Predicting state transitions in brain dynamics through spectral difference of phase-space graphs
- 8 Downloads
Networks are naturally occurring phenomena that are studied across many disciplines. The topological features of a network can provide insight into the dynamics of a system as it evolves, and can be used to predict changes in state. The brain is a complex network whose temporal and spatial behavior can be measured using electroencephalography (EEG). This data can be reconstructed to form a family of graphs that represent the state of the brain over time, and the evolution of these graphs can be used to predict changes in brain states, such as the transition from preictal to ictal in patients with epilepsy. This research proposes objective indications of seizure onset observed from minimally invasive scalp EEG. The approach considers the brain as a complex nonlinear dynamical system whose state can be derived through time-delay embedding of the EEG data and characterized to determine change in brain dynamics related to the preictal state. This method targets phase-space graph spectra as biomarkers for seizure prediction, correlates historical degrees of change in spectra, and makes accurate prediction of seizure onset. A significant trend of normalized dissimilarity over time indicates a departure from the norm, and thus a change in state. Our methods show high sensitivity (90–100%) and specificity (90%) on 241 h of scalp EEG training data, and sensitivity and specificity of 70%–90% on test data. Moreover, the algorithm was capable of processing 12.7 min of data per second on an Intel Core i3 CPU in Matlab, showing that real-time analysis is viable.
KeywordsGraph spectra Epilepsy Seizure prediction Phase-space graph analysis
Compliance with Ethical Standards
Conflict of interests
The authors declare that they have no conflict of interest.
- Andrzejak, R.G., Lehnertz, K., Mormann, F., Rieke, C., David, P., Elger, C.E. (2001). Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: dependence on recording region and brain state. Physical Review E, 64(6), 061,907.CrossRefGoogle Scholar
- Ashbee, W.S., Hively, L., McDonald, J. (2014). Nonlinear epilepsy forewarning by support vector machines. In Epilepsy topics: InTech.Google Scholar
- Bollobás, B. (2013). Modern graph theory, vol. 184. Springer Science & Business Media.Google Scholar
- Cook, M.J., O’Brien, T.J., Berkovic, S.F., Murphy, M., Morokoff, A., Fabinyi, G., D’Souza, W., Yerra, R., Archer, J., Litewka, L., et al. (2013). Prediction of seizure likelihood with a long-term, implanted seizure advisory system in patients with drug-resistant epilepsy: a first-in-man study. The Lancet Neurology, 12(6), 563–571.CrossRefGoogle Scholar
- Cook, M.J., Varsavsky, A., Himes, D., Leyde, K., Berkovic, S.F., O’Brien, T., Mareels, I. (2014). The dynamics of the epileptic brain reveal long-memory processes. Frontiers in Neurology, 5, 217.Google Scholar
- Epilepsy Foundation of Michigan. (2011). http://www.epilepsymichigan.org/page.php?id=358. Website.
- Fraleigh, J., Beauregard, R., Katz, V. (1995). Linear Algebra, vol. 53.Google Scholar
- Gantmacher, F.R. (1960). Theory of matrices. 2V. New York: Chelsea.Google Scholar
- Henry, B., Lovell, N., Camacho, F. (2012). Nonlinear dynamics time series analysis. Nonlinear Biomedical Signal Processing: Dynamic Analysis and Modeling, 2, 1–39.Google Scholar
- Hively, L. (2009). Prognostication of helicopter failure. ORNL/TM-2009, vol. 244.Google Scholar
- Hively, L.M., & Ng, E.G. (1998). Integrated method for chaotic time series analysis. US Patent 5,815,413.Google Scholar
- Hively, L., Clapp, N., Daw, C., Lawkins, W., Eisenstadt, M. (1995). Nonlinear analysis of EEG for epileptic seizures. ORNL/TM-12961, Oak Ridge National Laboratory, Oak Ridge.Google Scholar
- Hively, L.M., McDonald, J.T., Munro, N., Cornelius, E. (2013). Forewarning of epileptic events from scalp EEG. In Biomedical sciences and engineering conference (BSEC), 2013 (pp. 1–4): IEEE.Google Scholar
- Huang, X., Altahat, S., Tran, D., Sharma, D. (2012). Human identification with electroencephalogram (eeg) signal processing. In 2012 International symposium on communications and information technologies (ISCIT) (pp. 1021–1026). IEEE.Google Scholar
- Kandel, E.R., Schwartz, J.H., Jessell, T.M., Siegelbaum, S.A., Hudspeth, A.J. (2000). Principles of neural science (Vol. 4). New York: McGraw-Hill.Google Scholar
- Kantz, H., & Schreiber, T. (2004). Nonlinear time series analysis (Vol. 7). Cambridge: Cambridge University Press.Google Scholar
- Luckett, P., McDonald, J.T., Hively, L.M. (2017). Dissimilarity of graph invariant features from EEG phase-space analysis. Computer Engineering and Information Technology, 6(3).Google Scholar
- Meghdadi, A.H., Fazel-Rezai, R., Aghakhani, Y. (2017). Seizure prediction by nonlinear smoothness analysis of scalp eeg recording. CMBES Proceedings, 30(1).Google Scholar
- Osorio, I., Zaveri, H.P., Frei, M.G., Arthurs, S. (2016). Epilepsy: the intersection of neurosciences, biology, mathematics, engineering, and physics. Boca Raton: CRC Press.Google Scholar
- Sayama, H. (2015). Introduction to the modeling and analysis of complex systems. Open SUNY Textbooks.Google Scholar
- Takens, F. (1981). Detecting strange attractors in turbulence. In Dynamical systems and turbulence, Warwick 1980 (pp. 366–381). Berlin: Springer.Google Scholar
- World Health Organization. (2014). World health organization. http://www.who.int/mediacentre/factsheets/fs999/en/. Website.
- Xiao, C., Wang, S., Iasemidis, L., Wong, S., Chaovalitwongse, W.A. (2017). An adaptive pattern learning framework to personalize online seizure prediction. IEEE Transactions on Big Data, (1), 1-1.Google Scholar
- Zandi, A.S., Tafreshi, R., Javidan, M., Dumont, G.A. (2010). Predicting temporal lobe epileptic seizures based on zero-crossing interval analysis in scalp EEG. In 2010 annual international conference of the IEEE engineering in medicine and biology society (EMBC) (pp. 5537–5540). IEEE.Google Scholar
- Zheng, Y., Zhang, H., Yu, Y. (2015). Detecting collective anomalies from multiple spatio-temporal datasets across different domains. In Proceedings of the 23rd SIGSPATIAL international conference on advances in geographic information systems (p. 2). ACM.Google Scholar
- Zhu, J., He, W., Yang, H. (2008). Contrastive analysis of correlation dimension of EEG signals between normal and pathological groups. In Automation congress, 2008. WAC 2008. World (pp. 1–4). IEEE.Google Scholar