便携心电传感器的心房肥大诊断研究

基于便携式传感器的模式识别在心电(ECG)监护领域具有广泛的应用前景,并且在心律不齐、心肌梗塞、心室肥大等心电的识别算法上都已有大量的研究与应用,但在心房肥大诊断上却未有模式识别相关的研究成果。心房肥大病症的心电数据量不足给研究造成重大障碍,部分分类器无法适应小样本训练下的分类。针对小样本训练进行研究,对比了不同分类方法,显示了基于统计模式识别的支持向量机(SVM)应用于心房肥大的应用潜力。另外,由于不同个体的心房肥大心电存在差异,在实际应用环境中,SVM存在无法良好泛化的问题,存在类别错分的医学风险。针对类别错分情况,采用分类器融合的方法改进分类器,提出了在SVM分类器输出端增加了拒绝域的分类器(SVM-R)的方法。实验结果表明:SVMR有较高的分类准确率与诊断可信度。     

Mechanical modeling of a beating heart for a cardiac palpation training system

In cardiac plastic surgery, the cardiac surgeon touches the cardiac muscle to diagnose the patient's heart that may be diseased due to infarction or dilate cardiomyopathy to determine the regions where it needs plastic surgery. In other words, the cardiac surgeon needs to recognize the mechanical characteristics of the thin muscle regions by the haptic sensitivity of his/her fingertips. Cardiac images available before cardiac surgery could enable a qualitative estimation of the patient's heart. However, cardiac palpation is the only accurate way for making surgical plans for ventricular plastic surgery in the operating theater. Since young inexperienced cardiac surgeons have few occasions to perform cardiac palpation, even in operation cases, a cardiac palpation training system is highly desired. The training system for a cardiac palpation system we have developed consists of a virtual heart based on human left ventricular magnetic resonance images and a one-dimensional manipulator as a haptic device. Mechanical properties of the cardiac muscles of a pig and a dog are embedded into the virtual heart linked to a Windkessel model for the systemic circulation. Our experiments show that the developed training system enables users to feel the elasticity of the cardiac muscle wall through the manipulator in real-time.     

Feature saliency using signal-to-noise ratios in automated diagnostic systems developed for ECG beats

Artificial neural networks (ANNs) have been used in a great number of medical diagnostic decision support system applications and within feedforward ANNs framework there are a number of established measures such as saliency measures for identifying important input features. By identifying a set of salient features, the noise in a classification model can be reduced, resulting in more accurate classification. In this study, a signal-to-noise ratio (SNR) saliency measure was employed to determine saliency of input features of multilayer perceptron neural networks (MLPNNs) used in classification of electrocardiogram (ECG) beats (normal beat, congestive heart failure beat, ventricular tachyarrhythmia beat, atrial fibrillation beat) obtained from the Physiobank database. The SNR saliency measure determines the saliency of a feature by comparing it to that of an injected noise feature and the SNR screening method utilizes the SNR saliency measure to select a parsimonious set of salient features. ECG signals were decomposed into time–frequency representations using discrete wavelet transform. Input feature vectors were extracted using statistics over the set of the wavelet coefficients. The MLPNNs used in the ECG beats-classification were trained for the SNR screening method. The application results of the SNR screening method to the ECG signals demonstrated that classification accuracies of the MLPNNs with salient input features are higher than that of the MLPNNs with salient and non-salient input features.     

基于U-NET网络的心律失常信号识别算法研究

在心电信号心律失常自动识别系统中,针对心电信号形态复杂导致特征提取困难、自动分类模型准确度低、现实应用性差的问题,设计了一种基于U-NET全卷积神经网络的心电信号语义分割的识别分类方法。该方法通过全卷积神经网络的编码运算规则,将心电信号切片数据作为输入,标签地图作为输出,可划分出信号片段中的心拍位置与类别。仿真结果表明：该方法在正常窦性搏动、左束支传导阻滞、右束支传导阻滞、房性早搏和室性早搏五分类问题中取得较高准确率,实现了对心律失常信号的有效识别。     

Electrocardiogram beat classification via coupled boosting by filtering and preloaded mixture of experts

The role of electrocardiogram (ECG) as a noninvasive technique for detecting and diagnosing cardiac problems cannot be overemphasized. This paper introduces a modified version of boosted mixture of experts for the classification of three types of ECG beats. Our two-step preloading procedure, along noise injection, also regarded as smoothing regularization, proved to be a promising, effective, and safe means of classifying arrhythmias. The proposed model, according to the nature of implementation, is called coupled boosting by filtering and preloaded mixture of experts. The experimental results show our proposed method have better classification rate against other compared methods. Comparative evaluation is accomplished with ECG signals from MIT–BIH arrhythmia database.     

