Paper Info
Title
Electrocardiogram Based Neonatal Seizure Detection.
Abstract
A method for the detection of seizures in the new- born 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. Index Terms—ECG, linear discriminant, neonatal, seizure detection.
Year
DOI
Venue
2007
10.1109/TBME.2006.890137
IEEE Trans. Biomed. Engineering
Keywords
Field
DocType
pediatrics,mechanical engineering,pattern recognition,artificial intelligence,eeg,diagnosis,algorithms,paediatrics,linear discriminant,electroencephalography,linear discriminant analysis,frequency,automated
Neonatal seizure,Heartbeat,Seizure detection,Heart beat,Pattern recognition,Computer science,Speech recognition,Artificial intelligence,Linear discriminant analysis,Classifier (linguistics),Electrocardiography,Electroencephalography
Journal
Volume
Issue
ISSN
54
4
0018-9294
Citations 
PageRank 
References 
5
0.72
9
Authors
5
Name
Order
Citations
PageRank
Barry R. Greene110917.81
Philip de Chazal264456.50
Geraldine B Boylan37017.75
Sean Connolly4304.81
Richard B. Reilly573168.88