LSTM-Based Auto-Encoder Model for ECG Arrhythmias Classification

This paper introduces a novel deep learning-based algorithm that integrates a long short-term memory (LSTM)-based auto-encoder (AE) network with support vector machine (SVM) for electrocardiogram (ECG) arrhythmias classification. The LSTM-based AE network (LSTM-AE) is used to learn the features from ECG arrhythmias signals, and the SVM is used to classify those signals from the learned features. The LSTM-AE consists of an encoder model, which extracts high-level feature information from ECG arrhythmias signals through LSTM network, and a decoder model which outputs reconstruct ECG arrhythmias signals from high-level features through LSTM network. Experiments show that the proposed method can learn better features than the traditional method without any prior knowledge, presenting a good potential for the ECG arrhythmias classification. In the classification of five heartbeats types, including normal, left bundle branch block (LBBB), right bundle branch block (RBBB), atrial premature complexes (APC), premature ventricular contractions (PVC), the proposed method achieved average accuracy, sensitivity, and specificity of 99.74%, 99.35%, and 99.84%, respectively, in the beat-based cross-validation approach, and 85.20%, 62.99%, and 90.75%, respectively, in the record-based cross-validation approach, in public MIT-BIH Arrhythmia Database. While based on the Advancement of Medical Instrumentation (AAMI) standards, the proposed method achieved average accuracy, sensitivity, and specificity of 99.45%, 98.63%, and 99.66%, respectively, in the beat-based cross-validation approach.

[1]  U. Rajendra Acharya,et al.  An efficient compression of ECG signals using deep convolutional autoencoders , 2018, Cognitive Systems Research.

[2]  S. K. Mukhopadhyay,et al.  An ECG signal compression technique using ASCII character encoding , 2012 .

[3]  Chandan Chakraborty,et al.  Application of Higher Order cumulant Features for Cardiac Health Diagnosis using ECG signals , 2013, Int. J. Neural Syst..

[4]  Madhuchhanda Mitra,et al.  Application of Cross Wavelet Transform for ECG Pattern Analysis and Classification , 2014, IEEE Transactions on Instrumentation and Measurement.

[5]  Manu Thomas,et al.  Automatic ECG arrhythmia classification using dual tree complex wavelet based features , 2015 .

[6]  M. I. Owis,et al.  A novel technique for cardiac arrhythmia classification using spectral correlation and support vector machines , 2015, Expert systems with applications.

[7]  Saeed Karimifard,et al.  A robust method for diagnosis of morphological arrhythmias based on Hermitian model of higher-order statistics , 2011, Biomedical engineering online.

[8]  Fethi Bereksi-Reguig,et al.  Automatic Classification of Heartbeats Using Wavelet Neural Network , 2012, Journal of Medical Systems.

[9]  Moncef Gabbouj,et al.  Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks , 2016, IEEE Transactions on Biomedical Engineering.

[10]  U. Rajendra Acharya,et al.  Automated detection of coronary artery disease using different durations of ECG segments with convolutional neural network , 2017, Knowl. Based Syst..

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

[12]  Vikrant Bhateja,et al.  Entropy Index in Quantitative EEG Measurement for Diagnosis Accuracy , 2014, IEEE Transactions on Instrumentation and Measurement.

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

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

[15]  U. Rajendra Acharya,et al.  Automated diagnosis of arrhythmia using combination of CNN and LSTM techniques with variable length heart beats , 2018, Comput. Biol. Medicine.

[16]  Chengyu Liu,et al.  Combining Low-dimensional Wavelet Features and Support Vector Machine for Arrhythmia Beat Classification , 2017, Scientific Reports.

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

[18]  Sandeep Raj,et al.  ECG Signal Analysis Using DCT-Based DOST and PSO Optimized SVM , 2017, IEEE Transactions on Instrumentation and Measurement.

[19]  K. Toosi,et al.  Discrete Wavelet-based Fuzzy Network Architecture for ECG Rhythm-Type Recognition: Feature Extraction and Clustering- Oriented Tuning of Fuzzy Inference System , 2011 .

[20]  Xiangqian Ding,et al.  A Novel Method for Classification of ECG Arrhythmias Using Deep Belief Networks , 2016, Int. J. Comput. Intell. Appl..

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

[22]  C.-C. Jay Kuo,et al.  ECG-based biometrics using recurrent neural networks , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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

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

[25]  U. Rajendra Acharya,et al.  Application of stacked convolutional and long short-term memory network for accurate identification of CAD ECG signals , 2018, Comput. Biol. Medicine.

[26]  Naif Alajlan,et al.  Deep learning approach for active classification of electrocardiogram signals , 2016, Inf. Sci..

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

[28]  Özal Yildirim,et al.  A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification , 2018, Comput. Biol. Medicine.

[29]  Feng Lin,et al.  A stacked contractive denoising auto-encoder for ECG signal denoising , 2016, Physiological measurement.

[30]  Michel Verleysen,et al.  Weighted Conditional Random Fields for Supervised Interpatient Heartbeat Classification , 2012, IEEE Transactions on Biomedical Engineering.

[31]  Sandeep Raj,et al.  Sparse representation of ECG signals for automated recognition of cardiac arrhythmias , 2018, Expert Syst. Appl..

[32]  Shailja Shukla,et al.  ECG signal processing for abnormalities detection using multi-resolution wavelet transform and Artificial Neural Network classifier , 2013 .

[33]  Adrian D. C. Chan,et al.  Wavelet Distance Measure for Person Identification Using Electrocardiograms , 2008, IEEE Transactions on Instrumentation and Measurement.

[34]  Yu Tian,et al.  High-Performance Personalized Heartbeat Classification Model for Long-Term ECG Signal , 2017, IEEE Transactions on Biomedical Engineering.

[35]  Vinod Chandran,et al.  Cardiac Health Diagnosis Using Higher Order Spectra and Support Vector Machine , 2009, The open medical informatics journal.

[36]  U. Rajendra Acharya,et al.  A deep convolutional neural network model to classify heartbeats , 2017, Comput. Biol. Medicine.

[37]  Diego Andina,et al.  Application of Artificial Metaplasticity Neural Networks to Cardiac Arrhythmias Classification , 2013, IWINAC.

[38]  Kenneth E. Barner,et al.  A novel application of deep learning for single-lead ECG classification , 2018, Comput. Biol. Medicine.

[39]  Min Zhou,et al.  ECG Classification Using Wavelet Packet Entropy and Random Forests , 2016, Entropy.

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

[41]  Ataollah Ebrahimzadeh,et al.  Detection of electrocardiogram signals using an efficient method , 2014, Appl. Soft Comput..

[42]  B. V. K. Vijaya Kumar,et al.  Heartbeat Classification Using Morphological and Dynamic Features of ECG Signals , 2012, IEEE Transactions on Biomedical Engineering.

[43]  Lu Cao,et al.  Arrhythmia Classification Based on Multi-Domain Feature Extraction for an ECG Recognition System , 2016, Sensors.