Wearable ECG signal processing for automated cardiac arrhythmia classification using CFASE-based feature selection

Classification of electrocardiogram (ECG) signals is obligatory for the automatic diagnosis of cardiovascular disease. With the recent advancement of low-cost wearable ECG device, it becomes more feasible to utilize ECG for cardiac arrhythmia classification in daily life. In this paper, we propose a lightweight approach to classify five types of cardiac arrhythmia, namely, normal beat (N), atrial premature contraction (A), premature ventricular contraction (V), left bundle branch block beat (L), and right bundle branch block beat (R). The combined method of frequency analysis and Shannon entropy is applied to extract appropriate statistical features. Information gain criterion is employed to select features that the results show that 10 highly effective features can obtain performance measures comparable to those obtained by using the complete features. The selected features are then fed to the input of Random Forest, K-Nearest Neighbour, and J48 for classification. To evaluate classification performance, tenfold cross validation is used to verify the effectiveness of our method. Experimental results show that Random Forest classifier demonstrates significant performance with the highest sensitivity of 98.1%, the specificity of 99.5%, the precision of 98.1%, and the accuracy of 98.08%, outperforming other representative approaches for automated cardiac arrhythmia classification.     

ECG beat classifier designed by combined neural network model

This paper illustrates the use of combined neural network model to guide model selection for classification of electrocardiogram (ECG) beats. The ECG signals were decomposed into time-frequency representations using discrete wavelet transform and statistical features were calculated to depict their distribution. The first level networks were implemented for ECG beats classification using the statistical features as inputs. To improve diagnostic accuracy, the second level networks were trained using the outputs of the first level networks as input data. Four types of ECG beats (normal beat, congestive heart failure beat, ventricular tachyarrhythmia beat, atrial fibrillation beat) obtained from the Physiobank database were classified with the accuracy of 96.94% by the combined neural network. The combined neural network model achieved accuracy rates which were higher than that of the stand-alone neural network model.     

Statistics over features of ECG signals

This paper presented the usage of statistics over the set of the features representing the electrocardiogram (ECG) signals. Since classification is more accurate when the pattern is simplified through representation by important features, feature extraction and selection play an important role in classifying systems such as neural networks. Multilayer perceptron neural network (MLPNN) architectures were formulated and used as basis for detection of variabilities of the ECG signals. Four types of ECG beats (normal beat, congestive heart failure beat, ventricular tachyarrhythmia beat, atrial fibrillation beat) obtained from the Physiobank database were classified. The selected Lyapunov exponents, wavelet coefficients and the power levels of power spectral density (PSD) values obtained by eigenvector methods of the ECG signals were used as inputs of the MLPNN trained with Levenberg–Marquardt algorithm. The classification results confirmed that the proposed MLPNN has potential in detecting the variabilities of the ECG signals.     

Combining recurrent neural networks with eigenvector methods for classification of ECG beats

The purpose of this study is to evaluate the accuracy of the recurrent neural networks (RNNs) trained with Levenberg–Marquardt algorithm on the electrocardiogram (ECG) beats. Four types of ECG beats (normal beat, congestive heart failure beat, ventricular tachyarrhythmia beat, atrial fibrillation beat) obtained from the Physiobank database were analyzed. Decision making was performed in two stages: feature extraction by eigenvector methods and classification using the RNN trained on the extracted features. The RNNs were implemented for classification of the ECG beats using the statistical features as inputs. The ability of designed and trained Elman RNNs, combined with eigenvector methods, were explored to classify the ECG beats. The classification results demonstrated that the combined eigenvector methods/RNN approach can be useful in analyzing the ECG beats.     

