross-session recognition over months. However, this identity structure was not fully invariant across paradigms, showing stronger transfer in richer, higher-channel recordings than in low-channel consumer EEG under larger task shifts. We further show that the same subject-linked structure can inflate downstream clinical classification when evaluation is performed with naive segment-level splits, demonstrating that apparent diagnostic performance can partly reflect identity leakage rather than biomarker learning. These findings highlight subject identity as a measurable and persistent source of structured variance in spectral EEG features and support routine use of subject-wise evaluation and explicit confound diagnostics in EEG machine-learning studies.<\/jats:p>","DOI":"10.3390\/s26196180","type":"journal-article","created":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T15:14:37Z","timestamp":1790694877000},"page":"6180","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Quantifying Subject-Identity Variance in Spectral EEG Features and Its Role in Machine Learning Evaluation Leakage"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3084-1797","authenticated-orcid":false,"given":"Hassan","family":"Ugail","sequence":"first","affiliation":[{"name":"Centre for Visual Computing and Intelligent Systems, University of Bradford, Bradford BD7 1DP, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1149-9907","authenticated-orcid":false,"given":"Richard","family":"Wirt","sequence":"additional","affiliation":[{"name":"ni2o, 3614 Prospect St NW, Washington, DC 20007, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8503-3973","authenticated-orcid":false,"given":"Newton","family":"Howard","sequence":"additional","affiliation":[{"name":"School of Individualized Study, Rochester Institute of Technology, Rochester, NY 14623, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,29]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"767","DOI":"10.1016\/S1388-2457(02)00057-3","article-title":"Brain\u2013computer interfaces for communication and control","volume":"113","author":"Wolpaw","year":"2002","journal-title":"Clin. Neurophysiol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1007\/s00422-026-01049-1","article-title":"A three-component dynamical index of consciousness-related neural organisation","volume":"120","author":"Ugail","year":"2026","journal-title":"Biol. Cybern."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1473","DOI":"10.1038\/s41593-020-00709-0","article-title":"Issues and recommendations from the OHBM COBIDAS MEEG committee for reproducible EEG and MEG research","volume":"23","author":"Pernet","year":"2020","journal-title":"Nat. Neurosci."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"119056","DOI":"10.1016\/j.neuroimage.2022.119056","article-title":"Good scientific practice in EEG and MEG research: Progress and perspectives","volume":"257","author":"Niso","year":"2022","journal-title":"NeuroImage"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.neucom.2015.04.025","article-title":"Brainprint: Assessing the uniqueness, collectability, and permanence of a novel method for ERP biometrics","volume":"166","author":"Armstrong","year":"2015","journal-title":"Neurocomputing"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"103748","DOI":"10.1016\/j.compbiomed.2020.103748","article-title":"EEG fingerprinting: Subject-specific signature based on the aperiodic component of power spectrum","volume":"120","author":"Demuru","year":"2020","journal-title":"Comput. Biol. Med."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Fraschini, M., Meli, M., Demuru, M., Didaci, L., and Barberini, L. (2020). EEG fingerprints under naturalistic viewing using a portable device. Sensors, 20.","DOI":"10.3390\/s20226565"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1109\/LSP.2016.2516043","article-title":"EEG biometrics using visual stimuli: A longitudinal study","volume":"23","author":"Das","year":"2016","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2677","DOI":"10.1109\/TDSC.2021.3060775","article-title":"Session invariant EEG signatures using elicitation protocol fusion and convolutional neural network","volume":"19","author":"Debie","year":"2022","journal-title":"IEEE Trans. Dependable Secur. Comput."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Benomar, M., Cao, S., Vishwanath, M., Vo, K., and Cao, H. (2022). Investigation of EEG-based biometric identification using state-of-the-art neural architectures on a real-time Raspberry Pi-based system. Sensors, 22.","DOI":"10.3390\/s22239547"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1664","DOI":"10.1038\/nn.4135","article-title":"Functional connectome fingerprinting: Identifying individuals using patterns of brain connectivity","volume":"18","author":"Finn","year":"2015","journal-title":"Nat. Neurosci."