{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T16:05:59Z","timestamp":1753891559331,"version":"3.41.2"},"reference-count":44,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T00:00:00Z","timestamp":1682467200000},"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:sec><jats:title>Introduction<\/jats:title><jats:p>Modern consciousness research has developed diagnostic tests to improve the diagnostic accuracy of different states of consciousness via electroencephalography (EEG)-based mental motor imagery (MI), which is still challenging and lacks a consensus on how to best analyse MI EEG-data. An optimally designed and analyzed paradigm must detect command-following in all healthy individuals, before it can be applied in patients, e.g., for the diagnosis of disorders of consciousness (DOC).<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We investigated the effects of two important steps in the raw signal preprocessing on predicting participant performance (F1) and machine-learning classifier performance (area-under-curve, AUC) in eight healthy individuals, that are based solely on MI using high-density EEG (HD-EEG): artifact correction (manual correction with vs. without Independent Component Analysis [ICA]), region of interest (ROI; motor area vs. whole brain), and machine-learning algorithm (support-vector machine [SVM] vs. k-nearest neighbor [KNN]).<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Results revealed no significant effects of artifact correction and ROI on predicting participant performance (F1) and classifier performance (AUC) scores (all<jats:italic>p<\/jats:italic>s &amp;gt; 0.05) in the SVM classification model. In the KNN model, ROI had a significant influence on the classifier performance [<jats:italic>F<\/jats:italic><jats:sub>(1,8.939)<\/jats:sub>= 7.585,<jats:italic>p<\/jats:italic>= 0.023]. There was no evidence for artifact correction and ROI selection changing the prediction of participants performance and classifier performance in EEG-based mental MI if using SVM-based classification (71\u2013100% correct classifications across different signal preprocessing methods). The variance in the prediction of participant performance was significantly higher when the experiment started with a resting-state compared to a mental MI task block [<jats:italic>X<\/jats:italic><jats:sup>2<\/jats:sup><jats:sub>(1)<\/jats:sub>= 5.849,<jats:italic>p<\/jats:italic>= 0.016].<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>Overall, we could show that classification is stable across different modes of EEG signal preprocessing when using SVM models. Exploratory analysis gave a hint toward potential effects of the sequence of task execution on the prediction of participant performance, which should be taken into account in future studies.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fncom.2023.1142948","type":"journal-article","created":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T04:43:09Z","timestamp":1682484189000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Stability of mental motor-imagery classification in EEG depends on the choice of classifier model and experiment design, but not on signal preprocessing"],"prefix":"10.3389","volume":"17","author":[{"given":"Martin Justinus","family":"Rosenfelder","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Myra","family":"Spiliopoulou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Burkhard","family":"Hoppenstedt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"R\u00fcdiger","family":"Pryss","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrick","family":"Fissler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mario","family":"della Piedra Walter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Iris-Tatjana","family":"Kolassa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreas","family":"Bender","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2023,4,26]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"100003","DOI":"10.1016\/j.array.2019.100003","article-title":"Signal processing techniques for motor imagery brain computer interface: a review","volume":"1","author":"Aggarwal","year":"2019","journal-title":"Array"},{"key":"B2","doi-asserted-by":"publisher","first-page":"3001","DOI":"10.1007\/s11831-021-09684-6","article-title":"Review of machine learning techniques for EEG based brain computer interface","volume":"29","author":"Aggarwal","year":"2022","journal-title":"Arch. Computat. Methods Eng."},{"key":"B3","unstructured":"BallingsM. Van den PoelD. AUC: a grammar of data manipulation. Package AUC2013"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1129","DOI":"10.1162\/neco.1995.7.6.1129","article-title":"An information-maximization approach to blind separation and blind deconvolution","volume":"7","author":"Bell","year":"1995","journal-title":"Neural Comput"},{"key":"B5","doi-asserted-by":"publisher","first-page":"2120","DOI":"10.1093\/brain\/awx163","article-title":"Brain networks predict metabolism, diagnosis and prognosis at the bedside in disorders of consciousness","volume":"140","author":"Chennu","year":"2017","journal-title":"Brain"},{"key":"B6","doi-asserted-by":"publisher","first-page":"2497","DOI":"10.1056\/NEJMoa1812757","article-title":"Detection of brain