Electrocardiogram Based Neonatal Seizure Detection

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

[1]  Nicolaos B. Karayiannis,et al.  Extraction of motion strength and motor activity signals from video recordings of neonatal seizures , 2001, IEEE Transactions on Medical Imaging.

[2]  Guozhi Tao,et al.  Automated detection of videotaped neonatal seizures based on motion segmentation methods , 2006, Clinical Neurophysiology.

[3]  Gordon Lightbody,et al.  An evaluation of automated neonatal seizure detection methods , 2005, Clinical Neurophysiology.

[4]  C. M. Lim,et al.  Classification of cardiac abnormalities using heart rate signals , 2004, Medical and Biological Engineering and Computing.

[5]  B. Tharp,et al.  Neonatal Seizures and Syndromes , 2002, Epilepsia.

[6]  M. Zweig,et al.  Receiver-operating characteristic (ROC) plots: a fundamental evaluation tool in clinical medicine. , 1993, Clinical chemistry.

[7]  S. Huffel,et al.  Anticipation of epileptic seizures from standard EEG recordings , 2003, The Lancet.

[8]  Mostefa Mesbah,et al.  Time-Frequency Feature Extraction of Newborn EEG Seizure Using SVD-Based Techniques , 2004, EURASIP J. Adv. Signal Process..

[9]  J. Gotman,et al.  Heart Rate Changes and ECG Abnormalities During Epileptic Seizures: Prevalence and Definition of an Objective Clinical Sign , 2002, Epilepsia.

[10]  T. Inder,et al.  Seizure detection algorithm for neonates based on wave-sequence analysis , 2006, Clinical Neurophysiology.

[11]  J. Gotman,et al.  Evaluation of an automatic seizure detection method for the newborn EEG. , 1997, Electroencephalography and clinical neurophysiology.

[12]  Cornelis J Stam,et al.  Seizure detection in the neonatal EEG with synchronization likelihood , 2003, Clinical Neurophysiology.

[13]  A M Bye,et al.  Spatial and Temporal Characteristics of Neonatal Seizures , 1995, Epilepsia.

[14]  J Gotman Automated seizure detection in the newborn : methods and initial evaluation. Electroencephalogr , 1997 .

[15]  Hannah C. Glass,et al.  Neonatal seizures , 2009, Current treatment options in neurology.

[16]  G. Boylan,et al.  Automated neonatal seizure detection , 2006, Clinical Neurophysiology.

[17]  Patrick Gaydecki,et al.  The use of the Hilbert transform in ECG signal analysis , 2001, Comput. Biol. Medicine.

[18]  Eli M. Mizrahi,et al.  Characterization and classification of neonatal seizures , 1987, Neurology.

[19]  H. Troy Nagle,et al.  Assessing autonomic activity from the EKG related to seizure onset detection and localization , 1989, [1989] Proceedings. Second Annual IEEE Symposium on Computer-based Medical Systems.

[20]  Conor Heneghan,et al.  Automated processing of the single-lead electrocardiogram for the detection of obstructive sleep apnoea , 2003, IEEE Transactions on Biomedical Engineering.

[21]  K Kondo,et al.  Electroclinical Studies of Seizures in the Newborn , 1977, Folia psychiatrica et neurologica japonica.

[22]  A. Liu,et al.  Detection of neonatal seizures through computerized EEG analysis. , 1992, Electroencephalography and clinical neurophysiology.

[23]  S. Huffel,et al.  Anticipation of epileptic seizures from standard EEG recordings , 2003, The Lancet.

[24]  G B Boylan,et al.  Phenobarbitone, neonatal seizures, and video-EEG , 2002, Archives of disease in childhood. Fetal and neonatal edition.

[25]  J. Gotman,et al.  Automatic seizure detection in the newborn: methods and initial evaluation. , 1997, Electroencephalography and clinical neurophysiology.

[26]  J. Volpe Neurology of the Newborn , 1959, Major problems in clinical pediatrics.

[27]  Ciara O'Brien,et al.  Heart and respiration rate changes in the neonate during electroencephalographic seizure , 2005, Medical and Biological Engineering and Computing.

[28]  Paul B. Colditz,et al.  A computer-aided detection of EEG seizures in infants: a singular-spectrum approach and performance comparison , 2002, IEEE Transactions on Biomedical Engineering.

[29]  A. B. Geva,et al.  Forecasting epilepsy from the heart rate signal , 2005, Medical and Biological Engineering and Computing.

[30]  Shigeo Abe DrEng Pattern Classification , 2001, Springer London.

[31]  Philip de Chazal,et al.  Automatic classification of heartbeats using ECG morphology and heartbeat interval features , 2004, IEEE Transactions on Biomedical Engineering.

[32]  W. Art Chaovalitwongse,et al.  Adaptive epileptic seizure prediction system , 2003, IEEE Transactions on Biomedical Engineering.