Expert Systems with Applications, vol.184, 2021 (SCI-Expanded)
Epilepsy is a chronic brain disorder, and for at least one- third of epilepsy patients, medications do not adequately control seizures and surgery is the only potential cure. An automated seizure detector that requires a short period of normal EEG would shorten the seizure monitoring durations, decrease the need for manual assessment of large amount of recorded EEG data, and accordingly assist the neurologists focus on improving quality of care. In this work, we propose a novel approach based on the extended cumulative sum test to detect seizures using intracranial EEG. Different than the existing machine learning approaches, this method requires only a short period of normal EEG for training. In addition to a new proposed feature based on partial directed coherence and random graph theory, in this work, previously developed features used to characterize seizures are used as features in cumulative sum test for seizure detection. A total of 33 intracranial EEG recordings collected from a total of 9 patients corresponding to three different datasets have been used for the analysis purposes: (i) the first dataset includes 11 recorded EEG files (~12.5 min) from 4 patients; (ii) the second dataset includes 20 recorded EEG files (~30 min) from 4 patients; and (iii) two 24-hour long EEG files from a single patient. The proposed detector achieved a mean sensitivity and mean specificity for the first (0.77, 0.86), second (0.88, 0.9) and third datasets (0.92, 0.94) respectively. Statistical detection of seizures has shown success in detecting seizures without the need for highly customizable parameters or previously labelled EEG data. The proposed method could be used in real-time at hospital settings with a minimum requirement of training data.