Abstract
Epilepsy is characterized by uncontrollable seizure during which consciousness of patient is disturbed. Prediction of the seizure in advance will increase the remedial possibilities for the patients suffering from epilepsy. An automated system for seizure prediction is important for seizure enactment, prevention of sudden unexpected deaths and to avoid seizure related injuries. This paper proposes the prediction of an upcoming seizure by analyzing the 23 channel non-stationary EEG signal. EEG signal is divided into smaller segments to change it into quasi-stationary data using an overlapping moving window. Brain region is marked into four regions namely left hemisphere, right hemisphere, central region and temporal region to identify the epileptogenic region. The epileptogenic region shows significant variations during pre-ictal state in comparison to the other regions. So, seizure prediction is carried out by analyzing EEG signals from this region. Seizure prediction is proposed using features extracted from both time and frequency domain. Relative entropy and relative energy are extracted from wavelet transform and Pearson correlation coefficient is obtained from time domain EEG signal. Extracted features have been smoothened using moving average filter. First order derivative of relative features have been used to normalize the intervariability before deciding the threshold for marking the prediction of seizure. Isolated seizures where pre-ictal duration of more than 1 h is reported has been detected with an accuracy of 92.18% with precursory warning 18 min in advance and seizure confirmation 12 min in advance. An overall accuracy of 83.33% with false positive alarm rate of 0.01/h has been obtained for all seizure cases with average prediction time of 9.9 min.
-
Research funding: None declared.
-
Author contributions: All authors have accepted responsibility for the entire content of this manuscript and approved its submission.
-
Competing interests: Authors state no conflict of interest.
References
1. Teplan, M. Fundamentals of EEG measurement. Measurement Sci Rev 2002;2. https://doi.org/10.1021/pr0703501.Search in Google Scholar
2. Patterson, V. Telemedicine for epilepsy support in resource poor settings. Frontiers in Public Health 2014;2:8–11. https://doi.org/10.3389/fpubh.2014.00120.Search in Google Scholar
3. World Health Organization (WHO) Headquarters in Switzerland. 2017. Available from: http://www.who.int/mediacentre/factsheets/fs999/en/.Search in Google Scholar
4. Zhang, Z, Parhi, KA. Low complexity seizure forecasting from iEEG/sEEG using spectral power and ratios of spectral power. IEEE Transaction on Biomed Circuits and Sys 2015;8:10–25.Search in Google Scholar
5. Burle, B, SpieserL, Loger, C, Hasbroucq, T, Vidal, F. Spatial and temporal resolution of EEG: is it really black and white? A scalp density view. Inter J Psychophy 2015;9:210–20. https://doi.org/10.1016/j.ijpsycho.2015.05.004.Search in Google Scholar
6. Levan, M, Martinerie, J. Anticipation of epileptic seizure from standard EEG recordings. Lancet 2001;357:181–8. https://doi.org/10.1016/S0140-6736(00)03591-1.Search in Google Scholar
7. Andrzejak, RG, Elger CEand Lehnertz, K. Seizure prediction long and winding road. Brain 2007;130:314–33. https://doi.org/10.1093/brain/awl241.Search in Google Scholar
8. Iasemidis, LD, Shiau, D, Chaovalitwongse, W, Sackellars, JC, Pardalos, PM, Principe, JC, et al. Adaptive epilepticseizure prediction system. IEEE Trans Biomed Eng 2003;50:616–27.10.1109/TBME.2003.810689Search in Google Scholar
9. Drongelen, WM, Nayak, S, Frim, D. Seizure anticipation in pediatric epilepsy: use of kolmogorov entropy. J Peda Neuro 2003;29:207–13.10.1016/S0887-8994(03)00145-0Search in Google Scholar
10. Mirowski, P, Madhavan, D, Lecun, Y, Kuznieckly, R. Classification of pattern of EEG synchronization for seizure prediction. J Clin Neurophy 2009;120:1927–40. https://doi.org/10.1016/j.clinph.2009.09.002.Search in Google Scholar PubMed
11. Yadollahpour, A, Jalilifar, M. Seizure prediction methods: A review of current predicting techniques. J Biomed Pharmacol 2014;7:153–62. https://doi.org/10.13005/bpj/466.Search in Google Scholar
12. Sharma, A, Rai, JK, Tewari, RP. Multivariate EEG signal analysis for early prediction of epileptic seizure. In: Proc IEEE Conf on Recent Advances in Engineering and Computational Sciences RAECS -2015. Chandigarh, India; 1–5.10.1109/RAECS.2015.7453318Search in Google Scholar
13. Sharma, A, Rai, JK, Tewari, RP. Prior forecasting of epileptic seizure and localization of epileptogenic region. J Biomed Eng Applic Basis Commun 2017;29:1–16. https://doi.org/10.4015/S1016237217500120.Search in Google Scholar
