{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:59:50Z","timestamp":1780639190081,"version":"3.54.1"},"reference-count":56,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T00:00:00Z","timestamp":1780617600000},"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. Neurosci."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Accurately predicting seizures remains challenging. With advances in smart medical technology, EEG-based monitoring has become essential. This study aims to improve prediction accuracy using a hybrid framework that models multiscale EEG characteristics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>EEG signals are decomposed into multiple sub-bands using the Discrete Wavelet Transform, and representative time-frequency and nonlinear features are extracted. These features are fed into a channel-centric model integrating depthwise separable convolution, self-attention, and an enhanced bidirectional long short-term memory network (DC-SA-EBiLSTM). The architecture integrates depthwise separable convolution for local spatial feature extraction, multi-head self-attention for global inter-channel dependencies, and an enhanced BiLSTM for channel-wise sequence modeling. The proposed method was evaluated on the CHB-MIT dataset using a 10-fold cross-validation protocol. An event-level leave-one-seizure-event-out validation was also conducted to assess alarm-based prediction performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The proposed approach achieved an average accuracy of 95.89%, sensitivity of 96.70%, specificity of 95.48%, and AUC of 99.02%. In the event-level validation, the model achieved an event sensitivity of 95.96%, an average false alarm rate of 0.316 FPR\/h, and a mean early warning time of 30.52 min.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The DC-SA-EBiLSTM framework effectively captures local and global inter-channel dependencies and provides a feature-driven approach for patient-specific preictal state prediction, showing potential for EEG-based seizure prediction.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnins.2026.1856135","type":"journal-article","created":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:02:40Z","timestamp":1780635760000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing seizure prediction using a DC-SA-EBiLSTM framework with self-attention mechanism"],"prefix":"10.3389","volume":"20","author":[{"given":"Shunyun","family":"Wang","sequence":"first","affiliation":[{"name":"College of Information Engineering, Henan University of Science and Technology","place":["Luoyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jincan","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Henan University of Science and Technology","place":["Luoyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenna","family":"Chen","sequence":"additional","affiliation":[{"name":"The First Affiliated Hospital, and College of Clinical Medicine of Henan University of Science and Technology","place":["Luoyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Xiang","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Henan University of Science and Technology","place":["Luoyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongwei","family":"Jiang","sequence":"additional","affiliation":[{"name":"The First Affiliated Hospital, and College of Clinical Medicine of Henan University of Science and Technology","place":["Luoyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ganqin","family":"Du","sequence":"additional","affiliation":[{"name":"The First Affiliated Hospital, and College of Clinical Medicine of Henan University of Science and Technology","place":["Luoyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,5]]},"reference":[{"key":"B1","first-page":"1186","article-title":"Semi-Supervised Deep Learning System for Epileptic Seizures Onset Prediction","volume-title":"Proceedings of the 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA)","author":"Abdelhameed","year":"2018"},{"key":"B2","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1016\/j.future.2018.08.044","article-title":"Characterization of focal EEG signals: A review.","volume":"91","author":"Acharya","year":"2019","journal-title":"Future Generat. Comp. Syst."