Model-based seizure detection method using statistically optimal null filters

In this paper, a model-based seizure detection method using statistically optimal null filters (SONFs) is presented. A template seizure from a patient is first selected and the basis functions required by the SONF are derived from this template seizure using wavelet transform. Subsequent EEG (electroencephalogram) recording is processed by the SONF and the output represents the noise-free estimate of the seizure. The energy ratio between the output and the input of the SONF is calculated and used as the test statistic for the seizure detection. Experiments using the SEEG (stereoelectroencephalogram, or intracerebral EEG) recordings of two patients show that this is an effective and promising method, with the possibility of reduced false detections.

[1]  J. Gotman,et al.  A patient-specific algorithm for the detection of seizure onset in long-term EEG monitoring: possible use as a warning device , 1997, IEEE Transactions on Biomedical Engineering.

[2]  J Gotman,et al.  Automatic detection of seizures and spikes. , 1999, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[3]  M. Swamy,et al.  Statistically optimal null filter based on instantaneous matched processing , 2001 .

[4]  A J Gabor,et al.  Seizure detection using a self-organizing neural network: validation and comparison with other detection strategies. , 1998, Electroencephalography and clinical neurophysiology.