Grammatic representation of beat sequences for fuzzy arrhythmia diagnosis

The final stage of a system for automatic monitoring of cardiac arrhythmias is the diagnosis of the rhythm or arrhythmia present in the patient during the monitoring process. In this paper we approach the detection process by means of the analysis of the electrocardiographic signal (ECG) on a surface lead produced by those arrhythmias which can be recognized by identifying specific beat sequences and taking into account contextual information, mainly rhythm information. We have developed a diagnosis process for arrhythmias which uses a fuzzy classification of beats according to their etiology or focus of origin. The process we describe permits a more adequate consideration by the user of the arrhythmias diagnosed by the system, mainly in those cases in which the information derived from ECG analysis is not determinant.     

Arrhythmic Heartbeat Classification Using 2D Convolutional Neural Networks

BackgroundElectrocardiogram (ECG) is a method of recording the electrical activity of the heart and it provides a diagnostic means for heart-related diseases. Arrhythmia is any irregularity of the heartbeat that causes an abnormality in the heart rhythm. Early detection of arrhythmia has great importance to prevent many diseases. Manual analysis of ECG recordings is not practical for quickly identifying arrhythmias that may cause sudden deaths. Hence, many studies have been presented to develop computer-aided-diagnosis (CAD) systems to automatically identify arrhythmias.MethodsThis paper proposes a novel deep learning approach to identify arrhythmias in ECG signals. The proposed approach identifies arrhythmia classes using Convolutional Neural Network (CNN) trained by two-dimensional (2D) ECG beat images. Firstly, ECG signals, which consist of 5 different arrhythmias, are segmented into heartbeats which are transformed into 2D grayscale images. Afterward, the images are used as input for training a new CNN architecture to classify heartbeats.ResultsThe experimental results show that the classification performance of the proposed approach reaches an overall accuracy of 99.7%, sensitivity of 99.7%, and specificity of 99.22% in the classification of five different ECG arrhythmias. Further, the proposed CNN architecture is compared to other popular CNN architectures such as LeNet and ResNet-50 to evaluate the performance of the study.ConclusionsTest results demonstrate that the deep network trained by ECG images provides outstanding classification performance of arrhythmic ECG signals and outperforms similar network architectures. Moreover, the proposed method has lower computational costs compared to existing methods and is more suitable for mobile device-based diagnosis systems as it does not involve any complex preprocessing process. Hence, the proposed approach provides a simple and robust automatic cardiac arrhythmia detection scheme for the classification of ECG arrhythmias.     

基于多尺度快速样本熵与随机森林的心电图分析

目的:探讨基于多尺度快速样本熵与随机森林的心电图分析方法对常见心律失常(房性早搏、室性早搏)的自动诊断的可行性和有效性。方法:利用不同心律失常疾病的心电信号存在复杂性差异的特点,通过多尺度熵计算心电信号在不同尺度下的样本熵值以组成特征向量;利用kd树提高多尺度熵的计算效率,增强算法的实时性。利用训练样本的特征向量构建随机森林分类器,再根据众多决策树的分类结果结合投票原则确定测试样本心律失常疾病的类型。结果:本文提出的心电图分析方法能够有效地识别正常心律、房性早搏(APB)及室性早搏(VPB),平均识别准确率达到91.60%。结论:本文提出的心电图分析方法对常见心律失常(APB,VPB)具有较高的识别准确率及临床实用价值。     

Classification of electrocardiogram signals with support vector machines and genetic algorithms using power spectral features

This paper proposes a new power spectral-based hybrid genetic algorithm-support vector machines (SVMGA) technique to classify five types of electrocardiogram (ECG) beats, namely normal beats and four manifestations of heart arrhythmia. This method employs three modules: a feature extraction module, a classification module and an optimization module. Feature extraction module extracts electrocardiogram's spectral and three timing interval features. Non-parametric power spectral density (PSD) estimation methods are used to extract spectral features. Support vector machine (SVM) is employed as a classifier to recognize the ECG beats. We investigate and compare two such classification approaches. First they are specified experimentally by the trial and error method. In the second technique the approach optimizes the relevant parameters through an intelligent algorithm. These parameters are: Gaussian radial basis function (GRBF) kernel parameter σ and C penalty parameter of SVM classifier. Then their performances in classification of ECG signals are evaluated for eight files obtained from the MIT–BIH arrhythmia database. Classification accuracy of the SVMGA approach proves superior to that of the SVM which has constant and manually extracted parameter.     

