Accurate Classification of ECG Patterns with Subject-Dependent Feature Vector

Correct and accurate classification of ECG patterns in a long-term record requires optimal selection of feature vector. We propose a machine learning algorithm that learns from short randomly selected signal strips and, having an approval from a human operator, classifies all remaining patterns. We applied a genetic algorithm with aggressive mutation to select few most distinctive features of ECG signal. When applied to the MIT-BIH Arrhythmia Database records, the algorithm reduced the initial feature space of 57 elements to 3–5 features optimized for a particular subject. We also observe a significant reduction of misclassified beats percentage (from 2.7 % to 0.7 % in average for SVM classifier and three features) with regard to automatic correlation-based selection.

[1]  S Jokic,et al.  An efficient approach for heartbeat classification , 2010, 2010 Computing in Cardiology.

[2]  John H. Holland,et al.  Cognitive systems based on adaptive algorithms , 1977, SGAR.

[3]  K.C. Chang,et al.  Comparison of similarity measures for clustering electrocardiogram complexes , 2005, Computers in Cardiology, 2005.

[4]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[5]  A. Pizurica,et al.  Classifying electrocardiogram peaks using newwavelet domain features , 2008, 2008 Computers in Cardiology.

[6]  G. Castellanos-Dominguez,et al.  An improved method for unsupervised analysis of ECG beats based on WT features and J-means clustering , 2007, 2007 Computers in Cardiology.

[7]  M. Llamedo Soria,et al.  An ECG classification model based on multilead wavelet transform features , 2007, 2007 Computers in Cardiology.

[8]  Igor Kononenko,et al.  Estimating Attributes: Analysis and Extensions of RELIEF , 1994, ECML.

[9]  P. de Chazal,et al.  Beat classification for use in arrhythmia analysis , 2000, Computers in Cardiology 2000. Vol.27 (Cat. 00CH37163).

[10]  Stéphane Mallat,et al.  Characterization of Signals from Multiscale Edges , 2011, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[12]  Piotr Augustyniak.  Adaptive discrete ECG representation - comparing variable depth decimation and continuous non-uniform sampling , 2002, Computers in Cardiology.

[13]  Piotr Augustyniak,et al.  A cardiac telerehabilitation application for mobile devices , 2011, 2011 Computing in Cardiology.

[14]  Izabela Rejer.  Genetic Algorithms in EEG Feature Selection for the Classification of Movements of the Left and Right Hand , 2013, CORES.

[15]  V. Jacquemet,et al.  Spatiotemporal QRST cancellation method using separate QRS and T-waves templates , 2005, Computers in Cardiology, 2005.

[16]  J P Martinez,et al.  Analysis of multidomain features for ECG classification , 2009, 2009 36th Annual Computers in Cardiology Conference (CinC).

[17]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[18]  J. Kittler,et al.  Feature Set Search Alborithms , 1978 .

[19]  Izabela Rejer,et al.  Genetic algorithm with aggressive mutation for feature selection in BCI feature space , 2014, Pattern Analysis and Applications.

[20]  M Llamedo,et al.  Analysis of 12-lead classification models for ECG classification , 2010, 2010 Computing in Cardiology.

[21]  Piotr Augustyniak.  Wearable wireless heart rate monitor for continuous long-term variability studies. , 2011, Journal of electrocardiology.

[22]  Juan Pablo Martínez,et al.  Heartbeat Classification Using Feature Selection Driven by Database Generalization Criteria , 2011, IEEE Transactions on Biomedical Engineering.

[23]  Philip de Chazal,et al.  Automatic classification of heartbeats using ECG morphology and heartbeat interval features , 2004, IEEE Transactions on Biomedical Engineering.

[24]  W. Bystricky,et al.  Identifying and measuring representative QT intervals in predominantly non-normal ECGs , 2006, 2006 Computers in Cardiology.