Application of Higher Order cumulant Features for Cardiac Health Diagnosis using ECG signals

Electrocardiogram (ECG) is the electrical activity of the heart indicated by P, Q-R-S and T wave. The minute changes in the amplitude and duration of ECG depicts a particular type of cardiac abnormality. It is very difficult to decipher the hidden information present in this nonlinear and nonstationary signal. An automatic diagnostic system that characterizes cardiac activities in ECG signals would provide more insight into these phenomena thereby revealing important clinical information. Various methods have been proposed to detect cardiac abnormalities in ECG recordings. Application of higher order spectra (HOS) features is a seemingly promising approach because it can capture the nonlinear and dynamic nature of the ECG signals. In this paper, we have automatically classified five types of beats using HOS features (higher order cumulants) using two different approaches. The five types of ECG beats are normal (N), right bundle branch block (RBBB), left bundle branch block (LBBB), atrial premature contraction (APC) and ventricular premature contraction (VPC). In the first approach, cumulant features of segmented ECG signal were used for classification; whereas in the second approach cumulants of discrete wavelet transform (DWT) coefficients were used as features for classifiers. In both approaches, the cumulant features were subjected to data reduction using principal component analysis (PCA) and classified using three layer feed-forward neural network (NN) and least square-support vector machine (LS-SVM) classifiers. In this study, we obtained the highest average accuracy of 94.52%, sensitivity of 98.61% and specificity of 98.41% using first approach with NN classifier. The developed system is ready clinically to run on large datasets.

[1]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[2]  Farid Melgani,et al.  Classification of Electrocardiogram Signals With Support Vector Machines and Particle Swarm Optimization , 2008, IEEE Transactions on Information Technology in Biomedicine.

[3]  Yi Zhao,et al.  Equivalence between "feeling the pulse" on the human wrist and the pulse pressure wave at fingertip , 2005, Int. J. Neural Syst..

[4]  G.G. Cano,et al.  An approach to cardiac arrhythmia analysis using hidden Markov models , 1990, IEEE Transactions on Biomedical Engineering.

[5]  Yakup Kutlu,et al.  Feature extraction for ECG heartbeats using higher order statistics of WPD coefficients , 2012, Comput. Methods Programs Biomed..

[6]  C. M. Lim,et al.  Heart rate variability analysis using correlation dimension and detrended fluctuation analysis , 2002 .

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

[8]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[9]  Arkady Borisov,et al.  Ranking-Based Kernels in Applied Biomedical Diagnostics Using a Support Vector Machine , 2011, Int. J. Neural Syst..

[10]  Arturo Garcia-Perez,et al.  MUSIC‐ANN Analysis for Locating Structural Damages in a Truss‐Type Structure by Means of Vibrations , 2012, Comput. Aided Civ. Infrastructure Eng..

[11]  Ulrik Söderström,et al.  Reconstruction of occluded facial images using asymmetrical Principal Component Analysis , 2011, 2011 18th International Conference on Systems, Signals and Image Processing.

[12]  Hojjat Adeli,et al.  HeartSaver: A mobile cardiac monitoring system for auto-detection of atrial fibrillation, myocardial infarction, and atrio-ventricular block , 2011, Comput. Biol. Medicine.

[13]  Wei Wang,et al.  Structural Reliability Assessment by Local Approximation of Limit State Functions Using Adaptive Markov Chain Simulation and Support Vector Regression , 2012, Comput. Aided Civ. Infrastructure Eng..

[14]  Chandan Chakraborty,et al.  A two-stage mechanism for registration and classification of ECG using Gaussian mixture model , 2009, Pattern Recognit..

[15]  Hojjat Adeli,et al.  Wavelet Packet‐Autocorrelation Function Method for Traffic Flow Pattern Analysis , 2004 .

[16]  Hujun Yin,et al.  Efficient blind image deconvolution using spectral non-Gaussianity , 2012, Integr. Comput. Aided Eng..

[17]  U. Rajendra Acharya,et al.  Analysis and Automatic Identification of Sleep Stages Using Higher Order Spectra , 2010, Int. J. Neural Syst..

[18]  Stefan Arnborg,et al.  A bayesian recurrent neural network for unsupervised pattern recognition in large incomplete data sets , 2005, Int. J. Neural Syst..