activation in unresponsive patients with acute brain injury","volume":"380","author":"Claassen","year":"2019","journal-title":"N. Engl. J. Med"},{"journal-title":"Practical Nonparametric Statistics, Vol. 350","year":"1998","author":"Conover","key":"B7"},{"key":"B8","doi-asserted-by":"publisher","first-page":"S62","DOI":"10.1016\/j.apmr.2014.08.024","article-title":"Sensorimotor modulation assessment and brain-computer interface training in disorders of consciousness","volume":"96","author":"Coyle","year":"2015","journal-title":"Arch. Phys. Med. Rehabil"},{"key":"B9","doi-asserted-by":"publisher","first-page":"031001","DOI":"10.1088\/1741-2552\/ab0ab5","article-title":"Deep learning for electroencephalogram (eeg) classification tasks: a review","volume":"16","author":"Craik","year":"2019","journal-title":"J. Neural Eng"},{"key":"B10","doi-asserted-by":"publisher","first-page":"2088","DOI":"10.1016\/S0140-6736(11)61224-5","article-title":"Bedside detection of awareness in the vegetative state: a cohort study","volume":"378","author":"Cruse","year":"2011","journal-title":"Lancet"},{"key":"B11","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1212\/WNL.0b013e318249f764","article-title":"Relationship between etiology and covert cognition in the minimally conscious state","volume":"78","author":"Cruse","year":"","journal-title":"Neurology"},{"key":"B12","doi-asserted-by":"publisher","first-page":"e49933","DOI":"10.1371\/journal.pone.0049933","article-title":"Detecting awareness in the vegetative state: electroencephalographic evidence for attempted movements to command","volume":"7","author":"Cruse","year":"","journal-title":"PLoS ONE"},{"key":"B13","doi-asserted-by":"publisher","first-page":"3179","DOI":"10.1093\/brain\/awy251","article-title":"Robust EEG-based cross-site and cross-protocol classification of states of consciousness","volume":"141","author":"Engemann","year":"2018","journal-title":"Brain"},{"key":"B14","doi-asserted-by":"publisher","first-page":"108833","DOI":"10.1016\/j.jneumeth.2020.108833","article-title":"Improvement motor imagery EEG classification based on sparse common spatial pattern and regularized discriminant analysis","volume":"343","author":"Fu","year":"2020","journal-title":"J. Neurosci. Methods"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1556","DOI":"10.1016\/j.clinph.2013.11.034","article-title":"Complexity and familiarity enhance single-trial detectability of imagined movements with electroencephalography","volume":"125","author":"Gibson","year":"2014","journal-title":"Clin. Neurophysiol"},{"key":"B16","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1016\/S0140-6736(13)60125-7","article-title":"Reanalysis of \u201cbedside detection of awareness in the vegetative state: a cohort study\u201d","volume":"381","author":"Goldfine","year":"2013","journal-title":"Lancet"},{"key":"B17","doi-asserted-by":"publisher","first-page":"2157","DOI":"10.1016\/j.clinph.2011.03.022","article-title":"Determination of awareness in patients with severe brain injury using EEG power spectral analysis","volume":"122","author":"Goldfine","year":"2011","journal-title":"Clin. Neurophysiol"},{"key":"B18","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1177\/1550059414560397","article-title":"Protocol design challenges in the detection of awareness in aware subjects using EEG signals","volume":"47","author":"Henriques","year":"2016","journal-title":"Clin. EEG Neurosci"},{"key":"B19","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/j.ijpsycho.2012.10.015","article-title":"Real movement vs. motor imagery in healthy subjects","volume":"87","author":"H\u00f6ller","year":"","journal-title":"Int. J. Psychophysiol"},{"key":"B20","doi-asserted-by":"publisher","first-page":"e80479","DOI":"10.1371\/journal.pone.0080479","article-title":"Comparison of eeg-features and classification methods for motor imagery in patients with disorders of consciousness","volume":"8","author":"H\u00f6ller","year":"","journal-title":"PLoS ONE"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1009","DOI":"10.3389\/fnhum.2014.01009","article-title":"Detection of mental imagery and attempted movements in patients with disorders of consciousness using EEG","volume":"8","author":"Horki","year":"2014","journal-title":"Front. Hum. Neurosci"},{"key":"B22","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1111\/1469-8986.3720163","article-title":"Removing electroencephalographic artifacts by blind source separation","volume":"37","author":"Jung","year":"2000","journal-title":"Psychophysiology"},{"key":"B23","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1016\/j.brainresbull.2011.09.019","article-title":"Value of amplitude, phase, and coherence features for a sensorimotor rhythm-based brain-computer interface","volume":"87","author":"Krusienski","year":"2012","journal-title":"Brain Res. Bull"},{"key":"B24","doi-asserted-by":"publisher","first-page":"0460f","DOI":"10.1088\/1741-2552\/ac1ed0","article-title":"Multi-class motor imagery EEG classification method with high accuracy and low individual differences based on hybrid neural network","volume":"18","author":"Liu","year":"2021","journal-title":"J. Neural Eng"},{"key":"B25","doi-asserted-by":"publisher","first-page":"6093","DOI":"10.3390\/s22166093","article-title":"Motor