Detection of neonatal seizures through computerized EEG analysis

Neonatal seizures are a symptom of central nervous system disturbances. Neonatal seizures may be identified by direct clinical observation by the majority of electrographic seizures are clinically silent or subtle. Electrographic seizures in the newborn consist of periodic or rhythmic discharges that are distinctively different from normal background cerebral activity. Utilizing these differences, we have developed a technique to identify electrographic seizure activity. In this study, autocorrelation analysis was used to distinguish seizures from background electrocerebral activity. Autocorrelation data were scored to quantify the periodicity using a newly developed scoring system. This method, Scored Autocorrelation Moment (SAM) analysis, successfully distinguished epochs of EEGs with seizures from those without (N = 117 epochs, 58 with seizure and 59 without). SAM analysis showed a sensitivity of 84% and a specificity of 98%. SAM analysis of EEG may provide a method for monitoring electrographic seizures in high-risk newborns.