Ventricular Ectopic Beat Classification Using KNN Multi-Feature Classifier

The long-term outcome of athletes with frequent ventricular premature complexes (VPCs) and apparently normal heart has not been fully clarified. To evaluate the clinical and prognostic significance of VPCs and the influence of continuing sports activity during follow-up, we studied 120 healthy athletes (96 men; median age 16 years) in whom frequent VPCs (>100 VPCs/24 hours) were discovered by chance during preparticipation screening. All athletes were followed up for a median of 84 months. During follow-up, 96 underwent serial 24-hour Holter recording and 62 underwent serial echocardiography. The median number of VPCs/24 hours on basal Holter was 3,760. During follow-up, 81 athletes continued sports activity, whereas 39 did not. No athlete died or developed overt heart disease. The median number of VPCs/24 hours decreased in both athletes who continued sports activity and those who did not (from 3,805 to 1,124, p <0.0001 and from 5,787 to 1,298, p <0.0001, respectively). During follow-up, left ventricular ejection fraction slightly decreased to <55% in 9 of 62 athletes who, in respect to the remaining 53, had more VPCs/24 hours both in the basal state (12,000 vs 3,880) and during follow-up (10,702 vs 1,368), and a longer follow-up (95 vs 36 months). In conclusion, (1) frequent VPCs in athletes without heart disease have a long-term benign prognostic significance, (2) sporting activity does not modify this benign outcome, (3) during follow-up, the burden of VPCs decreases whether or not subjects continue sports activity, and (4) in 14.5% of athletes, ejection fraction slightly decreases over time.

The characteristics of premature ventricular beats predisposing to ventricular tachycardia or fibrillation were assessed by 24-h ambulatory monitoring and maximal treadmill exercise testing in 339 cardiac patients with premature ventricular beats. Premature ventricular beats were divided into early (Q-premature ventricular beat less than QT), late (within the last 20% of the cardiac cycle), and midcycle. Ventricular tachycardia was recorded in 45 patients and ventricular fibrillation, in three. The frequency of ventricular tachycardia or fibrillation was 32% in patients with late, 16% in patients with early, and 7% in patients with midcycle premature ventricular beats (P less than 0.05). Patients with frequent (less than 10/min) multiformed premature ventricular beats had a frequency of ventricular tachycardia or fibrillation of 44%, while only 13% of patients with frequent uniformed premature ventricular beats had ventricular tachycardia (P less than 0.05). Ambulatory patients with ventricular tachycardia or fibrillation have frequent multiformed premature ventricular beats, and the ventricular tachycardia or fibrillation is usually triggered by late premature ventricular beats.

ECG beat classification using particle swarm optimization and radial basis function neural network

Clinical observations indicate that increased QT interval dispersion in sinus beats may portend malignant ventricular arrhythmias and sudden cardiac death. The purpose of this study was to test the hypothesis that measures of QT dispersion in ventricular premature beats (QTd-V) may be also useful in identifying patients at high risk of arrhythmic events. In the group of 303 patients with ventricular premature beats on standard 12-lead ECG, the QTd-V was calculated as a difference between maximum and minimum QT interval in premature ventricular beats. During follow-up for 26 +/- 19 months the arrhythmic events (sustained ventricular tachycardia, ventricular fibrillation or sudden cardiac death) were noted in 42 patients. Patients with arrhythmic events had significantly (P < 0.005) greater values of QTd-V than those without arrhythmic events. Univariate predictors of arrhythmic events included QTd-V > or = 100 ms, left ventricular ejection fraction < 40%, QRS complex duration of ventricular premature beats > 150 ms, underlying heart disease and complete bundle branch block. Multivariate analysis using the Cox proportional hazard model showed that only QTd-V > or = 100 ms and ejection fraction < 40% were independent predictors of arrhythmic events. The results of this study indicate a significant relationship between QTd-V and the risk of arrhythmic events. The assessment of QTd-V may be useful for identifying patients with ventricular premature beats at high and low risk of subsequent arrhythmic events.

