Evaluation of Classifiers for Recognition of Ventricular Arrhythmia using DWT based Features

Ventricular tachycardia (VT) and Ventricular fibrillation (VF) are the critical ventricular arrhythmias that require treatment in an emergency. The automatic detection system is essential for recognition of VT and VF conditions at an early stage for better treatment. In this paper, discrete wavelet transform (DWT) was used to de-noise and decompose the ECG signals into different consecutive frequency bands. We have tested the ECG data from CU Ventricular Tachyarrhythmia Database (CUDB) and MIT-BIH Malignant Ventricular Ectopy Database (VFDB) datasets of PhysioNet databases. A set of time-frequency features consists of temporal, spectral, and statistical features were extracted and ranked by the correlation attribute evaluation with ranker search method and classified with the Multi Layer Perceptron (MLP) and the Support vector machine (SVM) classifiers. The proposed method yields the sensitivity of 85.52%, specificity of 95.84%, precision of 88.93% and accuracy of 94.65% for MLP. The obtained results prove that DWT based time-frequency features are the best choice for precise detection of ventricular arrhythmias.

[1]  M. J. Goldman.  Principles of Clinical Electrocardiography , 1973 .

[2]  Krishnanand Balasundaram,et al.  Wavelet-based features for characterizing ventricular arrhythmias in optimizing treatment options , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[3]  Hong-Bo Xie,et al.  Classification of ventricular tachycardia and fibrillation using fuzzy similarity-based approximate entropy , 2011, Expert Syst. Appl..

[4]  Leif Sörnmo,et al.  Electroatriography - time-frequency analysis of atrial fibrillation from modified 12-lead ECG configurations for improved diagnosis and therapy. , 2007, Medical hypotheses.

[5]  A. Amann,et al.  Reliability of old and new ventricular fibrillation detection algorithms for automated external defibrillators , 2005, Biomedical engineering online.

[6]  Qiao Li,et al.  Ventricular Fibrillation and Tachycardia Classification Using a Machine Learning Approach , 2014, IEEE Transactions on Biomedical Engineering.

[7]  A. Matsuyama,et al.  The application of wavelet and feature vectors to ECG signals , 2005, TENCON 2005 - 2005 IEEE Region 10 Conference.

[8]  Joon S. Lim,et al.  Finding Features for Real-Time Premature Ventricular Contraction Detection Using a Fuzzy Neural Network System , 2009, IEEE Transactions on Neural Networks.

[9]  M. Small,et al.  Uncovering non-linear structure in human ECG recordings , 2002 .

[10]  Naomie Salim,et al.  Arrhythmia recognition and classification using combined linear and nonlinear features of ECG signals , 2016, Comput. Methods Programs Biomed..

[11]  Lei Yang,et al.  Wavelet permutation entropy analysis of Ventricular Fibrillation and Sudden Cardiac Death ECG signals , 2015 .

[12]  José Luis Rojo-Álvarez,et al.  Detection of Life-Threatening Arrhythmias Using Feature Selection and Support Vector Machines , 2014, IEEE Transactions on Biomedical Engineering.

[13]  Yoon-Teck Bau,et al.  Fast Numerical Threshold Search Algorithm for C4.5 , 2014, 2014 IIAI 3rd International Conference on Advanced Applied Informatics.

[14]  Azeddine Mjahad,et al.  Ventricular Fibrillation and Tachycardia detection from surface ECG using time-frequency representation images as input dataset for machine learning , 2017, Comput. Methods Programs Biomed..

[15]  L. Khadra,et al.  Detection of life-threatening cardiac arrhythmias using the wavelet transformation , 1997, Medical and Biological Engineering and Computing.

[16]  A. Lazkano,et al.  Discrimination between ventricular tachycardia and ventricular fibrillation using the continuous wavelet transform , 2004, Computers in Cardiology, 2004.

[17]  Santanu Sahoo,et al.  Multiresolution wavelet transform based feature extraction and ECG classification to detect cardiac abnormalities , 2017 .

[18]  Sang-Hong Lee,et al.  Detection of ventricular fibrillation using Hilbert transforms, phase-space reconstruction, and time-domain analysis , 2013, Personal and Ubiquitous Computing.

[19]  W. Marsden.  I and J , 2012 .

[20]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[21]  Yongqin Li,et al.  An Algorithm Used for Ventricular Fibrillation Detection Without Interrupting Chest Compression , 2012, IEEE Transactions on Biomedical Engineering.

[22]  A. Murray,et al.  Recognition of ventricular fibrillation using neural networks , 1994, Medical and Biological Engineering and Computing.

[23]  Jasmina Novakovic,et al.  Using Information Gain Attribute Evaluation to Classify Sonar Targets , 2009 .