{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T13:09:01Z","timestamp":1779455341480,"version":"3.53.1"},"reference-count":36,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T00:00:00Z","timestamp":1779408000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Budget MIUR\u2014Dipartimenti di Eccellenza","award":["H97G23000100001"],"award-info":[{"award-number":["H97G23000100001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Bioengineering"],"abstract":"<jats:p>Traumatic brain injury (TBI) is one of the leading causes of acquired epilepsy, with a significant proportion of patients developing post-traumatic epilepsy (PTE) even months or years after the initial injury. The identification of reliable imaging biomarkers able to predict epileptogenesis remains a major clinical challenge. In recent years, diffusion-weighted imaging (DWI) and structural connectome analysis have emerged as promising tools to investigate brain network alterations associated with late seizure development. Machine learning approaches may further support the detection of predictive patterns in complex neuroimaging data. The goal of this study is to perform a binary classification between seizure-free and late seizure-affected patients following TBI, with a specific focus on the identification of the anatomical regions potentially connected with late seizure development. A dataset of 59 diffusion weighted images (DWI) scans from the EpiBioS4Rx project, including 42 seizure-free and 17 late seizure-affected TBI patients, was analyzed. A Random Forest classification algorithm was applied, incorporating network feature importance based on the Gini index to investigate model\u2019s decisions and allow a clinical interpretation. The model reported a 69% \u00b1 0.03 accuracy for discrimination and a 73% AUC \u00b1 0.05. Despite the limited and imbalanced nature of the dataset, and the fact that the performance does not significantly exceed chance once all data-dependent steps are taken into account, our approach allows us to achieve accurate classification results compared to the literature and to identify brain regions potentially associated with epileptogenesis.<\/jats:p>","DOI":"10.3390\/bioengineering13060598","type":"journal-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T12:14:52Z","timestamp":1779452092000},"page":"598","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Brain Connectivity Approach to Detect Diffusion-Weighted Imaging Changes in Post-Traumatic Epilepsy"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-9408-7336","authenticated-orcid":false,"given":"Emanuele C.","family":"Amato","sequence":"first","affiliation":[{"name":"Dipartimento Interateneo di Fisica, Universit\u00e0 degli Studi di Bari Aldo Moro, 70125 Bari, Italy"},{"name":"Istituto Nazionale di Fisica Nucleare, Sezione di Bari, 70125 Bari, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claudia","family":"Giliberti","sequence":"additional","affiliation":[{"name":"Dipartimento Interateneo di Fisica, Universit\u00e0 degli Studi di Bari Aldo Moro, 70125 Bari, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0211-0783","authenticated-orcid":false,"given":"Nicola","family":"Amoroso","sequence":"additional","affiliation":[{"name":"Istituto Nazionale di Fisica Nucleare, Sezione di Bari, 70125 Bari, Italy"},{"name":"Dipartimento di Scienze del Farmaco, Universit\u00e0 degli Studi di Bari Aldo Moro, 70125 Bari, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6714-9780","authenticated-orcid":false,"given":"Kseniia","family":"Kriukova","sequence":"additional","affiliation":[{"name":"Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alfonso","family":"Monaco","sequence":"additional","affiliation":[{"name":"Dipartimento Interateneo di Fisica, Universit\u00e0 degli Studi di Bari Aldo Moro, 70125 Bari, Italy"},{"name":"Istituto Nazionale di Fisica Nucleare, Sezione di Bari, 70125 Bari, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8407-9032","authenticated-orcid":false,"given":"Ester","family":"Pantaleo","sequence":"additional","affiliation":[{"name":"Dipartimento Interateneo di Fisica, Universit\u00e0 degli Studi di Bari Aldo Moro, 70125 Bari, Italy"},{"name":"Istituto Nazionale di Fisica