P and T waves annotation and detection in MIT-BIH arrhythmia database

A robust and numerically-efficient method based on two moving average filters followed by a dynamic event duration threshold has been developed to detect P and T waves in ECG signals. Detection of P and T waves is affected by the quality of the ECG recordings and the abnormalities in the ECG signals. The proposed method detects P and T waves in Arrhythmia ECG Signals that suffer from: 1) non-stationary effects, 2) low signal-to-noise ratio, 3) premature atrial complexes 4) premature ventricular complexes, 5) left bundle blocks, and 6) right bundle blocks. Interestingly, the P and T waves detector obtained a a sensitivity of 98.05 per cent and a positive predictivity of 97.11 per cent for P waves and a sensitivity of 99.86 per cent and a positive predictivity of 99.65 per cent for T waves over 10 records of MIT-BIH arrhythmia database with 21,702 beats. The P and T detection algorithm performed very well compared to traditional detection algorithms.

[1]  K. Ouni,et al.  An Approach Combining Wavelet Transform and Hidden Markov Models for ECG Segmentation , 2008, 2008 3rd International Conference on Information and Communication Technologies: From Theory to Applications.

[2]  David Power,et al.  The profitability of moving average trading rules in South Asian stock markets , 2001 .

[3]  P. Babyn,et al.  Bio-signal Characteristics Detection Utilizing Frequency Ordered Wavelet Packets , 2007, 2007 IEEE International Symposium on Signal Processing and Information Technology.

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

[5]  Cairo L. Nascimento,et al.  A neural network with asymmetric basis functions for feature extraction of ECG P waves , 2001, IEEE Trans. Neural Networks.

[6]  K. Ouni,et al.  ECG Signal Maxima Detection Using Wavelet Transform , 2006, 2006 IEEE International Symposium on Industrial Electronics.

[7]  N. V. Thakor,et al.  Optimal QRS detector , 1983, Medical and Biological Engineering and Computing.

[8]  P. Caminal,et al.  Evaluation of HRV by PP and RR interval analysis using a new time delay estimate , 1990, [1990] Proceedings Computers in Cardiology.

[9]  K. Chan,et al.  Characteristic wave detection in ECG signal using morphological transform , 2005, BMC cardiovascular disorders.

[10]  A. W. M. van den Enden,et al.  Discrete Time Signal Processing , 1989 .

[11]  Patrick E. McSharry,et al.  Advanced Methods And Tools for ECG Data Analysis , 2006 .

[12]  Senén Barro,et al.  A new approach for TU complex characterization , 2000, IEEE Transactions on Biomedical Engineering.

[13]  Roger G. Mark,et al.  The MIT-BIH Arrhythmia Database on CD-ROM and software for use with it , 1990, [1990] Proceedings Computers in Cardiology.

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

[15]  Friso De Boer,et al.  Premature atrial complexes detection using the Fisher Linear Discriminant , 2008, 2008 7th IEEE International Conference on Cognitive Informatics.

[16]  C.Y. Ryu,et al.  Conductive rubber electrode for wearable health monitoring , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[17]  S.N. Tandon,et al.  Using wavelet transforms for ECG characterization. An on-line digital signal processing system , 1997, IEEE Engineering in Medicine and Biology Magazine.

[18]  James Chen.  Essentials of Technical Analysis for Financial Markets , 2010 .

[19]  P. Avignon,et al.  Causes of Death , 1884, Nature.

[20]  Pawel Strumillo,et al.  Nested median filtering for detecting T-wave offset in ECGs , 2002 .

[21]  R. Magjarevic,et al.  Real time P-wave detector based on wavelet analysis , 2004, Proceedings of the 12th IEEE Mediterranean Electrotechnical Conference (IEEE Cat. No.04CH37521).

[22]  Kamrul Hasan,et al.  Automatic detection of ECG wave boundaries using empirical mode decomposition , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[23]  Bachir Boucheham,et al.  Digital fractional order differentiation-based algorithm for P and T-waves detection and delineation , 2005 .

[24]  I.S.N. Murthy,et al.  Analysis of ECG from pole-zero models , 1992, IEEE Transactions on Biomedical Engineering.

[25]  C. Li,et al.  Detection of ECG characteristic points using wavelet transforms. , 1995, IEEE transactions on bio-medical engineering.

[26]  V. Chouhan,et al.  Threshold-based Detection of P and T-wave in ECG using New Feature Signal , 2008 .

[27]  Rangaraj M. Rangayyan,et al.  Biomedical Signal Analysis: A Case-Study Approach , 2001 .

[28]  P. Libby,et al.  Braunwald's Heart Disease: A Textbook of Cardiovascular Medicine, 2-Volume Set, 9th Edition Expert Consult Premium Edition €“ Enhanced Online Features , 2011 .

[29]  W. Fong,et al.  Chasing trends: recursive moving average trading rules and internet stocks , 2005 .

[30]  H. T. Nagle,et al.  A comparison of the noise sensitivity of nine QRS detection algorithms , 1990, IEEE Transactions on Biomedical Engineering.

[31]  W V MACFARLANE,et al.  Australia's health. , 1962, Public health reports.

[32]  Pablo Laguna,et al.  A wavelet-based ECG delineator: evaluation on standard databases , 2004, IEEE Transactions on Biomedical Engineering.

[33]  Rolf Johansson,et al.  Classification of electrocardiographic P-wave morphology , 2001, IEEE Transactions on Biomedical Engineering.

[34]  N.V. Thakor,et al.  Applications of adaptive filtering to ECG analysis: noise cancellation and arrhythmia detection , 1991, IEEE Transactions on Biomedical Engineering.