A nonparametric feature for neonatal EEG seizure detection based on a representation of pseudo-periodicity

Stevenson, Nathan J.; O’Toole, John M.; Rankine, L.; Boylan, Geraldine B.; Boashash, Boualem

doi:10.1016/j.medengphy.2011.08.001

Cited by 36 publications

(31 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The level of agreement reached by the human expert, however, was impressive with a "false positive" rate of one every 7 h of reviewed EEG. A result which, so far, has not been matched by any automated method of neonatal seizure detection at equivalent seizure detection rates 23, 24, 25, 26. These results set a target of aspiration for such systems, which are relatively low cost, indefatigable, and constantly available.…”

Section: Discussionmentioning

confidence: 99%

Interobserver agreement for neonatal seizure detection using multichannel EEG

Stevenson

Clancy

Vanhatalo

et al. 2015

Ann Clin Transl Neurol

View full text Add to dashboard Cite

ObjectiveTo determine the interobserver agreement (IOA) of neonatal seizure detection using the gold standard of conventional, multichannel EEG.MethodsA cohort of full‐term neonates at risk of acute encephalopathy was included in this prospective study. The EEG recordings of these neonates were independently reviewed for seizures by three international experts. The IOA was estimated using statistical measures including Fleiss' kappa and percentage agreement assessed over seizure events (event basis) and seizure duration (temporal basis).ResultsA total of 4066 h of EEG recordings from 70 neonates were reviewed with an average of 2555 seizures detected. The IOA was high with temporal assessment resulting in a kappa of 0.827 (95% CI: 0.769–0.865; n = 70). The median agreement was 83.0% (interquartile range [IQR]: 76.6–89.5%; n = 33) for seizure and 99.7% (IQR: 98.9–99.8%; n = 70) for nonseizure EEG. Analysis of events showed a median agreement of 83.0% (IQR: 72.9–86.6%; n = 33) for seizures with 0.018 disagreements per hour (IQR: 0.000–0.090 per hour; n = 70). Observers were more likely to disagree when a seizure was less than 30 sec. Overall, 33 neonates were diagnosed with seizures and 28 neonates were not, by all three observers. Of the remaining nine neonates with contradictory EEG detections, seven presented with low total seizure burden.InterpretationThe IOA is high among experts for the detection of neonatal seizures using conventional, multichannel EEG. Agreement is reduced when seizures are rare or have short duration. These findings support EEG‐based decision making in the neonatal intensive care unit, inform EEG interpretation guidelines, and provide benchmarks for seizure detection algorithms.

show abstract

Section: Discussionmentioning

confidence: 99%

Interobserver agreement for neonatal seizure detection using multichannel EEG

Stevenson

Clancy

Vanhatalo

et al. 2015

Ann Clin Transl Neurol

View full text Add to dashboard Cite

show abstract

“…This information will be useful when constructing new nonstationary methods for automatic detection and classification of seizure or for improving existing methods such as [19,20]. This study was not exhaustive as there are other aspects of the seizure components that can be investigated as potential discriminating features.…”

Section: Discussionmentioning

confidence: 99%

“…Many IF estimating techniques have been proposed in the literature and an extensive review can be found in [26]. [20,28,29]. As seizure signals mostly have a high signal-to-noise (SNR) ratio [16,22], we decided to use this more established method for IF estimation rather than, for example, using the more recently proposed method for extracting IF from signals with low SNR [27].…”

Section: Instantaneous Frequencymentioning

confidence: 99%

“…In this study, we analysed newborn EEGs using a quadratic TFD with separable kernel to characterise seizures in the time-frequency domain. We extracted the instantaneous frequency (IF) from the TFD to determine its modulation law; an important descriptive characteristic of EEG seizure [14][15][16]19,20]. The IFs were extracted using a method designed specifically for multi-component signals [21] and applied to a separable kernel TFD with optimised parameters.…”

Section: Introductionmentioning

confidence: 99%

“…To further characterise the extracted IFs, we computed their mean frequency and frequency span. Characterisation of newborn EEG seizures is an essential step in a number of applications such as modelling [16,22] and detection/classification [15,19,20].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Instantaneous frequency based newborn EEG seizure characterisation

Mesbah

O’Toole

Colditz

et al. 2012

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

The electroencephalogram (EEG), used to noninvasively monitor brain activity, remains the most reliable tool in the diagnosis of neonatal seizures. Due to their nonstationary and multi-component nature, newborn EEG seizures are better represented in the joint time-frequency domain than in either the time domain or the frequency domain. Characterising newborn EEG seizure nonstationarities helps to better understand their time-varying nature and, therefore, allow developing efficient signal processing methods for both modelling and seizure detection and classification. In this article, we used the instantaneous frequency (IF) extracted from a time-frequency distribution to characterise newborn EEG seizures. We fitted four frequency modulated (FM) models to the extracted IFs, namely a linear FM, a piecewise-linear FM, a sinusoidal FM, and a hyperbolic FM. Using a database of 30-s EEG seizure epochs acquired from 35 newborns, we were able to show that, depending on EEG channel, the sinusoidal and piecewise-linear FM models best fitted 80-98% of seizure epochs. To further characterise the EEG seizures, we calculated the mean frequency and frequency span of the extracted IFs. We showed that in the majority of the cases (>95%), the mean frequency resides in the 0.6-3 Hz band with a frequency span of 0.2-1 Hz. In terms of the frequency of occurrence of the four seizure models, the statistical analysis showed that there is no significant difference (p = 0.332) between the two hemispheres. The results also indicate that there is no significant differences between the two hemispheres in terms of the mean frequency (p = 0.186) and the frequency span (p = 0.302).

show abstract