{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T18:54:27Z","timestamp":1785524067490,"version":"3.56.0"},"reference-count":49,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T00:00:00Z","timestamp":1785456000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study explores the potential of artificial intelligence (AI) using a hybrid deep learning Convolutional Neural Network\u2013Long Short-Term Memory (CNN-LSTM) framework, for EEG-based classification and analysis of Dravet Syndrome (DS).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Method<\/jats:title>\n                    <jats:p>The study cohort comprised nine pediatric patients with DS, confirmed through either a heterozygous pathogenic mutation in the SCN1A gene or a clinical diagnosis consistent with established diagnostic criteria. In addition, EEG recordings from age-matched healthy control subjects and pediatric patients with non-Dravet epilepsy (\u201cabnormal\u201d EEG) were included. Data on demographic information, seizure characteristics, developmental skills, cognitive functions, and genetic results were gathered from patient records. EEG recordings were analyzed using a subject-independent leave-one-subject-out validation strategy, spatial and temporal features by employing this model on preprocessed EEG data, effectively differentiating DS patients from Abnormal cases and healthy controls.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Result<\/jats:title>\n                    <jats:p>Among the evaluated CNN-LSTM models, the pre-trained architecture achieved superior performance with improved stability across most subjects, with an overall accuracy of 85%, balanced accuracy of 85%, a macro-averaged F1-score of 0.85, and a macro-averaged ROC\u2013AUC of 0.87, demonstrating stable performance for multi-class EEG classification of DS, Abnormal, and control subjects. The non-pretrained model showed reduced sensitivity and increased inter-class confusion, particularly for DS and Abnormal classes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study demonstrates that a pre-trained CNN-LSTM framework can support automated EEG-based classification of DS-related patterns as a proof-of-concept methodological approach, even in the context of limited subject availability. EEG-specific pretraining improves classification consistency and feature separability compared with training from scratch, highlighting the value of representation learning for rare epilepsy syndromes. Larger multi-center datasets and prospective validation will be required to assess robustness, generalizability, and clinical utility.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0352991","type":"journal-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T17:32:17Z","timestamp":1785519137000},"page":"e0352991","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning architectures for EEG-based classification of Dravet syndrome: A comparative study of pre-trained and non-pretrained hybrid CNN-LSTM models"],"prefix":"10.1371","volume":"21","author":[{"given":"Sikandar","family":"Hussain","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9984-3889","authenticated-orcid":true,"given":"Soyiba","family":"Jawed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Mir","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mona","family":"Ibrahim Ali","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raidah","family":"Al-Baradie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Norah","family":"Alaqili","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eman Mohammed","family":"Nassim Ali","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shahid","family":"Bashir","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,7,31]]},"reference":[{"key":"pone.0352991.ref001","unstructured":"Epileptic Syndromes in Infancy, Childhood and Adolescence - 6th ed. [cited 10 Sep 2025]. Available from: https:\/\/www.ilae.org\/education\/books-on-epilepsy\/epileptic-syndromes-in-infancy-childhood-and-adolescence-6th-ed"},{"key":"pone.0352991.ref002","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1111\/j.1528-1167.2011.02994.x","article-title":"The core Dravet syndrome phenotype","author":"C Dravet","year":"2011","journal-title":"Epilepsia"},{"key":"pone.0352991.ref003","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1111\/j.1528-1167.2011.03001.x","article-title":"Dravet syndrome: the long-term outcome","author":"P