Nucleare, Sezione di Bari, 70125 Bari, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4156-5377","authenticated-orcid":false,"given":"Tommaso","family":"Maggipinto","sequence":"additional","affiliation":[{"name":"Dipartimento Interateneo di Fisica, Universit\u00e0 degli Studi di Bari Aldo Moro, 70125 Bari, Italy"},{"name":"Istituto Nazionale di Fisica Nucleare, Sezione di Bari, 70125 Bari, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Loredana","family":"Bellantuono","sequence":"additional","affiliation":[{"name":"Istituto Nazionale di Fisica Nucleare, Sezione di Bari, 70125 Bari, Italy"},{"name":"Dipartimento di Biomedicina Traslazionale e Neuroscienze, Universit\u00e0 degli Studi di Bari Aldo Moro, 70124 Bari, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1013-3793","authenticated-orcid":false,"given":"Antonio","family":"La Calamita","sequence":"additional","affiliation":[{"name":"Dipartimento Interateneo di Fisica, Universit\u00e0 degli Studi di Bari Aldo Moro, 70125 Bari, Italy"},{"name":"Istituto Nazionale di Fisica Nucleare, Sezione di Bari, 70125 Bari, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roberto","family":"Bellotti","sequence":"additional","affiliation":[{"name":"Dipartimento Interateneo di Fisica, Universit\u00e0 degli Studi di Bari Aldo Moro, 70125 Bari, Italy"},{"name":"Istituto Nazionale di Fisica Nucleare, Sezione di Bari, 70125 Bari, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul M.","family":"Vespa","sequence":"additional","affiliation":[{"name":"David Geffen School of Medicine at UCLA, Los Angeles, CA 90095, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6154-9262","authenticated-orcid":false,"given":"Dominique","family":"Duncan","sequence":"additional","affiliation":[{"name":"Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marianna","family":"La Rocca","sequence":"additional","affiliation":[{"name":"Dipartimento Interateneo di Fisica, Universit\u00e0 degli Studi di Bari Aldo Moro, 70125 Bari, Italy"},{"name":"Istituto Nazionale di Fisica Nucleare, Sezione di Bari, 70125 Bari, Italy"},{"name":"Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"341","DOI":"10.3233\/NRE-2007-22502","article-title":"The impact of traumatic brain injuries: A global perspective","volume":"22","author":"Hyder","year":"2007","journal-title":"NeuroRehabilitation"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Martins da Silva, A., Rocha Vaz, A., Ribeiro, I., Melo, A., Nune, B., and Correia, M. (1990). Controversies in posttraumatic epilepsy. Proceedings of the Neurosurgical Aspects of Epilepsy: Proceedings of the Fourth Advanced Seminar in Neurosurgical Research of the European Association of Neurosurgical Societies Bresseo di Teolo, Padova, 17\u201318 May 1989, Springer.","DOI":"10.1007\/978-3-7091-9104-0_9"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Pitk\u00e4nen, A., Kyyri\u00e4inen, J., Andrade, P., Pasanen, L., and Ndode-Ekane, X.E. (2017). Epilepsy after traumatic brain injury. Models of Seizures and Epilepsy, Elsevier.","DOI":"10.1016\/B978-0-12-804066-9.00046-8"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"527","DOI":"10.2217\/thy.10.57","article-title":"Post-traumatic epilepsy: An overview","volume":"7","author":"Verellen","year":"2010","journal-title":"Therapy"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"La Rocca, M., Garner, R., Amoroso, N., Lutkenhoff, E.S., Monti, M.M., Vespa, P., Toga, A.W., and Duncan, D. (2020). Multiplex networks to characterize seizure development in traumatic brain injury patients. Front. Neurosci., 14.","DOI":"10.3389\/fnins.2020.591662"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1016\/j.neuroimage.2012.10.066","article-title":"The structural, connectomic and network covariance of the human brain","volume":"66","author":"Irimia","year":"2013","journal-title":"Neuroimage"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.nbd.2018.05.026","article-title":"Big data sharing and analysis to advance research in post-traumatic epilepsy","volume":"123","author":"Duncan","year":"2019","journal-title":"Neurobiol. Dis."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1007\/s40766-025-00073-4","article-title":"Artificial intelligence in medical physics","volume":"48","author":"Amoroso","year":"2025","journal-title":"Riv. Nuovo C."