},{"key":"B3","doi-asserted-by":"publisher","first-page":"1417748","DOI":"10.3389\/fnins.2024.1417748","article-title":"On the performance of seizure prediction machine learning methods across different databases: The sample and alarm-based perspectives.","volume":"18","author":"Andrade","year":"2024","journal-title":"Front. Neurosci."},{"key":"B4","doi-asserted-by":"publisher","first-page":"7251","DOI":"10.3390\/app12147251","article-title":"Classification of EEG signals for prediction of epileptic seizures.","volume":"12","author":"Aslam","year":"2022","journal-title":"Appl. Sci."},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/2107113","article-title":"A novel machine learning model for the detection of epilepsy and epileptic seizures using electroencephalographic signals based on chaos and fractal theories.","author":"Brari","year":"2021","journal-title":"Mathemat. Problems Eng."},{"key":"B6","doi-asserted-by":"publisher","first-page":"103665","DOI":"10.1016\/j.compbiomed.2020.103665","article-title":"Hilbert vibration decomposition-based epileptic seizure prediction with neural network.","volume":"119","author":"B\u00fcy\u00fck\u00e7ak\u0131r","year":"2020","journal-title":"Comp. Biol. Med."},{"key":"B7","doi-asserted-by":"crossref","DOI":"10.1109\/ISCAS58744.2024.10558341","article-title":"Epilepsy Seizure Detection and Prediction using an Approximate Spiking Convolutional Transformer","volume-title":"Proceedings of the 2024 IEEE International Symposium on Circuits and Systems (ISCAS)","author":"Chen","year":"2024"},{"key":"B8","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1186\/s12911-023-02180-w","article-title":"An automated detection of epileptic seizures EEG using CNN classifier based on feature fusion with high accuracy.","volume":"23","author":"Chen","year":"2023","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"B9","doi-asserted-by":"publisher","first-page":"102963","DOI":"10.1016\/j.bspc.2021.102963","article-title":"Patient-specific method of sleep electroencephalography using wavelet packet transform and Bi-LSTM for epileptic seizure prediction.","volume":"70","author":"Cheng","year":"2021","journal-title":"Biomed. Signal Process. Control"},{"key":"B10","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1109\/81.904882","article-title":"A comparison of waveform fractal dimension algorithms.","volume":"48","author":"Esteller","year":"2001","journal-title":"IEEE Trans. Circuits Syst. I"},{"key":"B11","doi-asserted-by":"publisher","first-page":"2350045","DOI":"10.1142\/S0218213023500458","article-title":"Epileptic seizure detection in EEG signal using optimized convolutional neural network with selected feature set.","volume":"32","author":"Fatma","year":"2023","journal-title":"Intern. J. Art. Intell. Tools"},{"key":"B12","doi-asserted-by":"publisher","first-page":"4900209","DOI":"10.1109\/JTEHM.2022.3144037","article-title":"Pediatric seizure prediction in scalp EEG using a multi-scale neural network with dilated convolutions.","volume":"10","author":"Gao","year":"2022","journal-title":"IEEE J. Transl. Eng. Health Med."},{"key":"B13","doi-asserted-by":"publisher","first-page":"8915961","DOI":"10.1155\/2020\/8915961","article-title":"Prediction of cognitive decline in temporal lobe epilepsy and mild cognitive impairment by EEG, MRI, and neuropsychology.","volume":"2020","author":"H\u00f6ller","year":"2020","journal-title":"Comp. Intell. Neurosci."