Genton","year":"2011","journal-title":"Epilepsia"},{"key":"pone.0352991.ref004","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1016\/j.pediatrneurol.2017.01.025","article-title":"Optimizing the Diagnosis and Management of Dravet Syndrome: Recommendations From a North American Consensus Panel","volume":"68","author":"EC Wirrell","year":"2017","journal-title":"Pediatr Neurol"},{"key":"pone.0352991.ref005","unstructured":"Promising Genetic Engineering Therapies for Dravet Syndrome - NHSJS. [cited 13 Sep 2025]. Available from: https:\/\/nhsjs.com\/2025\/promising-genetic-engineering-therapies-for-dravet-syndrome\/"},{"key":"pone.0352991.ref006","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/B978-0-12-802002-9.00004-2","article-title":"Dravet Syndrome: A Sodium Channel Interneuronopathy.","volume-title":"Ion Channels in Health and Disease","author":"WA. Catterall","year":"2016"},{"issue":"3","key":"pone.0352991.ref007","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1136\/jmg.2008.062323","article-title":"Spectrum of SCN1A gene mutations associated with Dravet syndrome: analysis of 333 patients","volume":"46","author":"C Depienne","year":"2009","journal-title":"J Med Genet"},{"key":"pone.0352991.ref008","doi-asserted-by":"crossref","first-page":"505","DOI":"10.3389\/fneur.2019.00505","article-title":"The clinical and genetic features of co-occurring epilepsy and autism spectrum disorder in Chinese children","volume":"10","author":"S Long","year":"2019","journal-title":"Front Neurol"},{"key":"pone.0352991.ref009","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1109\/TNSRE.2024.3351694","article-title":"Deep learning-based assessment model for real-time identification of visual learners using raw EEG","volume":"32","author":"S Jawed","year":"2024","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"issue":"5","key":"pone.0352991.ref010","doi-asserted-by":"crossref","first-page":"051001","DOI":"10.1088\/1741-2552\/ab260c","article-title":"Deep learning-based electroencephalography analysis: a systematic review","volume":"16","author":"Y Roy","year":"2019","journal-title":"J Neural Eng"},{"key":"pone.0352991.ref011","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1016\/j.compbiomed.2017.09.017","article-title":"Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals","volume":"100","author":"UR Acharya","year":"2018","journal-title":"Comput Biol Med"},{"key":"pone.0352991.ref012","doi-asserted-by":"crossref","first-page":"107041","DOI":"10.1016\/j.eplepsyres.2022.107041","article-title":"Dravet syndrome: Advances in etiology, clinical presentation, and treatment","volume":"188","author":"Z He","year":"2022","journal-title":"Epilepsy Res"},{"key":"pone.0352991.ref013","doi-asserted-by":"crossref","unstructured":"Khare P, Raja R, Jain A. Robust EEG Classification Using Enhanced Ensemble Methods for Seizure and Rhythmic Pattern Detection. 2025 International Conference on Networks and Cryptology (NETCRYPT). 2025. pp. 1169\u20131174. https:\/\/doi.org\/10.1109\/NETCRYPT65877.2025.11102578","DOI":"10.1109\/NETCRYPT65877.2025.11102578"},{"key":"pone.0352991.ref014","unstructured":"The ten-twenty electrode system of the International Federation | CiNii Research. [cited 11 Sep 2025]. Available from: https:\/\/cir.nii.ac.jp\/crid\/1571980075616656256"},{"issue":"7","key":"pone.0352991.ref015","doi-asserted-by":"crossref","first-page":"3033","DOI":"10.1109\/TCYB.2019.2905157","article-title":"Making sense of spatio-temporal preserving representations for EEG-based human intention recognition","volume":"50","author":"D Zhang","year":"2020","journal-title":"IEEE Trans Cybern"},{"key":"pone.0352991.ref016","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Advances in Neural Information Processing Systems","author":"A Paszke","year":"2019"},{"key":"pone.0352991.ref017","unstructured":"Chollet F. Keras. GitHub. 