{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,30]],"date-time":"2026-08-30T00:50:12Z","timestamp":1788051012069,"version":"build-2784847793"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,12,6]],"date-time":"2021-12-06T00:00:00Z","timestamp":1638748800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,12,6]],"date-time":"2021-12-06T00:00:00Z","timestamp":1638748800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Deep learning techniques have led to significant advancements in seizure prediction research. However, corresponding used benchmarks are not uniform in published results. Moreover, inappropriate training and evaluation processes used in various work create overfitted models, making prediction performance fluctuate or unreliable. In this study, we analyzed the various data preparation methods, dataset partition methods in related works, and explained the corresponding impacts to the prediction algorithms. Then we applied a robust processing procedure that considers the appropriate sampling parameters and the leave-one-out cross-validation method to avoid possible overfitting and provide prerequisites for ease benchmarking. Moreover, a deep learning architecture takes advantage of a one-dimension convolutional neural network and a bi-directional long short-term memory network is proposed for seizure prediction. The architecture achieves 77.6% accuracy, 82.7% sensitivity, and 72.4% specificity, and it outperforms the indicators of other prior-art works. The proposed model is also hardware friendly; it has 6.274 k parameters and requires only 12.825 M floating-point operations, which is advantageous for memory and power constrained device implementations.<\/jats:p>","DOI":"10.1038\/s41598-021-02798-8","type":"journal-article","created":{"date-parts":[[2021,12,6]],"date-time":"2021-12-06T11:06:13Z","timestamp":1638788773000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["Power efficient refined seizure prediction algorithm based on an enhanced benchmarking"],"prefix":"10.1038","volume":"11","author":[{"given":"Ziyu","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hemmings","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junming","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohamad","family":"Sawan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,12,6]]},"reference":[{"key":"2798_CR1","doi-asserted-by":"publisher","first-page":"786","DOI":"10.1046\/j.1460-9568.1998.00090.x","volume":"10","author":"CE Elger","year":"1998","unstructured":"Elger, C. E. & Lehnertz, K. Seizure prediction by non-linear time series analysis of brain electrical activity. Eur. J. Neurosci. 10, 786\u20139. https:\/\/doi.org\/10.1046\/j.1460-9568.1998.00090.x (1998).","journal-title":"Eur. J. Neurosci."},{"key":"2798_CR2","unstructured":"Hively, L. M., Clapp, N. E., Daw, S. C. & Lawkins, W.\u00a0F. Epileptic seizure prediction by non-linear methods (1999)."},{"key":"2798_CR3","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/BF00335153","volume":"42","author":"Z Rogowski","year":"1981","unstructured":"Rogowski, Z., Gath, I. & Bental, E. On the prediction of epileptic seizures. Biol. Cybern. 42, 9\u201315. https:\/\/doi.org\/10.1007\/BF00335153 (1981).","journal-title":"Biol. Cybern."},{"key":"2798_CR4","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1007\/BF02524422","volume":"36","author":"Y Salant","year":"1998","unstructured":"Salant, Y., Gath, I. & Henriksen, O. Prediction of epileptic seizures from two-channel EEG. Med. Biol. Eng. Comput. 36, 549\u201356. https:\/\/doi.org\/10.1007\/BF02524422 (1998).","journal-title":"Med. Biol. Eng. Comput."},{"key":"2798_CR5","doi-asserted-by":"publisher","first-page":"1299","DOI":"10.1016\/j.clinph.2017.04.026","volume":"128","author":"A Aarabi","year":"2017","unstructured":"Aarabi, A. & He, B. Seizure prediction in patients with focal hippocampal epilepsy. Clin. Neurophysiol. 128, 1299\u20131307. https:\/\/doi.org\/10.1016\/j.clinph.2017.04.026 (2017).","journal-title":"Clin. Neurophysiol."},{"key":"2798_CR6","doi-asserted-by":"publisher","DOI":"10.1142\/S012906571750006x","author":"B Direito","year":"2017","unstructured":"Direito, B., Teixeira, C. A., Sales, F., Castelo-Branco, M. & Dourado, A. A realistic seizure prediction study based on multiclass SVM. Int. J. Neural Syst. https:\/\/doi.org\/10.1142\/S012906571750006x (2017).","journal-title":"Int. J. Neural Syst."