{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T15:54:26Z","timestamp":1778169266754,"version":"3.51.4"},"reference-count":39,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2024,1,5]],"date-time":"2024-01-05T00:00:00Z","timestamp":1704412800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004329","name":"Javna Agencija za Raziskovalno Dejavnost RS","doi-asserted-by":"publisher","award":["P3-0293"],"award-info":[{"award-number":["P3-0293"]}],"id":[{"id":"10.13039\/501100004329","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004329","name":"Javna Agencija za Raziskovalno Dejavnost RS","doi-asserted-by":"publisher","award":["P5-0110"],"award-info":[{"award-number":["P5-0110"]}],"id":[{"id":"10.13039\/501100004329","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004329","name":"Javna Agencija za Raziskovalno Dejavnost RS","doi-asserted-by":"publisher","award":["P3-0338"],"award-info":[{"award-number":["P3-0338"]}],"id":[{"id":"10.13039\/501100004329","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The fusion of electroencephalography (EEG) with machine learning is transforming rehabilitation. Our study introduces a neural network model proficient in distinguishing pre- and post-rehabilitation states in patients with Broca\u2019s aphasia, based on brain connectivity metrics derived from EEG recordings during verbal and spatial working memory tasks. The Granger causality (GC), phase-locking value (PLV), weighted phase-lag index (wPLI), mutual information (MI), and complex Pearson correlation coefficient (CPCC) across the delta, theta, and low- and high-gamma bands were used (excluding GC, which spanned the entire frequency spectrum). Across eight participants, employing leave-one-out validation for each, we evaluated the intersubject prediction accuracy across all connectivity methods and frequency bands. GC, MI theta, and PLV low-gamma emerged as the top performers, achieving 89.4%, 85.8%, and 82.7% accuracy in classifying verbal working memory task data. Intriguingly, measures designed to eliminate volume conduction exhibited the poorest performance in predicting rehabilitation-induced brain changes. This observation, coupled with variations in model performance across frequency bands, implies that different connectivity measures capture distinct brain processes involved in rehabilitation. The results of this paper contribute to current knowledge by presenting a clear strategy of utilizing limited data to achieve valid and meaningful results of machine learning on post-stroke rehabilitation EEG data, and they show that the differences in classification accuracy likely reflect distinct brain processes underlying rehabilitation after stroke.<\/jats:p>","DOI":"10.3390\/s24020329","type":"journal-article","created":{"date-parts":[[2024,1,5]],"date-time":"2024-01-05T07:38:31Z","timestamp":1704440311000},"page":"329","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Integrating EEG and Machine Learning to Analyze Brain Changes during the Rehabilitation of Broca\u2019s Aphasia"],"prefix":"10.3390","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4977-8702","authenticated-orcid":false,"given":"Vanesa","family":"Mo\u010dilnik","sequence":"first","affiliation":[{"name":"Faculty of Medicine, University of Ljubljana, 1000 Ljubljana, Slovenia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Veronika","family":"Rutar Gori\u0161ek","sequence":"additional","affiliation":[{"name":"University Medical Centre Ljubljana, 1000 Ljubljana, Slovenia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1633-5983","authenticated-orcid":false,"given":"Jakob","family":"Sajovic","sequence":"additional","affiliation":[{"name":"Faculty of Medicine, University of Ljubljana, 1000 Ljubljana, Slovenia"},{"name":"University Medical Centre Ljubljana, 1000 Ljubljana, Slovenia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Janja","family":"Pretnar Oblak","sequence":"additional","affiliation":[{"name":"Faculty of Medicine, University of Ljubljana, 1000 Ljubljana, Slovenia"},{"name":"University Medical Centre Ljubljana, 1000 Ljubljana, Slovenia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9254-4931","authenticated-orcid":false,"given":"Gorazd","family":"Dreven\u0161ek","sequence":"additional","affiliation":[{"name":"Faculty of Medicine, University of Ljubljana, 1000 Ljubljana, Slovenia"},{"name":"Faculty of Mathematics, Natural Sciences and Information Technologies, University of Primorska, 6000 Koper, Slovenia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2939-6945","authenticated-orcid":false,"given":"Peter","family":"Rogelj","sequence":"additional","affiliation":[{"name":"Faculty of Mathematics, Natural Sciences and Information Technologies, University of Primorska, 6000 Koper, Slovenia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2024,1,5]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1177\/17474930211065917","article-title":"World Stroke Organization (WSO): Global Stroke Fact Sheet 2022","volume":"17","author":"Feigin","year":"2022","journal-title":"Int. J. Stroke"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1161\/STROKEAHA.118.022913","article-title":"Long-Term Survival and Function After Stroke","volume":"50","author":"Norrving","year":"2019","journal-title":"Stroke"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2538","DOI":"10.1161\/STROKEAHA.121.038155","article-title":"Long-Term Survival, Stroke Recurrence, and Life Expectancy After an Acute Stroke in Australia and New Zealand From 2008\u20132017: A Population-Wide Cohort Study","volume":"53","author":"Peng","year":"2022","journal-title":"Stroke"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2871","DOI":"10.1073\/pnas.1414491112","article-title":"Redefining the role of Broca\u2019s area in speech","volume":"112","author":"Flinker","year":"2015","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_5","unstructured":"Acharya, A.B., and Wroten, M. (2023). StatPearls, StatPearls Publishing."