imagery analysis from extensive EEG data representations using convolutional neural networks","volume":"22","author":"Lomelin-Ibarra","year":"2022","journal-title":"Sensors"},{"key":"B26","doi-asserted-by":"publisher","first-page":"566","DOI":"10.1109\/TNSRE.2016.2601240","article-title":"A deep learning scheme for motor imagery classification based on restricted Boltzmann machines","volume":"25","author":"Lu","year":"2016","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng"},{"key":"B27","doi-asserted-by":"publisher","first-page":"957","DOI":"10.1007\/s13246-018-0691-2","article-title":"Multi-class EEG classification of motor imagery signal by finding optimal time segments and features using SNR-based mutual information","volume":"41","author":"Mahmoudi","year":"2018","journal-title":"Austr. Phys. Eng. Sci. Med"},{"journal-title":"Independent Component Analysis of Simulated ERP Data","year":"1996","author":"Makeig","key":"B28"},{"journal-title":"MATLAB (R2017a), Version 9.2.0","year":"2017","key":"B29"},{"key":"B30","doi-asserted-by":"publisher","first-page":"2416","DOI":"10.1016\/j.neuroimage.2009.10.010","article-title":"Validation of ICA-based myogenic artifact correction for scalp and source-localized EEG","volume":"49","author":"McMenamin","year":"2010","journal-title":"Neuroimage"},{"key":"B31","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1016\/j.ymeth.2008.05.002","article-title":"Imaging motor imagery: methodological issues related to expertise","volume":"45","author":"Milton","year":"2008","journal-title":"Methods"},{"key":"B32","doi-asserted-by":"publisher","first-page":"21305","DOI":"10.1007\/s11042-017-5586-9","article-title":"Comparison of EEG signal decomposition methods in classification of motor-imagery BCI","volume":"77","author":"Mohamed","year":"2018","journal-title":"Multimedia Tools Appl"},{"journal-title":"Machine Learning-Kurz","year":"2018","author":"Nguyen","key":"B33"},{"key":"B34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neuroimage.2010.04.256","article-title":"ICA-based muscle artefact correction of EEG data: what is muscle and what is brain?: Comment on Mcmenamin et al","volume":"54","author":"Olbrich","year":"2011","journal-title":"Neuroimage"},{"key":"B35","doi-asserted-by":"publisher","first-page":"156869","DOI":"10.1155\/2011\/156869","article-title":"Fieldtrip: open source software for advanced analysis of MEG, EEG, and invasive electrophysiological data","volume":"2011","author":"Oostenveld","year":"2011","journal-title":"Comput. Intell. Neurosci"},{"key":"B36","doi-asserted-by":"publisher","first-page":"1419","DOI":"10.1111\/j.1460-9568.2008.06441.x","article-title":"Short-lived brain state after cued motor imagery in naive subjects","volume":"28","author":"Pfurtscheller","year":"2008","journal-title":"Eur. J. Neurosci"},{"key":"B37","doi-asserted-by":"crossref","unstructured":"PohlertT. Calculate Pairwise Multiple Comparisons of Mean Rank Sums. Package \u2018pmcmr'. R package version, 1(0)2018","DOI":"10.32614\/CRAN.package.PMCMRplus"},{"key":"B38","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1088\/1741-2560\/1\/3\/002","article-title":"Motor imagery classification by means of source analysis for brain-computer interface applications","volume":"1","author":"Qin","year":"2004","journal-title":"J. Neural Eng"},{"key":"B39","unstructured":"The R Stats Package. R Foundation for Statistical Computing, Vienna, Austria2019"},{"journal-title":"RStudio: Integrated Development Environment for R","year":"2020","key":"B40"},{"key":"B41","doi-asserted-by":"publisher","first-page":"5283","DOI":"10.3390\/s20185283","article-title":"Identification of motor and mental imagery EEG in two and multiclass subject-dependent tasks using successive decomposition index","volume":"20","author":"Sadiq","year":"2020","journal-title":"Sensors"},{"key":"B42","doi-asserted-by":"publisher","first-page":"328","DOI":"10.3389\/fnhum.2014.00328","article-title":"Mental representation and motor imagery training","volume":"8","author":"Schack","year":"2014","journal-title":"Front. Hum. Neurosci"},{"key":"B43","doi-asserted-by":"publisher","first-page":"514","DOI":"10.1016\/S0140-6736(14)60042-8","article-title":"Diagnostic precision of pet imaging and functional MRI in disorders of consciousness: a clinical validation study","volume":"384","author":"Stender","year":"2014","journal-title":"Lancet"},{"key":"B44","doi-asserted-by":"publisher","first-page":"016004","DOI":"10.1088\/1741-2552\/abca16","article-title":"Motor imagery recognition with automatic EEG channel selection and deep learning","volume":"18","author":"Zhang","year":"2021","journal-title":"J. Neural Eng"}],"container-title":["Frontiers in Computational Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2023.1142948\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T05:53:52Z","timestamp":1729317232000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2023.1142948\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,26]]},"references-count":44,"alternative-id":["10.3389\/fncom.2023.1142948"],"URL":"https:\/\/doi.org\/10.3389\/fncom.2023.1142948","relation":{},"ISSN":["1662-5188"],"issn-type":[{"type":"electronic","value":"1662-5188"}],"subject":[],"published":{"date-parts":[[2023,4,26]]},"article-number":"1142948"}}