Greene, BR,de Chazal, P,Boylan, GB,Connolly, S,Reilly, RB;

2007

April

IEEE Transactions On Biomedical Engineering

Electrocardiogram based neonatal seizure detection

Validated

()

ECG linear discriminant neonatal seizure detection EPILEPTIC SEIZURES EEG HEART CLASSIFICATION NEWBORN ABNORMALITIES RECORDINGS SIGNALS

54

673

682

A method for the detection of seizures in the newborn using the electrocardiogram (ECG) signal is presented. Using a database of eight recordings, a method was developed for automatically annotating each 1-min epoch as "nonseizure" or "seizure." The system uses a linear discriminant classifier to process 41 heartbeat timing interval features. Performance assessment of the method showed that on a patient-specific basis an average accuracy of 70.5% was achieved in detecting seizures with associated sensitivity of 62.2% and specificity of 71.8%. On a patient-independent basis the average accuracy was 68.3% with sensitivity of 54.6% and specificity of 77.3%. Shifting the decision threshold for the patient-independent classifier allowed an increase in sensitivity to 78.4% at the expense of decreased specificity (51.6%), leading to increased false detections. The results of our ECG-based method are comparable with those reported for EEG-based neonatal seizure detection systems and offer the benefit of an easier acquisition methodology for seizure detection.

DOI 10.1109/TBME.2006.890137