},{"key":"2798_CR7","doi-asserted-by":"publisher","first-page":"15491","DOI":"10.1038\/s41598-018-33969-9","volume":"8","author":"EB Assi","year":"2018","unstructured":"Assi, E. B., Gagliano, L., Rihana, S., Nguyen, D. K. & Sawan, M. Bispectrum features and multilayer perceptron classifier to enhance seizure prediction. Sci. Rep. 8, 15491. https:\/\/doi.org\/10.1038\/s41598-018-33969-9 (2018).","journal-title":"Sci. Rep."},{"key":"2798_CR8","doi-asserted-by":"publisher","first-page":"880","DOI":"10.1109\/Tnsre.2013.2282153","volume":"21","author":"SF Li","year":"2013","unstructured":"Li, S. F., Zhou, W. D., Yuan, Q. & Liu, Y. X. Seizure prediction using spike rate of intracranial EEG. IEEE Trans. Neural Syst. Rehabilit. Eng. 21, 880\u2013886. https:\/\/doi.org\/10.1109\/Tnsre.2013.2282153 (2013).","journal-title":"IEEE Trans. Neural Syst. Rehabilit. Eng."},{"key":"2798_CR9","doi-asserted-by":"publisher","first-page":"1104","DOI":"10.1016\/j.clinph.2013.09.047","volume":"125","author":"Y Zheng","year":"2014","unstructured":"Zheng, Y., Wang, G., Li, K., Bao, G. & Wang, J. Epileptic seizure prediction using phase synchronization based on bivariate empirical mode decomposition. Clin. Neurophysiol. 125, 1104\u20131111. https:\/\/doi.org\/10.1016\/j.clinph.2013.09.047 (2014).","journal-title":"Clin. Neurophysiol."},{"key":"2798_CR10","doi-asserted-by":"publisher","first-page":"693","DOI":"10.1109\/Tbcas.2015.2477264","volume":"10","author":"ZS Zhang","year":"2016","unstructured":"Zhang, Z. S. & Parhi, K. K. Low-complexity seizure prediction from IEEG\/SEEG using spectral power and ratios of spectral power. IEEE Trans. Biomed. Circuits Syst. 10, 693\u2013706. https:\/\/doi.org\/10.1109\/Tbcas.2015.2477264 (2016).","journal-title":"IEEE Trans. Biomed. Circuits Syst."},{"key":"2798_CR11","doi-asserted-by":"publisher","DOI":"10.1109\/RBME.2020.3008792","author":"K Rasheed","year":"2020","unstructured":"Rasheed, K. et al. Machine learning for predicting epileptic seizures using EEG signals: A review. IEEE Rev. Biomed. Eng. https:\/\/doi.org\/10.1109\/RBME.2020.3008792 (2020).","journal-title":"IEEE Rev. Biomed. Eng."},{"key":"2798_CR12","doi-asserted-by":"publisher","first-page":"1045","DOI":"10.21437\/Interspeech.2010-343","volume":"2010","author":"T Mikolov","year":"2010","unstructured":"Mikolov, T. et al. Recurrent neural network based language model. Interspeech 2010, 1045\u20131048 (2010).","journal-title":"Interspeech"},{"key":"2798_CR13","unstructured":"Vaswani, A. et\u00a0al. Attention is all you need. in Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS\u201917, 6000\u20136010 (Curran Associates Inc., 2017)."},{"key":"2798_CR14","doi-asserted-by":"publisher","unstructured":"Shahbazi, M. & Aghajan, H. A generalizable model for seizure prediction based on deep learning using CNN-LSTM architecture. in 2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP), 469\u2013473, https:\/\/doi.org\/10.1109\/GlobalSIP.2018.8646505 (2018).","DOI":"10.1109\/GlobalSIP.2018.8646505"},{"key":"2798_CR15","doi-asserted-by":"publisher","unstructured":"Pedoeem, J., Abittan, S., Yosef, G.\u00a0B. & Keene, S. Tabs: Transformer based seizure detection. in 2020 IEEE Signal Processing in Medicine and Biology Symposium (SPMB), 1\u20136, https:\/\/doi.org\/10.1109\/SPMB50085.2020.9353612 (2020).","DOI":"10.1109\/SPMB50085.2020.9353612"},{"key":"2798_CR16","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1016\/j.neunet.2018.04.018","volume":"105","author":"ND Truong","year":"2018","unstructured":"Truong, N. D. et al. Convolutional neural networks for seizure prediction using intracranial and scalp electroencephalogram. Neural Netw. 105, 104\u2013111. https:\/\/doi.org\/10.1016\/j.neunet.2018.04.018 (2018).","journal-title":"Neural Netw."},{"key":"2798_CR17","doi-asserted-by":"publisher","unstructured":"Netoff, T., Park, Y. & Parhi, K. Seizure prediction using cost-sensitive support vector machine. in 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Vol. 1\u201320, 3322\u20133325. https:\/\/doi.org\/10.1109\/Iembs.2009.5333711 (2009).","DOI":"10.1109\/Iembs.2009.5333711"},{"key":"2798_CR18","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1109\/TBME.2016.2553131","volume":"64","author":"MZ Parvez","year":"2017","unstructured":"Parvez, M. Z. & Paul, M. Seizure prediction using undulated global and local features. IEEE Trans. Biomed. Eng. 64, 208\u2013217 (2017).","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"2798_CR19","doi-asserted-by":"publisher","first-page":"1011","DOI":"10.1109\/TBME.2016.2586475","volume":"64","author":"HT