The surgeon's mental load during decision making at various stages of operations

In surgeons while opening the wound, during the operation proper, closing the skin and immediately after the operation, the ECG was recorded telemetrically for 5-min periods. From the ECG recordings, indices reflecting cardiac arrhythmia and emotional level were calculated. It is concluded that the process of decision making during the vital stages of operations causes a fall in the CHRV (the coefficient of heart rate variability), S2 (the variance of R-R intervals) and VR (the variability range of R-R intervals). It seems that of the indices studied, the most suitable for evaluation of the degree of mental loading due to decision making processes are the CHRV and S2. During all the stages of surgery studied, and immediately after the operation, an increase in tonus of the sympathetic nervous system occurs in surgeons indicating a rise in emotional level.     

老年人动态心电图心律失常特点及对阵发性 房颤的诊断

目的:分析65岁以上老年人十二导联动态心电图(12-Holter)心律失常的特点及其对阵发性房颤的诊断价值。方法:①采用回顾性分析的方法,随机选择500例65岁以上老年人的动态心电图进行心律失常情况的统计分析,并同时选择500例小于65岁的心电图作为对照;②另选择500例65岁以上老年人的十二导联普通心电图(ECG)作为对照,对比分析12-Holter与ECG两种方法对老年人阵发性房颤的检出率。结果:①65岁以上老年人动态心电图各种心律失常、ST-T改变的发生率高。而在各类心律失常中房性早搏、室性期前收缩、房性心动过速、房颤发生率较高。②动态心电图对于阵发性房颤的检出率显著高于普通十二导联心电图。结论:①老年人动态心电图检查结果异常率高;②与普通心电图比较,动态心电图诊断老年人阵发性房颤有较高的价值。     

A fiber optic sensor system for control of rate-adaptive cardiac pacemakers and implantable defibrillators.

Commercially available cardiac pacemakers and implantable cardioverters/defibrillators (ICDs) predominantly use an intracardiac-derived electrocardiogram (ECG) for the detection of arrhythmias. To achieve automatic control of the heart frequency in accordance with cardiovascular strain and improved detection of life-threatening arrhythmias, it is desirable to monitor the heart by an input signal correlated with the hemodynamic state. One possible approach to derive such a signal is to measure the inotropy (mechanical contraction strength of the heart muscle). For this purpose, an optoelectronic measurement system has been designed. The fundamental function of the system has been shown in earlier investigations using an isolated beating pig heart. In this paper the design of two algorithms for use in pacemakers and ICDs based on a fiber optic sensor signal is presented.     

Automatic classification of electrocardiogram signals based on transfer learning and continuous wavelet transform

Classification and subsequent diagnosis of cardiac arrhythmias is an important research topic in clinical practice. Confirmation of the type of arrhythmia at an early stage is critical for reducing the risk and occurrence of cardiovascular events. Nevertheless, diagnoses must be confirmed by a combination of specialist experience and electrocardiogram (ECG) examination, which can lead to delays in diagnosis. To overcome such obstacles, this study proposes an automatic ECG classification algorithm based on transfer learning and continuous wavelet transform (CWT). The transfer learning method is able to transfer the domain knowledge and features of images to a EGG, which is a one-dimensional signal when a convolutional neural network (CNN) is used for classification. Meanwhile, CWT is used to convert a one-dimensional ECG signal into a two-dimensional signal map consisting of time-frequency components. Considering that morphological features can be helpful in arrhythmia classification, eight features related to the R peak of an ECG signal are proposed. These auxiliary features are integrated with the features extracted by the CNN and then fed into the fully linked arrhythmia classification layer. The CNN developed in this study can also be used for bird activity detection. The classification experiments were performed after converting the two types of audio files containing songbird sounds and those without songbird sounds from the NIPS4Bplus bird song dataset into the Mel spectrum. Compared to the most recent methods in the same field, the classification results improved accuracy and recognition by 11.67% and 11.57%, respectively.     

