An approach of cardiac disease prediction by analyzing ECG signal
01 Sep 2016-pp 1-5
TL;DR: In this proposed method diseases are modeled using the time domain features of ECG signal which are extracted using BIOPAC AcqKnowledge software, which can be used to detect cardiac arrhythmia.
Abstract: Electrocardiogram (ECG) gives useful information about morphological and functional details of heart which is used to predict various cardiac diseases. In this paper a method of detecting cardiac diseases using support vector machine (SVM) is proposed. In this proposed method diseases are modeled using the time domain features of ECG signal which are extracted using BIOPAC AcqKnowledge software. Raw ECG signal contains these useful features which can be used to detect cardiac arrhythmia. The various ECG parameters like heart rate, QRS complex, PR interval, ST segment elevation, ST interval of ECG signal are used for analysis. Based on these parameters of ECG signal, different heart disease like atrial fibrillation, sinus tachycardia, myocardial infarction and apnea are detected. The individual accuracy of tachycardia arrhythmia, MI arrhythmia, atrial fibrillation arrhythmia and apnea proposed by SVM are 83.3%, 86.4%, 88% and 85.7% respectively.
Citations
More filters
TL;DR: A highly-effective feature-ranking algorithm is proposed to reduce the complexity of the classification task and the accuracy, sensitivity, precision, and F1 score of the CB model perform better than ET and RC models.
21 citations
TL;DR: In this article, a method of cross validation is introduced to identify the mislabeled samples and retain the correctly labeled ones with the help of 10-fold cross validation, and a new training set is provided to the final classifiers to acquire higher classification accuracies.
17 citations
Posted Content•
TL;DR: In this paper, a method of cross validation is introduced to identify the mislabeled samples and retain the correctly labeled ones with the help of 10-fold cross validation, and a new training set is provided to the final classifiers to acquire higher classification accuracies.
Abstract: The classification accuracy of electrocardiogram signal is often affected by diverse factors in which mislabeled training samples issue is one of the most influential problems. In order to mitigate this negative effect, the method of cross validation is introduced to identify the mislabeled samples. The method utilizes the cooperative advantages of different classifiers to act as a filter for the training samples. The filter removes the mislabeled training samples and retains the correctly labeled ones with the help of 10-fold cross validation. Consequently, a new training set is provided to the final classifiers to acquire higher classification accuracies. Finally, we numerically show the effectiveness of the proposed method with the MIT-BIH arrhythmia database.
11 citations
01 Jan 2022
TL;DR: In this article, a deep neural network classifier was used for prediction of arrhythmia if present based on some predefined value and connected it to the user interface to which the native users can check the level of arrrhythmia.
Abstract: Due to advancement of new edge medical technologies, many methods have been applied to solve medical issues including machine learning approach. Cardiac Arrhythmia is one of the common diseases which can be solved using various machine learning approaches. There are many approaches which have already been introduced to classify arrhythmia and abnormality detection. This paper has a solution, introduces supervised and unsupervised models in which supervised models generate a good classification result. However, in this paper, we have also introduced a deep neural network classifier and used for prediction of arrhythmia if present based on some predefined value. In this paper, we have also connected it to the user interface to which the native users can check the level of arrhythmia.
10 citations
25 Jun 2018
TL;DR: This paper proposes to enhance the random forest method by suggesting a new simulated annealing (SA) algorithm to find the optimal number of trees where the accuracy of classifying the ECG signal is tackled as an objective function.
Abstract: Cardiac diseases are one of the foremost reasons of mortality in the worldwide. To cope with this issue, cardiology doctors insist on the early detection of cardiac diseases often with the use of an electrocardiogram (ECG) signal, providing timely and appropriate treatment for heart patients. In the literature, there are many efficient classification approaches like random forest method, conceived for ECG signal analysis to detect cardiac diseases. However, the execution of random forest requests introducing manually the number of trees as a parameter user, which is considered as a major drawback of this method, since often the user did not find the optimal tree value. In this paper, we propose to enhance the random forest method by suggesting a new simulated annealing (SA) algorithm to find the optimal number of trees where the accuracy of classifying the ECG signal is tackled as an objective function. The proposed system involves four main steps namely data collecting of ECG signal, pretreatment and denoising this data, feature extraction and classifying this signal using the enhanced random forest approach. To validate this proposal, a set of experiments was conducted on the well-known European Physionet ST-T and MIT/BIH databases as well as the USA Heart Disease Data Set and Arrhythmia Data Set of UCI machine learning repository. The results obtained showed that the enhanced random forest can reach 99.62% of classification accuracy according to the optimal found number of trees.