ECG信号自动诊断中回归建模法特征提取的研究

This article explores the ability of multivariate autoregressive model (MAR) and scalar AR model to extract the features from two-lead electrocardiogram signals in order to classify certain cardiac arrhythmias. The classification performance of four different ECG feature sets based on the model coefficients are shown. The data in the analysis including normal sinus rhythm, atria premature contraction, premature ventricular contraction, ventricular tachycardia, ventricular fibrillation and superventricular tachycardia is obtained from the MIT-BIH database. The classification is performed using a quadratic discriminant function. The results show the MAR coefficients produce the best results among the four ECG representations and the MAR modeling is a useful classification and diagnosis tool.     

Detection of electrocardiogram beats using a fuzzy similarity index

Abstract: A new approach based on the computation of a fuzzy similarity index (FSI) is presented for the detection of electrocardiogram (ECG) beats. Four types of ECG beats (normal beat, congestive heart failure beat, ventricular tachyarrhythmia beat, atrial fibrillation beat) obtained from the Physiobank database were analysed. The ECG signals were decomposed into time–frequency representations using the discrete wavelet transform and wavelet coefficients were calculated to represent the signals. The aim of the study is detection of ECG beats by the combination of wavelet coefficients and the FSI. Toward achieving this aim, fuzzy sets were obtained from the feature sets (wavelet coefficients) of the signals under study. The results demonstrated that the similarity between the fuzzy sets of the studied signals indicated the variabilities in the ECG signals. Thus, the FSI could discriminate the normal beat and the other three types of beats (congestive heart failure beat, ventricular tachyarrhythmia beat, atrial fibrillation beat).     

Detection of cardiac arrhythmia in electrocardiograms using adaptive feature extraction and modified support vector machines

The electrocardiogram (ECG) analysis is one of the most important approaches to cardiac arrhythmia detection. Many algorithms have been proposed, however, the recognition rate is still unsatisfactory due to unreliable feature extraction in signal characteristic analysis or poor generalization capability of the classifier. In this paper, we propose a system for cardiac arrhythmia detection in ECGs with adaptive feature selection and modified support vector machines (SVMs). Wavelet transform-based coefficients and signal amplitude/interval parameters are first enumerated as candidates, but only a few specific ones are adaptively selected for the classification of each class pair. A new classifier, which integrates k-means clustering, one-against-one SVMs, and a modified majority voting mechanism, is proposed to further improve the recognition rate for extremely similar classes. The experimental results show that the proposed ECG analysis approach can obtain a higher recognition rate than the published approaches. By testing the system with more than 100,000 samples in MIT-BIH arrhythmia database, the average recognition rate is 98.92%, and the recognition rate for each class is kept above 92%.     

基于智能手机的心电实时监护系统的设计*

介绍了基于智能手机的心电实时监护系统的设计方法。该系统由测量节点、智能手机节点和监护中心端组成,智能手机节点通过蓝牙实时接收由穿戴式心电采集节点传来的心电数据,并将监护结果通过GPRS网络传输到监护中心端。该系统由病人随身携带,能对多种常见的心律失常症状进行智能诊断,提供实时准确的远程心电监护。通过功能测试,该系统运行良好。     

Adaptive control of left ventricular bypass assist devices

This paper presents a computer-based adaptive control system for left ventricular bypass assist devices consisting of air driven diaphragm pumps. The system provides for 1) synchronization of pumping with ECG signals and 2) control of atrial pressure at desired levels. The system design includes an adaptive control algorithm which is a self-tuning PID-controller based on pole placement. The performance of the system has been demonstrated by in vitro experiments_ on a mock circulatory system. When there is an increase in atrial pressure, the system responds with an increase in stroke volume. Following major changes in the circulatory system, the control algorithm retunes itself and restores the system to the desired state.     

Autoregressive modeling and power spectral estimate of R-R interval time series in arrhythmic patients

The signal constituted by the successive R-R intervals in the ECG tracing carries important information about the control mechanisms of heart rate. The present paper describes advanced methods of parameter extraction from the R-R duration time series which use autoregressive (AR) modeling and power spectral estimates applied to patients in the MIT-BIH arrhythmia data base. The described methodologies enhance information which characterize the most common rhythm disturbances (A-V block, bigeminy/trigeminy, atrial and ventricular flutter, atrial fibrillation, etc.). Important applications of such methods are in the area of the pathophysiological comprehension of cardiac rhythm control mechanisms in the research side and the classification of abnormal rhythms as well in the clinical side. A few examples from the data base are illustrated which show interesting properties of signal processing and classification in respect to the more traditional methods.     

