Classifier Cascade to Aid in Detection of Epileptiform Transients in Interictal EEG

The presence of Epileptiform Transients (ET) in the electroencephalogram (EEG) is a key finding in the medical workup of a patient with suspected epilepsy. Automated ET detection can increase the uniformity and speed of ET detection. Current ET detection methods suffer from insufficient precision and high false positive rates. Since ETs occur infrequently in the EEG of most patients, the majority of recordings comprise background EEG waveforms. In this work we establish a method to exclude as much background data as possible from EEG recordings by applying a classifier cascade. The remaining data can then be classified using other ET detection methods. We compare a single Support Vector Machine (SVM) to a cascade of SVMs for detecting ETs. Our results show that the precision and false positive rate improve significantly by incorporating a classifier cascade before ET detection. Our method can help improve the precision and false positive rate of an ET detection system. At a fixed sensitivity, we were able to improve precision by 6.78%; and at a fixed false positive rate, the sensitivity improved by 2.83%.

[1]  Scott B. Wilson,et al.  Spike detection: Inter-reader agreement and a statistical Turing test on a large data set , 2017, Clinical Neurophysiology.

[2]  Justin Dauwels,et al.  SpikeGUI: Software for rapid interictal discharge annotation via template matching and online machine learning , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[3]  Justin Dauwels,et al.  Fast and efficient rejection of background waveforms in interictal EEG , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[4]  Michel J. A. M. van Putten,et al.  Inter-ictal spike detection using a database of smart templates , 2013, Clinical Neurophysiology.

[5]  Min Wang,et al.  Automatic detection of interictal epileptiform discharges based on time-series sequence merging method , 2013, Neurocomputing.

[6]  Giridhar P Kalamangalam,et al.  Characteristics of EEG Interpreters Associated With Higher Interrater Agreement , 2017, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[7]  K. P. Indiradevi,et al.  A multi-level wavelet approach for automatic detection of epileptic spikes in the electroencephalogram , 2008, Comput. Biol. Medicine.

[8]  Selim R. Benbadis,et al.  Errors in EEGs and the misdiagnosis of epilepsy: Importance, causes, consequences, and proposed remedies , 2007, Epilepsy & Behavior.

[9]  C. V. van Donselaar,et al.  Value of the electroencephalogram in adult patients with untreated idiopathic first seizures. , 1992, Archives of neurology.

[10]  Elif Derya Übeyli,et al.  Adaptive neuro-fuzzy inference system for classification of EEG signals using wavelet coefficients , 2005, Journal of Neuroscience Methods.

[11]  Stefan Seidel,et al.  Incidental epileptiform discharges in patients of a tertiary centre , 2016, Clinical Neurophysiology.

[12]  Justin Dauwels,et al.  Interictal epileptiform discharge characteristics underlying expert interrater agreement , 2017, Clinical Neurophysiology.

[13]  Robert J. Schalkoff,et al.  Standardized database development for EEG epileptiform transient detection: EEGnet scoring system and machine learning analysis , 2013, Journal of Neuroscience Methods.

[14]  N. Fountain,et al.  EEG Is an Essential Clinical Tool: Pro and Con , 2006, Epilepsia.

[15]  Peter Dayan,et al.  A novel method for automated classification of epileptiform activity in the human electroencephalogram-based on independent component analysis , 2008, Medical & Biological Engineering & Computing.

[16]  Yung-Nien Sun,et al.  Model-Based Spike Detection of Epileptic EEG Data , 2013, Sensors.

[17]  Patrick Van Bogaert,et al.  Cluster-based spike detection algorithm adapts to interpatient and intrapatient variation in spike morphology , 2012, Journal of Neuroscience Methods.

[18]  Jurriaan M. Peters,et al.  Automated quantification of spikes , 2013, Epilepsy & Behavior.

[19]  Ronald P. Lesser,et al.  Automated spike detection in EEG , 2017, Clinical Neurophysiology.

[20]  Jonathan J. Halford,et al.  Computerized epileptiform transient detection in the scalp electroencephalogram: Obstacles to progress and the example of computerized ECG interpretation , 2009, Clinical Neurophysiology.

[21]  Lawrence Ver Hoef,et al.  Effect of Detection Parameters on Automated Electroencephalography Spike Detection Sensitivity and False-Positive Rate , 2010, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.