14. Faust, O, Acharya, UR, Adeli, H, Adeli, A. Wavelet based EEG processing for computer-aid seizure detection and epilepsy diagonsis. J Seizure 2015;26:56–64.10.1016/j.seizure.2015.01.012Search in Google Scholar PubMed
15. Tzallas, AT, Tsipouras, MG, Fotiadis, DI. Epileptic seizure detection using time-frequency analysis. IEEE Trans Info Tech Biomed 2009;13:703–10. https://doi.org/10.1109/TITB.2009.2017939.Search in Google Scholar PubMed
16. Gandhi, TK, Chakaraborty, P, Roy, GG, Panigrahi, BK. Discrete harmony search based expert model for epileptic seizure detection in electroencephalography. Expert Sys App 2012;39:4055–62. https://doi.org/10.1016/j.eswa.2011.09.093.Search in Google Scholar
17. Acharya, UR, Sree, SV, Ang, PCA, Yanti, R, Suri, JS. Application of non-linear and wavelet based features for automated identification of EEG signals. Int J Neural Syst 2012;22:1–14. https://doi.org/10.1142/S0129065712500025.Search in Google Scholar PubMed
18. Li, S, Zhon, W, Yuan, Q, Liu, Y. Seizure prediction using spike rate of intracranial EEG. IEEE Trans Neural Syst Rehabil Eng 2013;21:880–6. https://doi.org/10.1109/TNSRE.2013.2282153.Search in Google Scholar PubMed
19. Zheng, Y, Wang, G, Wang, J. Epileptic seizure prediction using phase synchronization based on bivariate empirical mode decomposition. J Clin Neurophy 2014;125:1101–11. https://doi.org/10.1016/j.clinph.2013.09.047.Search in Google Scholar PubMed
20. Zandi, AS, Dumont, AS, Javidan, M, Tafreshi, R. An entropy based feature to predict seizure in temporal lobe epilepsy using scalp EEG. In: Proc. of IEEE conference on Engineeing in Medicine and Biological Science. Minneapolis, USA, 228–31; 2009.10.1109/IEMBS.2009.5333971Search in Google Scholar PubMed
21. Aarabi, A, He, B. A rule based seizure predictor method for focal neocortical epilepsy. J Clin Neurophy 2012;123:1111–22. https://doi.org/10.1016/j.clinph.2012.01.014.Search in Google Scholar PubMed PubMed Central
22. Leestma, JE, Kalekar, MB, Teas, SS, Jay, GW, Hughes, JR. Sudden unexpected death associated with seizures: analysis of 66 cases. Epilepsia 1984;25:84–8. https://doi.org/10.1111/j.1528-1157.1984.tb04159.x.Search in Google Scholar PubMed
23. Goldberger, AL, Amaral, LAN, Glass, L, Hausdorff, JM, Lvanaon, PCh, Mark, RG, et al. Physiobank, Physiotoolkit and Physionet: components of a new research resource for complex physiological signals. Circulation 2000;101:e215–20.10.1161/01.CIR.101.23.e215Search in Google Scholar
24. Hamaneh, MB, Chitravas, N, Kaiboriboon, K, Lohatoo, SD. Automated removal of EKG artefacts from EEG data using independent component analysis and continuous wavelet transfrom. IEEE Trans Biomed Eng 2014;61:1634–41. https://doi.org/10.1109/TBME.2013.2295173.Search in Google Scholar
25. Jin, W, Yao, L. An automated detection and correction method of EOGartifacts in EEG based BCI. In: Proc. of ICME international conference on complex medical engineering. Temple, AZ, 1–5; 2009.Search in Google Scholar
26. Mahesh, S, Chavan, S, Agarwala, RA, Uplane, MD. Rectangular window for interference reduction in EEG. In: Proc. of 7th WEAS transaction on signal processing, Istnabul, Turkey, 110–14; 2008.Search in Google Scholar
27. Khan, YU, Gotman, J. Wavelet based automatic seizure detection in intracerebral electroencephalogram. J Clin Neurophy 2003;114:898–908. https://doi.org/10.1016/S1388-2457(03)00035-X.Search in Google Scholar
28. Glavinovitch, A, Swamy, MS, Plotkin, EI. Wavelet-based segmentation techniques in the detection of microarousals in the sleep EEG. In: IEEE proceedings in 48th Midwest Symposium on Circuits and Systems, Covington, KY, USA, 1302–5; 2005.10.1109/MWSCAS.2005.1594348Search in Google Scholar
29. Johankhani, P, Kodogiannis, V, Revett, K. EEG signal classification using wavelet feature extraction and neural networks. IEEE Inter Symp Modern Comput 2006;120–24. https://doi.org/10.1109/JVA.2006.17.Search in Google Scholar
30. Dimoulas, C, Kalliris, G, Papanikolaou, G, Kalampakas, A. Long-term signal detection, segmentation and summarization using wavelets and fractal dimension: A bioacoustics application in gastrointestinal-motility monitoring. Comput Biol Med 2007;37:438–62. https://doi.org/10.1016/j.compbiomed.2006.08.013.Search in Google Scholar PubMed
31. Chien, TW, Dillon, DG, Hsu, HC, Huang, S, Barrick, E, Liu, YH. Depression detection using relative EEG power induced by emotionally positive images and a conformal kernel support vector machine. J Appl Sci 2018;8:1–18. https://doi.org/10.3390/app8081244.Search in Google Scholar
© 2020 Walter de Gruyter GmbH, Berlin/Boston