A modified mixture of experts network structure for ECG beats classification with diverse features

This paper illustrates the use of modified mixture of experts (MME) network structure to guide model selection for classification of electrocardiogram (ECG) beats with diverse features. The MME is a modular neural network architecture for supervised learning. Expectation-maximization (EM) algorithm was used for training the MME so that the learning process is decoupled in a manner that fits well with the modular structure. The wavelet coefficients and Lyapunov exponents of the ECG signals were computed and statistical features were calculated to depict their distribution. The statistical features, which were used for obtaining the diverse features of the ECG signals, were then input into the MME network structure for training and testing purposes. We explored the ability of designed and trained MME network structure, combined with wavelet preprocessing (computing wavelet coefficients) and nonlinear dynamics tools (computing Lyapunov exponents), to discriminate five types of ECG beats (normal beat, congestive heart failure beat, ventricular tachyarrhythmia beat, atrial fibrillation beat, partial epilepsy beat) obtained from the Physiobank database. The MME achieved accuracy rates which were higher than that of the mixture of experts (ME) and feedforward neural network models (multilayer perceptron neural network—MLPNN). The proposed MME approach can be useful in classifying long-term ECG signals for early detection of heart diseases/abnormalities.     

Fractal QRS-complexes pattern recognition for imperative cardiac arrhythmias

This paper proposes using fractal QRS-complexes pattern recognition for imperative cardiac arrhythmias. A typical electrocardiogram (ECG) signal is comprised of P-wave, QRS-complex, and T-wave. Fractal dimension transformation (FDT) is employed to adjoin the QRS-complex from time-domain ECG signals, including the fractal features of supraventricular ectopic beat, bundle branch ectopic beat, and ventricular ectopic beat. FDT with fractal dimension (FD) is addressed for constructing various symptomatic features, and can produce family functions and enhance features, making the difference between healthy and unhealthy subjects more significant. The probabilistic neural network (PNN) is proposed for recognizing the states of cardiac physiologic function. The proposed method is tested using the MIT–BIH (Massachusetts Institute of Technology–Beth Israel Hospital) arrhythmia database. Compared with other methods, the numerical experiments demonstrate greater efficiency and higher accuracy in recognizing ECG signals.     

Constructing a 3-D mesh model for electrical cardiac activity simulation.

The 3-D ventricle model in this study was reconstructed from a series of MRI torso cross-section data. We used a 3-D voxel array to represent the ventricle. As in cardiac simulations proposed by previous studies, the activation sequence and body surface ECG were simulated in this model. But to reduce the amount of elements in the model, so that the amount of parameters in the model can be handled numerically, we propose another approach to simulate cardiac activity. A mesh model was constructed on the closed surface formed by epicardiac and endocardiac surfaces of the ventricle. We propose a method to simulate the activation sequence on the epicardiac and endocardiac surfaces of the mesh model. As with the uniform double layer theorem, body surface ECG can be estimated in terms of epicardiac and endocardiac surface current source. Consequently, we can also generate ECG waveforms corresponding to this mesh simulation. Both the depolarization sequence and ECG simulated by the mesh model resemble those generated by the 3-D voxel model. However, the mesh model greatly simplified the process of ECG simulation. Both the simulation of depolarization and ECG estimation were expressed in terms of clear and simple mathematical representations. Consequently, we can analytically investigate the effects of the mesh model's parameters on the cardiac activation sequence and ECG. It could be a useful tool to numerically study the relation of ECG waveforms and electrical activity of the heart.     

Simulation system of arrhythmia using ActiveX control

A simulation system for arrhythmias has been developed using Windows-based software technology, ActiveX control. The cardiac module consists of six cells, the sinus, atrium, AV node, ventricle, and ectopic foci. The physiological properties of the cells, the automaticity and conduction delay, were modelled, respectively, by the phase response curve and the excitability recovery curve. Cell functions were implemented in the ActiveX control and incorporated into the cardiac module. The system draws the ECG sequence as a ladder diagram in real time. The system interactively shows diverse arrhythmias for various user settings of the cell function and bidirectional conduction between the cells. Users are able to experiment virtually by setting up a so-called electrophysiological stimulation. This system is useful for learning and for teaching the interaction between the cells and arrhythmias.