A fiberoptic sensor system for cardiac monitoring and electrotherapy.

Commercially available cardiac pacemakers and implantable cardioverters/defibrillators (ICD) predominantly use the intracardiac derived electrocardiogram (ECG) for detection of arrhythmias. To achieve an automatic control of the heart frequency in accordance with cardiovascular strain and an improved detection of life-threatening arrhythmias, it is desirable to monitor the heart by an input signal correlated with the hemodynamic state. One possible approach to derive such a signal, is to measure the inotropy (mechanical contraction strength of the heart muscle). For this purpose an optoelectronic measurement system has been designed. The fundamental function of the system has been shown in earlier investigations using an isolated beating pig heart. In this paper further results showing the correlation of the fiberoptic sensor signal with the left ventricular stroke volume are presented. To make the system useful for implantable devices, further improvements with regard to power consumption and signal quality were achieved.     

Optimisation of Embryonic and Larval ECG Measurement in Zebrafish for Quantifying the Effect of QT Prolonging Drugs

Effective chemical compound toxicity screening is of paramount importance for safe cardiac drug development. Using mammals in preliminary screening for detection of cardiac dysfunction by electrocardiography (ECG) is costly and requires a large number of animals. Alternatively, zebrafish embryos can be used as the ECG waveform is similar to mammals, a minimal amount of chemical is necessary for drug testing, while embryos are abundant, inexpensive and represent replacement in animal research with reduced bioethical concerns. We demonstrate here the utility of pre-feeding stage zebrafish larvae in detection of cardiac dysfunction by electrocardiography. We have optimised an ECG recording system by addressing key parameters such as the form of immobilization, recording temperature, electrode positioning and developmental age. Furthermore, analysis of 3 days post fertilization (dpf) zebrafish embryos treated with known QT prolonging drugs such as terfenadine, verapamil and haloperidol led to reproducible detection of QT prolongation as previously shown for adult zebrafish. In addition, calculation of Z-factor scores revealed that the assay was sensitive and specific enough to detect large drug-induced changes in QTc intervals. Thus, the ECG recording system is a useful drug-screening tool to detect alteration to cardiac cycle components and secondary effects such as heart block and arrhythmias in zebrafish larvae before free feeding stage, and thus provides a suitable replacement for mammalian experimentation.     

动态心电图与常规心电图诊断冠心病患者心律失常的效果比较

目的:分析冠心病(Coronary heart disease,CHD)心律失常(Arrhythmia)患者诊断中常规心电图(ECG)和动态心电图(DCG)两种诊断方式效果。方法:选取我院收治的CHD患者84例作为研究对象,分别使用ECG和DCG两种方式进行诊断,判断2种方法冠心病检测阳性率、心律失常检出率的情况。结果:动态组检测的阳性率为63.10%(53例),常规组为58.33%(49例),数据差异无统计学意义P0.05;8项心律失常指标中房性/室上性早搏早发、方式传导阻滞等检出率差异无统计学意义,P0.05;其余5项检出率差异显著,P0.05。结论:冠心病心律失常患者的诊断时采用动态心电图在冠心病诊断阳性率和心律失常检出率方面均有一定的优势。     

Discrete-wavelet-transform-based noise removal and feature extraction for ECG signals

Nowadays, doctors use electrocardiogram (ECG) to diagnose heart diseases commonly. However, some nonideal effects are often distributed in ECG. Discrete wavelet transform (DWT) is efficient for nonstationary signal analysis. In this paper, the Symlets sym5 is chosen as the wavelet function to decompose recorded ECG signals for noise removal. Soft-thresholding method is then applied for feature detection. To detect ECG features, R peak of each heart beat is first detected, and the onset and offset of the QRS complex are then detected. Finally, the signal is reconstructed to remove high frequency interferences and applied with adaptive searching window and threshold to detect P and T waves. We use the MIT-BIH arrhythmia database for algorithm verification. For noise reduction, the SNR improvement is achieved at least 10 dB at SNR 5 dB, and most of the improvement SNR are better than other methods at least 1 dB at different SNR. When applying to the real portable ECG device, all R peaks can be detected when patients walk, run, or move at the speed below 9 km/h. The performance of delineation on database shows in our algorithm can achieve high sensitivity in detecting ECG features. The QRS detector attains a sensitivity over 99.94%, while detectors of P and T waves achieve 99.75% and 99.7%, respectively.     