This study evaluates four databases from PhysioNet: The American Heart Association database (AHADB), Creighton University Ventricular Tachyarrhythmia database (CUDB), MIT-BIH Arrhythmia database (MITDB), and MIT-BIH Noise Stress Test database (NSTDB). The ANSI/AAMI EC57:2012 is used for the evaluation of the algorithms for the supraventricular ectopic beat (SVEB), ventricular ectopic beat (VEB), atrial fibrillation (AF), and ventricular fibrillation (VF) via the evaluation of the sensitivity, positive predictivity and false positive rate. Sample entropy, fast Fourier transform (FFT), and multilayer perceptron neural network with backpropagation training algorithm are selected for the integrated detection algorithms. For this study, the result for SVEB has some improvements compared to a previous study that also utilized ANSI/AAMI EC57. In further, VEB sensitivity and positive predictivity gross evaluations have greater than 80%, except for the positive predictivity of the NSTDB database. For AF gross evaluation of MITDB database, the results show very good classification, excluding the episode sensitivity. In advanced, for VF gross evaluation, the episode sensitivity and positive predictivity for the AHADB, MITDB, and CUDB, have greater than 80%, except for MITDB episode positive predictivity, which is 75%. The achieved results show that the proposed integrated SVEB, VEB, AF, and VF detection algorithm has an accurate classification according to ANSI/AAMI EC57:2012. In conclusion, the proposed integrated detection algorithm can achieve good accuracy in comparison with other previous studies. Furthermore, more advanced algorithms and hardware devices should be performed in future for arrhythmia detection and evaluation.

The heart is one of the crucial parts of the human being. The graphical recording of the cardiac cycle produced by an Electrocardiograph is called an Electrocardiogram (ECG) signal. To predict the occurrence of an arrhythmia, an electrocardiogram (ECG) is generally used by doctors to identify the condition of the patient. Hence, to accurately detect the abnormalities of the heart in advance and classify those diseases without human involvement many machine learning algorithms are used. The MIT-BIH Arrhythmia database is being used to classify the beat classification performance. This paper presents the hardware implementation of a classifier using an Artificial Neural Network (ANN) to classify four abnormalities (Normal beat, Supraventricular ectopic beat, Ventricular ectopic beat, Fusion beat) of heartbeat with high accuracy. To an appropriate input vector for the classifier, several preprocessing stages have been applied. Discrete Wavelet Transform (DWT) is used to extract the features from the ECG signal. To implement this work, Xilinx Artix-7 NESYS 4 DDR FPGA board is used. This model got 86% testing accuracy in simulation and 85.6% in hardware.

Brugada syndrome is a well-known form of idiopathic ventricular fibrillation (VF). Few data suggest that this arrhythmia may be triggered by ventricular premature beats (VPBs), and an association with other arrhythmia such as monomorphic ventricular tachycardia (VT) or supraventricular tachycardia (SVT) has been reported. In a highly symptomatic 18-year-old-male patient with this syndrome, frequent episodes of VF, fast polymorphic VT, and fast monomorphic sustained regular tachycardia were observed. The tachycardia episodes were classified as VT or VF and as a consequence received appropriate therapies with the implanted cardioverter defibrillator (ICD). Precipitating VPBs that were stored in the ICD memory and on the electrocardiogram (ECG) exhibited the same morphology as frequent isolated VPBs. During the electrophysiological study, right and left atrial tachycardia (AT) with one-to-one atrioventricular conduction were also induced and successfully ablated. VF was ablated using the same noncontact mapping (NCM) system triggering VPBs from right ventricular outflow tract (RVOT).

심전도 신호 분석 및 부정맥 분류는 환자를 진단하고 치료하는데 중요한 역할을 한다. 부정맥은 맥박이 불규칙한 상태로 심실빈맥(VT)이나 심실세동(VF) 환자에게 심각한 위협이 될 수 있다. 심방조기수축(APC)과 상심실성빈맥(SVT), 심실조기수축(PVC)은 심실빈맥(VT)만큼 치명적이지는 않지만 심장질환을 진단하는데 중요한 부정맥이다. 본 논문은 2~3개의 부정맥 분류만을 고려한 기존의 방법을 극복하고 다양한 부정맥을 분류하기 위한 새로운 방법을 제시한다. 심전도 신호의 특징 추출을 위해서 EMD 방법으로 신호를 분해하여 IMFs를 얻는다. 입력 데이터의 양은 분류기 성능에 영향을 미치므로 신호 데이터의 차원을 감소시키기 위해 Burg 알고리즘을 IMFs에 적용하여 AR 계수를 구하고 여러 개의 이진 분류기를 결합한 다중 클래스 SVM의 입력으로 사용한다. 최적의 SVM 성능 파라미터를 선택하고 부정맥 분류에 적용한 결과 검출의 정확성은 96.8%~99.5%였다. 실험 결과는 제안한 EMD 방법에 의한 전처리 및 특징 추출과 다중 클래스 SVM에 의한 부정맥 분류의 유용성을 보여준다. Electrocardiogram(ECG) analysis and arrhythmia recognition are critical for diagnosis and treatment of ill patients. Cardiac arrhythmia is a condition in which heart beat may be irregular and presents a serious threat to the patient recovering from ventricular tachycardia (VT) and ventricular fibrillation (VF). Other arrhythmias like atrial premature contraction (APC), Premature ventricular contraction (PVC) and superventricular tachycardia (SVT) are important in diagnosing the heart diseases. This paper presented new method to classify various arrhythmias contrary to other techniques which are limited to only two or three arrhythmias. ECG is decomposed into Intrinsic Mode Functions (IMFs) by Empirical Mode Decomposition (EMD). Burg algorithm was performed on IMFs to obtain AR coefficients which can reduce the dimension of feature vector and utilized as Multi-class SVM inputs which is basically extended from binary SVM. We chose optimal parameters for SVM classifier, applied to arrhythmias classification and achieved the accuracies of detecting NSR, APC, PVC, SVT, VT and VP were 96.8% to 99.5%. The results showed that EMD was useful for the preprocessing and feature extraction and multi-class SVM for classification of cardiac arrhythmias, with high usefulness.

