Support vector machine-based arrhythmia classification using reduced features of heart rate variability signal

OBJECTIVE: This paper presents an effective cardiac arrhythmia classification algorithm using the heart rate variability (HRV) signal. The proposed algorithm is based on the generalized discriminant analysis (GDA) feature reduction scheme and the support vector machine (SVM) classifier. METHODOLOGY: Initially 15 different features are extracted from the input HRV signal by means of linear and nonlinear methods. These features are then reduced to only five features by the GDA technique. This not only reduces the number of the input features but also increases the classification accuracy by selecting most discriminating features. Finally, the SVM combined with the one-against-all strategy is used to classify the HRV signals. RESULTS: The proposed GDA- and SVM-based cardiac arrhythmia classification algorithm is applied to input HRV signals, obtained from the MIT-BIH arrhythmia database, to discriminate six different types of cardiac arrhythmia. In particular, the HRV signals representing the six different types of arrhythmia classes including normal sinus rhythm, premature ventricular contraction, atrial fibrillation, sick sinus syndrome, ventricular fibrillation and 2 degrees heart block are classified with an accuracy of 98.94%, 98.96%, 98.53%, 98.51%, 100% and 100%, respectively, which are better than any other previously reported results. CONCLUSION: An effective cardiac arrhythmia classification algorithm is presented. A main advantage of the proposed algorithm, compared to the approaches which use the ECG signal itself is the fact that it is completely based on the HRV (R-R interval) signal which can be extracted from even a very noisy ECG signal with a relatively high accuracy. Moreover, the usage of the HRV signal leads to an effective reduction of the processing time, which provides an online arrhythmia classification system. A main drawback of the proposed algorithm is however that some arrhythmia types such as left bundle branch block and right bundle branch block beats cannot be detected using only the features extracted from the HRV signal.     

A new arrhythmia clustering technique based on Ant Colony Optimization

In this paper, a new method for clustering analysis of QRS complexes is proposed. We present an efficient Arrhythmia Clustering and Detection algorithm based on medical experiment and Ant Colony Optimization technique for QRS complex. The algorithm has been developed based on not only the general signal detection knowledge, but also on the ECG signal’s specific features. Furthermore, our study brings the power of Ant Colony Optimization technique to the ECG clustering area. ACO-based clustering technique has also been improved using nearest neighborhood interpolation. At the beginning of our algorithm, we implement signal filtering, baseline wandering and parameter extraction procedures. Next is the learning phase which consists of clustering the QRS complexes based on the Ant Colony Optimization technique. A Neural Network algorithm is developed in parallel to verify and measure the success of our novel algorithm. The last stage is the testing phase to control the efficiency and correctness of the algorithm. The method is tested with MIT-BIH database to classify six different arrhythmia types of vital importance. These are normal sinus rhythm, premature ventricular contraction (PVC), atrial premature contraction (APC), right bundle branch block, ventricular fusion and fusion. Our simulation results indicate that this new approach has correctness and speed improvements.     

一种基于多层感知器的房颤心电图检测方法

目的:提出一种基于多层感知器（MLP）的新型房颤识别算法。方法:首先设计一种新型自适应的R波阈值检测算法,然后以R波位置和幅度为特征,MLP为分类器进行正常/房颤心电图识别。MLP的网络参数采用深层置信网络预训练算法进行初始化,最后用误差反向传播算法对MLP网络权重进行调整。结果:在单通道心电图数据集上对正常、房颤心电信号进行分类,本研究方法的灵敏度达96.00%,特异性为84.18%,平均识别率为90.09%。结论:这种基于MLP的心电识别算法准确率高、计算复杂度较低,可为房颤的智能诊断提供一种新方法。     

慢性肺心病急性发作期的心电图特点

目的：探讨慢性肺心病急性发作期的心电图特点。方法：回顾性分析50例慢性肺心病急性发作患者的心电图资料。结果：慢性肺心病急性发作期可出现多种形式的异常心电图表现，其中以肺型P波、窦性心动过速、肢体导联低电压、ST—T改变、房性早搏、短阵房性心动过速、完全性右束支传导阻滞、心房颤动最为常见。结论：心律失常是慢性肺心病最常见的并发症之一，尤其在急性发作期以室上性心律失常为主，了解其心电图特点对慢性肺心病急性发作期的诊断和治疗具有重要的临床意义。     

