Arrhythmia detection using deep convolutional neural network with long duration ECG signals.

A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification

A survey on ECG analysis

New methodology based on single lead and analysis of longer (10-s) ECG signal fragments is proposed.New training based on genetic algorithm coupled with 10-fold cross-validation is employed.17 classes: normal sinus rhythm + pacemaker rhythm + 15 cardiac disorders are recognized.New feature extraction and selection based on PSD, DFT and GA are employed.Recognition sensitivity at a level of 90.20% (98 errors per 1000 classifications) is promising. This article presents an innovative research methodology that enables the efficient classification of cardiac disorders (17 classes) based on ECG signal analysis and an evolutionary-neural system.From a social point of view, it is extremely important to prevent heart diseases, which are the most common cause of death worldwide. According to statistical data, 50 million people are at risk for cardiac diseases worldwide. The subject of ECG signal analysis is very popular. However, due to the great difficulty of the task undertaken, and high computational complexity of existing methods, there remains substantial work to perform.This research collected 1000 fragments of ECG signals from the MIH-BIH Arrhythmia database for one lead, MLII, from 45 patients. An original methodology that consisted of the analysis of longer (10-s) fragments of the ECG signal was used (an average of 13 times less classifications). To enhance the characteristic features of the ECG signal, the spectral power density was estimated (using Welchs method and a discrete Fourier transform). Genetic optimization of parameters and genetic selection of features were tested. Pre-processing, normalization, feature extraction and selection, cross-validation and machine learning algorithms (SVM, kNN, PNN, and RBFNN) were used.The best evolutionary-neural system, based on the SVM classifier, obtained a recognition sensitivity of 17 myocardium dysfunctions at a level of 90.20% (98 errors per 1000 classifications, accuracy = 98.85%, specificity = 99.39%, time for classification of one sample = 0.0023 [s]). Against the background of the current scientific literature, these results are some of the best results to date.

Novel methodology of cardiac health recognition based on ECG signals and evolutionary-neural system

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.

LSTM-Based Auto-Encoder Model for ECG Arrhythmias Classification

Early detection of cardiac diseases using computer aided diagnosis system reduces the high mortality rate among heart patients. The detection of cardiac arrhythmias is a challenging task since the small variations in electrocardiogram (ECG) signals cannot be distinguished precisely by human eye. In this paper, dual tree complex wavelet transform (DTCWT) based feature extraction technique for automatic classification of cardiac arrhythmias is proposed. The feature set comprises of complex wavelet coefficients extracted from the fourth and fifth scale DTCWT decomposition of a QRS complex signal in conjunction with four other features (AC power, kurtosis, skewness and timing information) extracted from the QRS complex signal. This feature set is classified using multi-layer back propagation neural network. The performance of the proposed feature set is compared with statistical features extracted from the sub-bands obtained after decomposition of the QRS complex signal using discrete wavelet transform (DWT) and with four other features (AC power, kurtosis, skewness and timing information) extracted from the QRS complex signal. The experimental results indicate that the DWT and DTCWT based feature extraction technique classifies ECG beats with an overall sensitivity of 91.23% and 94.64%, respectively when tested over five types of ECG beats of MIT-BIH Arrhythmia database.

Automatic ECG arrhythmia classification using dual tree complex wavelet based features

The electrocardiogram (ECG) is a standard diagnostic tool to distinguish the different types of arrhythmias. This paper develops a novel framework for feature extraction technique based on dual tree complex wavelet transform (DTCWT). The feature set comprises of complex wavelet coefficients extracted from the 4th and 5th scale of DTCWT decomposition and four other features (AC power, kurtosis, skewness and timing information). This feature set is classified using feed forward neural network. In this work, five types of ECG beats (Normal, Paced, Right Bundle Branch Block, Left Bundle Branch Block and Premature Ventricular Contraction) are classified from the MIT-BIH arrhythmia database. The performance of the proposed method is compared with statistical features extracted using discrete wavelet transform (DWT). The experimental result shows that the proposed method classifies ECG beats with an overall sensitivity of 97.80%.

Classification of cardiac arrhythmias based on dual tree complex wavelet transform

Electrocardiogram (ECG) signal provides the valuable information for detection of abnormal heart disease. Detection of QRS complexes is the first step towards recognition of heart disease from the ECG signal. ECG would be much more useful as a diagnostic tool if unwanted noise embedded in the signal is removed. The aims of the work are to (i) ECG signal enhancement using empirical mode decomposition (EMD) based method. (ii) Detection of QRS complexes using continuous wavelet transform method from the enhanced signal. The experiments are carried out on MIT-BIH database. The results show that our proposed method is very effective and an efficient method for fast computation of R peak detection.

http://dspace.nitrkl.ac.in:8080/dspace/bitstream/2080/1577/1/On%20an%20Algorithm.pdf

Manab Kr Das

Papers

Automatic ECG arrhythmia classification using dual tree complex wavelet based features

Classification of cardiac arrhythmias based on dual tree complex wavelet transform

On an algorithm for detection of QRS complexes in noisy electrocardiogram signal