},{"key":"B14","doi-asserted-by":"publisher","first-page":"1321","DOI":"10.1109\/TNSRE.2023.3244045","article-title":"Exploring the applicability of transfer learning and feature engineering in epilepsy prediction using hybrid transformer model.","volume":"31","author":"Hu","year":"2023","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"B15","doi-asserted-by":"publisher","first-page":"012019","DOI":"10.1088\/1742-6596\/1844\/1\/012019","article-title":"Fractal based feature extraction method for epileptic seizure detection in long-term EEG recording.","volume":"1844","author":"Humairani","year":"2021","journal-title":"J. Phys. Conf. Series"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1551","DOI":"10.3390\/biomedicines10071551","article-title":"Multi-Channel vision transformer for epileptic seizure prediction.","volume":"10","author":"Hussein","year":"2022","journal-title":"Biomedicines"},{"key":"B17","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1016\/j.neunet.2021.03.008","article-title":"Semi-dilated convolutional neural networks for epileptic seizure prediction.","volume":"139","author":"Hussein","year":"2021","journal-title":"Neural Netw."},{"key":"B18","doi-asserted-by":"publisher","first-page":"e2627","DOI":"10.1212\/WNL.0000000000011849","article-title":"Sudden unexpected death in epilepsy: A personalized prediction tool.","volume":"96","author":"Jha","year":"2021","journal-title":"Neurology"},{"key":"B19","doi-asserted-by":"publisher","first-page":"967116","DOI":"10.3389\/fnins.2022.967116","article-title":"Efficient graph convolutional networks for seizure prediction using scalp EEG.","volume":"16","author":"Jia","year":"2022","journal-title":"Front. Neurosci."},{"key":"B20","doi-asserted-by":"publisher","first-page":"1191683","DOI":"10.3389\/fnins.2023.1191683","article-title":"Epileptic seizures detection and the analysis of optimal seizure prediction horizon based on frequency and phase analysis.","volume":"17","author":"Jiang","year":"2023","journal-title":"Front. Neurosci."},{"key":"B21","doi-asserted-by":"publisher","first-page":"560","DOI":"10.4103\/0028-3886.317233","article-title":"Artificial intelligence in epilepsy.","volume":"69","author":"Kaur","year":"2021","journal-title":"Neurol. India"},{"key":"B22","doi-asserted-by":"publisher","first-page":"S99","DOI":"10.1111\/epi.17406","article-title":"Learning to generalize seizure forecasts.","volume":"64","author":"Leguia","year":"2023","journal-title":"Epilepsia"},{"key":"B23","doi-asserted-by":"publisher","first-page":"37495","DOI":"10.1109\/ACCESS.2020.2976156","article-title":"Deep C-LSTM neural network for epileptic seizure and tumor detection using high-dimension EEG signals.","volume":"8","author":"Liu","year":"2020","journal-title":"IEEE Access"},{"key":"B24","doi-asserted-by":"publisher","first-page":"7710","DOI":"10.3390\/s21227710","article-title":"Epileptic seizures detection in EEG signals using fusion handcrafted and deep learning features.","volume":"21","author":"Malekzadeh","year":"2021","journal-title":"Sensors"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1902","DOI":"10.1016\/j.clinph.2020.04.172","article-title":"EEG autoregressive modeling analysis: A diagnostic tool for patients with epilepsy without epileptiform discharges.","volume":"131","author":"Ouyang","year":"2020","journal-title":"Clin. Neurophysiol."},{"key":"B26","doi-asserted-by":"publisher","first-page":"197","DOI":"10.37394\/232014.2020.16.22","article-title":"Predication and analysis of epileptic seizure neurological disorder using intracranial electroencephalography (iEEG).","volume":"16","author":"Pawar","year":"2021","journal-title":"WSEAS Trans. Signal Process."},{"key":"B27","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1016\/S1474-4422(20)30396-3","article-title":"Forecasting seizure risk in adults with focal epilepsy: A development and validation study.","volume":"20","author":"Proix","year":"2021","journal-title":"Lancet Neurol."},{"key":"B28","doi-asserted-by":"publisher","first-page":"1450","DOI":"10.1080\/10255842.2024.2326097","article-title":"Seizure prediction based on improved vision transformer model for EEG channel optimization.","volume":"28","author":"Qi","year":"2025","journal-title":"Comp. Methods Biomechan. Biomed. Eng."},{"key":"B29","doi-asserted-by":"publisher","first-page":"2322","DOI":"10.1109\/TNSRE.2021.3125023","article-title":"A generative model to synthesize EEG data for epileptic seizure prediction.","volume":"29","author":"Rasheed","year":"","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"B30","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1109\/RBME.2020.3008792","article-title":"Machine learning for predicting epileptic seizures using EEG signals: A review.","volume":"14","author":"Rasheed","year":"","journal-title":"IEEE Rev. Biomed. Eng."