2015. Available from: https:\/\/github.com\/fchollet\/keras"},{"key":"pone.0352991.ref018","volume-title":"Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: concepts, tools, and techniques to build intelligent systems","author":"A G\u00e9ron","year":"2019","edition":"2"},{"key":"pone.0352991.ref019","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"N Srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"pone.0352991.ref020","article-title":"Adam: A Method for Stochastic Optimization","author":"DP Kingma","year":"2017","journal-title":"arXiv"},{"key":"pone.0352991.ref021","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1007\/3-540-49430-8_3","article-title":"Early Stopping - But When?","volume-title":"Neural Networks: Tricks of the Trade","author":"L. Prechelt","year":"1998"},{"key":"pone.0352991.ref022","doi-asserted-by":"crossref","first-page":"464","DOI":"10.1109\/WACV.2017.58","article-title":"Cyclical Learning Rates for Training Neural Networks","volume-title":"2017 IEEE Winter Conference on Applications of Computer Vision (WACV)","author":"LN Smith","year":"2017"},{"issue":"2","key":"pone.0352991.ref023","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1002\/cns3.20061","article-title":"EEG band power and phase\u2010amplitude coupling in patients with Dravet syndrome","volume":"2","author":"JC Hall","year":"2024","journal-title":"Ann Child Neurol Soc"},{"issue":"2","key":"pone.0352991.ref024","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1002\/cns3.20061","article-title":"EEG band power and phase\u2010amplitude coupling in patients with Dravet syndrome","volume":"2","author":"JC Hall","year":"2024","journal-title":"Ann Child Neurol Soc"},{"key":"pone.0352991.ref025","doi-asserted-by":"crossref","unstructured":"Banville H, Albuquerque I, Hyv\u00e4rinen A, Moffat G, Engemann D-A, Gramfort A. Self-Supervised Representation Learning from Electroencephalography Signals. 2019 IEEE 29th International Workshop on Machine Learning for Signal Processing (MLSP). 2019. pp. 1\u20136. https:\/\/doi.org\/10.1109\/MLSP.2019.8918693","DOI":"10.1109\/MLSP.2019.8918693"},{"key":"pone.0352991.ref026","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1109\/PDP50117.2020.00033","article-title":"Multi-level Binarized LSTM in EEG Classification for Wearable Devices","volume-title":"2020 28th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)","author":"N Nazari","year":"2020"},{"key":"pone.0352991.ref027","doi-asserted-by":"crossref","first-page":"432","DOI":"10.1016\/j.semradonc.2022.06.012","article-title":"Regulatory aspects of the use of artificial intelligence medical software","volume":"32","author":"F Zanca","year":"2022","journal-title":"Semin Radiat Oncol"},{"key":"pone.0352991.ref028","unstructured":"Dravet syndrome: Early electroclinical findings and long\u2010term outcome in adolescents and adults - Darra - 2019 - Epilepsia - Wiley Online Library. 2019. [cited 12 Sep 2025]. Available from: https:\/\/onlinelibrary.wiley.com\/doi\/full\/10.1111\/epi.16297"},{"key":"pone.0352991.ref029","volume-title":"Brain Informatics: 17th International Conference, BI 2024, Bangkok, Thailand, December 13\u201315, 2024, Proceedings, Part I","author":"S Itthipuripat","year":"2025"},{"key":"pone.0352991.ref030","doi-asserted-by":"crossref","first-page":"110327","DOI":"10.1016\/j.yebeh.2025.110327","article-title":"Unlocking new frontiers in epilepsy through AI: From seizure prediction to personalized medicine","volume":"166","author":"MA AbuAlrob","year":"2025","journal-title":"Epilepsy Behav"},{"key":"pone.0352991.ref031","unstructured":"Revolutionizing healthcare: the role of artificial intelligence in clinical practice | BMC Medical Education. [cited 12 Sep 2025]. Available from: https:\/\/link.springer.com\/article\/10.1186\/s12909-023-04698-z"},{"key":"pone.0352991.ref032","doi-asserted-by":"crossref","unstructured":"A Comprehensive Review of Emerging Trends and Innovative Therapies in Epilepsy Management. [cited 12 Sep 2025]. Available from: https:\/\/www.mdpi.com\/2076-3425\/13\/9\/1305","DOI":"10.3390\/brainsci13091305"},{"issue":"11","key":"pone.0352991.ref033","doi-asserted-by":"crossref","first-page":"5391","DOI":"10.1002\/hbm.23730","article-title":"Deep learning with convolutional neural networks for EEG decoding and visualization","volume":"38","author":"RT Schirrmeister","year":"2017","journal-title":"Hum Brain Mapp"},{"issue":"5","key":"pone.0352991.ref034","doi-asserted-by":"crossref","first-page":"056013","DOI":"10.1088\/1741-2552\/aace8c","article-title":"EEGNet: a compact convolutional neural network for EEG-based brain-computer interfaces","volume":"15","author":"VJ Lawhern","year":"2018","journal-title":"J Neural Eng"},{"key":"pone.0352991.ref035","unstructured":"Deep learning-based electroencephalography analysis: a systematic review - IOPscience. [cited 27 Jan 2026]. Available from: https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ab260c\/meta"},{"key":"pone.0352991.ref036","doi-asserted-by":"crossref","unstructured":"van de Velden D. Neural network integration from multimodal imaging in epilepsy and healthy controls. doctoralThesis. 