[19]  Mohammad Bagher Shamsollahi,et al.  Robust Detection of Premature Ventricular Contractions Using a Wave-Based Bayesian Framework , 2010, IEEE Transactions on Biomedical Engineering.

[20]  Seongyun Cho,et al.  Modelling and Prediction for Chaotic FIR Laser Attractor Using Rational Function Neural Network , 2001, Int. J. Neural Syst..

[21]  D. Mozaffarian,et al.  Heart disease and stroke statistics--2009 update: a report from the American Heart Association Statistics Committee and Stroke Statistics Subcommittee. , 2009, Circulation.

[22]  Thomas W. Rauber,et al.  Diagnosing multiple faults in oil rig motor pumps using support vector machine classifier ensembles , 2011, Integr. Comput. Aided Eng..

[23]  Ataollah Ebrahimzadeh,et al.  Classification of electrocardiogram signals with support vector machines and genetic algorithms using power spectral features , 2010, Biomed. Signal Process. Control..

[24]  Terrill Fancott,et al.  A Minicomputer System for Direct High Speed Analysis of Cardiac Arrhythmia in 24 h Ambulatory ECG Tape Recordings , 1980, IEEE Transactions on Biomedical Engineering.

[25]  Hojjat Adeli,et al.  Hybrid Control of Smart Structures Using a Novel Wavelet‐Based Algorithm , 2005 .

[26]  Ali H. Shoeb,et al.  Non-Invasive Computerized System for Automatically Initiating Vagus Nerve Stimulation Following Patient-Specific Detection of Seizures or epileptiform discharges , 2009, Int. J. Neural Syst..

[27]  Hojjat Adeli,et al.  Neural Network-Wavelet Microsimulation Model for Delay and Queue Length Estimation at Freeway Work Zones , 2006 .

[28]  Hojjat Adeli,et al.  Principal Component Analysis-Enhanced Cosine Radial Basis Function Neural Network for Robust Epilepsy and Seizure Detection , 2008, IEEE Transactions on Biomedical Engineering.

[29]  J. Deckers,et al.  Right bundle branch block: prevalence, risk factors, and outcome in the general population: results from the Copenhagen City Heart Study. , 2013, European heart journal.

[30]  I. Daskalov,et al.  Effect of Contour Shape of Nervous System Electromagnetic Stimulation Coils on the Induced Electrical Field Distribution , 2002, Biomedical engineering online.

[31]  Hojjat Adeli,et al.  Wavelet-Synchronization Methodology: A New Approach for EEG-Based Diagnosis of ADHD , 2010, Clinical EEG and neuroscience.

[32]  Willis J. Tompkins,et al.  A Real-Time QRS Detection Algorithm , 1985, IEEE Transactions on Biomedical Engineering.

[33]  Malek Adjouadi,et al.  A New Parametric Feature Descriptor for the Classification of Epileptic and Control EEG Records in Pediatric Population , 2012, Int. J. Neural Syst..

[34]  D. Ge,et al.  Cardiac arrhythmia classification using autoregressive modeling , 2002, Biomedical engineering online.

[35]  Brij N. Singh,et al.  Optimal selection of wavelet basis function applied to ECG signal denoising , 2006, Digit. Signal Process..

[36]  Roberto Kawakami Harrop Galvão,et al.  Improving the Discriminatory Capabilities of a Neural Classifier by Using a Biased-Wavelet Layer , 1999, Int. J. Neural Syst..

[37]  Hojjat Adeli,et al.  Wavelet energy spectrum for time‐frequency localization of earthquake energy , 2003, Int. J. Imaging Syst. Technol..

[38]  Anne M. P. Canuto,et al.  Improving Artmap Learning Through Variable Vigilance , 2001, Int. J. Neural Syst..

[39]  Elif Derya Übeyli.  Usage of eigenvector methods in implementation of automated diagnostic systems for ECG beats , 2008, Digit. Signal Process..

[40]  Paul S Addison,et al.  Wavelet transforms and the ECG: a review , 2005, Physiological measurement.

[41]  Duanping Liao,et al.  Relation of atrial and/or ventricular premature complexes on a two-minute rhythm strip to the risk of sudden cardiac death (the Atherosclerosis Risk in Communities [ARIC] study). , 2011, The American journal of cardiology.

