Principal component analysis in ECG signal processing
01 Jan 2007-EURASIP Journal on Advances in Signal Processing (Springer International Publishing)-Vol. 2007, Iss: 1, pp 98-98
TL;DR: Several ECG applications are reviewed where PCA techniques have been successfully employed, including data compression, ST-T segment analysis for the detection of myocardial ischemia and abnormalities in ventricular repolarization, extraction of atrial fibrillatory waves for detailed characterization of atrium fibrillation, and analysis of body surface potential maps.
Abstract: This paper reviews the current status of principal component analysis in the area of ECG signal processing. The fundamentals of PCA are briefly described and the relationship between PCA and Karhunen-Loeve transform is explained. Aspects on PCA related to data with temporal and spatial correlations are considered as adaptive estimation of principal components is. Several ECG applications are reviewed where PCA techniques have been successfully employed, including data compression, ST-T segment analysis for the detection of myocardial ischemia and abnormalities in ventricular repolarization, extraction of atrial fibrillatory waves for detailed characterization of atrial fibrillation, and analysis of body surface potential maps.
Citations
More filters
TL;DR: This work surveys the current state-of-the-art methods of ECG-based automated abnormalities heartbeat classification by presenting the ECG signal preprocessing, the heartbeat segmentation techniques, the feature description methods and the learning algorithms used.
635 citations
Cites methods from "Principal component analysis in ECG..."
...The PCA technique separates the sources according to the energy contribution to the signal....
[...]
...According to Kallas et al. [83], KPCA performs better, due to its nonlinear structure....
[...]
...In that work, a comparison between PCA the ECG signal....
[...]
...Aiming at reducing the dimension of the feature vector, various techniques have been applied directly on the samples that represent the heartbeat (in the neighborhood of the R peak) as principal component analysis (PCA) [75–77], or independent component analysis (ICA) [78–80], in which new coefficients are extracted to represent the heartbeat....
[...]
...Another technique based on PCA, the Kernel Principal Component Analisys (KPCA), was used by Kanaan et al. [82]....
[...]
TL;DR: The proposed framework for classification of EMG signals using multiscale principal component analysis (MSPCA) for de-noising, discrete wavelet transform (DWT) for feature extraction and decision tree algorithms for classification can be used to support clinicians for diagnosis of neuromuscular disorders.
213 citations
Cites methods from "Principal component analysis in ECG..."
...This approach is applied in different studies such as data reduction, beat detection, classification, signal segmentation and feature extraction [25, 3]....
[...]
TL;DR: An innovative research methodology is presented that enables the efficient classification of cardiac disorders (17 classes) based on ECG signal analysis and an evolutionary-neural system and these results are some of the best results to date.
Abstract: 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.
181 citations
TL;DR: An algorithm for analyzing changes in ECG morphology based on principal component analysis (PCA) is presented and applied to the derivation of surrogate respiratory signals from single-lead ECGs.
Abstract: An algorithm for analyzing changes in ECG morphology based on principal component analysis (PCA) is presented and applied to the derivation of surrogate respiratory signals from single-lead ECGs. The respiratory-induced variability of ECG features, P waves, QRS complexes, and T waves are described by the PCA. We assessed which ECG features and which principal components yielded the best surrogate for the respiratory signal. Twenty subjects performed controlled breathing for 180 s at 4, 6, 8, 10, 12, and 14 breaths per minute and normal breathing. ECG and breathing signals were recorded. Respiration was derived from the ECG by three algorithms: the PCA-based algorithm and two established algorithms, based on RR intervals and QRS amplitudes. ECG-derived respiration was compared to the recorded breathing signal by magnitude squared coherence and cross-correlation. The top ranking algorithm for both coherence and correlation was the PCA algorithm applied to QRS complexes. Coherence and correlation were significantly larger for this algorithm than the RR algorithm(p < 0.05 and p < 0.0001, respectively) but were not significantly different from the amplitude algorithm. PCA provides a novel algorithm for analysis of both respiratory and nonrespiratory related beat-to-beat changes in different ECG features.
169 citations
TL;DR: The experimental results have successfully validated that the integration of the PNN classifier with the proposed feature reduction method can achieve satisfactory classification accuracy.
162 citations
References
More filters
Book•
01 May 1986TL;DR: In this article, the authors present a graphical representation of data using Principal Component Analysis (PCA) for time series and other non-independent data, as well as a generalization and adaptation of principal component analysis.