2024. https:\/\/doi.org\/10.53846\/goediss-10280","DOI":"10.53846\/goediss-10280"},{"key":"pone.0352991.ref037","unstructured":"Multimodal Medical Image Fusion: Techniques, Databases, Evaluation Metrics, and Clinical Applications -A Comprehensive Review. [cited 27 Jan 2026]. Available from: https:\/\/openneuroimagingjournal.com\/VOLUME\/18\/ELOCATOR\/e18744400417835"},{"key":"pone.0352991.ref038","doi-asserted-by":"crossref","first-page":"1625731","DOI":"10.3389\/frobt.2025.1625731","article-title":"EEG-CLIP: learning EEG representations from natural language descriptions","volume":"12","author":"T Camaret Ndir","year":"2025","journal-title":"Front Robot AI"},{"key":"pone.0352991.ref039","doi-asserted-by":"crossref","unstructured":"Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D. Grad-CAM: Visual Explanations From Deep Networks via Gradient-Based Localization. 2017. pp. 618\u201326. Available from: https:\/\/openaccess.thecvf.com\/content_iccv_2017\/html\/Selvaraju_Grad-CAM_Visual_Explanations_ICCV_2017_paper.html","DOI":"10.1109\/ICCV.2017.74"},{"key":"pone.0352991.ref040","doi-asserted-by":"crossref","DOI":"10.1016\/j.pediatrneurol.2017.01.025","article-title":"Optimizing the Diagnosis and Management of Dravet Syndrome: recommendations from a North American Consensus Panel","volume":"68","author":"EC Wirrell","year":"2017","journal-title":"Pediatr Neurol"},{"issue":"04","key":"pone.0352991.ref041","doi-asserted-by":"crossref","first-page":"1850051","DOI":"10.1142\/S0218348X18500512","article-title":"Age-based variations of fractal structure of eeg signal in patients with epilepsy","volume":"26","author":"H Namazi","year":"2018","journal-title":"Fractals"},{"key":"pone.0352991.ref042","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1016\/j.neuroimage.2018.03.032","article-title":"A subject-transfer framework for obviating inter- and intra-subject variability in EEG-based drowsiness detection","volume":"174","author":"C-S Wei","year":"2018","journal-title":"Neuroimage"},{"issue":"7","key":"pone.0352991.ref043","doi-asserted-by":"crossref","first-page":"979","DOI":"10.1111\/epi.12652","article-title":"Dravet syndrome--from epileptic encephalopathy to channelopathy","volume":"55","author":"A Brunklaus","year":"2014","journal-title":"Epilepsia"},{"key":"pone.0352991.ref044","doi-asserted-by":"crossref","unstructured":"Application of Machine Learning in Epileptic Seizure Detection. [cited 27 Jan 2026]. Available from: https:\/\/www.mdpi.com\/2075-4418\/12\/11\/2879","DOI":"10.3390\/diagnostics12112879"},{"key":"pone.0352991.ref045","volume-title":"Transfusion: Understanding Transfer Learning for Medical Imaging. Advances in Neural Information Processing Systems","author":"M Raghu","year":"2019"},{"key":"pone.0352991.ref046","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1016\/j.media.2019.03.009","article-title":"Not-so-supervised: A survey of semi-supervised, multi-instance, and transfer learning in medical image analysis","volume":"54","author":"V Cheplygina","year":"2019","journal-title":"Med Image Anal"},{"key":"pone.0352991.ref047","unstructured":"Deep learning-based electroencephalography analysis: a systematic review - IOPscience. [cited 27 Jan 2026]. Available from: https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ab260c\/meta"},{"issue":"3","key":"pone.0352991.ref048","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1016\/j.psychres.2007.05.006","article-title":"Blinded, multi-center validation of EEG and rating scales in identifying ADHD within a clinical sample","volume":"159","author":"SM Snyder","year":"2008","journal-title":"Psychiatry Res"},{"key":"pone.0352991.ref049","doi-asserted-by":"crossref","unstructured":"Mrazek V, Jawed S, Arif M, Malik AS. Effective EEG feature selection for interpretable MDD (major depressive disorder) classification. In: Proceedings of the Genetic and Evolutionary Computation Conference. 2023. pp. 1427\u201335.","DOI":"10.1145\/3583131.3590398"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0352991","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T17:32:24Z","timestamp":1785519144000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0352991"}},"subtitle":[],"editor":[{"given":"Gennady S.","family":"Cymbalyuk","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,7,31]]},"references-count":49,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7,31]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0352991","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,31]]}}}