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1111\/epi.18131","article-title":"Exploring multimodal biomarker candidates of post-traumatic epilepsy following moderate to severe traumatic brain injury: A systematic review and meta-analysis","volume":"66","author":"Bruckhaus","year":"2025","journal-title":"Epilepsia"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Akbar, M.N., La Rocca, M., Garner, R., Duncan, D., and Erdo\u011fmu\u015f, D. (2020). Prediction of epilepsy development in traumatic brain injury patients from diffusion weighted mri. Proceedings of the 13th ACM International Conference on Pervasive Technologies Related to Assistive Environments, Association for Computing Machinery.","DOI":"10.1145\/3389189.3397655"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Akbar, M.N., Ruf, S., La Rocca, M., Garner, R., Barisano, G., Cua, R., Vespa, P., Erdo\u011fmu\u015f, D., and Duncan, D. (2021). Lesion normalization and supervised learning in post-traumatic seizure classification with diffusion mri. Proceedings of the International Workshop on Computational Diffusion MRI, Springer.","DOI":"10.1101\/2021.08.06.21261733"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"107201","DOI":"10.1016\/j.eplepsyres.2023.107201","article-title":"Image data harmonization tools for the analysis of post-traumatic epilepsy development in preclinical multisite MRI studies","volume":"195","author":"Bhagavatula","year":"2023","journal-title":"Epilepsy Res."},{"key":"ref_13","first-page":"100066","article-title":"A rehabilitation design concept based on brain\u2013computer interface and McKibben artificial muscle","volume":"2","author":"Peng","year":"2026","journal-title":"Healthc. Rehabil."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1016\/j.nbd.2018.07.025","article-title":"The epilepsy bioinformatics study for anti-epileptogenic therapy (EpiBioS4Rx) clinical biomarker: Study design and protocol","volume":"123","author":"Vespa","year":"2019","journal-title":"Neurobiol. Dis."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"116137","DOI":"10.1016\/j.neuroimage.2019.116137","article-title":"MRtrix3: A fast, flexible and open software framework for medical image processing and visualisation","volume":"202","author":"Tournier","year":"2019","journal-title":"Neuroimage"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1016\/j.neuroimage.2014.07.061","article-title":"Multi-tissue constrained spherical deconvolution for improved analysis of multi-shell diffusion MRI data","volume":"103","author":"Jeurissen","year":"2014","journal-title":"NeuroImage"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1038\/nrn2575","article-title":"Complex brain networks: Graph theoretical analysis of structural and functional systems","volume":"10","author":"Bullmore","year":"2009","journal-title":"Nat. Rev. Neurosci."},{"key":"ref_18","unstructured":"Fornito, A., Zalesky, A., and Bullmore, E. (2016). Fundamentals of Brain Network Analysis, Academic Press."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Van Wijk, B.C., Stam, C.J., and Daffertshofer, A. (2010). Comparing brain networks of different size and connectivity density using graph theory. PLoS ONE, 5.","DOI":"10.1371\/journal.pone.0013701"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"101673","DOI":"10.1016\/j.nicl.2019.101673","article-title":"Graph theory analysis of DTI tractography in children with traumatic injury","volume":"21","author":"Watson","year":"2019","journal-title":"NeuroImage Clin."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"111403","DOI":"10.1016\/j.brainresbull.2025.111403","article-title":"Alterations of white matter functional networks in pediatric drug-resistant temporal lobe epilepsy: A graph theory analysis study","volume":"227","author":"Huang","year":"2025","journal-title":"Brain Res. Bull."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J. Artif. Intell. Res."