[Heartbeat-based end-to-end classification of arrhythmias].

OBJECTIVE: We propose a heartbeat-based end-to-end classification of arrhythmias to improve the classification performance for supraventricular ectopic beat (SVEB) and ventricular ectopic beat (VEB). METHODS: The ECG signals were preprocessed by heartbeat segmentation and heartbeat alignment. An arrhythmia classifier was constructed based on convolutional neural network, and the proposed loss function was used to train the classifier. RESULTS: The proposed algorithm was verified on MIT-BIH arrhythmia database. The AUC of the proposed loss function for SVEB and VEB reached 0.77 and 0.98, respectively. With the first 5 min segment as the local data, the diagnostic sensitivities for SVEB and VEB were 78.28% and 98.88%, respectively; when 0, 50, 100, and 150 samples were used as the local data, the diagnostic sensitivities for SVEB and VEB reached 82.25% and 93.23%, respectively. CONCLUSIONS: The proposed method effectively reduces the negative impact of class-imbalance and improves the diagnostic sensitivities for SVEB and VEB, and thus provides a new solution for automatic arrhythmia classification.

A correlative study of myocardial infarction scar characteristics by DE-MR and the Lown's classification of ventricular premature beats.

OBJECTIVE: Correlation between myocardial infarction (MI) scar by cardiac magnetic resonance and the Lown's classification of ventricular premature beats (VPBs) is poorly understood. This study aims to investigate the correlation between the MI scar characteristics by delayed-enhancement magnetic resonance imaging (DE-MRI) and the Lown's classification of VPBs. METHODS: Sixty-five patients, in the convalescence stage and consolidation phase of MI, were included in this retrospective study. All patient were divided into VPBs group (n = 39) and non-VPBs group (n = 26 patients) according to the clinical diagnostic criteria of Universal Definition of MI scar. VPBs patients were assigned to Lown's I-II group and Lown's III-IV subgroup in accordance with the Lown classification criteria. Cardiac function parameters and MI scar characteristics were detected by cardiac magnetic resonance (CMR) and DE-MRI, respectively. RESULTS: Lown's classification was negatively correlated with left ventricular ejection fraction (LVEF), peak ejection rate (PER) and peak filling rate (PFR) (-0.724, -0.628, -0.559), and positively correlated with MI area, MI integral, MI segments number and left ventricular end systolic volume (LVESV) (0.673, 0.655, 0.586, and 0.514), respectively.CONCLUSIONSThe study indicated that MI area and MI integral were strongly associated with Lown's classification.

Idiopathic Ventricular Premature Contraction and Ventricular Tachycardia: Distribution of the Origin, Diagnostic Algorithm, and Catheter Ablation.

Idiopathic ventricular premature contractions (VPCs), defined as VPCs in the absence of obvious structural heart disease, are one of the common types of arrhythmia in clinical practice. They are sometimes complicated with non-sustained ventricular tachycardia (VT), and/or sustained VT with almost same QRS morphology in 12 leads ECG. Idiopathic VT (IVT) commonly occurs by focal mechanisms and the origins are distributed in a variety of sites in both ventricles. In this article, the clinical characteristics of IVT/IVPCs, the diagnostic algorithm, and how to ablate them will be reviewed.

[Ventricular arrhythmias in ion channel diseases]. / Ventrikuläre Arrhythmien bei Ionenkanalerkrankungen.

In patients with ion channel disease the predominant arrhythmias are polymorphic ventricular tachycardias (VT), torsade de pointes tachycardia and ventricular fibrillation (VF). In only extremely rare cases is very rapid monomorphic ventricular tachycardia observed. This is why implantable cardioverter-defibrillators (ICDs) should always be programmed for treatment of VF only with high detection rates to avoid inappropriate discharges. In idiopathic VF and catecholaminergic polymorphic ventricular tachycardia (CPVT), no baseline electrocardiographic abnormalities can be detected, whereas in Brugada syndrome, long QT syndrome, early repolarisation syndrome and Anderson-Tawil syndrome alterations of the baseline ECG are very important to identify patients at risk.

Use of self-gated radial cardiovascular magnetic resonance to detect and classify arrhythmias (atrial fibrillation and premature ventricular contraction).