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"295","DOI":"10.3389\/fneur.2019.00295","article-title":"Neuroplasticity of Language Networks in Aphasia: Advances, Updates, and Future Challenges","volume":"10","author":"Kiran","year":"2019","journal-title":"Front. Neurol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1021","DOI":"10.1093\/brain\/awac129","article-title":"Recovery from aphasia in the first year after stroke","volume":"146","author":"Wilson","year":"2022","journal-title":"Brain"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1080\/02687038.2010.530672","article-title":"Recent developments in functional and structural imaging of aphasia recovery after stroke","volume":"25","author":"Meinzer","year":"2011","journal-title":"Aphasiology"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1038\/s41582-019-0282-1","article-title":"The neural and neurocomputational bases of recovery from post-stroke aphasia","volume":"16","author":"Stefaniak","year":"2020","journal-title":"Nat. Rev. Neurol."},{"key":"ref_10","first-page":"67","article-title":"Translating concepts of neural repair after stroke: Structural and functional targets for recovery","volume":"38","author":"Regenhardt","year":"2020","journal-title":"Restor. Neurol. Neurosci."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Cerasa, A., Tartarisco, G., Bruschetta, R., Ciancarelli, I., Morone, G., Calabr\u00f2, R.S., Pioggia, G., Tonin, P., and Iosa, M. (2022). Predicting Outcome in Patients with Brain Injury: Differences between Machine Learning versus Conventional Statistics. Biomedicines, 10.","DOI":"10.3390\/biomedicines10092267"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.neuroimage.2017.11.056","article-title":"Neuroimaging of stroke recovery from aphasia \u2013 Insights into plasticity of the human language network","volume":"190","author":"Hartwigsen","year":"2019","journal-title":"NeuroImage"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/j.cortex.2022.07.001","article-title":"Aberrant beta-band brain connectivity predicts speech motor planning deficits in post-stroke aphasia","volume":"155","author":"Sarmukadam","year":"2022","journal-title":"Cortex"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1098","DOI":"10.1016\/j.clinph.2019.04.004","article-title":"Brain networks and their relevance for stroke rehabilitation","volume":"130","author":"Guggisberg","year":"2019","journal-title":"Clin. Neurophysiol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"844","DOI":"10.1093\/brain\/awaa023","article-title":"Dynamics of language reorganization after left temporo-parietal and frontal stroke","volume":"143","author":"Stockert","year":"2020","journal-title":"Brain A J. Neurol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1177\/15459683221078294","article-title":"The Prognostic Utility of Electroencephalography in Stroke Recovery: A Systematic Review and Meta-Analysis","volume":"36","author":"Vatinno","year":"2022","journal-title":"Neurorehabilit. Neural Repair"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3390\/biomed3010001","article-title":"Machine Learning Techniques for the Prediction of Functional Outcomes in the Rehabilitation of Post-Stroke Patients: A Scoping Review","volume":"3","author":"Kokkotis","year":"2022","journal-title":"BioMed"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Lassi, M., Bandini, A., Spina, V., Azzollini, V., Dalise, S., Mazzoni, A., Chisari, C., and Micera, S. (2023, January 24\u201327). Classification of Upper Limb Impairment in Acute Stroke Patients Using Resting-State EEG Markers and Machine Learning. Proceedings of the 2023 11th International IEEE\/EMBS Conference on Neural Engineering (NER), Baltimore, MD, USA.","DOI":"10.1109\/NER52421.2023.10123720"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zhang, J., Huang, Y., Ye, F., Yang, B., Li, Z., and Hu, X. (2022). Evaluation of Post-Stroke Impairment in Fine Tactile Sensation by Electroencephalography (EEG)-Based Machine Learning. Appl. Sci., 12.","DOI":"10.3390\/app12094796"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"258","DOI":"10.1016\/j.cortex.2023.05.015","article-title":"Neural oscillations reveal disrupted functional connectivity associated with impaired speech auditory feedback control in post-stroke aphasia","volume":"166","author":"Sarmukadam","year":"2023","journal-title":"Cortex"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1016\/j.bandl.2016.08.003","article-title":"Beyond Aphasia: Altered EEG Connectivity in Broca\u2019s Patients during Working Memory Task","volume":"163","author":"Manouilidou","year":"2016","journal-title":"Brain Lang."