A Powerful Algorithm to aid Cardiac Arrhythmia Diagnosis

Abstract

The Electrocardiogram (ECG), represents the electrical activity of the heart. It is characterised by a number of waves P, QRS, T which are correlated to the status of the heart activity. In this paper, the aim is to present a powerful algorithm to aid cardiac diagnosis. The approach used is based on a determinist method, that of the tree decision. However, the different waves of the ECG signal need to be identified and then measured following a signal to noise enhancement. Signal to noise enhancement is performed by a combiner linear adaptive filter whereas P, QRS, T wave identification and measurement are performed by a derivative approach. Results obtained on simulated and real ECG signals are shown to be highly, satisfactory in the aid of cardiac arrhythmia diagnosis, such as junctionnal escapes, blocks, etc.     

Electrocardiogram abnormalities in captive chimpanzees (Pan troglodytes)

Although cardiovascular disease is the leading cause of death in the captive chimpanzee population, little is known about the prevalence and etiology of heart disease in this species. We reviewed the physical exam records of 265 common chimpanzees (Pan troglodytes) for electrocardiogram abnormalities. During the 24-mo period reviewed (August 2003 through August 2005), 34 animals were diagnosed with cardiac arrhythmias consisting of ventricular arrhythmias, supraventricular arrhythmias, conduction disturbances, mixed arrhythmias, and bradycardia. The incidence of cardiac arrhythmia was significantly higher in male animals, chimpanzees 20 to 39 y old, and those with structural heart disease. Incidence of cardiac arrhythmia was not significantly higher in animals with hypertension, hyperlipidemia, or chronic viral infections. During the retrospective period, 7 animals with cardiac arrhythmias died or were euthanized. Mortality was significantly higher in animals with ventricular arrhythmias compared with those without ventricular arrhythmias. We conclude that in the common chimpanzee, age, male gender, and structural heart disease are risk factors for developing cardiac arrhythmias and that ventricular arrhythmias are risk factors for mortality.     

A Powerful Algorithm to aid Cardiac Arrhythmia Diagnosis

The Electrocardiogram (ECG), represents the electrical activity of the heart. It is characterised by a number of waves P, QRS, T which are correlated to the status of the heart activity. In this paper, the aim is to present a powerful algorithm to aid cardiac diagnosis. The approach used is based on a determinist method, that of the tree decision. However, the different waves of the ECG signal need to be identified and then measured following a signal to noise enhancement. Signal to noise enhancement is performed by a combiner linear adaptive filter whereas P, QRS, T wave identification and measurement are performed by a derivative approach. Results obtained on simulated and real ECG signals are shown to be highly, satisfactory in the aid of cardiac arrhythmia diagnosis, such as junctionnal escapes, blocks, etc.     

Tolerance of chick embryos to low temperatures in reference to the heart rate

Ten-day-old embryos were exposed to 28, 18 and 8 degrees C environments and their electrocardiograms (ECG) monitored. Embryos in 28 and 18 degrees C environments maintained a constant heart rate averaging 97 and 25 beats/min, respectively, followed by arrhythmias and cardiac arrest at 101 and 59 hr. Embryos in an 8 degrees C environment went into cardiac arrest after 2-4 hr, but recovered 20 hr later upon rewarming to 38 degrees C. Six to 20-day-old embryos exposed to 8 degrees C were examined for tolerance time after cardiac arrest. The younger the embryo the longer its tolerance to prolonged cardiac arrest.     

