EEG Features as Biomarkers for Discrimination of Preictal States
- 1.3k Downloads
The aim of this study is the selection of the most relevant features of electroencephalograms (EEG) for classification and clustering of preictal states. First, a sum of 312 time series features were computed on consecutive segments of preictal EEG (simple statistical measures, linear and nonlinear measures), where some of them regard different method specific parameters. The efficiency of three methods for feature selection was assessed, i.e., the Forward Sequential Selection (FSS), Support Vector Machines with Recursive Feature Elimination (SVM-RFE) and a MI filter. The classification was applied first to 1000 realizations of simulated data from the Mackey–Glass system at different high dimensional chaotic regimes, and next to 12 scalp early and late preictal EEG recordings of different epileptic patients (about 3 h and half an hour before the seizure onset, respectively). The optimal feature subsets selected by the three feature selection strategies for the same classification problems were found very often to have common features. Based on these feature subsets, classification with k-means partitioning as well as SVM was assessed on test sets of EEG from the same recordings. Feature subsets for each channel and episode or only episode did not classify on the test set as well as a global feature subset of a sufficiently large number of the most frequent features over all channels and episodes. We concluded that a global feature subset of 16 most frequent features can play the role of a biomarker and distinguish early and late preictal states.
KeywordsFeature Selection Feature Subset Detrended Fluctuation Analysis Feature Selection Algorithm Recursive Feature Elimination
Unable to display preview. Download preview PDF.
We thank Pål G. Larsson from the National Center of Epilepsy of Norway for providing the EEG data.
- 1.Berry, M.J., Linoff, G.: Data Mining Techniques: For Marketing, Sales, and Customer Support. John Wiley & Sons, Inc., New York, NY (1997)Google Scholar
- 2.Brown, B.: A new perspective for information theoretic feature selection. In: 12th International Conference on Artificial Intelligence and Statistics (AISTATS), vol. 5. Journal of Machine Learning Research (2009)Google Scholar
- 4.Bruzzo, A.A., Gesierich, B., Santi, M., Tassinari, C.A., Birbaumer, N., Rubboli, G.: Permutation entropy to detect vigilance changes and preictal states from scalp EEG in epileptic patients. a preliminary study. Neurological Sciences 29(1), 3 – 9 (2008)Google Scholar
- 8.D’Alessandro, M., Esteller, R., Vachtsevanos, G., Hinson, A., Echauz, J., Litt, B.: Epileptic seizure prediction using hybrid feature selection over multiple intracranial EEG electrode contacts: a report of four patients. IEEE Transactions on Biomedical Engineering 50(5), 603 – 615 (2007)CrossRefGoogle Scholar
- 10.Duda, R., Hart, P., Stork, D.: Pattern Classification, second edn. Wiley-Interscience (2001)Google Scholar
- 17.Iasemidis, L., Pardalos, P., Shiau, D.S., Chaovalitwongse, W., Narayanan, K., Kumar, S., Carney, P., Sackellares, J.: Prediction of human epileptic seizures based on optimization and phase changes of brain electrical activity. Journal of Optimization Methods and Software 18(1), 81 – 104 (2003)MathSciNetzbMATHCrossRefGoogle Scholar
- 24.Kugiumtzis, D., Vlachos, I., Papana, A., Larsson, P.G.: Assessment of measures of scalar time series analysis in discriminating preictal states. International Journal of Bioelectromagnetism 9(3), 134–145 (2007)Google Scholar
- 26.Liu, H., Liu, L., Zhang, H.: Feature selection using mutual information: An experimental study. In: T.B. Ho, Z.H. Zhou (eds.) PRICAI 2008: Trends in Artificial Intelligence, Lecture Notes in Computer Science, vol. 5351, pp. 235–246. Springer Berlin / Heidelberg (2008)Google Scholar
- 27.Liu, H., Motoda, H.: Computational Methods of Feature Selection. Chapman and Hall, CRC Press (2008)Google Scholar
- 30.Meisler, M., E., J., O’Brien, E., Sharkey, M.: Sodium channel gene family: epilepsy mutations, gene interactions and modifier effects. The Journal of Physiology 588(11), 1841 – 1848 (2010)Google Scholar
- 32.Raymer, M., Punch, W., Goodman E.D.and Kuhn, L., Jain, A.: Dimensionality reduction using genetic algorithms. IEEE Transactions on Evolutionary Computation 4, 164 – 171 (2000)Google Scholar
- 36.Tsimpiris, A., Kugiumgis, D.: Feature selection for classification of oscillating time series. Expert Systems, doi:10.1111/j.1468-0394.2011.00605.x (2011)Google Scholar
- 37.Xu, G., Wang, J., Q, Z., Zhu, J.: An epileptic seizure prediction algorithm from scalp EEG based on morphological filter and Kolmogorov complexity. Lecture Notes in Computer Science 4561, 736 – 746 (2007)Google Scholar
- 39.Zaffalon, M., Hutter, M.: Robust feature selection by mutual information distributions. In: Proceedings of the 18th International Conference on Uncertainty in Artificial Intelligence (UAI-2002), pp. 577 – 584. Morgan Kaufmann (2002)Google Scholar