Improved patient specific seizure detection during pre-surgical evaluation

Abstract

Publication informationClinical Neurophysiology, 122 (4): 672-679Publisher Elsevier Item record/more information http://hdl.handle.net/10197/7034 Publisher's statementThis is the author's version of a work that was accepted for publication in Clinical Neurophysiology. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Clinical Neurophysiology (VOL 122, ISSUE 4, (2011) AbstractObjective: There is considerable interest in improved off-line automated seizure detection methods that will decrease the workload of EEG monitoring units. Also, subject-specific approaches have been demonstrated to perform better than subject-independent ones. However, for pre-surgical diagnostics, the traditional method of obtaining a priori data to train subject-specific classifiers is not practical. We present an alternative method that works by adapting the threshold of a subject-independent to a specific subject based on feedback from the user. Methods:A subject-independent quadratic discriminant classifier incorporating modified features based partially on the Gotman algorithm was first built. It was then used to derive subject-specific classifiers by determining subject-specific posterior probability thresholds via user interaction. The two schemes were tested on 529 hours of intracranial EEG containing 63 seizures from 15 subjects undergoing pre-surgical evaluation. To provide comparison, the standard Gotman algorithm was implemented and optimised for this dataset by tuning the detection thresholds.Results: Compared to the tuned Gotman algorithm, the subject-independent scheme reduced the false positive rate by 51 % (0.23 h -1 to 0.11 h -1 ) while increasing sensitivity from 53 % to 62 %. The subject-specific scheme further improved sensitivity to 78 %, but with a small increase in false positive rate to 0.18 h -1 ). Conclusions:The results suggest that a subject-independent classifier scheme with modified features is useful for reducing false positive rate, while subject adaptation further enhances performance by improving sensitivity. The results also suggest that 4 the proposed subject-adapted classifier scheme approximate the performance of the subject-specific Gotman algorithm. Significance:The proposed method could potentially help increase productivity of offline EEG analysis. The approach could also be generalised to enhance the performance of other subject independent algorithms. 5

Wavelet multiresolution analysis and dyadic scalogram for detection of epileptiform paroxysms in electroencephalographic signals

“…Other wavelet-based systems in (Aarabi et al, 2009), (Chua et al, 2011) and (Ayoubian et al, 2013) achieved a sensitivity of 68.9%, 78%, and 72%, respectively, closed to our results (77.98%). Hence, the wavelet dyadic scalogram and artificial neural network proposed here have obtained competitive results in comparison with current expert systems for epilepsy detection.…”

An algorithm for seizure onset detection using intracranial EEG

“…Algorithms such as those described by Chan et al [17] and Chua et al [18] were designed for offline IEEG analysis, and cannot be implemented as part of a real-time warning system. The patient-specific method of Zhang et al [19] yielded a sensitivity of 98.8%, a mean latency of 10.8 seconds, and a combined false alarm rate of 11.8/day when tested on IEEG from 21 patients.…”

Seizure detection approach using S-transform and singular value decomposition

“…Experimental results show that our proposed method achieved a sensitivity of 96.40%, with a false detection rate of 0.16/h. Improved patient-specific seizure detection [27] 78 63 0.18 -Differential windowed variance [28] 91.525 59 -3 Multistage seizure detection [29] 87.5 24 -3 A fuzzy logic system [30] 95 …”

“…Chua et al developed an improved patientspecific seizure detection system in which four features, including relative half-wave amplitude, rectified zero crossings, coefficient of variation of half-wave duration, and line length, were used with a quadratic discriminant analysis (QDA) classifier to distinguish between seizure and nonseizure data [27]. The algorithm was tested on 63 seizures Fig.…”