FPGA based real-time epileptic seizure prediction system

• Autorzy: Cosgun Ercan , Çelebi Anil

Identyfikatory

DOI

10.1016/j.bbe.2021.01.006

• Języki publikacji: EN

Abstrakty

EN

The development of systems that can predict epileptic seizures in real-time offers great hope for epilepsy patients. These systems aim to prevent accidents that patients may experience caused by the loss of consciousness during seizures. Therefore, patients must use real-time epileptic seizure prediction systems that do not interfere with their daily activities. In this study, using the unipolar EEG data from a surface electrode, a patient-specific estimation system is implemented in real-time on a system on chip (SoC) that contains an embedded processor and programmable logic blocks. The European epilepsy database EPILEPSIAE is used in the scope of this work. In the proposed system, pre-processing is applied to the EEG data. Then, the features of the data in the frequency domain are extracted. The classifier model is trained with the RusBoosted Tree cluster classifier, which is a machine learning algorithm. Testing is carried out using the proposed classification model. Threshold values are determined, and then false alarms and erroneous classifications are prevented by post-processing. At the end of the tests, prediction success, sensitivity (SEN), Specificity (SPE), False Prediction Rate (FPR), and prediction times are obtained as 77.30%, 95.94%, 0.041 h^_1, and 33.23 min, respectively. The proposed system outperforms other studies in the liter-ature in the number of electrodes, real-time operation, hardware/software architecture, and FPR performance. A wearable seizure prediction system seems to be commercialized according to the results achieved in this study.

Słowa kluczowe

EN

epileptic seizure prediction; field programmable gate array; FPGA; system-on-chip; SOC; electroencephalogram; EEG; hardware architecture; HW/SW co-design

PL

przewidywanie napadu padaczkowego; FPGA; SOC; elektroencefalogram; EEG; architektura sprzętowa

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2021
• Tom: Vol. 41, no. 1
• Strony: 278--292
• Opis fizyczny: Bibliogr. 83 poz., rys., tab., wykr.

Twórcy

autor

Cosgun Ercan

• University of Kirklareli, Vocational School of Technical Sciences, Electronics & Automation Department, Kirklareli, Turkey

autor

Çelebi Anil

• University of Kocaeli, Electronics and Telecommunications Engineering Department, Kocaeli, Turkey

