MedicineNet是一家在线医疗保健出版公司，通过友好的交互式网站为用户提供通俗易读的专业权威性医学信息。该网站编辑团队由训练有素、极富经验的内科学、健康管理、互联网技术和商业领域资深专家组成，主体成员为经董事会认证的70多位内科医生。网站自成立以来得到了全美国用户的认可。

MedicineNet

A survey on ECG analysis

Multiresolution wavelet transform based feature extraction and ECG classification to detect cardiac abnormalities

An efficient heart sound segmentation (HSS) method that automatically detects the location of first ( S1) and second ( S2) heart sound and extracts them from heart auscultatory raw data is presented here. The heart phonocardiogram is analyzed by employing ensemble empirical mode decomposition (EEMD) combined with kurtosis features to locate the presence of S1, S2, and extract them from the recorded data, forming the proposed HSS scheme, namely HSS-EEMD/K. Its performance is evaluated on an experimental dataset of 43 heart sound recordings performed in a real clinical environment, drawn from 11 normal subjects, 16 patients with aortic stenosis, and 16 ones with mitral regurgitation of different degrees of severity, producing 2608 S1 and S2 sequences without and with murmurs, respectively. Experimental results have shown that, overall, the HSS-EEMD/K approach determines the heart sound locations in a percentage of 94.56% and segments heart cycles correctly for the 83.05% of the cases. Moreover, results from a noise stress test with additive Gaussian noise and respiratory noises justify the noise robustness of the HSS-EEMD/K. When compared with four other efficient methods that mainly employ wavelet transform, energy, simplicity, and frequency measures, respectively, using the same experimental database, the HSS-EEMD/K scheme exhibits increased accuracy and prediction power over all others at the level of 7-19% and 4-9%, respectively, both in controls and pathological cases. The promising performance of the HSS-EEMD/K paves the way for further exploitation of the diagnostic value of heart sounds in everyday clinical practice.

Efficient Heart Sound Segmentation and Extraction Using Ensemble Empirical Mode Decomposition and Kurtosis Features

Accurate measurement of heart sound and murmur parameters is of great importance in the automated analysis of phonocardiogram (PCG) signals. In this paper, we propose a novel unified PCG signal delineation and murmur classification method without the use of reference signal for automatic detection and classification of heart sounds and murmurs. The major components of the proposed method are the empirical wavelet transform-based PCG signal decomposition for discriminating heart sounds from heart murmurs and suppressing background noises, the Shannon entropy envelope extraction, the instantaneous phase-based boundary determination, heart sound and murmur parameter extraction, the systole/diastole discrimination and the decision rules-based murmur classification. The accuracy and robustness of the proposed method is evaluated using a wide variety of normal and abnormal PCG signals taken from the standard PCG databases, including PASCAL heart sounds challenge database, PhysioNet/CinC challenge heart sound database, and real-time PCG signals. Evaluation results show that the proposed method achieves an average sensitivity (Se) of 94.38%, positive predictivity (Pp) of 97.25%, and overall accuracy (OA) of 91.92% for heart sound segmentation and Se of 97.58%, Pp of 96.46%, and OA of 94.21% in detecting the presence of heart murmurs for SNR of 10 dB. The method yields an average classification accuracy of 95.5% for the PCG signals with SNR of 20 dB. Results show that the proposed method outperforms other existing heart sound segmentation and murmur classification methods.

Effective Heart Sound Segmentation and Murmur Classification Using Empirical Wavelet Transform and Instantaneous Phase for Electronic Stethoscope

The electrocardiogram (ECG) signal is considered as one of the most important tools in clinical practice in order to assess the cardiac status of patients. In this study, an improved QRS (Q wave, R wave, S wave) complex detection algorithm is proposed based on the multiresolution wavelet analysis. In the first step, high frequency noise and baseline wander can be distinguished from ECG data based on their specific frequency contents. Hence, removing corresponding detail coefficients leads to enhance the performance of the detection algorithm. After this, the author's method is based on the power spectrum of decomposition signals for selecting detail coefficient corresponding to the frequency band of the QRS complex. Hence, the authors have proposed a function g as the combination of the selected detail coefficients using two parameters λ 1 and λ 2, which correspond to the proportion of the frequency ranges of the selected detail compared with the frequency range of the QRS complex. The proposed algorithm is evaluated using the whole arrhythmia database. It presents considerable capability in cases of low signal-to-noise ratio, high baseline wander and abnormal morphologies. The results of evaluation show the good detection performance; they have obtained a global sensitivity of 99.87%, a positive predectivity of 99.79% and a percentage error of 0.34%.