BACKGROUND: Arrhythmia can significantly alter the image quality of cardiovascular magnetic resonance (CMR); automatic detection and sorting of the most frequent types of arrhythmias during the CMR acquisition could potentially improve image quality. New CMR techniques, such as non-Cartesian CMR, can allow self-gating: from cardiac motion-related signal changes, we can detect cardiac cycles without an electrocardiogram. We can further use this data to obtain a surrogate for RR intervals (valley intervals: VV). Our purpose was to evaluate the feasibility of an automated method for classification of non-arrhythmic (NA) (regular cycles) and arrhythmic patients (A) (irregular cycles), and for sorting of common arrhythmia patterns between atrial fibrillation (AF) and premature ventricular contraction (PVC), using the cardiac motion-related signal obtained during self-gated free-breathing radial cardiac cine CMR with compressed sensing reconstruction (XD-GRASP). METHODS: One hundred eleven patients underwent cardiac XD-GRASP CMR between October 2015 and February 2016; 33 were included for retrospective analysis with the proposed method (6 AF, 8 PVC, 19 NA; by recent ECG). We analyzed the VV, using pooled statistics (histograms) and sequential analysis (Poincaré plots), including the median (medVV), the weighted mean (meanVV), the total number of VV values (VVval), and the total range (VVTR) and half range (VVHR) of the cumulative frequency distribution of VV, including the median to half range (medVV/VVHR) and the half range to total range (VVHR/VVTR) ratios. We designed a simple algorithm for using the VV results to differentiate A from NA, and AF from PVC. RESULTS: Between NA and A, meanVV, VVval, VVTR, VVHR, medVV/VVHR and VVHR/VVTR ratios were significantly different (p values = 0.00014, 0.0027, 0.000028, 5×10-9, 0.002, respectively). Between AF and PVC, meanVV, VVval and medVV/VVHR ratio were significantly different (p values = 0.018, 0.007, 0.044, respectively). Using our algorithm, sensitivity, specificity, and accuracy were 93 %, 95 % and 94 % to discriminate between NA and A, and 83 %, 71 %, and 77 % to discriminate between AF and PVC, respectively; areas under the ROC curve were 0.93 and 0.89. CONCLUSIONS: Our study shows we can reliably detect arrhythmias and differentiate AF from PVC, using self-gated cardiac cine XD-GRASP CMR.

Interpolated premature ventricular contractions with postponed compensatory pauses: a misnomer?

Selected strips of a Holter recording obtained from a healthy young person with rare unifocal premature ventricular contractions (PVCs) were obtained. Occasionally, the PVCs were interpolated and showed the phenomenon originally named postponed compensatory pause by Langendorf [Am Heart J 1953;46:401]. But this is a misnomer because, by definition, interpolated PVCs do not have compensatory pauses. Thus, it follows that what does not exist cannot be postponed. In reality, the basic manifest feature is a prolongation of the first RR interval that follows the interpolated beat. However, in view of its use for more than half a century, it is probably best to continue using this terminology, but only as long as its underlying mechanism and fundamental manifestations are properly understood.

An arrhythmia classification system based on the RR-interval signal.

OBJECTIVE: This paper proposes a knowledge-based method for arrhythmic beat classification and arrhythmic episode detection and classification using only the RR-interval signal extracted from ECG recordings. METHODOLOGY: A three RR-interval sliding window is used in arrhythmic beat classification algorithm. Classification is performed for four categories of beats: normal, premature ventricular contractions, ventricular flutter/fibrillation and 2 degrees heart block. The beat classification is used as input of a knowledge-based deterministic automaton to achieve arrhythmic episode detection and classification. Six rhythm types are classified: ventricular bigeminy, ventricular trigeminy, ventricular couplet, ventricular tachycardia, ventricular flutter/fibrillation and 2 degrees heart block. RESULTS: The method is evaluated by using the MIT-BIH arrhythmia database. The achieved scores indicate high performance: 98% accuracy for arrhythmic beat classification and 94% accuracy for arrhythmic episode detection and classification. CONCLUSION: The proposed method is advantageous because it uses only the RR-interval signal for arrhythmia beat and episode classification and the results compare well with more complex methods.

Premature ventricular contraction classification by the Kth nearest-neighbours rule.