基于极限学习机的左束支传导阻滞辅助诊断研究

左束支传导阻滞(LBBB)作为临床常见的一种心律失常,是左心室收缩功能减低、患者死亡率增加的标志;利用机器学习算法对其进行辅助诊断,将对LBBB早发现、早治疗起到积极的推动作用。然而,由于目前常用的支持向量机(SVM)等传统的机器学习算法容易产生局部最优解,准确度有待提高,因此提出一种基于极限学习机(ELM)的LBBB辅助诊断算法。首先,利用小波进行心电信号预处理,包括基线漂移、肌电噪声及工频干扰的去除;接着,确定QRS波群与T波位置;然后,根据临床上LBBB患者比正常人的QRS波群持续时间延长等特点,建立融合时域、形态与能量3类特征的特征模型;最后,利用该模型提取的特征集合,提出基于ELM的LBBB辅助诊断算法。此外,在MIT_BIH数据库中的5 000份ECG数据上进行实验验证,结果表明所提出的预处理与波形提取算法能有效去除噪声并提取QRS-T特征波;在LBBB的判别上,相比SVM算法、ELM算法的训练时间缩短了88.5%;同时,在准确率、灵敏度、特异度、LBBB检出率和正常人检出率的指标上,分别提升2.4%、5.4%、1.2%、3.6%和2%。因此,基于ELM的LBBB辅助诊断算法具有明显优势。     

全数据库评估概率密度函数法利用R-R间期检测房颤精度

研究整个MIT-BIH心律失常数据库评估概率密度函数法利用R-R间期检测房颤的精度。研究发现正常窦性心律含较多早搏时[（早搏次数/总心搏次数）>9.3%],识别房颤的精度下降到约70%;左束支传导阻滞含较多早搏时,识别房颤的精度下降到约80%;而房颤心电中频繁早搏对辨别房颤精度影响很小,仍达91%。可见该算法适用于区分关联性强的序列与关联性弱的序列。正常窦性心律和左束支传导阻滞心律相邻R-R间期关联性强,频繁早搏使其相邻R-R间期关联性减弱,从而降低识别房颤的精度;而房颤相邻R-R间期无关联性,频繁早搏对检测精度无影响。尽管数据库中有种类繁多的心律失常,且伴有频繁的早搏,算法全数据库共约110 000次心跳辨别房颤精度达82%~86%。     

窦性和房性心律失常的DFA分析

研究证据表明许多自然系统和生物系统没有固定的特征尺度,而是展现自相似特性。本文利用消除趋势波动分析(DFA)方法,分析窦性心律、房性心律失常的ECG信号的自相似特性,以实现这两种心律失常的检测。并利用DFA方法对MIT-BIH标准数据库中的正常窦性心律、房性期前收缩(也称为房性早搏)、窦性心动过缓信号进行了分析和检测,得到这三种信号的尺度指数,据此区分出窦性心律、房性心律失常和正常窦性心律,此结果表明DFA方法能够检测窦性和房性心律失常。     

Advanced fuzzy cellular neural network: application to CT liver images

OBJECTIVE: To achieve better boundary integrities and recall accuracies for segmented liver images, use of the advanced fuzzy cellular neural network (AFCNN), as a variant of the fuzzy cellular neural network (FCNN), is proposed to effectively segment CT liver images. MATERIALS AND METHODS: In order to better utilize relevant contour and gray information from liver images, we have improved the FCNN [Wang S, Wang M. A new algorithm NDA based on fuzzy cellular neural networks for white blood cell detection. IEEE Trans Inform Technol Biomed, in press], which proved to be very effective for the segmentation of microscopic white blood cell images, to create the novel neural network, AFCNN. Its convergent property and global stability are proved. Based on the FCNN-based NDA algorithm [Wang S, Wang M. A new algorithm NDA based on fuzzy cellular neural networks for white blood cell detection. IEEE Trans Inform Technol Biomed, in press], we developed the AFCNN-based NDA algorithm, which we used to segment 5 CT liver images. For comparison, we also segmented the same 5 CT liver images using the FCNN-based NDA algorithm. RESULTS AND CONCLUSION: : AFCNN has distinct advantages over FCNN in both boundary integrity and recall accuracy. In particular, the performance index Binary_rate is generally much higher for AFCNN than for FCNN when applied to CT liver images.     