Shiao","year":"2017","unstructured":"Shiao, H. T. et al. SVM-based system for prediction of epileptic seizures from IEEG signal. IEEE Trans. Biomed. Eng. 64, 1011\u20131022 (2017).","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"2798_CR20","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0096235","author":"A Eftekhar","year":"2014","unstructured":"Eftekhar, A., Juffali, W., El-Imad, J., Constandinou, T. G. & Toumazou, C. Ngram-derived pattern recognition for the detection and prediction of epileptic seizures. PLoS ONE https:\/\/doi.org\/10.1371\/journal.pone.0096235 (2014).","journal-title":"PLoS ONE"},{"key":"2798_CR21","doi-asserted-by":"publisher","first-page":"804","DOI":"10.1109\/Tbcas.2019.2929053","volume":"13","author":"H Daoud","year":"2019","unstructured":"Daoud, H. & Bayoumi, M. A. Efficient epileptic seizure prediction based on deep learning. IEEE Trans. Biomed. Circuits Syst. 13, 804\u2013813. https:\/\/doi.org\/10.1109\/Tbcas.2019.2929053 (2019).","journal-title":"IEEE Trans. Biomed. Circuits Syst."},{"key":"2798_CR22","doi-asserted-by":"publisher","first-page":"3415","DOI":"10.1038\/s41598-021-82828-7","volume":"11","author":"MF Pinto","year":"2021","unstructured":"Pinto, M. F. et al. A personalized and evolutionary algorithm for interpretable EEG epilepsy seizure prediction. Sci. Rep. 11, 3415. https:\/\/doi.org\/10.1038\/s41598-021-82828-7 (2021).","journal-title":"Sci. Rep."},{"key":"2798_CR23","doi-asserted-by":"publisher","first-page":"1761","DOI":"10.1111\/j.1528-1167.2011.03138.x","volume":"52","author":"Y Park","year":"2011","unstructured":"Park, Y., Luo, L., Parhi, K. K. & Netoff, T. Seizure prediction with spectral power of EEG using cost-sensitive support vector machines. Epilepsia 52, 1761\u20131770 (2011).","journal-title":"Epilepsia"},{"key":"2798_CR24","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.neunet.2020.04.022","volume":"128","author":"HH Chen","year":"2020","unstructured":"Chen, H. H. & Cherkassky, V. Performance metrics for online seizure prediction. Neural Netw. 128, 22\u201332. https:\/\/doi.org\/10.1016\/j.neunet.2020.04.022 (2020).","journal-title":"Neural Netw."},{"key":"2798_CR25","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.compbiomed.2018.05.019","volume":"99","author":"KM Tsiouris","year":"2018","unstructured":"Tsiouris, K. M. et al. A long short-term memory deep learning network for the prediction of epileptic seizures using EEG signals. Comput. Biol. Med. 99, 24\u201337. https:\/\/doi.org\/10.1016\/j.compbiomed.2018.05.019 (2018).","journal-title":"Comput. Biol. Med."},{"key":"2798_CR26","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-020-03426-4","author":"SS Zhang","year":"2020","unstructured":"Zhang, S. S. et al. A lightweight solution to epileptic seizure prediction based on EEG synchronization measurement. J. Supercomput. https:\/\/doi.org\/10.1007\/s11227-020-03426-4 (2020).","journal-title":"J. Supercomput."},{"key":"2798_CR27","doi-asserted-by":"publisher","first-page":"1008","DOI":"10.1109\/TBCAS.2020.3018465","volume":"14","author":"J Yang","year":"2020","unstructured":"Yang, J. & Sawan, M. From seizure detection to smart and fully embedded seizure prediction engine: A review. IEEE Trans. Biomed. Circuits Syst. 14, 1008\u20131023. https:\/\/doi.org\/10.1109\/TBCAS.2020.3018465 (2020).","journal-title":"IEEE Trans. Biomed. Circuits Syst."},{"key":"2798_CR28","doi-asserted-by":"publisher","first-page":"e215","DOI":"10.1161\/01.CIR.101.23.e215","volume":"101","author":"AL Goldberger","year":"2000","unstructured":"Goldberger, A. L. et al. Physiobank, physiotoolkit, and physionet. Circulation 101, e215\u2013e220. https:\/\/doi.org\/10.1161\/01.CIR.101.23.e215 (2000).","journal-title":"Circulation"},{"key":"2798_CR29","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","volume":"18","author":"A Graves","year":"2005","unstructured":"Graves, A. & Schmidhuber, J. Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw. 18, 602\u2013610. https:\/\/doi.org\/10.1016\/j.neunet.2005.06.042 (2005).","journal-title":"Neural Netw."