Patient-Specific Early Seizure Detection From Scalp Electroencephalogram

Abstract

Objective Develop a method for automatic detection of seizures prior to or immediately after clinical onset using features derived from scalp EEG. Methods This detection method is patient-specific. It uses recurrent neural networks and a variety of input features. For each patient we trained and optimized the detection algorithm for two cases: 1) during the period immediately preceding seizure onset, and 2) during the period immediately following seizure onset. Continuous scalp EEG recordings (duration 15 – 62 h, median 25 h) from 25 patients, including a total of 86 seizures, were used in this study. Results Pre-onset detection was successful in 14 of the 25 patients. For these 14 patients, all of the testing seizures were detected prior to seizure onset with a median pre-onset time of 51 sec and false positive rate was 0.06/h. Post-onset detection had 100% sensitivity, 0.023/hr false positive rate and median delay of 4 sec after onset. Conclusions The unique results of this study relate to pre-onset detection. Significance Our results suggest that reliable pre-onset seizure detection may be achievable for a significant subset of epilepsy patients without use of invasive electrodes.

Personalized neuroscience: User modeling of cognitive function and brain activity in the cloud

“…The adult brain also reliably expresses electrical activity patterns, enabling detection and prediction of specific states or events, such as drowsiness, seizure, and loss of focus [5], [6]. Development of a neurobehavioral user model that would enable the identification of deviations from typical patterns remains difficult due to the lack of a generic model upon which to base comparisons and build adaptive changes.…”

E EG - Based Epileptic Seizures Detection with Adaptive Learning Capability

“…Seizure detection method should be able to automatically adapt it properties to tackle this condition. However most of the proposed methods rely on extensive pre-training process for their machine learning algorithm (e.g, using ANN [11,14,16] or SVM [10,12,[21][22]). Huge training data, both for normal EEG and EEG with seizures, are needed to obtain accurate seizure detector.…”

“…Recently, several promising EEG signal processing and feature extraction methods for seizure detection are proposed [10][11][12][13][14][15][16][17][18][19][20][21][22][23]. These methods could be further categorized into: timedomain (e.g, [10,11]), frequency-domain (e.g, using filter bank [12] and sign periodogram transform [13]), time-frequency domain (e.g, wavelet transform [14][15][16][17]), nonlinear methods (e.g, using various entropies [18][19]) or combination of them (e.g, [10,20]).…”

“…These methods could be further categorized into: timedomain (e.g, [10,11]), frequency-domain (e.g, using filter bank [12] and sign periodogram transform [13]), time-frequency domain (e.g, wavelet transform [14][15][16][17]), nonlinear methods (e.g, using various entropies [18][19]) or combination of them (e.g, [10,20]). Other methods include using spatial filter (e.g, common spatial filter [21]) and transforming EEG signal into 2D image (e.g, image texture analysis [22]).…”

“…Other methods include using spatial filter (e.g, common spatial filter [21]) and transforming EEG signal into 2D image (e.g, image texture analysis [22]). Different artificial intelligent and machine learning techniques are used also for EEG signal classification such as artificial neural network (ANN) [11,14,16], support vector machines (SVM) [10,12,[21][22] and k-nearest neighbor (KNN) [20].…”