An analysis of electrocardiographic pattern recognition parameters for premature ventricular contraction (PVC) and normal (N) beat classification is presented. Twenty-six parameters were defined: 11 x 2 for the two electrocardiogram (ECG) leads, width of the complex and three parameters derived from a single-plane vectorcardiogram (VCG). Some of the parameters include amplitudes of maximal positive and maximal negative peaks, area of absolute values, area of positive values, area of negative values, number of samples with 70% higher amplitude than that of the highest peak, amplitude and angle of the QRS vector in a VCG plane. They were measured for all heartbeats annotated as N or PVC in all 48 ECG recordings of the MIT-BIH arrhythmia database. Two reference sets for the Kth nearest-neighbours rule were used-global and local. The classification indices obtained with the global reference set were 75.4% specificity and 80.9% sensitivity. Using the local reference set we increased the specificity to 96.7% and the sensitivity to 96.9%. The achieved specificity and sensitivity are comparable with, and greater than, the results reported in the literature.

[Detection of PVCs with support vector machine].

The classifiction of heart beats is the foundation for automated arrhythmia monitoring devices. Support vector machnies (SVMs) have meant a great advance in solving classification or pattern recognition. This study describes SVM for the identification of premature ventricular contractions (PVCs) in surface ECGs. Features for the classification task are extracted by analyzing the heart rate, morphology and wavelet energy of the heart beats from a single lead. The performance of different SVMs is evaluated on the MIT-BIH arrhythmia database following the association for the advancement of medical instrumentation (AAMI) recommendations.

Characterization of fetal arrhythmias by means of fetal magnetocardiography in three cases of difficult ultrasonographic imaging.

Characterization of ultrasound detected fetal arrhythmias is generally performed by means of M-mode and pulsed Doppler echocardiography (fECHO), sonographic techniques that allow only indirect and approximate reconstruction of the true electrophysiological events that occur in the fetal heart. Several studies demonstrated the ability of fetal magnetocardiography (fMCG) to identify fetal arrhythmias. We report on three women, studied after the 32nd gestational week, who were referred for fMCG because of unsatisfying fetal cardiac visualization with fECHO due to maternal obesity, fetus in constant dorsal position hiding the fetal heart, intrauterine growth retardation, and oligohydramnios. Minor pericardial effusion was present in the third patient and digoxin therapy was given. FMCG were recorded with a 77-channel MCG system working in a shielded room. Independent Component Analysis (FastICA algorithm) was used to reconstruct fetal signals. The good quality of the retrieved fetal signals allowed real-time detection of arrhythmias and their classification as supraventricular extrasystoles (SVE), with/without aberrant ventricular conduction and/or atrioventricular block. The time course of the fetal cardiac rhythm was reconstructed for the entire recording duration; hence, fetal heart rate variability could be studied in time and frequency. Since isolated extrasystoles may progress to more hazardous supraventricular tachycardias, the noninvasive antenatal characterization of, even transient, fetal arrhythmias and their monitoring during pregnancy can be of great clinical impact.

Ranking of pattern recognition parameters for premature ventricular contractions classification by neural networks.

Detection and classification of ventricular complexes from a limited number of ECG leads is of considerable importance in critical care or operating room patient monitoring. Beat-to-beat detection allows the heart rhythm evolution to be followed and various types of arrhythmia to be recognized. A quantitative analysis is proposed of pattern recognition parameters for classification of normal QRS complexes and premature ventricular contractions (PVC). Twenty-six parameters have been defined: the width of the QRS complex, three vectorcardiogram parameters and 11 from two ECG leads. These parameters include: amplitudes of positive and negative peaks, area of positive and negative waves, various time-interval durations, amplitude and angle of the QRS vector, etc. They are measured for all QRS complexes annotated as 'normals' and 'PVCs' from the 48 ECG recordings of the MIT-BIH arrhythmia database. Neural networks (NN) are shown to be a useful instrument for the analysis of large quantities of parameters. Separate ranking of any parameter and homogeneous group ranking (amplitude, area, interval, slope and vector) were performed. From the two ECG leads, the first three ranked parameter groups for clustering of PVCs are amplitude, slope and interval, while for N clustering they are vector, amplitude and area. Considering the entire parameter set, we obtained N = 99.7% correct detection of normal QRS complexes and PVC = 98.5% of premature ventricular complexes. The study also shows that simultaneous analysis of two ECG channels yields better accuracy compared to using a single channel: the improvement is 0.1% in the classification of N beats and 4.5% for PVC beats.

Radiofrequency ablation of idiopathic ventricular fibrillation guided by noncontact mapping.