8 citations
Cites methods from "An approach of cardiac disease pred..."
...In the state of the art of ECG machine learning, several efficient classification approaches were proposed such as support vector machine (SVM) [5] [6], Neural Network [7] [8], Kmeans [9], and random forest method (RF) [10] [11] [12]....
[...]
...Authors of [5] applied the support vector machine (SVM) to detect cardiac diseases, in this proposal the disease is modeled by the time domain features of ECG signal, which is extracted using a software called BIOPAC AcqKnowledge....
[...]
References
More filters
TL;DR: The results show that the proposed MEES approach can successfully detect the MI pathologies and help localize different types of MIs.
Abstract: In this paper, a novel technique on a multiscale energy and eigenspace (MEES) approach is proposed for the detection and localization of myocardial infarction (MI) from multilead electrocardiogram (ECG). Wavelet decomposition of multilead ECG signals grossly segments the clinical components at different subbands. In MI, pathological characteristics such as hypercute T-wave, inversion of T-wave, changes in ST elevation, or pathological Q-wave are seen in ECG signals. This pathological information alters the covariance structures of multiscale multivariate matrices at different scales and the corresponding eigenvalues. The clinically relevant components can be captured by eigenvalues. In this study, multiscale wavelet energies and eigenvalues of multiscale covariance matrices are used as diagnostic features. Support vector machines (SVMs) with both linear and radial basis function (RBF) kernel and K-nearest neighbor are used as classifiers. Datasets, which include healthy control, and various types of MI, such as anterior, anteriolateral, anterioseptal, inferior, inferiolateral, and inferioposterio-lateral, from the PTB diagnostic ECG database are used for evaluation. The results show that the proposed technique can successfully detect the MI pathologies. The MEES approach also helps localize different types of MIs. For MI detection, the accuracy, the sensitivity, and the specificity values are 96%, 93%, and 99% respectively. The localization accuracy is 99.58%, using a multiclass SVM classifier with RBF kernel.
235 citations
"An approach of cardiac disease pred..." refers background in this paper
...The abnormalities in heart is found by the doctors by observing the deviation of P, QRS and T signal from the normal signal in terms of time duration and amplitude[4]....
[...]
...P wave is the first electrical positive signal in the normal ECG....
[...]
TL;DR: A novel L2 MKL least squares support vector machine (LSSVM) algorithm is proposed, which is shown to be an efficient and promising classifier for large scale data sets processing and large scale numerical experiments indicate that when cast as semi-infinite programming, LSSVM MKL can be solved more efficiently than SVMMKL.
Abstract: This paper introduces the notion of optimizing different norms in the dual problem of support vector machines with multiple kernels. The selection of norms yields different extensions of multiple kernel learning (MKL) such as L∞, L1, and L2 MKL. In particular, L2 MKL is a novel method that leads to non-sparse optimal kernel coefficients, which is different from the sparse kernel coefficients optimized by the existing L∞ MKL method. In real biomedical applications, L2 MKL may have more advantages over sparse integration method for thoroughly combining complementary information in heterogeneous data sources. We provide a theoretical analysis of the relationship between the L2 optimization of kernels in the dual problem with the L2 coefficient regularization in the primal problem. Understanding the dual L2 problem grants a unified view on MKL and enables us to extend the L2 method to a wide range of machine learning problems. We implement L2 MKL for ranking and classification problems and compare its performance with the sparse L∞ and the averaging L1 MKL methods. The experiments are carried out on six real biomedical data sets and two large scale UCI data sets. L2 MKL yields better performance on most of the benchmark data sets. In particular, we propose a novel L2 MKL least squares support vector machine (LSSVM) algorithm, which is shown to be an efficient and promising classifier for large scale data sets processing. This paper extends the statistical framework of genomic data fusion based on MKL. Allowing non-sparse weights on the data sources is an attractive option in settings where we believe most data sources to be relevant to the problem at hand and want to avoid a "winner-takes-all" effect seen in L∞ MKL, which can be detrimental to the performance in prospective studies. The notion of optimizing L2 kernels can be straightforwardly extended to ranking, classification, regression, and clustering algorithms. To tackle the computational burden of MKL, this paper proposes several novel LSSVM based MKL algorithms. Systematic comparison on real data sets shows that LSSVM MKL has comparable performance as the conventional SVM MKL algorithms. Moreover, large scale numerical experiments indicate that when cast as semi-infinite programming, LSSVM MKL can be solved more efficiently than SVM MKL. The MATLAB code of algorithms implemented in this paper is downloadable from http://homes.esat.kuleuven.be/~sistawww/bioi/syu/l2lssvm.html
.