Bibliografia

• [1] WHO EPILEPSY 2019. https://www.who.int/news-room/fact-sheets/detail/ epilepsy.
• [2] Zack MM, Kobau R. National and state estimates of the numbers of adults and children with active epilepsy — united States, 2015. Morb Mortal Wkly Rep Surveill Summ 2017;66:821–5. http://dx.doi.org/10.15585/mmwr.mm6631a1.
• [3] Rogers SL, Buzsáki G. What is epilepsy and how can you help someone with it? Front Young Minds 2019;7:1–7. http://dx.doi.org/10.3389/frym.2019.00052.
• [4] Rao S, Stino A, Seraji-Bozorgzad N, Shah AK, Basha MM. Seizure-related injury and postictal aggression in refractory epilepsy patients. Epilepsy Res 2020;160106281. http://dx.doi.org/10.1016/j.eplepsyres.2020.106281.
• [5] Bandarabadi M, Rasekhi J, Teixeira CA, Karami MR, Dourado A. On the proper selection of preictal period for seizure prediction. Epilepsy Behav 2015;46:158–66. http://dx.doi.org/10.1016/j.yebeh.2015.03.010.
• [6] Asharindavida F, Shamim Hossain M, Thacham A, Khammari H, Ahmed I, Alraddady F, et al. A forecasting tool for prediction of epileptic seizures using a machine learning approach. Concurr Comput 2020;32:1–24. http://dx.doi.org/10.1002/cpe.5111.
• [7] Zhang Z, Parhi KK. Low-complexity seizure prediction from iEEG/sEEG using spectral power and ratios of spectral power. IEEE Trans Biomed Circuits Syst 2016;10:693–706. http://dx.doi.org/10.1109/TBCAS.2015.2477264.
• [8] Ramina P, Vanitha M, Professor A. Fast and effective real time seizure prediction on streaming EEG signals. Int J Electron Commun Instrum Eng Res Dev 2017;9:167–79.
• [9] Alickovic E, Kevric J, Subasi A. Performance evaluation of empirical mode decomposition, discrete wavelet transform, and wavelet packed decomposition for automated epileptic seizure detection and prediction. Biomed Signal Process Control 2018;39:94–102. http://dx.doi.org/10.1016/j.bspc.2017.07.022.
• [10] Wilson SB, Scheuer ML, Plummer C, Young B, Pacia S. Seizure detection: correlation of human experts. Clin Neurophysiol 2003;114:2156–64. http://dx.doi.org/10.1016/S1388-2457(03)00212-8.
• [11] Zhang Q, Hu Y, Potter T, Li R, Quach M, Zhang Y. Establishing functional brain networks using a nonlinear partial directed coherence method to predict epileptic seizures. J Neurosci Methods 2020;329108447. http://dx.doi.org/10.1016/j.jneumeth.2019.108447.
• [12] Yu Z, Nie W, Zhou W, Xu F, Yuan S, Leng Y, et al. Epileptic seizure prediction based on local mean decomposition and deep convolutional neural network. J Supercomput 2018. http://dx.doi.org/10.1007/s11227-018-2600-6.
• [13] Bigelow MD, Kouzani AZ. Neural stimulation systems for the control of refractory epilepsy: a review. J Neuroeng Rehabil 2019;16:1–17. http://dx.doi.org/10.1186/s12984-019-0605-x.
• [14] Agboola HA, Solebo C, Aribike DS, Lesi AE, Susu A. Seizure prediction with adaptive feature representation learning. J Neurol Neurosci 2019;10:1–12. http://dx.doi.org/10.36648/2171-6625.10.2.294.
• [15] Park Y, Luo L, Parhi KK, Netoff T. Seizure prediction with spectral power of EEG using cost-sensitive support vector machines. Epilepsia 2011;52:1761–70. http://dx.doi.org/10.1111/j.1528-1167.2011.03138.x.
• [16] Rukhsar S, Khan YU, Farooq O, Sarfraz M, Khan AT. Patient-specific epileptic seizure prediction in long-term scalp EEG signal using multivariate statistical process control. Irbm 2019;40:320–31. http://dx.doi.org/10.1016/j.irbm.2019.08.004.
• [17] Direito B, Teixeira CA, Sales F, Castelo-Branco M, Dourado A. A realistic seizure prediction study based on multiclass SVM. Int J Neural Syst 2017;27. http://dx.doi.org/10.1142/S012906571750006X.