The Effect of Aging on the Specialized Conducting System: A Telemetry ECG Study in Rats over a 6 Month Period

Advanced age alone appears to be a risk factor for increased susceptibility to cardiac arrhythmias. We previously observed in the aged rat heart that sinus rhythm ventricular activation is delayed and characterized by abnormal epicardial patterns although conduction velocity is normal. While these findings relate to an advanced stage of aging, it is not yet known when and how ventricular electrical impairment originates and which is the underlying substrate. To address these points, we performed continuous telemetry ECG recordings in freely moving rats over a six-month period to monitor ECG waveform changes, heart rate variability and the incidence of cardiac arrhythmias. At the end of the study, we performed in-vivo multiple lead epicardial recordings and histopathology of cardiac tissue. We found that the duration of ECG waves and intervals gradually increased and heart rate variability gradually decreased with age. Moreover, the incidence of cardiac arrhythmias gradually increased, with atrial arrhythmias exceeding ventricular arrhythmias. Epicardial multiple lead recordings confirmed abnormalities in ventricular activation patterns, likely attributable to distal conducting system dysfunctions. Microscopic analysis of aged heart specimens revealed multifocal connective tissue deposition and perinuclear myocytolysis in the atria. Our results demonstrate that aging gradually modifies the terminal part of the specialized cardiac conducting system, creating a substrate for increased arrhythmogenesis. These findings may open new therapeutic options in the management of cardiac arrhythmias in the elderly population.     

Electrocardiographic aspects of skin diving

Electrocardiographic (ECG) aspects of skin diving were monitored by means of continuous ECG recording in a pool 15 m deep. Ten regularly trained divers with different levels of experience divid a minimum of three consecutive times, holding their beath, reaching depths of 6 m, 9 m, and 12 or 15 m. The water temperature was 28 degrees C. During the ascending part of these dives, bradycardia was observed in all skin-divers. Minimal heart rate correlated negatively with the diver's experience (number of dives previously performed). In six divers cardiac arrhythmia was observed. Atrial arrhythmias were sometimes isolated occurrences, but more frequently they were multiple. Ventricular arrhythmias tended to be bigeminal. Apparently, forced expiration through the snorkel when surfacing precipitated these rhythmic disorders.     

基于心脏电生理模型的心律失常机制研究进展

揭示发病机制是心律失常诊断、治疗、药物研发和设备设计的关键.整合当前在心脏分子生物学、生物化学、生理学及解剖学方面的最新成果,构建从离子通道、心肌细胞、心肌纤维、心肌组织、心脏器官到躯体各个层次的多尺度多模态心脏电生理模型,用于系统研究微观局部变化发生、发展、转化为宏观心律失常表现的过程,将彻底改变传统从基因突变、蛋白质表达、细胞电生理、临床表现单独研究心律失常的方式,实现微观与宏观研究的统一,使心脏电生理模型成为系统研究心律失常发病机制的有力手段.本文综述了心脏电生理模型的构建方法和研究进展,讨论了多尺度心脏电生理模型在揭示心律失常机制研究中的作用和地位,给出了基于心脏电生理模型心律失常研究的挑战和重要发展方向.     

ECG beat classification using PCA,LDA, ICA and Discrete Wavelet Transform

Electrocardiogram (ECG) is the P-QRS-T wave, representing the cardiac function. The information concealed in the ECG signal is useful in detecting the disease afflicting the heart. It is very difficult to identify the subtle changes in the ECG in time and frequency domains. The Discrete Wavelet Transform (DWT) can provide good time and frequency resolutions and is able to decipher the hidden complexities in the ECG. In this study, five types of beat classes of arrhythmia as recommended by Association for Advancement of Medical Instrumentation (AAMI) were analyzed namely: non-ectopic beats, supra-ventricular ectopic beats, ventricular ectopic beats, fusion betas and unclassifiable and paced beats. Three dimensionality reduction algorithms; Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA) and Independent Component Analysis (ICA) were independently applied on DWT sub bands for dimensionality reduction. These dimensionality reduced features were fed to the Support Vector Machine (SVM), neural network (NN) and probabilistic neural network (PNN) classifiers for automated diagnosis. ICA features in combination with PNN with spread value (σ) of 0.03 performed better than the PCA and LDA. It has yielded an average sensitivity, specificity, positive predictive value (PPV) and accuracy of 99.97%, 99.83%, 99.21% and 99.28% respectively using ten-fold cross validation scheme.