基于最大散度的特征搜索算法用于心搏分类的研究

在对心电图进行离散小波变换获得特征空间的基础上,提出了基于最大散度的特征搜索算法.对特征空间进行搜索得到不同维数下的优化特征组合,通过研究这些优化特征组合的散度值随维数的变化趋势,最终确定特征向量的特征构成,并以此特征向量训练BP神经网络.取自MIT-BIH数据库的四类心电图(正常心搏、左束支传导阻滞心搏、右束支传导阻滞心搏和起搏心搏)的分类正确率达到93.9%,检出率较高.     

Classification enhancible grey relational analysis for cardiac arrhythmias discrimination

This paper proposes a method for electrocardiogram (ECG) heartbeat recognition using classification enhancible grey relational analysis (GRA). The ECG beat recognition can be divided into a sequence of stages, starting with feature extraction and then according to characteristics to identify the cardiac arrhythmias including the supraventricular ectopic beat, bundle branch ectopic beat, and ventricular ectopic beat. Gaussian wavelets are used to enhance the features from each heartbeat, and GRA performs the recognition tasks. With the MIT-BIH arrhythmia database, the experimental results demonstrate the efficiency of the proposed non-invasive method. Compared with artificial neural network, the test results also show high accuracy, good adaptability, and faster processing time for the detection of heartbeat signals.     

A practical reconstructed phase space approach for ECG arrhythmias classification

Abstract

Atrial and ventricular arrhythmias are symptoms of the main common causes of rapid death. The severity of these arrhythmias depends on their occurrence either within the atria or ventricles. These abnormalities of the heart activity may cause an immediate death or cause damage of the heart. In this paper, a new algorithm is proposed for the classification of life threatening cardiac arrhythmias including atrial fibrillation (AF), ventricular tachycardia (VT) and ventricular fibrillation (VF). The proposed technique uses a simple signal processing technique for analysing the non-linear dynamics of the ECG signals in the time domain. The classification algorithm is based upon the distribution of the attractor in the reconstructed phase space (RPS). The behaviour of the ECG signal in the reconstructed phase space is used to determine the classification features of the whole classifier. It is found that different arrhythmias occupy different regions in the reconstructed phase space. Three regions in the RPS are found to be more representative of the considered arrhythmias. Therefore, only three simple features are extracted to be used as classification parameters. To evaluate the performance of the presented classification algorithm, real datasets are obtained from the MIT database. A learning dataset is used to design the classification algorithm and a testing dataset is used to verify the algorithm. The algorithm is designed to guarantee achieving both 100% sensitivity and 100% specificity. The classification algorithm is validated by using 45 ECG signals spanning the considered life threatening arrhythmias. The obtained results show that the classification algorithm attains a sensitivity ranging from 85.7–100%, a specificity ranging from 86.7–100% and an overall accuracy of 95.55%.     

基于空洞卷积神经网络的心律失常分类算法

本文提出了一种基于卷积网络的心电信号分类算法,设计了空洞卷积池化金字塔模块,通过不同尺寸的空洞卷积提取信息,再将各通道的信息聚合,在增强网络的特征提取能力的同时可以降低参数量。本文聚焦于窦性心律、房性早搏、心动过速以及心动过缓4种分类,使用的心电图数据集来自医院的实测数据,数据集包含75000名不同检测者的心电记录。经过测试,本文提出的模型在该数据集上取得了0.89的F1值,另外在CinC2017数据集上也达到了0.87的F1值。实验结果表明该分类算法具有优秀的特征提取和分类能力,在心电信号的实时分类中具备应用前景。     

Cardiac rhythm in healthy elderly subjects

Summary To study the normal cardiac rhythm in elderly subjects we performed 24-h Holter monitoring on 94 subjects aged over 70 years. We had previously discarded those with cardiac disease by using history, physical examination, electrocardiography (ECG), chest X-radiography and Doppler echocardiography. The maximum, average and minimum heart rates were 113, 79 and 62, respectively, during the day, and 90, 64 and 53 during the night. Supraventricular and ventricular arrhythmias were frequent (91% and 89.4% respectively). Some 50% of the subjects had complex ventricular arrhythmias. Two subjects presented with sinus pauses of more than 2 s, and 4 had Wenckebach second-degree atrioventricular (AV) block. During a follow-up averaging 20.8 months, there were no deaths or symptoms of an arrhythmic origin.Abbreviations ECG electrocardiogram - AV atrioventricular - HBP hypertension - AT atrial tachycardia - FC functional class - VT ventricular tachycardia - bpm beats per minute - SVE supraventricular extrasystoles - AF atrial fibrillation - VE ventricular extrasystole - W-AVB Wenckebach atrioventricular block     

