An automatic warning system for epileptic seizures recorded on intracerebral EEGs

Objective A new clinical seizure waning system for intracerebral EEG is proposed. It is aimed at a better performance than existing systems and at user tuneability. Methods The system employs data filtering in multiple bands, spectral feature extraction, Bayesʹ theorem, and spatio-temporal analysis. The a priori information in Bayesʹ theorem was provided by 407 h of EEG from 19 patients having 152 seizures. Results The testing data (19 patients, 389 h, 100 seizures, independent of the training data) yielded a sensitivity of 89.4%, a false detection rate of 0.22/h, and median delay time of 17.1 s when tuning was used, and 86%, 0.47/h and 16.2 s without tuning. Missed seizures were of short duration or had subtle seizure activity. False detections were caused by technical artefacts, non-epileptic large amplitude rhythmic bursts or very low amplitude activity. It was established that performance could easily be tuned. Results were also compared to the clinical system of Gotman (1990). Conclusions The system offers a performance that is acceptable for clinical use. User tuneability allows for reduction in false detection with minimal loss to sensitivity. Significance Epilepsy monitoring generates large amounts of recordings and requires intense observation. Automatic seizure detection and warning systems reduce review time and facilitate observation. We propose a method with high sensitivity and few false alarms.