• Barry R Greene, Philip de Chazal, Geraldine B Boylan, Seán Connolly, and Richard B Reilly.
• School of Electrical, Electronic & Mechanical Engineering, University College Dublin, Ireland. barry.greene@ee.ucd.ie
• IEEE Trans Biomed Eng. 2007 Apr 1; 54 (4): 673-82.

AbstractA 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.

19 keywords...

hide…