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"402","DOI":"10.1016\/j.neuroimage.2012.12.066","article-title":"Estimating false positives and negatives in brain networks","volume":"70","year":"2013","journal-title":"Neuroimage"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Chikkerur, S., Cartwright, A.N., and Govindaraju, V. (2006). K-plet and coupled BFS: A graph based fingerprint representation and matching algorithm. Proceedings of the International Conference on Biometrics, Springer.","DOI":"10.1007\/11608288_42"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_26","first-page":"627","article-title":"Receiver operating characteristic (ROC) curve analysis for medical diagnostic test evaluation","volume":"4","year":"2013","journal-title":"Casp. J. Intern. Med."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Xia, M., Wang, J., and He, Y. (2013). BrainNet Viewer: A network visualization tool for human brain connectomics. PLoS ONE, 8.","DOI":"10.1371\/journal.pone.0068910"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"366","DOI":"10.1038\/nn.4240","article-title":"Confidence and certainty: Distinct probabilistic quantities for different goals","volume":"19","author":"Pouget","year":"2016","journal-title":"Nat. Neurosci."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/j.nbd.2018.05.014","article-title":"Early seizures and temporal lobe trauma predict post-traumatic epilepsy: A longitudinal study","volume":"123","author":"Tubi","year":"2019","journal-title":"Neurobiol. Dis."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"347","DOI":"10.3174\/ajnr.A7436","article-title":"Neuroanatomic markers of posttraumatic epilepsy based on mr imaging and machine learning","volume":"43","author":"Akrami","year":"2022","journal-title":"Am. J. Neuroradiol."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1222","DOI":"10.1111\/j.1528-1157.1999.tb00850.x","article-title":"Posttraumatic epilepsy risk factors: One-year prospective study after head injury","volume":"40","author":"Angeleri","year":"1999","journal-title":"Epilepsia"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"102386","DOI":"10.1016\/j.compmedimag.2024.102386","article-title":"Advancing post-traumatic seizure classification and biomarker identification: Information decomposition based multimodal fusion and explainable machine learning with missing neuroimaging data","volume":"115","author":"Akbar","year":"2024","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"482","DOI":"10.1111\/epi.18210","article-title":"Development of individualized risk assessment models for predicting post-traumatic epilepsy 1 and 2 years after moderate-to-severe traumatic brain injury: A traumatic brain injury model system study","volume":"66","author":"Awan","year":"2025","journal-title":"Epilepsia"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Amoroso, N., Quarto, S., La Rocca, M., Tangaro, S., Monaco, A., and Bellotti, R. (2023). An eXplainability Artificial Intelligence approach to brain connectivity in Alzheimer\u2019s disease. Front. Aging Neurosci., 15.","DOI":"10.3389\/fnagi.2023.1238065"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"106053","DOI":"10.1016\/j.nbd.2023.106053","article-title":"Functional connectivity alterations in traumatic brain injury patients with late seizures","volume":"179","author":"Barisano","year":"2023","journal-title":"Neurobiol. Dis."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Sibarov, D.A., Tsytsarev, V., Volnova, A., Vaganova, A.N., Alves, J., Rojas, L., Sanabria, P., Ignashchenkova, A., Savage, E.D., and Inyushin, M. (2023). Arc protein, a remnant of ancient retrovirus, forms virus-like particles, which are abundantly generated by neurons during epileptic seizures, and affects epileptic susceptibility in rodent models. Front. Neurol., 14.","DOI":"10.3389\/fneur.2023.1201104"}],"container-title":["Bioengineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5354\/13\/6\/598\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T12:45:29Z","timestamp":1779453929000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5354\/13\/6\/598"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,22]]},"references-count":36,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["bioengineering13060598"],"URL":"https:\/\/doi.org\/10.3390\/bioengineering13060598","relation":{},"ISSN":["2306-5354"],"issn-type":[{"value":"2306-5354","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,22]]}}}