Faculty of Biomedical and Health Science Engineering, Universiti Teknologi Malaysia, Skudai, Malaysia.
IEEE Trans Biomed Eng. 2009 Nov;56(11):2594-603. doi: 10.1109/TBME.2009.2026908. Epub 2009 Jul 21.
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.
本文研究了心率变异性（HRV）在自动新生儿癫痫检测中的应用。所提出的方法包括一系列处理步骤，即从心电图中获取 HRV，提取有区别的 HRV 特征集，从完整的特征集中选择最佳的子集，最后使用监督统计分类器将 HRV 分类为癫痫/非癫痫。由于 HRV 信号是非平稳的，因此提出并提取了一组来自新生儿 HRV 的时频特征。为了实现基于 HRV 的高效自动新生儿癫痫检测，使用了基于封装的两阶段特征选择技术来选择具有最小冗余度和最大类可分性的特征子集。在从 8 名经 EEG 确认有癫痫发作的新生儿获得的心电图记录上进行测试，所提出的基于 HRV 的新生儿癫痫检测算法实现了 85.7%的灵敏度和 84.6%的特异性。这些结果表明，HRV 对癫痫引起的心脏调节系统变化敏感，因此可作为自动癫痫检测的基础。
