The Application of Neural Networks in Classification of Epilepsy Using EEG Signals
Epilepsy is a disorder of cortical excitability and still an important medical problem. The correct diagnosis of a patient’s epilepsy syndrome clarifies the choice of drug treatment and also allows an accurate assessment of prognosis in many cases. The aim of this study is to evaluate epileptic patients and classify epilepsy groups by using Multi-Layer Perceptron Neural Networks (MLPNNs). 418 patients with epilepsy diagnoses according to International League against Epilepsy (ILAE, 1981) were included in this study. The correct classification of this data was performed by two expert neurologists before they were executed by MLPNNs. The MLPNNs were trained by the parameters obtained from the EEG signals and clinic properties of the patients. We classified the epilepsy into two groups such as partial and primary generalized epilepsy and we achieved an 89.2% correct prediction rate by using MLPNN model. The parameters of the loss of consciousness in the course of seizure, the duration and ritmicity of abnormal activities found in EEG constituted the most significant variables in the classification of epilepsy by using MLPNN. These results indicate that the classification performance of MLPNN model for epilepsy groups is satisfactory and we think that this model may be used in clinical studies as a decision support tool to confirm the classification of epilepsy groups after they are developed.
KeywordsEpilepsy EEG Multilayer Perceptron Neural Network (MLPNN) Levenberg-Marquardt
Unable to display preview. Download preview PDF.
- 1.Pedley, T.A., Mendiratta, A., Walczak, T.S.: Seizures and epilepsy. In: Ebersole, J.S., Pedley, T.A. (eds.) Current Practice of Clinical Electroencephalography, pp. 506–587. Lippincott Williams & Wilkins Comp., USA (2002)Google Scholar
- 3.Smith, S.J.M.: EEG in diagnosis, classification, and management of patients with epilepsy. J. Neurol. Neurosurg. Psychiatry 76, 2–7 (2005)Google Scholar
- 5.Trescher, H.W., Lesser, R.P.: The Epilepsies. In: Bradley, G.W., Daroff, B.R. (eds.) Neurology in Clinical Practice, pp. 1745–1779. Buterworth-Heineman, USA (2000)Google Scholar
- 6.Kiloh, L.G., McComas, A.J., Osselton, J.W.: Clinical Electroencephalography, pp. 168–200. Butterworht & Co ltd., Great Britain (1972)Google Scholar
- 8.Tomida, S., Hanai, T., Koma, N., Suzuki, Y., Kobayashi, T., Honda, H.: Artificial neural network predictive model for allergic disease using neural network nucleotide polymorphisms data. Journal of Bioscience and Bioengineering 93(5), 470–478 (2002)Google Scholar
- 10.Itchhaaporia, D., Snow, P.B., Almassy, R.J., Oetgen, W.J.: Artificial neural networks: current status in cardiovascular medicine. JACC 28(2), 515–521 (1996)Google Scholar
- 19.Kellaway, P.: Orderly approach to visual analysis: Elements of the normal EEG and their characteristics in children and adults. In: Ebersole, J.S., Pedley, T.A. (eds.) Current practice of clinical electroencephalography, pp. 100–159. Lippincott Williams & Wilkins, Philadelphia (2002)Google Scholar
- 21.Bernand, E.: Optimization training neural nets. IEEE Trans. Neural Networks 3(2), 989–993 (1992)Google Scholar
- 23.Wilamowki, B.M., Iqlikci, S., Kaynak, O., Onder, E.M.: An algorithm for fast converges in training neural networks. In: IEEE Proceedings of International Joint Conference on Neural Networks, pp. 1778–1782 (2005)Google Scholar
- 25.Manolis, I.A.L., Antonis, A.A.: Is Levenberg-Marquardt the most efficient optimization algorithm for implementing bundle adjustment? IEEE Proceedings of International Conference on Computer Vision 2, 1526–1531 (2005)Google Scholar
- 26.Gaafar, L.K., Choueiki, M.H.A.: Neural network model for solving the lot sizing problem. The International Journal of Management Science 28, 175–184 (1999)Google Scholar
- 30.Grünewald, R.A., Chroni, E., Panayiotopoulos, P.P.: Delayed diagnosis of juvenile myoclonic epilepsy. J. Neurol. Neurosurg. Psychiatry 55, 487–490 (1992)Google Scholar