[42]  S. Gunn.  Support Vector Machines for Classification and Regression , 1998 .

[43]  Hojjat Adeli,et al.  Wavelet-Hybrid Feedback Linear Mean Squared Algorithm for Robust Control of Cable-Stayed Bridges , 2005 .

[44]  Hojjat Adeli,et al.  Time‐Frequency Signal Analysis of Earthquake Records Using Mexican Hat Wavelets , 2003 .

[45]  Charles R. Farrar,et al.  Influence of the Autoregressive Model Order on Damage Detection , 2011, Comput. Aided Civ. Infrastructure Eng..

[46]  J. Nazuno.  Haykin, Simon. Neural networks: A comprehensive foundation, Prentice Hall, Inc. Segunda Edición, 1999 , 2000 .

[47]  Sankaran Mahadevan,et al.  Bayesian wavelet packet denoising for structural system identification , 2007 .

[48]  Jing Wang,et al.  A wavelet-based particle swarm optimization algorithm for digital image watermarking , 2012, Integr. Comput. Aided Eng..

[49]  Chandan Chakraborty,et al.  Application of principal component analysis to ECG signals for automated diagnosis of cardiac health , 2012, Expert Syst. Appl..

[50]  Hojjat Adeli,et al.  A new supervised learning algorithm for multiple spiking neural networks with application in epilepsy and seizure detection , 2009, Neural Networks.

[51]  Elif Derya Übeyli.  Combining recurrent neural networks with eigenvector methods for classification of ECG beats , 2009, Digit. Signal Process..

[52]  U. Rajendra Acharya,et al.  Automatic Detection of Epileptic EEG Signals Using Higher Order cumulant Features , 2011, Int. J. Neural Syst..

[53]  Hojjat Adeli,et al.  Fractality and a Wavelet-Chaos-Neural Network Methodology for EEG-Based Diagnosis of Autistic Spectrum Disorder , 2010, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[54]  Dimitris C. Theodoridis,et al.  Dynamical Recurrent Neuro-Fuzzy Identification Schemes Employing Switching parameter Hopping , 2012, Int. J. Neural Syst..

[55]  Kang-Ping Lin,et al.  QRS feature extraction using linear prediction , 1989, IEEE Transactions on Biomedical Engineering.

[56]  Moncef Gabbouj,et al.  A Generic and Robust System for Automated Patient-Specific Classification of ECG Signals , 2009, IEEE Transactions on Biomedical Engineering.

[57]  R. Acharya U,et al.  Comprehensive analysis of cardiac health using heart rate signals , 2004, Physiological measurement.

[58]  Hojjat Adeli,et al.  Object-oriented backpropagation and its application to structural design , 1994, Neurocomputing.

[59]  M.M.A. Hadhoud,et al.  Computer Aided Diagnosis of Cardiac Arrhythmias , 2006, 2006 International Conference on Computer Engineering and Systems.

[60]  H. Adeli,et al.  A spatio-temporal wavelet-chaos methodology for EEG-based diagnosis of Alzheimer's disease , 2008, Neuroscience Letters.

[61]  H. Adeli,et al.  Fractality and a Wavelet-chaos-Methodology for EEG-based Diagnosis of Alzheimer Disease , 2011, Alzheimer disease and associated disorders.

[62]  Chrysostomos L. Nikias,et al.  Higher-order spectral analysis , 1993, Proceedings of the 15th Annual International Conference of the IEEE Engineering in Medicine and Biology Societ.

[63]  Hojjat Adeli,et al.  Pseudospectra, MUSIC, and dynamic wavelet neural network for damage detection of highrise buildings , 2007 .

[64]  W.J. Tompkins,et al.  A patient-adaptable ECG beat classifier using a mixture of experts approach , 1997, IEEE Transactions on Biomedical Engineering.

[65]  Philip de Chazal,et al.  A Patient-Adapting Heartbeat Classifier Using ECG Morphology and Heartbeat Interval Features , 2006, IEEE Transactions on Biomedical Engineering.

[66]  Wolfgang Graf,et al.  Recurrent neural networks for fuzzy data , 2011, Integr. Comput. Aided Eng..

[67]  Gregory T. A. Kovacs,et al.  Robust Neural-Network-Based Classification of Premature Ventricular Contractions Using Wavelet Transform and Timing Interval Features , 2006, IEEE Transactions on Biomedical Engineering.