},{"key":"B31","doi-asserted-by":"publisher","first-page":"035040","DOI":"10.1088\/2057-1976\/ad3afd","article-title":"A hybrid 1D CNN-BiLSTM model for epileptic seizure detection using multichannel EEG feature fusion.","volume":"10","author":"Ravi","year":"2024","journal-title":"Biomed. Phys. Eng. Express"},{"key":"B32","doi-asserted-by":"publisher","first-page":"106053","DOI":"10.1016\/j.compbiomed.2022.106053","article-title":"An overview of deep learning techniques for epileptic seizures detection and prediction based on neuroimaging modalities: Methods, challenges, and future works.","volume":"149","author":"Shoeibi","year":"2022","journal-title":"Comp. Biol. Med."},{"key":"B33","doi-asserted-by":"crossref","first-page":"3579","DOI":"10.1109\/TENCON.2016.7848724","article-title":"Data Mining Approach in Seizure Detection","volume-title":"Proceedings of the 2016 IEEE Region 10 Conference (TENCON)","author":"Siddiqui","year":"2016"},{"key":"B34","doi-asserted-by":"publisher","first-page":"1491","DOI":"10.1007\/s12008-020-00715-3","article-title":"Machine learning based novel cost-sensitive seizure detection classifier for imbalanced EEG data sets.","volume":"14","author":"Siddiqui","year":"2020","journal-title":"Int. J. Interact. Des. Manuf."},{"key":"B35","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1007\/978-3-319-69179-4_27","article-title":"Analyzing Performance of Classification Techniques in Detecting Epileptic Seizure","volume-title":"Advanced Data Mining and Applications","author":"Siddiqui","year":"2017"},{"key":"B36","doi-asserted-by":"publisher","first-page":"5595","DOI":"10.1007\/s00521-018-3381-9","article-title":"A novel quick seizure detection and localization through brain data mining on ECoG dataset.","volume":"31","author":"Siddiqui","year":"2019","journal-title":"Neural Comput. Appl."},{"key":"B37","doi-asserted-by":"publisher","first-page":"2405","DOI":"10.1007\/s40747-021-00627-z","article-title":"Two-layer LSTM network-based prediction of epileptic seizures using EEG spectral features.","volume":"8","author":"Singh","year":"2022","journal-title":"Complex Intell. Syst."},{"key":"B38","doi-asserted-by":"publisher","first-page":"162","DOI":"10.7555\/JBR.34.20190097","article-title":"Epileptic seizure prediction based on EEG spikes detection of ictal-preictal states.","volume":"34","author":"Slimen","year":"2020","journal-title":"J. Biomed. Res."},{"key":"B39","doi-asserted-by":"publisher","first-page":"684825","DOI":"10.3389\/fnins.2021.684825","article-title":"Clinical application of machine learning models for brain imaging in epilepsy: A review.","volume":"15","author":"Sone","year":"2021","journal-title":"Front. Neurosci."},{"key":"B40","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1177\/0883073819883157","article-title":"Prediction of drug-resistant epilepsy in children with cerebral palsy.","volume":"35","author":"Tokatly Latzer","year":"2020","journal-title":"J. Child Neurol."},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1707.01976","article-title":"A generalised seizure prediction with convolutional neural networks for intracranial and scalp electroencephalogram data analysis.","author":"Truong","year":"2017","journal-title":"arXiv"},{"key":"B42","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.compbiomed.2018.05.019","article-title":"A Long Short-Term Memory deep learning network for the prediction of epileptic seizures using EEG signals.","volume":"99","author":"Tsiouris","year":"2018","journal-title":"Comp. Biol. Med."},{"key":"B43","doi-asserted-by":"publisher","first-page":"50","DOI":"10.21833\/ijaas.2019.03.008","article-title":"Principle components analysis for seizures prediction using wavelet transform.","volume":"6","author":"Usman","year":"2019","journal-title":"Int. J. Adv. Appl. Sci."