Background & Objectives: Epilepsy is a neurological disorder that is associated with repeated episodes of seizures. In epilepsy, the normal pattern of neural activity is disturbed, causing the patient to experience various symptoms ranging from staring blanking for a few seconds to long periods of vigorous convulsions and unconsciousness. In many patients, the injuries they endure are a direct result of the confusion, loss of muscle control, and unconsciousness caused by the seizure. These injuries include fractures, head injuries, and burns. In an attempt to mitigate such risks, extensive research has been dedicated to developing a device that can detect or predict the onset of seizure episodes. The clinical behavior of an epileptic seizure is preceded and then accompanied by electroencephalographic alterations. As a result, electroencephalography (EEG) is the most common tool to measure these alterations. EEG measures the voltage fluctuations resulting from ionic current flows within the neurons of the brain. Research has demonstrated that epileptic seizures are caused by disturbances in the electrical activity between neurons in the brain. In the healthy brain, neurons fire in an asynchronous manner, relaying messages from one neural network to the other. However, in the epileptic brain, the complex interactions between neuronal networks are characterized by the evolution of synchronization between them. Excessive neuronal synchronization leads to a hyper-synchronous state that triggers the onset of a seizure. Methods: There are many ways to measure the synchrony between two or more continuous time series of brain activity, ranging from linear approaches such as the cross correlation and the spectral coherence function as well as nonlinear measures like mutual information, transfer entropy, Granger causality, or nonlinear interdependence. These measures yield low values for independent time series and high values for correlated time series. In this research, we present a novel patient-specific epileptic seizure onset detector using scalp EEG. The proposed detector employs a novel neural synchronization measure to compute the level of EEG channel synchronization at a particular time instant. Training a support vector machine, in the classification stage of the detector, on the calculated level of neural synchronization from a patient's pre-ictal, ictal, and post-ictal EEG, the detector is able to identify the electrographic onset of an imminent seizure. Results: The proposed detector successfully identifies EEG epochs that are highly synchronized as seizure epochs, while pre-ictal and post-ictal epochs are shown to have a significantly lower level of synchrony. The performance evaluation results of the proposed detector are closely aligned with the electrographic seizure onset time that an expert has visually determined. Conclusion: The quality of life of epileptic patients that suffer from intractable seizures can be enhanced by equipping them with a device that can alert them ahead of time of an imminent seizure. The dramatic increase of synchronization between neuron firing during a seizure is clearly detected using the novel synchronization measure that we propose. The proposed seizure onset detector clearly identifies times of increased neural synchrony and sends an alarm at the earliest abnormal electrographic changes of a patient.


Article metrics loading...

Loading full text...

Full text loading...

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error