[68]  Pamela J Schreiner,et al.  Usefulness of ventricular premature complexes to predict coronary heart disease events and mortality (from the Atherosclerosis Risk In Communities cohort). , 2006, The American journal of cardiology.

[69]  Asim Karim,et al.  INCIDENT DETECTION ALGORITHM USING WAVELET ENERGY REPRESENTATION OF TRAFFIC PATTERNS , 2002 .

[70]  Luping Shi,et al.  Presynaptic Learning and Memory with a Persistent Firing Neuron and a Habituating Synapse: a Model of Short Term Persistent Habituation , 2012, Int. J. Neural Syst..

[71]  C. M. Lim,et al.  Analysis of epileptic EEG signals using higher order spectra , 2009, Journal of medical engineering & technology.

[72]  Hojjat Adeli,et al.  Mesoscopic-Wavelet Freeway Work Zone Flow and Congestion Feature Extraction Model , 2004 .

[73]  Carsten Peterson,et al.  Clustering ECG complexes using Hermite functions and self-organizing maps , 2000, IEEE Trans. Biomed. Eng..

[74]  Elif Derya Übeyli.  ECG beats classification using multiclass support vector machines with error correcting output codes , 2007, Digit. Signal Process..

[75]  Ming Liang,et al.  Wavelet‐Based Detection of Beam Cracks Using Modal Shape and Frequency Measurements , 2012, Comput. Aided Civ. Infrastructure Eng..

[76]  Hojjat Adeli,et al.  Wavelet‐Clustering‐Neural Network Model for Freeway Incident Detection , 2003 .

[77]  Ary L. Goldberger,et al.  Clinical Electrocardiography: A Simplified Approach, 8th Edition , 2012 .

[78]  Stanislaw Osowski,et al.  ECG beat recognition using fuzzy hybrid neural network , 2001, IEEE Trans. Biomed. Eng..

[79]  C. M. Lim,et al.  Cardiac state diagnosis using higher order spectra of heart rate variability , 2008, Journal of medical engineering & technology.

[80]  Chandan Chakraborty,et al.  Cardiac decision making using higher order spectra , 2013, Biomed. Signal Process. Control..

[81]  S. Yusuf,et al.  Stemming the global tsunami of cardiovascular disease , 2011, The Lancet.

[82]  Wang-Ji Yan,et al.  Operational Modal Parameter Identification from Power Spectrum Density Transmissibility , 2012, Comput. Aided Civ. Infrastructure Eng..

[83]  Paramasivan Saratchandran,et al.  Eeg Source Localization: A Compartive Study of Classical and Neural Network Methods , 2001, Int. J. Neural Syst..

[84]  A. Goldberger.  Clinical Electrocardiography: A Simplified Approach , 1977 .

[85]  David G. Stork,et al.  Pattern Classification , 1973 .

[86]  Hojjat Adeli,et al.  Recurrent Neural Network for Approximate Earthquake Time and Location Prediction Using Multiple Seismicity Indicators , 2009, Comput. Aided Civ. Infrastructure Eng..

[87]  Chandan Chakraborty,et al.  Application of higher order cumulants to ECG signals for the cardiac health diagnosis , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[88]  Truong Q. Nguyen,et al.  Wavelets and filter banks , 1996 .

[89]  Hojjat Adeli,et al.  Improved spiking neural networks for EEG classification and epilepsy and seizure detection , 2007, Integr. Comput. Aided Eng..

[90]  Luigi Tavazzi,et al.  Left bundle-branch block is associated with increased 1-year sudden and total mortality rate in 5517 outpatients with congestive heart failure: a report from the Italian network on congestive heart failure. , 2002, American heart journal.

[91]  Hojjat Adeli,et al.  Parallel backpropagation learning algorithms on CRAY Y-MP8/864 supercomputer , 1993, Neurocomputing.

[92]  D. Mozaffarian,et al.  Heart disease and stroke statistics--2009 update: a report from the American Heart Association Statistics Committee and Stroke Statistics Subcommittee. , 2009, Circulation.

[93]  Chih-Min Lin,et al.  Adaptive Control for MIMO uncertain nonlinear Systems Using Recurrent Wavelet Neural Network , 2012, Int. J. Neural Syst..