• [18] Truong ND, Nguyen AD, Kuhlmann L, Bonyadi MR, Yang J, Ippolito S, et al. Convolutional neural networks for seizure prediction using intracranial and scalp electroencephalogram. Neural Netw 2018;105:104–11. http://dx.doi.org/10.1016/j.neunet.2018.04.018.
• [19] Sharif B, Jafari AH. Prediction of epileptic seizures from EEG using analysis of ictal rules on Poincaré plane. Comput Methods Programs Biomed 2017;145:11–22. http://dx.doi.org/10.1016/j.cmpb.2017.04.001.
• [20] D'Alessandro M, Esteller R, Echauz J, Vachtsevanos G, Hinson A, Litt B. Epileptic seizure prediction using hybrid feature selection over multiple intracranial EEG electrode contacts: a report of four patients. IEEE Trans Biomed Eng 2003;50:603–15. http://dx.doi.org/10.1109/TBME.2003.810706.
• [21] Li Q, Gao J, Zhang Z, Huang Q, Wu Y, Xu B. Distinguishing epileptiform discharges from normal electroencephalograms using adaptive fractal and network analysis: a clinical perspective. Front Physiol 2020;11:1–15. http://dx.doi.org/10.3389/fphys.2020.00828.
• [22] Bandarabadi M, Teixeira CA, Rasekhi J, Dourado A. Epileptic seizure prediction using relative spectral power features. Clin Neurophysiol 2015;126:237–48. http://dx.doi.org/10.1016/j.clinph.2014.05.022.
• [23] Alexandre Teixeira C, Direito B, Bandarabadi M, Le Van Quyen M, Valderrama M, Schelter B, et al. Epileptic seizure predictors based on computational intelligence techniques: a comparative study with 278 patients. Comput Methods Programs Biomed 2014;114:324–36. http://dx.doi.org/10.1016/j.cmpb.2014.02.007.
• [24] Rasekhi J, Mollaei MRK, Bandarabadi M, Teixeira CA, Dourado A. Preprocessing effects of 22 linear univariate features on the performance of seizure prediction methods. J Neurosci Methods 2013;217:9–16. http://dx.doi.org/10.1016/j.jneumeth.2013.03.019.
• [25] Quintero-Rincón A, Pereyra M, D'Giano C, Risk M, Batatia H. Fast statistical model-based classification of epileptic EEG signals. Biocybern Biomed Eng 2018;38:877–89. http://dx.doi.org/10.1016/j.bbe.2018.08.002.
• [26] Sudalaimani C, Sivakumaran N, Elizabeth TT, Rominus VS. Automated detection of the preseizure state in EEG signal using neural networks. Biocybern Biomed Eng 2019;39:160–75. http://dx.doi.org/10.1016/j.bbe.2018.11.007.
• 27] Khan H, Marcuse L, Fields M, Swann K, Yener B. Focal onset seizure prediction using convolutional networks. IEEE Trans Biomed Eng 2018;65:2109–18. http://dx.doi.org/10.1109/TBME.2017.2785401.
• [28] Tzallas AT, Tsipouras MG, Fotiadis DI. Epileptic seizure detection in EEGs using time-frequency analysis. IEEE Trans Inf Technol Biomed 2009;13:703–10. http://dx.doi.org/10.1109/TITB.2009.2017939.
• [29] Samiee K, Kovács P, Gabbouj M. Epileptic seizure detection in long-term EEG records using sparse rational decomposition and local Gabor binary patterns feature extraction. Knowledge-Based Syst 2017;118:228–40. http://dx.doi.org/10.1016/j.knosys.2016.11.023.
• [30] Yu H, Fan C, Zhang Y, Huang C. Epilepsy detection in EEG using grassmann discriminant analysis method. Comput Math Methods Med 2020;2020. http://dx.doi.org/10.1155/2020/2598140.
• [31] Chen G, Xie W, Bui TD, Krzyzak A. Automatic epileptic seizure detection in EEG using nonsubsampled wavelet– Fourier features. J Med Biol Eng 2017;37:123–31. http://dx.doi.org/10.1007/s40846-016-0214-0.
• [32] Krishnan PT, Joseph Raj AN, Balasubramanian P, Chen Y. Schizophrenia detection using MultivariateEmpirical Mode Decomposition and entropy measures from multichannel EEG signal. Biocybern Biomed Eng 2020;40:1124–39. http://dx.doi.org/10.1016/j.bbe.2020.05.008.
