COMPARATIVE STUDY OF QRS DETECTION IN SINGLE LEAD AND 12-LEAD ECG BASED ON ENTROPY AND COMBINED ENTROPY CRITERIA USING SUPPORT VECTOR MACHINE

Application of Support Vector Machine (SVM) for QRS detection in single lead and 12-lead Electrocardiogram (ECG) using entropy and combined entropy criterion is presented in this paper. The ECG signal is filtered using digital filtering techniques to remove power line interference and base line wander. SVM is used as a classifier for detection of QRS complexes in ECG. Using the standard CSE ECG database, both the algorithms performed highly effectively. The performance of the algorithm with sensitivity (Se) of 99.70% and positive prediction (+P) of 97.75% is achieved when tested using single lead ECG with entropy criteria. It improves to 99.79% and 99.15% respectively for combined entropy criteria. Similarly for simultaneously recorded 12-lead ECG signal, sensitivity of 99.93% and positive prediction of 99.13% is achieved when tested using entropy criteria and sensitivity of 99.93% and positive prediction of 99.46% respectively is achieved for combined entropy criteria. The percentage of false positive and false negative are reduced substantially when simultaneously recorded 12-lead ECG signal is used. The proposed algorithms perform better as compared with published results of other QRS detectors tested on the same database.

[1]  Julius T. Tou,et al.  Pattern Recognition Principles , 1974 .

[2]  M. Karakoy,et al.  Classification of Lung Data by Sampling and Support Vector Machine , 2004, The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[3]  Stanislaw Osowski,et al.  Support vector machine-based expert system for reliable heartbeat recognition , 2004, IEEE Transactions on Biomedical Engineering.

[4]  Szi-Wen Chen,et al.  A real-time QRS detection method based on moving-averaging incorporating with wavelet denoising , 2006, Comput. Methods Programs Biomed..

[5]  S. T. Hamde,et al.  Feature extraction from ECG signals using wavelet transforms for disease diagnostics , 2002, Int. J. Syst. Sci..

[6]  J. van Alsté,et al.  Removal of Base-Line Wander and Power-Line Interference from the ECG by an Efficient FIR Filter with a Reduced Number of Taps , 1985, IEEE Transactions on Biomedical Engineering.

[7]  George Carayannis,et al.  QRS detection through time recursive prediction techniques , 1988 .

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

[9]  John Platt,et al.  Fast training of svms using sequential minimal optimization , 1998 .

[10]  C Zywietz,et al.  Common Standards for Quantitative Electrocardiography: Goals and Main Results , 1990, Methods of Information in Medicine.

[11]  P.E. Trahanias,et al.  An approach to QRS complex detection using mathematical morphology , 1993, IEEE Transactions on Biomedical Engineering.

[12]  J. Millet-Roig,et al.  Support vector machine for arrhythmia discrimination with wavelet transform-based feature selection , 2000, Computers in Cardiology 2000. Vol.27 (Cat. 00CH37163).

[13]  D Haussler,et al.  Knowledge-based analysis of microarray gene expression data by using support vector machines. , 2000, Proceedings of the National Academy of Sciences of the United States of America.

[14]  Natalia M. Arzeno,et al.  Quantitative Analysis of QRS Detection Algorithms Based on the First Derivative of the ECG , 2006, 2006 International Conference of the IEEE Engineering in Medicine and Biology Society.

[15]  E. Skordalakis,et al.  Bottom-up approach to the ECG pattern-recognition problem , 2006, Medical and Biological Engineering and Computing.

[16]  Willis J. Tompkins,et al.  A Learning Filter for Removing Noise Interference , 1983, IEEE Transactions on Biomedical Engineering.

[17]  F. Gritzali.  Towards a generalized scheme for QRS detection in ECG waveforms , 1988 .

[18]  Emmanuel Skordalakis,et al.  Syntactic Pattern Recognition of the ECG , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  P Caminal,et al.  Automatic detection of wave boundaries in multilead ECG signals: validation with the CSE database. , 1994, Computers and biomedical research, an international journal.

[20]  S. C. Saxena,et al.  Computer-aided interpretation of ECG for diagnostics , 1996, Int. J. Syst. Sci..

[21]  Carlo Marchesi,et al.  Discovering dangerous patterns in long-term ambulatory ECG recordings using a fast QRS detection algorithm and explorative data analysis , 2006, Comput. Methods Programs Biomed..

[22]  Brenda K. Wiederhold,et al.  ECG to identify individuals , 2005, Pattern Recognit..

[23]  R. Orglmeister,et al.  The principles of software QRS detection , 2002, IEEE Engineering in Medicine and Biology Magazine.

[24]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[25]  Nurettin Acir.  Classification of ECG beats by using a fast least square support vector machines with a dynamic programming feature selection algorithm , 2005, Neural Computing & Applications.

[26]  S. Jankowski,et al.  Computer-aided morphological analysis of Holter ECG recordings based on support vector learning system , 2003, Computers in Cardiology, 2003.

[27]  K. Egiazarian,et al.  Comparative study of morphological and time-frequency ECG descriptors for heartbeat classification. , 2006, Medical engineering & physics.

[28]  S. Yoo,et al.  Support Vector Machine Based Arrhythmia Classification Using Reduced Features , 2005 .

[29]  Nurettin Acir.  A support vector machine classifier algorithm based on a perturbation method and its application to ECG beat recognition systems , 2006, Expert Syst. Appl..

[30]  Mehmet Engin,et al.  ECG beat classification using neuro-fuzzy network , 2004, Pattern Recognit. Lett..