Predicting termination of atrial fibrillation based on the structure and quantification of the recurrence plot

Predicting the spontaneous termination of the atrial fibrillation (AF) leads to not only better understanding of mechanisms of the arrhythmia but also the improved treatment of the sustained AF. A novel method is proposed to characterize the AF based on structure and the quantification of the recurrence plot (RP) to predict the termination of the AF. The RP of the electrocardiogram (ECG) signal is firstly obtained and eleven features are extracted to characterize its three basic patterns. Then the sequential forward search (SFS) algorithm and Davies-Bouldin criterion are utilized to select the feature subset which can predict the AF termination effectively. Finally, the multilayer perceptron (MLP) neural network is applied to predict the AF termination. An AF database which includes one training set and two testing sets (A and B) of Holter ECG recordings is studied. Experiment results show that 97% of testing set A and 95% of testing set B are correctly classified. It demonstrates that this algorithm has the ability to predict the spontaneous termination of the AF effectively.     

基于矢量传播算法的束支传导阻滞QRST波形仿真

心脏生物电兴奋传播的仿真是心电正问题一个重要方面，仿真结果不仅是心电正问题模型精度和可靠性的判断标准，而且具有一定的研究和临床价值。我们对人体心脏左束支传导阻滞和右束支传导阻滞情况下心脏兴奋传播和心电QRST波形进行了仿真。仿真过程中借助了矢量传播算法，该算法具有精度高、快速、适用于各向．异性介质的优点。仿真结果 符合临床中实测波形。     

一种适用于手势动作sEMG信号识别的改进型模糊推理分类器

提出了一种基于自适应提取模糊规则的改进型模糊推理分类器,其中,模糊规则的提取采用由势函数法初始化聚类中心的K-means聚类算法,分类器的训练采用基于梯度下降算法的最小均方误差准则来实现.此改进型模糊分类器克服了基于K-means聚类算法提取模糊规则的模糊推理分类器需要手工设定模糊规则数目和对初始化参数非常敏感的两大缺点.对10位受试者的6类手势动作sEMG信号的分类研究结果表明,此改进型模糊推理分类器的分类能力优于未改进的模糊推理分类器,且具有效果稳定、自适应提取模糊规则、对初始化参数不敏感以及可排除孤立点的影响等优点.     

基于相空间分析的心律失常检测

通过心电信号分析区分心脏的不同病态,对自动体外除颤器等治疗心律失常的设备至关重要.基于相空间分析可以有效地检测心律失常:先重构心电信号的相空间;然后从几何和信息论的角度计算重构相空间中点的密度分布熵,作为下一步分类的特征;最后用以马氏距离为度量标准的最近邻法对窦性、室上速、房扑和房颤信号进行分类.为评价本算法检测心律失常的敏感性、特异性和准确率,分别对MIT-BIH的arrhythmias数据库和犬心外膜数据库进行实验研究.结果表明:本方法计算简单,能快速准确地检测窦性、室上速、房扑和房颤信号,有望应用于治疗心律失常的自动装置.     

The AV junction region of the heart: a comprehensive study correlating gross anatomy and direct three-dimensional analysis. Part I. Architecture and topography.

There is little detailed knowledge of the architecture of the AV junction region, the cytoarchitecture of the AV node or of its atrial connections. In the present study, the gross anatomy and topography of intracardiac structures in 21 adult canine hearts were photographically compared in whole and dissected hearts and tissue blocks and serial histologic sections made in three orthogonal planes. There are seven major new findings: 1) A coronary sinus fossa exists at the crux of the heart. It separates the right medial atrial wall (MAW) superoposterior region from the left atrium, its floor is the coronary sinus, and it carries the medial atrionodal bundle and proximal AV bundle on its right wall. 2) The posterior MAW forms two isolated bridges of myocardium as it surrounds the coronary sinus ostium, is isolated from the sinus venarum with crista terminalis and interatrial septum-by the floor of the inferior vena cava, and the narrow bridges link the posterior atrial wall to the mid MAW. 3) The tendon of Todaro has both epicardial and endocardial exposures, terminates in the superoposterior MAW and its medial aspect is adjacent sequentially to the medial atrionodal bundle and proximal AV bundle. 4) Only ordinary myocardium contacts the anulus fibrosus. 5) The ventricular septum's shoulder is humped shape posteriorly, is completely overlaid by anular myocardium and the medial leaflet and is joined by struts of papillary muscle. 6) The membranous septum joins the anterior ventricular septum to the crista supraventricularis, forms part of the posterior noncoronary and right aortic valve sinus walls and encases the right bundle branch. 7) The specialized conduction tissues, the superior, medial and lateral atrionodal bundles, the proximal AV bundle, AV node, distal AV bundle and right bundle branch are subjacent to MAW epicardium outside the right atrium, share regular intracardiac relationships with topographic landmarks and the medial atrionodal bundle, terminal superior atrionodal bundle, the proximal AV bundle and AV node are aligned to the medial leg of Koch's triangle. Thus, atrial myocardium of the AV junction region is that of the MAW. The floor of the inferior vena cava forms a natural barrier to impulse transmission along the full extent of the posterior MAW. The specialized tissues are outside of the MAW. Anatomic landmarks form reliable topographic landmarks for the specialized AV junction region tissues. A knowledge of the association of the specialized conduction tissues with specific regions of the MAW is useful in localizing the tissues and along with the coronary sinus fossa provides several extracardiac approaches.     