Abstract: Introduction * Properties of Population Principal Components * Properties of Sample Principal Components * Interpreting Principal Components: Examples * Graphical Representation of Data Using Principal Components * Choosing a Subset of Principal Components or Variables * Principal Component Analysis and Factor Analysis * Principal Components in Regression Analysis * Principal Components Used with Other Multivariate Techniques * Outlier Detection, Influential Observations and Robust Estimation * Rotation and Interpretation of Principal Components * Principal Component Analysis for Time Series and Other Non-Independent Data * Principal Component Analysis for Special Types of Data * Generalizations and Adaptations of Principal Component Analysis
17,446 citations
Book•
18 May 2001TL;DR: Independent component analysis as mentioned in this paper is a statistical generative model based on sparse coding, which is basically a proper probabilistic formulation of the ideas underpinning sparse coding and can be interpreted as providing a Bayesian prior.
Abstract: In this chapter, we discuss a statistical generative model called independent component analysis. It is basically a proper probabilistic formulation of the ideas underpinning sparse coding. It shows how sparse coding can be interpreted as providing a Bayesian prior, and answers some questions which were not properly answered in the sparse coding framework.
8,333 citations
Journal Article•
TL;DR: In this paper, a preliminary attempt was made to determine from blood pressure records the relative influence of the heart action and of vaso-canstriction, and it was suggested that it might be necessary to estimate the duration of ventricular systole for different heart rates.
Abstract: IN a preliminary attempt (which requires considerable modification) to determine from blood-pressure records the relative influence of the heart action and of vaso-canstriction, I suggestedS that it might be necessary to estimate the duration of ventricular systole for different heart rates. In order to obtain this information a number of measurements have been made of electrocardiographic curves, including some obtained by myself and a selection of curves from Dr. T. Lewis’s collection, which he very kindly put at my disposal. Electrical records have been preferred to mechanical, because it is easier to secure accuracy, and it has been shown by many workers that as a rub the electrical and mechanical changes correspond fairly closely. Lewis ,*7 in a comparison of the heart sounds with the electrical changes, found the first sound to commence 0.011 of a second to 0.039 of a second after the commencement of Q, while the second sound started either before or after the end of T but usually within 0.01 of a second of it. WiggersYS1 working with dogs, found the mechanical systole to commence 0.03 to 0.045 after the rise of R, and to terminate 0.034 to 0.048 after the end of T, so that as a rule the two changes corresponded in duration, but he found that adrenalin shortens the duration of the mechanical change more than the electrical, and under these conditions the ventrical contrsction ended before the end of the T wave. In considering, therefore, the relative duration of systole and diastole, both electrical and mechanical records are useful, if these differences be allowed for. Walleflsgivee the following values for the durebtion of mechanical systole with different heart rates, and it will be seen that almost exactly similar figures are obtained by calculation from the formula systole = K Vcycle, where K hae 8 value of 0.343.
4,324 citations
TL;DR: New guidelines for management of supraventricular tachyarrhythmia characterized by uncoordinated atrial activation with consequent deterioration of atrial mechanical function are published.
Abstract: Atrial fibrillation (AF), the most common sustained cardiac rhythm disturbance, is increasing in prevalence as the population ages. Although it is often associated with heart disease, AF occurs in many patients with no detectable disease. Hemodynamic impairment and thromboembolic events result in significant morbidity, mortality, and cost. Accordingly, the American College of Cardiology (ACC), the American Heart Association (AHA), and the European Society of Cardiology (ESC) created a committee of experts to establish guidelines for management of this arrhythmia.
The committee was composed of 8 members representing the ACC and AHA, 4 representing the ESC, 1 from the North American Society of Pacing and Electrophysiology (NASPE), and a representative of the Johns Hopkins University Evidence-Based Practice Center representing the Agency for Healthcare Research and Quality’s report on Atrial Fibrillation in the Elderly. This document was reviewed by 3 official reviewers nominated by the ACC, 3 nominated by the AHA, and 3 nominated by the ESC, as well as by the ACC Clinical Electrophysiology Committee, the AHA ECG and Arrhythmia Committee, NASPE, and 25 reviewers nominated by the writing committee. The document was approved for publication by the governing bodies of the ACC, AHA, and ESC and officially endorsed by NASPE. These guidelines will be reviewed annually by the task force and will be considered current unless the task force revises or withdraws them from distribution.
The committee conducted a comprehensive review of the literature from 1980 to June 2000 relevant to AF using the following databases: PubMed/Medline, EMBASE, the Cochrane Library (including the Cochrane Database of Systematic Reviews and the Cochrane Controlled Trials Registry), and Best Evidence. Searches were limited to English language sources and to human subjects.
### A. Atrial Fibrillation
AF is a supraventricular tachyarrhythmia characterized by uncoordinated atrial activation with consequent deterioration of atrial mechanical function. On the electrocardiogram (ECG), AF …
1,628 citations