Background: Although idiopathic ventricular tachycardia (VT) and premature ventricular complex (PVC) originating from the ventricular outflow tract (RVOT) are considered benign, sometimes ventricular fibrillation (VF) and polymorphic ventricular tachycardia (PVT) are initiating by PVC from the RVOT, resulting in sudden cardiac death. Objectives: The aim of this study was to assess the characteristics of initiated PVC from the RVOT about surface ECG in the patients who ware documented VT and/or PVT. Method: For 15 patients in whom radiofrequency catheter ablation (RFCA) was performed for idiopathic ventricular tachyarrthymia arising from the RVOT, we examined the surface ECG of PVC from the RVOT and the clinical characteristics of patients. Results: Among 15 patients, the episodes of VF were documented in 2 patients, VT and cardiac shock in 1 patient, 1 patient had prior episodes of syncope. These 4 patients were called “VF group” . All patients of VF group showed V1 positive QRS in 12-lead ECG of PVC from the RVOT, but only 2 patients of another patients showed V1 positive QRS. Conclusion: Our findings may predict the causing VF and/or PVT resulting in cardiac sudden death. To examine whether it is correct or not, we need more patients and electrophysiological investigations.

Computer-aided diagnosis of Electrocardiographic (ECG) signal consists of processing the signal to extract parameters in time, frequency, scale, etc. Then distinct parameters that provide significant differences between normal and arrhythmic ECG beats are selected as a feature vector. This feature vector is fed to either a supervised or an unsupervised classifier for detection. Seeking significant features is an important step for the success of the classifier. In this paper, we address combining both continuous wavelets transform (CWT) and the Teager-Kaiser Energy (TKE) for feature extraction. This is for developing a method for the detection of premature ventricular contraction (PVC) beats in ECG. The proposed method has been tested by the MIT-BIH arrhythmia database. The method has shown promising detection accuracy of 100% in classifying normal and PVC beats.

Changes in sinus RR interval patterns preceding ventricular ectopic beats: assessment with rate enhancement and dynamic heart rate trends

A rapid wide complex tachycardia

In their paper published in this issue of Heart , Birati and colleagues report the cardiac location from which arise the premature ventricular beats initiating torsades de pointes (TdP) in...

this study aims to evaluate the prevalence of various arrhythmias and other electrocardiographic patterns within the group of individuals with overweight and obesity. One hundred eighty-one adults (90 females and 91 males) were qualified for inclusion in the experimental group. All participants had a body mass index (BMI) exceeding 25 kg/m2 (98 patients with obesity and 83 with overweight). The mean BMI in the obesity group was 33.6 kg/m2, and all participants had class 1 obesity. The control group comprised 69 individuals (56 females and 13 males) with normal BMI. The basic measurements were performed, and the participants filled out questionnaires describing their health conditions and lifestyles. Each participant underwent an electrocardiographic (ECG) examination and a 24 h Holter ECG examination. In patients with class 1 obesity compared to the control patients, the average numbers of premature ventricular beats (PVBs) and premature supraventricular beats (SPBs) were statistically significantly higher (p = 0.030 and p = 0.042). There was a positive correlation between body weight and PVB (p = 0.028) and between body weight and SPB (p = 0.028). Moreover, BMI and waist circumference were correlated with SPB (p = 0.043 and p = 0.031). In the backward stepwise multivariate regression model considering 24 h Holter ECG monitoring, concerning SPB as the dependent variable, it was observed that BMI (especially obesity class 1), type 2 diabetes, and thyroid disease exhibited the highest regression coefficients. obesity, even in class 1, might be a factor in a more frequent occurrence of abnormalities in electrocardiographic tests.

Short-term fluctuations in sinus cycle length after premature ventricular beats in patients with hypertrophic cardiomyopathy and myocardial infarction