Danny Flanagan

Automatic seizure detection in the newborn: methods and initial evaluation

Seizures are most common in the newborn period, but at that age seizures can be very difficult to identify by clinical observation. Therefore the EEG plays an even greater role in newborns than in older children and adults. The electrographic features of seizures and EEG background in the newborn are, however, very different to those found in adults. We present a set of methods for the automatic detection of seizures in the newborn. The methods are aimed at detecting a wide range of patterns, including rhythmic paroxysmal discharges at a wide range of frequencies, as well as repetitive spike patterns, even when they are not very rhythmic. The methods were developed using EEGs obtained from 55 newborns, recorded at 3 hospitals that used differing monitoring protocols. A total of 281 h of recordings containing 679 seizures were analyzed. An initial evaluation indicated that 71% of the seizures and 78% of seizure clusters (group of seizures separated by less than 90 s) were detected, with a false detection rate of 1.7/h. The methods were developed so that they can be implemented to operate in real time.

Spatial and Temporal Characteristics of Neonatal Seizures

Summary: Thirty‐two neonates (26 term and 6 premature) having seizures were prospectively recruited and studied. Using prolonged video/EEG monitoring, we quantified seizure variables (electrographic and clinical seizure durations, interictal periods and electrographic seizure spread) for all 1,420 seizures recorded. The effects of time and antiepileptic drug (AED) therapy were analyzed statistically. Seizures were generally frequent, with limited electrographic spread. However, some neonates had consistently longer interictal periods and 13% had mean interictal periods >60 min. Seizure variables were relatively stable over time, but they changed with AED therapy. There was a trend to decreased seizure duration, increased length of interictal periods, and decreased electrographic spread. Furthermore, there was evidence of reduced clinical features after sequential AED infusions. Seizures ceased during the monitoring period in 22 neonates. Eighty‐five percent of all seizures had no clinical manifestations. Among neonates with clear clinical correlates, clinical observations underestimated electrographic seizures in individual neonates by a mean of 54% (range 0–95%). Seizures generally had limited electrographic spread. Use of only four recording electrodes, characteristic of some portable EEG systems, underestimated seizures in 19 neonates, and missed all seizures in 2.

Evaluation of an automatic seizure detection method for the newborn EEG.

In another publication, we described a set of methods for automatic detection of EEG seizures in the newborn. We describe here the evaluation of these methods using a completely new set of data, which were not used in developing the method. This testing data set consisted of recording from 54 patients, lasting an average of 4.4 h. Recordings had 8-16 channels and were obtained, in approximately equal numbers, from 3 institutions in Canada, the USA and Australia. Recording conditions varied from short recordings fully attended by a technologist to overnight recordings largely unattended. The average seizure detection rate was 69% (77%, 53%, 84% in the 3 institutions). False detections occurred at the average rate of 2.3/h (4.1, 1.0, 2.7 in the 3 institutions), with fluctuations that reflected largely the technical quality and level of supervision of the recordings. The results are similar to those obtained in the commonly used method of epilepsy monitoring in adults and allow us to envisage clinical application.

Outcome of neonates with electrographically identified seizures, or at risk of seizures

A prospective study was conducted to investigate survival at 1 month and survival and developmental outcome at 1 year in a cohort of 53 neonates either suspected of or at risk of having seizures. For all patients, presence of seizures, diagnoses, and structural abnormalities were identified. If seizures were present, seizure variables were quantified. Correlations between neonatal parameters and subsequent outcome were investigated. Forty-three patients survived the first month of life. Background EEG was the only significant predictor of survival at 1 month. Three patients died after 1 month, and 2 of the three had extremely depressed interictal EEGs. Development outcome at 1 year was determined for all available surviving patients. Abnormal findings from brain imaging studies and number of independent electrographic seizure foci were correlated with some aspects of outcome at 1 year. No other correlations were identified between neonatal parameters and outcome.

Electroencephalograms, clinical observations and the monitoring of neonatal seizures.

: To identify neonatal seizures and evaluate the efficiency of clinical observations and short duration electroencephalograms (EEG).

Improvement in the performance of automated spike detection using dipole source features for artefact rejection

OBJECTIVE We evaluated the use of an efficient dipole source algorithm to improve performance of automated spike detection by identifying false detections caused by artefacts. METHODS Automated spike detections were acquired from 26 patients undergoing prolonged electroencephalograph (EEG) monitoring. Data from 6 patients were used to develop the method and data from 20 patients were used to test the method. To provide a standard against which to evaluate the results, an electroencephalographer (EEGer) visually categorized all automated detections before the dipole models were calculated for all events. The event categories (as defined by the EEGer) were then combined with properties of the dipole model and features were identified that differentiated spike and artefact detections. The resulting method was then applied to the testing data set. RESULTS Residual variance and eccentricity of the dipole models differentiated artefact and spike detections. A separate set of rules defining eye blink artefact was also developed. The combined criteria removed a mean of 53.2% of artefact from the testing data set. Some spike detections (4.3%) were also lost. CONCLUSIONS The features of the dipole source of a detected event can be used to differentiate artefacts from spikes. This algorithm is computationally light and could be implemented on-line.

Computer-aided spatial classification of epileptic spikes

Summary The authors present a method that can be used to identify exemplar spikes from prolonged EEG recordings. To achieve this they have calculated single dipole source models for each automatically detected spikelike waveform. They used a dipole source algorithm that is computationally light and can be run on-line during EEG acquisition. Although a single dipole source model may not provide anatomically accurate information about the location of generators of all epileptiform abnormalities, it does provide a novel spatial parameter that may be useful in its own right. The authors use this spatial parameter and present the relative spatial density of the dipole locations in the form of three planar projections of the spherical model (a view from above, a view from the right, and a view from behind) and allow users to define the x-, y-, and z-coordinates of points of interest within the spherical model. They then present 10 example waveforms of events that have dipole source model locations that occur close to that seed coordinate. Overall, they found that this method performs very well for frequent events, but does not perform well for rare events or for diffuse EEG abnormalities.

Clinical features of neonatal seizures.

Objectives: Identification of seizures in neonates is difficult. This study analyses the clinical features of seizures in a cohort of neonates.

The effects of morphine and midazolam on EEGs in neonates

We investigated the effect of morphine, midazolam and their active metabolites on background electroencephalogram (EEG) in 6 neonates undergoing extracorporeal membrane oxygenation (ECMO) by conducting simultaneous EEGs and serum drug levels. Despite serum levels that were sufficient to produce adequate sedation, no patients had burstsuppressed or flat EEG backgrounds. We did, however, note that scalp oedema caused by prolonged immobility led to artefactual attenuation of EEG background. We conclude that an EEG prior to sedation will provide important baseline information that allows subsequent comparison and an awareness that scalp oedema after prolonged sedation and immobility will reduce misinterpretation of artefactual EEG attenuation.