118 citations
18 Jun 2010
TL;DR: This paper presents automatic detection and localization of myocardial infarction using back propagation neural networks (BPNN) classifier with features extracted from 12 lead ECG using the PTB database.
Abstract: This paper presents automatic detection and localization of myocardial infarction (MI) using back propagation neural networks (BPNN) classifier with features extracted from 12 lead ECG. Detection of MI aims to classify healthy and subjects having MI. Localization is the task of specifying the infarcted region of the heart. The electrocardiogram (ECG) source used is the PTB database available on Physio-bank. Time domain features of each beat in the ECG signal such as T wave amplitude, Q wave and ST level deviation, which are indicative of MI, are extracted. For localization, lead-wise principal components analysis (PCA) is done on the data extracted from ST-T region and Q wave region of each beat. The resulting principal components are used as features for localization of seven types of myocardial infarction. For detection, it is found that the sensitivity and specificity of BPNN for beat classification is 97.5 % and 99.1% respectively. For localization, PCA based features using back propagation neural network classifier resulted in a beat classification accuracy of 93.7%. The proposed method due to its simplicity and high accuracy over the PTB database can be very helpful in correct diagnosis of MI in a practical scenario.
51 citations
01 Oct 2012
TL;DR: The developed real time fetal electrocardiogram (FECG) feature extraction system based on multi-scale discrete wavelet transform (DWT) and two-channel perfect reconstruction (PR) filter banks are used to implement the efficient way discreteWavelet transform is implemented.
Abstract: In this study we have developed real time fetal electrocardiogram (FECG) feature extraction system based on multi-scale discrete wavelet transform (DWT). Wavelet based peak detection are used to detect QRS complex more accurately for identifying peaks and valleys of noisy FECG signal. Two-channel perfect reconstruction (PR) filter banks are used to implement the efficient way discrete wavelet transform. The developed fetal maternal ECG monitor machine has been tested in a local hospital on a sample group of 35 pregnant women at different interval during gestation period. This reliable system detects all FECG beats to the accuracy better than 99.5 % considering limitation of measuring system parameters in five minutes recording of each subject.
31 citations
20 Jul 2011
TL;DR: An Artificial Neural Network (ANN) based cardiac arrhythmia disease diagnosis system using standard 12 lead ECG signal recordings data and replacing missing attributes by closest column value of the concern class is proposed.
Abstract: Changes in the normal rhythm of a human heart may result in different cardiac arrhythmias, which may be immediately fatal or cause irreparable damage to the heart sustained over long periods of time. The ability to automatically identify arrhythmias from ECG recordings is important for clinical diagnosis and treatment. In this paper we proposed an Artificial Neural Network (ANN) based cardiac arrhythmia disease diagnosis system using standard 12 lead ECG signal recordings data. In this study, we are mainly interested in classifying disease in normal and abnormal classes. We have used UCI ECG signal data to train and test three different ANN models. In arrhythmia analysis, it is unavoidable that some attribute values of a person would be missing. Therefore we have replaced these missing attributes by closest column value of the concern class. ANN models are trained by static backpropagation algorithm with momentum learning rule to diagnose cardiac arrhythmia. The classification performance is evaluated using measures such as mean squared error (MSE), classification specificity, sensitivity, accuracy, receiver operating characteristics (ROC) and area under curve (AUC). Out of three different ANN models Multilayer perceptron ANN model have given very attractive classification results in terms of classification accuracy and sensitivity of 86.67% and 93.75% respectively while Modular ANN have given 93.1% classification specificity.
20 citations