Automatic spike detection via an artificial neural network using raw EEG data: effects of data preparation and implications in the limitations of online recognition

OBJECTIVE Automatic detection of epileptic EEG spikes via an artificial neural network has been reported to be feasible using raw EEG data as input. This study re-investigated its suitability by further exploring the effects of data preparation on classification performance testing. METHODS Six hundred EEG files (300 spikes and 300 non-spikes) taken from 20 patients were included in this study. Raw EEG data were sent to the neural network using the architecture reported to give best performance (30 input-layer and 6 hidden-layer neurons). RESULTS Significantly larger weighting of the 10th input-layer neuron was found after training with prepared raw EEG data. The classification process was thus dominated by the peak location. Subsequent analysis showed that online spike detection with an erroneously trained network yielded an area less than 0.5 under the receiver-operating-characteristic curve, and hence performed inferiorly to random assignments. Networks trained and tested using the same unprepared EEG data achieved no better than about 87% true classification rate at equal sensitivity and specificity. CONCLUSIONS The high true classification rate reported previously is believed to be an artifact arising from erroneous data preparation and off-line validation. Spike detection using raw EEG data as input is unlikely to be feasible under current computer technology.

[1]  D E Blum,et al.  Computer-based electroencephalography: technical basics, basis for new applications, and potential pitfalls. , 1998, Electroencephalography and clinical neurophysiology.

[2]  Ilker Yaylali,et al.  Multilevel neural network system for EEG spike detection , 1991, [1991] Computer-Based Medical Systems@m_Proceedings of the Fourth Annual IEEE Symposium.

[3]  A J Gabor,et al.  Automated interictal EEG spike detection using artificial neural networks. , 1992, Electroencephalography and clinical neurophysiology.

[4]  O Ozdamar,et al.  Detection of spikes with artificial neural networks using raw EEG. , 1998, Computers and biomedical research, an international journal.

[5]  Benjamin M. W. Tsui,et al.  Principles of Medical Imaging , 1992 .

[6]  Ronald G. Emerson,et al.  Spike detection II: automatic, perception-based detection and clustering , 1999, Clinical Neurophysiology.

[7]  P Naitoh,et al.  Intra-hemispheric phase relationships during self-regulated alpha activity. , 1974, Electroencephalography and clinical neurophysiology.

[8]  E. Wyllie,et al.  The Treatment of Epilepsy: Principles and Practice , 1997 .

[9]  W R Webber,et al.  Practical detection of epileptiform discharges (EDs) in the EEG using an artificial neural network: a comparison of raw and parameterized EEG data. , 1994, Electroencephalography and clinical neurophysiology.

[10]  Separable Regions.  On Hidden Nodes for Neural Nets , 1989 .

[11]  J Gotman,et al.  Seizure recognition and analysis. , 1985, Electroencephalography and clinical neurophysiology. Supplement.

[12]  I. Bankman,et al.  Automatic EEG spike detection: what should the computer imitate? , 1993, Electroencephalography and clinical neurophysiology.