https://ietresearch.onlinelibrary.wiley.com/doi/pdf/10.1049/iet-spr.2013.0391

Multiresolution wavelet-based QRS complex detection algorithm suited to several abnormal morphologies

Heart sounds that are multicomponent non-stationary signals characterise the normal phonocardiogram (PCG) signals and the pathological PCG signals. The time-frequency analysis is a powerful tool in the analysis of non-stationary signals especially for PCG signals. It permits detecting and characterising abnormal murmurs in the diagnosis of heart disease. In this study, the authors introduce a novel method based on time-frequency analysis in conjunction with a threshold evaluated on Renyi entropy for the segmentation and the analysis of PCG signals. The method was applied to different sets of PCG signals: early aortic stenosis, late systolic aortic stenosis, pulmonary stenosis and mitral regurgitation. The analysis has been conducted on real biomedical data. Tests performed proved the ability of the method for segmentation between the main components and the pathological murmurs of the PCG signal. Also, the method permits elucidating and extracting useful features for diagnosis and pathological recognition.

Segmentation and identification of some pathological phonocardiogram signals using time-frequency analysis

Empirical mode decomposition (EMD) allows decomposing an observed multicomponent signal into a set of monocomponent signals called Intrinsic Mode Functions (IMFs). EMD provides a large number of IMFs and it is important to select the fundamental IMFs and eliminate the redundant ones. This paper proposes a new criterion, based simultaneously on the Minkowski distance and the Jensen Renyi divergence of order α (α-JRD), to automatically select the appropriate IMFs in a set of the extracted ones. Examples, using synthetic and real-life heart sound signals, are presented in order to validate the performance of the proposed technique.

On the selection of Intrinsic Mode Function in EMD method: Application on heart sound signal

The authors have proposed a new automatic classification scheme based on the conjoint use of the multi-layer perceptron (MLP) neural network and an enhanced particle swarm optimisation (EPSO) algorithm for its training. In this work, six predominant categories of heartbeats from MIT-BIH database are considered, which are: normal, premature ventricular contraction, atrial premature contraction, right bundle branch block, left bundle branch block and paced beats. First, the authors have applied the standard particle swarm optimisation (PSO) algorithm to select the network structure for each features vector. Then, the relevant electrocardiogram (ECG) features to the studied arrhythmias were chosen, which suited to the optimised training performance of the classifier. The recognition performance of the proposed EPSO-MLP classification system is evaluated considering two different versions of the EPSO algorithm. In the first version (EPSOw), the inertia weight factor of the PSO algorithm is proposed to be a variable with iterations. However, two PSO parameters are taken to be variables in the second version of the improved learning algorithm (EPSOwc). The obtained experimental results prove the enhancement of the convergence ability of the MLP neural network and confirm the superiority of the proposed EPSO-MLP classification scheme on comparison with the other last published classification systems.

https://ietresearch.onlinelibrary.wiley.com/doi/pdf/10.1049/iet-spr.2018.5465

Automatic ECG arrhythmias classification scheme based on the conjoint use of the multi-layer perceptron neural network and a new improved metaheuristic approach

This paper presents a method to characterize, identify and classify some pathological Electroencephalogram (EEG) signals. We use some Time Frequency Distributions (TFDs) to analyze its nonstationarity. The analysis is conducted by the spectrogram (SP), the Choi–Williams Distribution (CWD) and the Smoothed Pseudo Wigner Ville Distribution (SPWVD). The studies are carried on some real EEG signals collected from a known database. The estimation of the best value of parameters for each distribution is achieved using the Renyi entropy (RE). The time-frequency results have permitted to characterize some pathological EEG signals. In addition, the Renyi Marginal Entropy (RME) is used for the purpose of detecting the peak seizures and discriminates between normal and pathological EEG signals. The frequency bands are evaluated using the Marginal Frequency (MF). The EEG signal classification of two sets A and E containing normal and pathologic EEG signals, respectively, is performed using our proposed method based on energy extraction of signals from time-frequency plane. Also, the Moving Average (MA) is used as a tool to obtain better classification results. The results conducted on real-life EEG signals illustrate the effectiveness of the proposed method.

Daoud Boutana

Papers

Multiresolution wavelet-based QRS complex detection algorithm suited to several abnormal morphologies

Segmentation and identification of some pathological phonocardiogram signals using time-frequency analysis

On the selection of Intrinsic Mode Function in EMD method: Application on heart sound signal

Automatic ECG arrhythmias classification scheme based on the conjoint use of the multi-layer perceptron neural network and a new improved metaheuristic approach

EEG Signals Classification Based on Time Frequency Analysis