• [33] Usman SM, Usman M, Fong S. Epileptic seizures prediction using machine learning methods. Comput Math Methods Med 2017;2017. http://dx.doi.org/10.1155/2017/9074759.
• [34] Bishop CM. Pattern recognition and machine learning;New York, NY 2006.
• [35] Hu W, Cao J, Lai X, Liu J. Mean amplitude spectrum based epileptic state classification for seizure prediction using convolutional neural networks. J Ambient Intell Humaniz Comput 2019;0:0. http://dx.doi.org/10.1007/s12652-019-01220-6.
• [36] Dhiman R, Saini JS, Priyanka. Genetic algorithms tuned expert model for detection of epileptic seizures from EEG signatures. Appl Soft Comput J 2014;19:8–17. http://dx.doi.org/10.1016/j.asoc.2014.01.029.
• [37] Chisci L, Mavino A, Perferi G, Sciandrone M, Anile C, Colicchio G, et al. Real-time epileptic seizure prediction using AR models and support vector machines. IEEE Trans Biomed Eng 2010;57:1124–32. http://dx.doi.org/10.1109/TBME.2009.2038990.
• [38] Ibrahim S, Djemal R, Alsuwailem A. Electroencephalography (EEG) signal processing for epilepsy and autism spectrum disorder diagnosis. Biocybern Biomed Eng 2018;38:16–26. http://dx.doi.org/10.1016/j.bbe.2017.08.006.
• [39] Wang L, Wang C, Fu F, Yu X, Guo H, Xu C, et al. Temporal lobe seizure prediction based on a complex Gaussian wavelet. Clin Neurophysiol 2011;122:656–63. http://dx.doi.org/10.1016/j.clinph.2010.09.018.
• [40] Sadeghzadeh H, Hosseini-Nejad H, Salehi S. Real-time epileptic seizure prediction based on online monitoring of pre-ictal features. Med Biol Eng Comput 2019;57:2461–9. http://dx.doi.org/10.1007/s11517-019-02039-1.
• [41] Savadkoohi M, Oladunni T, Thompson L. A machine learning approach to epileptic seizure prediction using Electroencephalogram (EEG) Signal. Biocybern Biomed Eng 2020;40:1328–41. http://dx.doi.org/10.1016/j.bbe.2020.07.004.
• [42] Li M, Chen W, Zhang T. Automatic epilepsy detection using wavelet-based nonlinear analysis and optimized SVM. Biocybern Biomed Eng 2016;36:708–18. http://dx.doi.org/10.1016/j.bbe.2016.07.004.
• [43] Xiang J, Li C, Li H, Cao R, Wang B, Han X, et al. The detection of epileptic seizure signals based on fuzzy entropy. J Neurosci Methods 2015;243:18–25. http://dx.doi.org/10.1016/j.jneumeth.2015.01.015.
• [44] Mamli S, Kalbkhani H. Gray-level co-occurrence matrix of Fourier synchro-squeezed transform for epileptic seizure detection. Biocybern Biomed Eng 2019;39:87–99. http://dx.doi.org/10.1016/j.bbe.2018.10.006.
• [45] Li M, Chen W, Zhang T. Automatic epileptic EEG detection using DT-CWT-based non-linear features. Biomed Signal Process Control 2017;34:114–25. http://dx.doi.org/10.1016/j.bspc.2017.01.010.
• [46] Zhang T, Chen W, Li M. Generalized Stockwell transform and SVD-based epileptic seizure detection in EEG using random forest. Biocybern Biomed Eng 2018;38:519–34. http://dx.doi.org/10.1016/j.bbe.2018.03.007.
• [47] Li M, Chen W, Zhang T. Application of MODWT and log-normal distribution model for automatic epilepsy identification. Biocybern Biomed Eng 2017;37:679–89. http://dx.doi.org/10.1016/j.bbe.2017.08.003.
• [48] Li M, Chen W, Zhang T. Classification of epilepsy EEG signals using DWT-based envelope analysis and neural network ensemble. Biomed Signal Process Control 2017;31:357–65. http://dx.doi.org/10.1016/j.bspc.2016.09.008.
• [49] Solaija MSJ, Saleem S, Khurshid K, Hassan SA, Kamboh AM. Dynamic mode decomposition based epileptic seizure detection from scalp EEG. IEEE Access 2018;6:38683–92. http://dx.doi.org/10.1109/ACCESS.2018.2853125.
