Sensitivity of amplitude-integrated electroencephalography for neonatal seizure detection

Abstract

Background: Conventional electroencephalography remains the gold standard for the diagnosis and quantification of neonatal seizures. However, amplitude-integrated electroencephalography (aEEG) is being introduced to neonatal intensive care as an adjunct for neonatal seizure detection.

Objectives: This study's purpose was to determine the sensitivity of neonatal seizure detection in a single electroencephalogram channel (C3-->C4), used to simulate the raw signal from which aEEG is derived. We also aimed to determine the sensitivity of seizure detection by neonatologists by using aEEG and to establish those neonatal seizure characteristics that are associated with their correct detection by aEEG.

Methods: Conventional electroencephalograms with neonatal seizures were reviewed for electroencephalogram background and neonatal seizure characteristics (site of onset, duration, and peak-to-peak amplitude). The presence, duration, and peak-to-peak amplitude of each seizure were simultaneously noted in a single electroencephalogram channel (C3-->C4). aEEGs generated from this channel were reviewed for background and seizures by 6 neonatologists with varying aEEG interpretation expertise.

Results: A total of 851 neonatal seizures from 125 conventional electroencephalograms were analyzed. The patients' conceptional ages were 34 to 50 weeks. Because 94% of the conventional electroencephalograms had > or = 1 neonatal seizure visible in C3-->C4, and 78% of all neonatal seizures appeared in the C3-->C4 channel, the theoretical sensitivity of seizure detection in a single electroencephalogram channel was high. However, seizures were briefer and lower in amplitude in C3-->C4 compared with conventional electroencephalography. Neonatologists identified seizures in 22% to 57% of the 125 records of neonatal seizure. They detected 12% to 38% of the 851 individual seizures. Multivariate analysis revealed that the appearance of seizures in C3-->C4, neonatal seizure duration, seizure amplitude, seizure count per hour, and neonatologists' experience with aEEG interpretation all correlated with neonatal seizure detection.

Conclusions: Even among physicians who have extensive experience, many neonatal seizures are difficult to detect on an aEEG, especially when they are infrequent, brief, or of low amplitude.