流行性出血热心电图分析

收集我院传染科确诊为流行性出血热41例心电图资料。41例心电图中,异常31例,达75.6％。异常心电图以心律失常最为多见(窦性心律失常18例,房性早搏2例,房颤2例,窦房结—心房交界区游走1例,室性早搏3例,各种传导阻滞3例);其次是T—U融合,符合低钾改变5例,高钾改变1例,低电压3例,其它3例。 流行性出血热病毒造成广泛性、全身性血管受损,多种免疫反应参与,使血管壁通透性增加,血浆外渗,组织水肿和出血,微循环障碍和急性肾功能衰竭。心电图检查主要用于显示心肌损伤和血钾紊乱情况,可指导临床治疗工作。文中讨论了病理解剖与心电图改变、电解质紊乱与心电图改变的关系,心电图低电压可能性因素,提出应注意心室损害的观察。     

The AV junction region of the heart: A comprehensive study correlating gross anatomy and direct three‐dimensional analysis. Part I. Architecture and topography

There is little detailed knowledge of the architecture of the AV junction region, the cytoarchitecture of the AV node or of its atrial connections. In the present study, the gross anatomy and topography of intracardiac structures in 21 adult canine hearts were photographically compared in whole and dissected hearts and tissue blocks and serial histologic sections made in three orthogonal planes. There are seven major new findings: 1) A coronary sinus fossa exists at the crux of the heart. It separates the right medial atrial wall (MAW) superoposterior region from the left atrium, its floor is the coronary sinus, and it carries the medial atrionodal bundle and proximal AV bundle on its right wall. 2) The posterior MAW forms two isolated bridges of myocardium as it surrounds the coronary sinus ostium, is isolated from the sinus venarum with crista terminalis and interatrial septum—by the floor of the inferior vena cava, and the narrow bridges link the posterior atrial wall to the mid MAW. 3) The tendon of Todaro has both epicardial and endocardial exposures, terminates in the superoposterior MAW and its medial aspect is adjacent sequentially to the medial atrionodal bundle and proximal AV bundle. 4) Only ordinary myocardium contacts the anulus fibrosus. 5) The ventricular septum's shoulder is humped shape posteriorly, is completely overlaid by anular myocardium and the medial leaflet and is joined by struts of papillary muscle. 6) The membranous septum joins the anterior ventricular septum to the crista supraventricularis, forms part of the posterior noncoronary and right aortic valve sinus walls and encases the right bundle branch. 7) The specialized conduction tissues, the superior, medial and lateral atrionodal bundles, the proximal AV bundle, AV node, distal AV bundle and right bundle branch are subjacent to MAW epicardium outside the right atrium, share regular intracardiac relationships with topographic landmarks and the medial atrionodal bundle, terminal superior atrionodal bundle, the proximal AV bundle and AV node are aligned to the medial leg of Koch's triangle. Thus, atrial myocardium of the AV junction region is that of the MAW. The floor of the inferior vena cava forms a natural barrier to impulse transmission along the full extent of the posterior MAW. The specialized tissues are outside of the MAW. Anatomic landmarks form reliable topographic landmarks for the specialized AV junction region tissues. A knowledge of the association of the specialized conduction tissues with specific regions of the MAW is useful in localizing the tissues and along with the coronary sinus fossa provides several extracardiac approaches. Anat Rec 256:49–63, 1999. © 1999 Wiley‐Liss, Inc.