• [50] Das K, Daschakladar D, Roy PP, Chatterjee A, Saha SP. Epileptic seizure prediction by the detection of seizure waveform from the pre-ictal phase of EEG signal. Biomed Signal Process Control 2020;57101720. http://dx.doi.org/10.1016/j.bspc.2019.101720.
• [51] Burrello A, Schindler K, Benini L, Rahimi A. One-shot learning for iEEG seizure detection using end-to-end binary operations: local binary patterns with hyperdimensional computing. ArXiv 2018.
• [52] Kueh SM, Kazmierski TJ. Low-power and low-cost dedicated bit-serial hardware neural network for epileptic seizure prediction system. IEEE J Transl Eng Heal Med 2018;6. http://dx.doi.org/10.1109/JTEHM.2018.2867864.
• [53] Safaei A, Wu QMJ, Yang Y. System-on-a-chip (SoC)-based hardware acceleration for foreground and background identification. J Franklin Inst 2018;355:1888–912. http://dx.doi.org/10.1016/j.jfranklin.2017.07.037.
• [54] Kocaoglu S, Akdogan E. Design and development of an intelligent biomechatronic tumor prosthesis. Biocybern Biomed Eng 2019;39:561–70. http://dx.doi.org/10.1016/j.bbe.2019.05.004.
• [55] Karpova EV, Karyakin EE, Karyakin AA. Wearable non- invasive monitors of diabetes and hypoxia through continuous analysis of sweat. Talanta 2020;215120922. http://dx.doi.org/10.1016/j.talanta.2020.120922.
• [56] Bent B, Goldstein BA, Kibbe WA, Dunn JP. Investigating sources of inaccuracy in wearable optical heart rate sensors. Npj Digit Med 2020;3:1–9. http://dx.doi.org/10.1038/s41746-020-0226-6.
• [57] Teohari VM, Ungureanu C, Bui V, Arends JBAM, Aarts RM. Epilepsy seizure detection app for wearable technologies; 2014. pp. 1–6.
• [58] Iranmanesh S, Raikos G, Imtiaz SA, Rodriguez-Villegas E. A seizure-based power reduction SoC for wearable EEG in epilepsy. IEEE Access 2019;7:151682–91. http://dx.doi.org/10.1109/ACCESS.2019.2948231.
• [59] Gu Y, Cleeren E, Dan J, Claes K, Van Paesschen W, Van Huffel S, et al. Comparison between scalp EEG and behindtheear EEG for development of a wearable seizure detection system for patients with focal epilepsy. Sensors (Switzerland) 2018;18:1–17. http://dx.doi.org/10.3390/s18010029.
• [60] Imtiaz SA, Logesparan L, Rodriguez-Villegas E. Performance-power consumption tradeoff in wearable epilepsy monitoring systems. IEEE J Biomed Heal Informatics 2015;19:1019–28. http://dx.doi.org/10.1109/JBHI.2014.2342501.
• [61] Meisel C, El Atrache R, Jackson M, Schubach S, Ufongene C, Loddenkemper T. Machine learning from wristband sensor data for wearable, noninvasive seizure forecasting. Epilepsia 2020. http://dx.doi.org/10.1111/epi.16719.
• [62] Ihle M, Feldwisch-Drentrup H, Teixeira CA, Witon A, Schelter B, Timmer J, et al. EPILEPSIAE - A European epilepsy database. Comput Methods Programs Biomed 2012;106:127–38. http://dx.doi.org/10.1016/j.cmpb.2010.08.011.
• [63] Truong ND, Kuhlmann L, Bonyadi MR, Querlioz D, Zhou L, Kavehei O. Epileptic seizure forecasting with generative adversarial networks. IEEE Access 2019;7:143999–4009. http://dx.doi.org/10.1109/ACCESS.2019.2944691.
• [64] European Epilepsy Database 2012. http://epilepsy-database.eu/ (accessed June 30, 2020).
• [65] Huang NE, Shen Z, Long SR, Wu MC, Snin HH, Zheng Q, et al. The empirical mode decomposition and the Hubert spectrum for nonlinear and non-stationary time series analysis. Proc R Soc A Math Phys Eng Sci 1998;454:903–95. http://dx.doi.org/10.1098/rspa.1998.0193.
• [66] Gul S, Siddiqui MF, Ur Rehman N. FPGA based real-time implementation of online EMD with fixed point architecture. IEEE Access 2019;7:176565–77. http://dx.doi.org/10.1109/ACCESS.2019.2957819.