A 32-year-old man with idiopathic ventricular fibrillation and an implantable cardioverter defibrillator presented during a ventricular fibrillation storm. Frequent monomorphic ventricular ectopics with left bundle branch block morphology were documented, some of which initiated fibrillation. He underwent noncontact mapping of the right ventricle, during which the ventricular ectopics were mapped to a site in the free wall displaying a diastolic potential 80 ms before ectopic QRS onset. Following three radiofrequency energy applications, the ectopics were abolished. After 11-month follow-up, he has experienced no further arrhythmias. Noncontact mapping may identify ablatable triggers of ventricular fibrillation and lead to successful outcomes even when only single ectopics are present.

Characterization of paroxysmal and persistent atrial fibrillation in the human left atrium during initiation and sustained episodes.

INTRODUCTION: Atrial fibrillation (AF) in the left atrium (LA) is poorly defined in terms of regional differences in the degree of organization, characteristics of paroxysmal and persistent variants, and electrophysiologic events that develop at the onset of episodes. METHODS AND RESULTS: The study population consisted of 21 patients (15 men and 6 women; mean age 58+/-9.4 years) with paroxysmal (10 patients) or persistent (11 patients) AF. Mapping of the LA during sustained episodes and the onset of AF was performed with a 64-electrode basket catheter. At the onset of AF, repetitive beats starting with atrial premature complexes and ending with generation of the earliest fibrillatory activity were defined as intermediary rhythm. Patients with paroxysmal AF had longer AF cycle lengths and more pronounced regional differences than patients with persistent AF. In total, AF cycle lengths in the LA in patients with persistent AF were 20% shorter than in patients with paroxysmal AF. Initiation of AF was preceded by an intermediary rhythm of 5.5+/-2.5 cycles (6.3+/-2.7 cycles in paroxysmal AF vs 4.2+/-1.0 cycles in persistent AF; P = 0.026). At the onset of AF, the earliest generators of fibrillatory activity were located more frequently in the posterior wall of the LA. CONCLUSION: AF in the LA displays substantial regional differences in terms of AF cycle lengths and degree of organization. Patients with persistent AF have shorter cycle lengths and a higher degree of disorganized activity than patients with paroxysmal AF. Intermediary rhythms play an important role in initiation of AF via activation of generator regions in the LA.

One-year outcome after radiofrequency catheter ablation of symptomatic ventricular arrhythmia from right ventricular outflow tract.

Although ventricular premature complexes (VPCs) in patients without structural heart disease are benign, many patients experience disabling symptoms. Many patients need long-term medication, which is often ineffective and may have adverse effects. Radiofrequency catheter ablation (RFCA) may be an alternative treatment. RFCA was performed in 33 patients with severely symptomatic VPCs that were refractory to medication. Mean VPCs were 23,987 +/- 2,077 beats/24 hours. Twenty-four-hour ambulatory electrocardiographic monitoring, quality of life, and symptoms were assessed at a screening visit and 1 and 12 months after RFCA. RFCA was successfully performed in 32 patients (97%). This resulted in a significant improvement in symptoms, severity of ventricular arrhythmia, and quality of life at 1 and 12 months after the procedure. There were no major complications related to the procedure. Eight patients (24%) had residual arrhythmia. Five of them underwent repeated ablation with successful results. Thus, catheter ablation is a safe and effective treatment for symptomatic ventricular arrhythmia from the right ventricular outflow tract. It also improves the quality of life. Catheter ablation is a viable alternative to drugs in the presence of disabling symptoms.

Congestive heart failure and ventricular arrhythmias in relation to serum magnesium.

Congestive Heart Failure (CHF) is associated with biochemical evidence of electrolyte imbalance including magnesium deficit, which may increase myocardial electrical instability, risk of malignant arrhythmias and sudden death. The aim of this study was to determine serum magnesium concentration in 45 patients (Group I; 24 male, 21 female; the average age 49.7 years) with CHF, New York Heart Association (NYHA) Class II, III who were treated with lisinopril [Angiotensin-Converting Enzyme Inhibitor (ACEI)], frusemide (diuretic) and digoxin. All patients were subjected to resting 12-lead electrocardiography (ECG) and ventricular arrhythmias were analysed in relation to serum magnesium concentration at baseline and at end of the fourth week of treatment. Control group (Group II; 24 male, 21 female; the average age 49.3 years) were matched with Group I. Serum magnesium was determined by Atomic Absorption Spectrophotometer (AAS). Statistical analysis was with Student's t-test. It was observed that 6 (13.3%) CHF patients had ventricular arrhythmias at the commencement of the study. This number increased to 17 (37.8%) by the end of the fourth week of treatment. At four weeks, there was significant difference in serum magnesium between CHF patients without arrhythmias (0.69 +/- 0.11 mmol x L(-1)) and those with arrhythmias (0.50 +/- 0.01 mmol x L(-1)), P < 0.0001. Results obtained suggest that CHF patients having hypomagnesemia had higher prevalence of ventricular arrhythmias. It should be stressed, however, that 24 hour ECG monitoring and classification of ventricular arrhythmias according to Lown may give a more accurate picture. Nevertheless, routine serum magnesium assays, as part of the electrolyte profile of CHF patients would assist in early prevention and detection of magnesium depletion. This would go a long way to reduce the susceptibility to lethal arrhythmias and sudden death.

