Newborn Seizure Detection Based on Heart Rate Variability
Authors:
- 21 July 2009
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 56 (11) , 2594-2603
Abstract
In this paper, we investigate the use of heart rate variability (HRV) for automatic newborn seizure detection. The proposed method consists of a sequence of processing steps, namely, obtaining HRV from the ECG, extracting a discriminating HRV feature set, selecting an optimal subset from the full feature set, and, finally, classifying the HRV into seizure/nonseizure using a supervised statistical classifier. Due to the fact that HRV signals are nonstationary, a set of time-frequency features from the newborn HRV is proposed and extracted. In order to achieve efficient HRV-based automatic newborn seizure detection, a two-phase wrapper-based feature selection technique is used to select the feature subset with minimum redundancy and maximum class discriminability. Tested on ECG recordings obtained from eight newborns with identified EEG seizure, the proposed HRV-based neonatal seizure detection algorithm achieved 85.7% sensitivity and 84.6% specificity. These results suggest that the HRV is sensitive to changes in the cardioregulatory system induced by the seizure, and therefore, can be used as a basis for an automatic seizure detection.Keywords
This publication has 42 references indexed in Scilit:
- Individual Time-Dependent Spectral Boundaries for Improved Accuracy in Time-Frequency Analysis of Heart Rate VariabilityIEEE Transactions on Biomedical Engineering, 2005
- An evaluation of automated neonatal seizure detection methodsClinical Neurophysiology, 2005
- Instantaneous parameter estimation in cardiovascular time series by harmonic and time-frequency analysisIEEE Transactions on Biomedical Engineering, 2002
- A computer-aided detection of EEG seizures in infants: a singular-spectrum approach and performance comparisonIEEE Transactions on Biomedical Engineering, 2002
- Measuring time-frequency information content using the Renyi entropiesIEEE Transactions on Information Theory, 2001
- Heart Rate Variability; An Index for Monitoring and Analyzing Human Autonomic Activities.Applied Human Science, 1999
- Neonatal seizuresEuropean Journal of Pediatrics, 1997
- Feature selection for classificationIntelligent Data Analysis: An International Journal, 1997
- Estimating and interpreting the instantaneous frequency of a signal. I. FundamentalsProceedings of the IEEE, 1992
- Electroclinical Studies of Seizures in the NewbornPsychiatry and Clinical Neurosciences, 1977