• [67] Wang G, Chen XY, Qiao FL, Wu Z, Huang NE. On intrinsic mode function. Adv Adapt Data Anal 2010;2:277–93. http://dx.doi.org/10.1142/S1793536910000549.
• [68] Huang NE, Shen Z, Long SR, Wu MC, Shih HH, Zheng Q, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc R Soc London Ser A Math Phys Eng Sci 1998;454:903–95. http://dx.doi.org/10.1098/rspa.1998.0193.
• [69] Rato RT, Ortigueira MD, Batista AG. On the HHT, its problems, and some solutions. Mech Syst Signal Process 2008;22:1374–94. http://dx.doi.org/10.1016/j.ymssp.2007.11.028.
• [70] Karabiber Cura O, Kocaaslan Atli S, Türe HS, Akan A. Epileptic seizure classifications using empirical mode decomposition and its derivative. Biomed Eng Online 2020;19:10. http://dx.doi.org/10.1186/s12938-020-0754-y.
• [71] Sankari ES, Manimegalai D. Predicting membrane protein types using various decision tree classifiers based on various modes of general PseAAC for imbalanced datasets. J Theor Biol 2017;435:208–17. http://dx.doi.org/10.1016/j.jtbi.2017.09.018.
• [72] Lim Chee-Keong Alfred, Chia WC. Analysis of single-electrode EEG rhythms using MATLAB to elicit correlation with cognitive stress. Int J Comput Theory Eng 2015;7:149– 55. http://dx.doi.org/10.7763/IJCTE.2015.V7.947.
• [73] Jain G, Mittal D, Thakur D, Mittal MK. A deep learning approach to detect Covid-19 coronavirus with X-Ray images. Biocybern Biomed Eng 2020;40:1391–405. http://dx.doi.org/10.1016/j.bbe.2020.08.008.
• [74] Seiffert C, Khoshgoftaar TM, Van Hulse J, Napolitano A. RUSBoost: A hybrid approach to alleviating class imbalance. IEEE Trans Syst Man Cybern Part ASystems Humans 2010;40:185–97. http://dx.doi.org/10.1109/TSMCA.2009.2029559.
• [75] Spring D. On the second derivative test for constrained local extrema. Am Math Mon 1985;92:631–43. http://dx.doi.org/10.1080/00029890.1985.11971702.
• [76] Faires RB. J. Numerical analysis. ninth edit. BROOKS/COLE; 2010.
• [77] Feldwisch-Drentrup H, Ihle M, le van Quyen M, Teixeira C, Dourado A, Timmer J, et al. Anticipating the unobserved: prediction of subclinical seizures. Epilepsy Behav 2011;22: S119–26. http://dx.doi.org/10.1016/j.yebeh.2011.08.023.
• [78] Zandi AS, Tafreshi R, Javidan M, Dumont GA. Predicting epileptic seizures in scalp EEG based on a variational bayesian gaussian mixture model of zero-crossing intervals. IEEE Trans Biomed Eng 2013;60:1401–13. http://dx.doi.org/10.1109/TBME.2012.2237399.
• [79] Zhang Z, Chen Z, Zhou Y, Du S, Zhang Y, Mei T, et al. Construction of rules for seizure prediction based on approximate entropy. Clin Neurophysiol 2014;125:1959–66. http://dx.doi.org/10.1016/j.clinph.2014.02.017.
• [80] Ibrahim SW, Djemal R, Alsuwailem A, Gannouni S. Electroencephalography (EEG)-based epileptic seizure prediction using entropy and K-nearest neighbor (KNN). Commun Sci Technol 2017;2:6–10. http://dx.doi.org/10.21924/cst.2.1.2017.44.
• [81] Zhu T, Huang L, Tian X. Epileptic seizure prediction by using empirical mode decomposition and complexity analysis of single-channel scalp electroencephalogram. Proc 2009 2nd Int Conf Biomed Eng Informatics; 2009. pp. 1– 4. http://dx.doi.org/10.1109/BMEI.2009.5305382.
• [82] Kappel SL, Rank ML, Toft HO, Andersen M, Kidmose P. Dry-contact electrode Ear-EEG. IEEE Trans Biomed Eng 2019;66:150–8. http://dx.doi.org/10.1109/TBME.2018.2835778.
• [83] Yin L, Zhang C, Cui Z. Experimental research on real-time acquisition and monitoring of wearable EEG based on TGAM module. Comput Commun 2020;151:76–85. http://dx.doi.org/10.1016/j.comcom.2019.12.055.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).