},{"key":"B44","doi-asserted-by":"crossref","DOI":"10.1109\/AICAS51828.2021.9458539","article-title":"A Two-Layer LSTM Deep Learning Model for Epileptic Seizure Prediction","volume-title":"Proceedings of the 2021 IEEE 3rd International Conference on Artificial Intelligence Circuits and Systems (AICAS)","author":"Varnosfaderani","year":"2021"},{"key":"B45","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"B46","doi-asserted-by":"publisher","first-page":"3531","DOI":"10.1109\/TNSRE.2024.3460348","article-title":"A compact graph convolutional network with adaptive functional connectivity for seizure prediction.","volume":"32","author":"Wei","year":"2024","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"B47","doi-asserted-by":"publisher","first-page":"841","DOI":"10.1109\/TNSRE.2023.3235390","article-title":"C2 SP-Net: Joint compression and classification network for epilepsy seizure prediction.","volume":"31","author":"Wu","year":"2023","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"B48","doi-asserted-by":"publisher","first-page":"3516","DOI":"10.1109\/TBME.2022.3171982","article-title":"Multichannel synthetic preictal EEG signals to enhance the prediction of epileptic seizures.","volume":"69","author":"Xu","year":"2022","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"B49","doi-asserted-by":"publisher","first-page":"4158","DOI":"10.3390\/app12094158","article-title":"Seizure prediction based on transformer using scalp electroencephalogram.","volume":"12","author":"Yan","year":"2022","journal-title":"Appl. Sci."},{"key":"B50","doi-asserted-by":"publisher","first-page":"1604","DOI":"10.1109\/TNSRE.2021.3103210","article-title":"An effective dual self-attention residual network for seizure prediction.","volume":"29","author":"Yang","year":"2021","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"B51","doi-asserted-by":"publisher","first-page":"14767","DOI":"10.1038\/s41598-024-65619-8","article-title":"Data imbalance in cardiac health diagnostics using CECG-GAN.","volume":"14","author":"Yang","year":"","journal-title":"Sci. Rep."},{"key":"B52","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1186\/s12967-024-04945-x","article-title":"Technological vanguard: The outstanding performance of the LTY-CNN model for the early prediction of epileptic seizures.","volume":"22","author":"Yang","year":"","journal-title":"J. Transl. Med."},{"key":"B53","doi-asserted-by":"publisher","first-page":"9372","DOI":"10.3390\/s22239372","article-title":"Wearable epileptic seizure prediction system based on machine learning techniques using ECG, PPG and EEG signals.","volume":"22","author":"Zambrana-Vinaroz","year":"2022","journal-title":"Sensors"},{"key":"B54","doi-asserted-by":"publisher","first-page":"16916","DOI":"10.1038\/s41598-024-67855-4","article-title":"A scheme combining feature fusion and hybrid deep learning models for epileptic seizure detection and prediction.","volume":"14","author":"Zhang","year":"2024","journal-title":"Sci. Rep."},{"key":"B55","doi-asserted-by":"publisher","first-page":"108447","DOI":"10.1016\/j.jneumeth.2019.108447","article-title":"Establishing functional brain networks using a nonlinear partial directed coherence method to predict epileptic seizures.","volume":"329","author":"Zhang","year":"2020","journal-title":"J. Neurosci. Methods"},{"key":"B56","doi-asserted-by":"publisher","first-page":"2050072","DOI":"10.1142\/S0129065720500720","article-title":"Roughness-Length-Based characteristic analysis of intracranial EEG and epileptic seizure prediction.","volume":"30","author":"Zhang","year":"2020","journal-title":"Intern. J. Neural Syst."}],"container-title":["Frontiers in Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2026.1856135\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:02:42Z","timestamp":1780635762000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2026.1856135\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,5]]},"references-count":56,"alternative-id":["10.3389\/fnins.2026.1856135"],"URL":"https:\/\/doi.org\/10.3389\/fnins.2026.1856135","relation":{},"ISSN":["1662-453X"],"issn-type":[{"value":"1662-453X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,5]]},"article-number":"1856135"}}