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Clercq, P.D., Kries, J., Mehraram, R., Vanthornhout, J., Francart, T., and Vandermosten, M. (2023). Detecting post-stroke aphasia using EEG-based neural envelope tracking of natural speech. medRxiv.","DOI":"10.1101\/2023.03.14.23287194"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2050067","DOI":"10.1142\/S0129065720500677","article-title":"Electroencephalography-Derived Prognosis of Functional Recovery in Acute Stroke Through Machine Learning Approaches","volume":"30","author":"Chiarelli","year":"2020","journal-title":"Int. J. Neural Syst."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1044\/2018_AJSLP-16-0180","article-title":"Considerations for the Use of Neuroimaging Technologies for Predicting Recovery of Speech and Language in Aphasia","volume":"27","author":"Shuster","year":"2018","journal-title":"Am. J. Speech-Lang. Pathol."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"4247","DOI":"10.1007\/s10072-023-06981-9","article-title":"Quantitative measures of the resting EEG in stroke: A systematic review on clinical correlation and prognostic value","volume":"44","author":"Lanzone","year":"2023","journal-title":"Neurol. Sci."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1016\/j.cortex.2019.12.017","article-title":"Alterations to dual stream connectivity predicts response to aphasia therapy following stroke","volume":"125","author":"Iyer","year":"2020","journal-title":"Cortex"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"3048","DOI":"10.1093\/brain\/awv200","article-title":"Coherent neural oscillations predict future motor and language improvement after stroke","volume":"138","author":"Nicolo","year":"2015","journal-title":"Brain"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1016\/S0093-934X(02)00004-4","article-title":"Prognostic relevance of quantitative topographical EEG in patients with poststroke aphasia","volume":"82","author":"Szelies","year":"2002","journal-title":"Brain Lang."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1126\/science.153.3736.652","article-title":"High-Speed Scanning in Human Memory","volume":"153","author":"Sternberg","year":"1966","journal-title":"Science"},{"key":"ref_30","doi-asserted-by":"crossref","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":"ref_31","unstructured":"Touretzky, D., Mozer, M., and Hasselmo, M. (1995). Advances in Neural Information Processing Systems, MIT Press."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1162\/089976699300016719","article-title":"Independent Component Analysis Using an Extended Infomax Algorithm for Mixed Subgaussian and Supergaussian Sources","volume":"11","author":"Lee","year":"1999","journal-title":"Neural Comput."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1007\/s10548-006-0011-0","article-title":"Spherical Splines and Average Referencing in Scalp Electroencephalography","volume":"19","author":"Ferree","year":"2006","journal-title":"Brain Topogr."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"175","DOI":"10.3389\/fnsys.2015.00175","article-title":"A Tutorial Review of Functional Connectivity Analysis Methods and Their Interpretational Pitfalls","volume":"9","author":"Bastos","year":"2016","journal-title":"Front. Syst. Neurosci."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"\u0160verko, Z., Vranki\u0107, M., Vlahini\u0107, S., and Rogelj, P. (2022). Complex Pearson Correlation Coefficient for EEG Connectivity Analysis. Sensors, 22.","DOI":"10.3390\/s22041477"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.patrec.2014.02.013","article-title":"t-Test feature selection approach based on term frequency for text categorization","volume":"45","author":"Wang","year":"2014","journal-title":"Pattern Recognit. Lett."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1177\/1545968316680490","article-title":"A Rehabilitation-Internet-of-Things in the Home to Augment Motor Skills and Exercise Training","volume":"31","author":"Dobkin","year":"2017","journal-title":"Neurorehabilit. Neural Repair"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1606","DOI":"10.1161\/STROKEAHA.121.036749","article-title":"Multimodal Neural and Behavioral Data Predict Response to Rehabilitation in Chronic Poststroke Aphasia","volume":"53","author":"Billot","year":"2022","journal-title":"Stroke"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1249","DOI":"10.1016\/j.neubiorev.2020.09.008","article-title":"What has social neuroscience learned from hyperscanning studies of spoken communication? A systematic review","volume":"132","author":"Kelsen","year":"2022","journal-title":"Neurosci. Biobehav. Rev."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/2\/329\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T13:40:45Z","timestamp":1760103645000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/2\/329"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,5]]},"references-count":39,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,1]]}},"alternative-id":["s24020329"],"URL":"https:\/\/doi.org\/10.3390\/s24020329","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,5]]}}}