Ventricular premature beat-driven intermittent restoration of coronary blood flow reduces the incidence of reperfusion-induced ventricular fibrillation in a cat model of regional ischemia.

With a cat model of regional cardiac ischemia, we examined whether the incidence of reperfusion-induced ventricular fibrillation (VF) could be reduced by ventricular premature beat (VPB)-driven intermittent reperfusion. In addition, we assessed whether the effect of the intermittent reperfusion was comparable with that of ischemic preconditioning in suppressing the VF. Of 15 cats subjected to uninterrupted reperfusion after 20-minute occlusion of the left anterior descending coronary artery, 13 (86.70%) had VF, whereas only 1 (7.1%) of 14 cats subjected to the VPB-driven intermittent reperfusion had VF. This incidence of VF was significantly lower than that of the animal group subjected to uninterrupted reperfusion. However, it was not statistically different from that (3 of 15) of the group subjected to a 10-minute episode of the coronary artery occlusion before the 20-minute occlusion (i.e., "ischermic preconditioning"). Our results suggest that the VPB-driven intermittent reperfusion (i.e., "postconditioning") is very effective in preventing reperfusion-induced VF and as good as, if not better than, ischemic preconditioning.

Classification of cardiac arrhythmias using fuzzy ARTMAP.

We have investigated the QRS complex, extracted from electrocardiogram (ECG) data, using fuzzy adaptive resonance theory mapping (ARTMAP) to classify cardiac arrhythmias. Two different conditions have been analyzed: normal and abnormal premature ventricular contraction (PVC). Based on MIT/BIH database annotations, cardiac beats for normal and abnormal QRS complexes were extracted from this database, scaled, and Hamming windowed, after bandpass filtering, to yield a sequence of 100 samples for each ORS segment. From each of these sequences, two linear predictive coding (LPC) coefficients were generated using Burg's maximum entropy method. The two LPC coefficients, along with the mean-square value of the QRS complex segment, were utilized as features for each condition to train and test a fuzzy ARTMAP neural network for classification of normal and abnormal PVC conditions. The test results show that the fuzzy ARTMAP neural network can classify cardiac arrhythmias with greater than 99% specificity and 97% sensitivity.

Classification of arrhythmic events in ambulatory electrocardiogram, using artificial neural networks.

We propose artificial neural networks (ANN) for ambulatory ECG arrhythmic event classification, and we compare them with some traditional classifiers (TC). Among them, the one based on the median method (heuristic algorithm) was chosen and taken as a quality reference in this study, while a back propagation based classifier, designed as an autoassociator for its peculiar capability of rejecting unknown patterns, was examined. Two tests were performed: the first to discriminate normal vs ventricular beats and the second to distinguish among three classes of arrhythmic events. The results show that the ANN approach is more reliable than the traditional classifiers in discriminating among many classes of arrhythmic events: 98% by ANN vs 99% by a TC for correctly classified normal beats, 98% by ANN vs 96% by TC for correctly classified ventricular ectopic beats, 96% by ANN vs 59% by TC for correctly classified supraventricular ectopic beats, and 83% by ANN vs 86% by median method for correctly classified aberrated atrial premature beats. This paper also tackles the problem of the management of classification uncertainty. Two concurrent uncertainty criteria have been introduced, to reduce the classification error of the unknown ventricular and supraventricular arrhythmic beats respectively. The error in ventricular beats case was kept close to 0% in average and for supraventricular beats was kept at 35% in average. So we can state that the ANN approach is powerful in classifying beats represented in the training set and that it manages the uncertainty in such a way as to reduce, in any case, the global error percentage.