},{"key":"2798_CR30","doi-asserted-by":"publisher","unstructured":"Chamseddine, A. & Sawan, M. Deep learning based method for output regularization of the seizure prediction classifier. in 2018 IEEE Life Sciences Conference (LSC), 118\u2013121, https:\/\/doi.org\/10.1109\/LSC.2018.8572221 (2018).","DOI":"10.1109\/LSC.2018.8572221"},{"key":"2798_CR31","doi-asserted-by":"publisher","unstructured":"Xu, Y., Yang, J., Zhao, S., Wu, H. & Sawan, M. An end-to-end deep learning approach for epileptic seizure prediction. in 2020 2nd IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS), 266\u2013270, https:\/\/doi.org\/10.1109\/AICAS48895.2020.9073988 (2020).","DOI":"10.1109\/AICAS48895.2020.9073988"},{"key":"2798_CR32","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/aace8c","author":"VJ Lawhern","year":"2018","unstructured":"Lawhern, V. J. et al. EEGNet: A compact convolutional neural network for EEG-based brain\u2013computer interfaces. J. Neural Eng. https:\/\/doi.org\/10.1088\/1741-2552\/aace8c (2018).","journal-title":"J. Neural Eng."},{"key":"2798_CR33","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1109\/JBHI.2019.2933046","volume":"24","author":"Y Zhang","year":"2020","unstructured":"Zhang, Y., Guo, Y., Yang, P., Chen, W. & Lo, B. Epilepsy seizure prediction on EEG using common spatial pattern and convolutional neural network. IEEE J. Biomed. Health Inform. 24, 465\u2013474. https:\/\/doi.org\/10.1109\/JBHI.2019.2933046 (2020).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"2798_CR34","doi-asserted-by":"publisher","first-page":"2109","DOI":"10.1109\/TBME.2017.2785401","volume":"65","author":"H Khan","year":"2018","unstructured":"Khan, H., Marcuse, L., Fields, M., Swann, K. & Yener, B. Focal onset seizure prediction using convolutional networks. IEEE Trans. Biomed. Eng. 65, 2109\u20132118. https:\/\/doi.org\/10.1109\/TBME.2017.2785401 (2018).","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"2798_CR35","doi-asserted-by":"publisher","unstructured":"H\u00fcgle, M. et\u00a0al. Early seizure detection with an energy-efficient convolutional neural network on an implantable microcontroller. in 2018 International Joint Conference on Neural Networks (IJCNN), 1\u20137, https:\/\/doi.org\/10.1109\/IJCNN.2018.8489493 (2018).","DOI":"10.1109\/IJCNN.2018.8489493"},{"key":"2798_CR36","doi-asserted-by":"publisher","first-page":"2653","DOI":"10.1111\/epi.16719","volume":"61","author":"C Meisel","year":"2020","unstructured":"Meisel, C. et al. Machine learning from wristband sensor data for wearable, noninvasive seizure forecasting. Epilepsia 61, 2653\u20132666. https:\/\/doi.org\/10.1111\/epi.16719 (2020).","journal-title":"Epilepsia"},{"key":"2798_CR37","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1109\/Tbme.2017.2700086","volume":"65","author":"I Korshunova","year":"2018","unstructured":"Korshunova, I. et al. Towards improved design and evaluation of epileptic seizure predictors. IEEE Trans. Biomed. Eng. 65, 502\u2013510. https:\/\/doi.org\/10.1109\/Tbme.2017.2700086 (2018).","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"2798_CR38","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1016\/j.bspc.2017.02.001","volume":"34","author":"EB Assi","year":"2017","unstructured":"Assi, E. B., Nguyen, D. K., Rihana, S. & Sawan, M. Towards accurate prediction of epileptic seizures: A review. Biomed. Signal Process. Control 34, 144\u2013157. https:\/\/doi.org\/10.1016\/j.bspc.2017.02.001 (2017).","journal-title":"Biomed. Signal Process. Control"},{"key":"2798_CR39","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/j.clinph.2018.10.010","volume":"130","author":"R Hussein","year":"2019","unstructured":"Hussein, R., Palangi, H., Ward, R. K. & Wang, Z. J. Optimized deep neural network architecture for robust detection of epileptic seizures using EEG signals. Clin. Neurophysiol. 130, 25\u201337. https:\/\/doi.org\/10.1016\/j.clinph.2018.10.010 (2019).","journal-title":"Clin. Neurophysiol."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-02798-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-02798-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-02798-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,3]],"date-time":"2022-12-03T17:55:35Z","timestamp":1670090135000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-02798-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,6]]},"references-count":39,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["2798"],"URL":"https:\/\/doi.org\/10.1038\/s41598-021-02798-8","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,6]]},"assertion":[{"value":"7 May 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 November 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 December 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"23498"}}