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Brookshire, G., Kasper, J., Blauch, N.M., Wu, Y.C., Glatt, R., Merrill, D.A., Gerrol, S., Yoder, K.J., Quirk, C., and Lucero, C. (2024). Data leakage in deep learning studies of translational EEG. Front. Neurosci., 18.","DOI":"10.3389\/fnins.2024.1373515"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Chaibub Neto, E., Pratap, A., Perumal, T.M., Tummalacherla, M., Bot, B.M., Mangravite, L., and Omberg, L. (2019, January 4\u20138). A permutation approach to assess confounding in machine learning applications for digital health. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, AK, USA.","DOI":"10.1145\/3292500.3330903"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"de Ataide, M.L., Patel, K., Vetrekar, N., and Gad, R.S. (2024, January 13\u201315). Influence of evaluating cross-stimulation on the EEG biometric verification performance: Benchmarking study. Proceedings of the Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP 2024), Bengaluru, India.","DOI":"10.1145\/3702250.3702273"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"6537","DOI":"10.1016\/j.eswa.2014.05.013","article-title":"Electroencephalogram subject identification: A review","volume":"41","author":"Alonso","year":"2014","journal-title":"Expert Syst. Appl."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"8254","DOI":"10.1038\/s41598-018-25089-1","article-title":"The quest for identifiability in human functional connectomes","volume":"8","author":"Amico","year":"2018","journal-title":"Sci. Rep."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"119666","DOI":"10.1016\/j.neuroimage.2022.119666","article-title":"M3CV: A multi-subject, multi-session, and multi-task database for EEG-based biometrics challenge","volume":"264","author":"Huang","year":"2022","journal-title":"NeuroImage"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.bspc.2015.07.003","article-title":"Review on EEG and ERP predictive biomarkers for major depressive disorder","volume":"22","author":"Mumtaz","year":"2015","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_19","unstructured":"Mumtaz, W. (2026, September 14). MDD Patients and Healthy Controls EEG Data (New); Figshare Dataset, 2016. Available online: https:\/\/figshare.com\/articles\/dataset\/EEG_Data_New\/4244171\/2."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Ugail, H., Howard, N., Elmahmudi, A.A., and Mnasri, Z. (2026). Subject-wise depression screening from eight-channel resting-state EEG using asymmetry-aware spectral features and connectivity ablation. Sensors, 26.","DOI":"10.3390\/s26103065"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"718","DOI":"10.1038\/s41597-024-03546-z","article-title":"SignEEG v1.0: Multimodal dataset with electroencephalography and hand-written signature for biometric systems","volume":"11","author":"Mishra","year":"2024","journal-title":"Sci. Data"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1069","DOI":"10.1038\/s41597-025-05378-x","article-title":"A longitudinal EEG dataset of event-related potential","volume":"12","author":"Zhang","year":"2025","journal-title":"Sci. Data"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1034","DOI":"10.1109\/TBME.2004.827072","article-title":"BCI2000: A general-purpose brain-computer interface (BCI) system","volume":"51","author":"Schalk","year":"2004","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"e215","DOI":"10.1161\/01.CIR.101.23.e215","article-title":"PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals","volume":"101","author":"Goldberger","year":"2000","journal-title":"Circulation"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1016\/j.jcm.2016.02.012","article-title":"A guideline of selecting and reporting intraclass correlation coefficients for reliability research","volume":"15","author":"Koo","year":"2016","journal-title":"J. Chiropr. Med."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1016\/j.future.2019.04.025","article-title":"Deep face recognition using imperfect facial data","volume":"99","author":"Elmahmudi","year":"2019","journal-title":"Future Gener. Comput. Syst."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"031005","DOI":"10.1088\/1741-2552\/aab2f2","article-title":"A review of classification algorithms for EEG-based brain\u2013computer interfaces: A 10 year update","volume":"15","author":"Lotte","year":"2018","journal-title":"J. Neural Eng."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1080\/2326263X.2017.1297192","article-title":"Riemannian geometry for EEG-based brain\u2013computer interfaces; a primer and a review","volume":"4","author":"Congedo","year":"2017","journal-title":"Brain-Comput. Interfaces"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"105259","DOI":"10.1016\/j.ebiom.2024.105259","article-title":"Machine learning of brain-specific biomarkers from EEG","volume":"106","author":"Bomatter","year":"2024","journal-title":"EBioMedicine"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/19\/6180\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T04:14:32Z","timestamp":1791519272000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/19\/6180"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,29]]},"references-count":29,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2026,10]]}},"alternative-id":["s26196180"],"URL":"https:\/\/doi.org\/10.3390\/s26196180","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,29]]}}}