HRV feature selection based on discriminant and redundancy analysis for neonatal seizure detection

This paper addresses the feature selection problem by using a discriminant and redundancy based method to select a feature subset with high discriminatory power between the classes of newborn heart rate variability (HRV) corresponding to seizure and non-seizure. The proposed method combines the Fast Correlation Based Filter (FCBF) criteria for redundancy analysis with the area under the Receiver Operating Curves (AUC) for discriminant analysis. The classification accuracies of the selected features were compared using 3 different classifiers, namely linear classifier, quadratic classifier and A-Nearest Neighbour (k- NN) statistical classifiers in a leave-one-out (LOO) cross validation. It was found that the 1-NN outperformed the other classifiers resulting in a significant reduction in feature dimensionality while achieving 85.7% sensitivity and 84.6% specificity.

[1]  Mostefa Mesbah,et al.  Time-Frequency Analysis of Heart Rate Variability for Neonatal Seizure Detection , 2007, EURASIP J. Adv. Signal Process..

[2]  L. Sörnmo,et al.  Delineation of the QRS complex using the envelope of the e.c.g. , 1983, Medical and Biological Engineering and Computing.

[3]  Huan Liu,et al.  Efficient Feature Selection via Analysis of Relevance and Redundancy , 2004, J. Mach. Learn. Res..

[4]  Frans Coetzee,et al.  Correcting the Kullback-Leibler distance for feature selection , 2005, Pattern Recognit. Lett..

[5]  Bradley V. Vaughn,et al.  Heart period variability in seizure-related sinus arrest , 1997 .

[6]  R. Grebe,et al.  Feature Selection Based on Discriminant and Redundancy Analysis Applied to Seizure Detection in Newborn , 2005, Conference Proceedings. 2nd International IEEE EMBS Conference on Neural Engineering, 2005..

[7]  Mark A. Hall,et al.  Correlation-based Feature Selection for Discrete and Numeric Class Machine Learning , 1999, ICML.

[8]  S. Brown,et al.  Electrocardiograph QT lengthening associated with epileptiform EEG discharges—a role in sudden unexplained death in epilepsy? , 1996, Seizure.

[9]  T. Subba Rao,et al.  Classification, Parameter Estimation and State Estimation: An Engineering Approach Using MATLAB , 2004 .

[10]  F Horwat,et al.  Evaluation of Hjorth parameters in forearm surface EMG analysis during an occupational repetitive task. , 1996, Electroencephalography and clinical neurophysiology.

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

[12]  H. N. Guimarães,et al.  A comparative analysis of preprocessing techniques of cardiac event series for the study of heart rhythm variability using simulated signals. , 1998, Brazilian journal of medical and biological research = Revista brasileira de pesquisas medicas e biologicas.

[13]  Mostefa Mesbah,et al.  Heart Rate Variability Characterization Using a Time-Frequency Based Instantaneous Frequency Estimation Technique , 2007 .

[14]  Daphne Koller,et al.  Toward Optimal Feature Selection , 1996, ICML.

[15]  Huan Liu,et al.  Feature Selection for Classification , 1997, Intell. Data Anal..

[16]  B. Ripley,et al.  Pattern Recognition , 1968, Nature.

[17]  Shane T. Mueller,et al.  Upper and Lower Bounds of Area Under ROC Curves and Index of Discriminability of Classifier Performance , 2006 .

[18]  T. Schaible,et al.  Short term heart rate variability in healthy neonates: normative data and physiological observations. , 2005, Early human development.

[19]  Anil K. Jain,et al.  Statistical Pattern Recognition: A Review , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  Pavel Pudil,et al.  Introduction to Statistical Pattern Recognition , 2006 .

[21]  Kevin J. Dalton,et al.  Using upper bounds on attainable discrimination to select discrete valued features , 1996, Neural Networks for Signal Processing VI. Proceedings of the 1996 IEEE Signal Processing Society Workshop.