Autoencoder-Based Extrasystole Detection and Modification of RRI Data for Precise Heart Rate Variability Analysis.

Heart rate variability, which is the fluctuation of the R-R interval (RRI) in electrocardiograms (ECG), has been widely adopted for autonomous evaluation. Since the HRV features that are extracted from RRI data easily fluctuate when arrhythmia occurs, RRI data with arrhythmia need to be modified appropriately before HRV analysis. In this study, we consider two types of extrasystoles-premature ventricular contraction (PVC) and premature atrial contraction (PAC)-which are types of extrasystoles that occur every day, even in healthy persons who have no cardiovascular diseases. A unified framework for ectopic RRI detection and a modification algorithm that utilizes an autoencoder (AE) type of neural network is proposed. The proposed framework consists of extrasystole occurrence detection from the RRI data and modification, whose targets are PVC and PAC. The RRI data are monitored by means of the AE in real time in the detection phase, and a denoising autoencoder (DAE) modifies the ectopic RRI caused by the detected extrasystole. These are referred to as AE-based extrasystole detection (AED) and DAE-based extrasystole modification (DAEM), respectively. The proposed framework was applied to real RRI data with PVC and PAC. The result showed that AED achieved a sensitivity of 93% and a false positive rate of 0.08 times per hour. The root mean squared error of the modified RRI decreased to 31% in PVC and 73% in PAC from the original RRI data by DAEM. In addition, the proposed framework was validated through application to a clinical epileptic seizure problem, which showed that it correctly suppressed the false positives caused by PVC. Thus, the proposed framework can contribute to realizing accurate HRV-based health monitoring and medical sensing systems.

Deep learning for comprehensive ECG annotation.

BACKGROUND: Increasing utilization of long-term outpatient ambulatory electrocardiographic (ECG) monitoring continues to drive the need for improved ECG interpretation algorithms. OBJECTIVE: The purpose of this study was to describe the BeatLogic® platform for ECG interpretation and to validate the platform using electrophysiologist-adjudicated real-world data and publicly available validation data. METHODS: Deep learning models were trained to perform beat and rhythm detection/classification using ECGs collected with the Preventice BodyGuardian® Heart monitor. Training annotations were created by certified ECG technicians, and validation annotations were adjudicated by a team of board-certified electrophysiologists. Deep learning model classification results were used to generate contiguous annotation results, and performance was assessed in accordance with the EC57 standard. RESULTS: On the real-world validation dataset, BeatLogic beat detection sensitivity and positive predictive value were 99.84% and 99.78%, respectively. Ventricular ectopic beat classification sensitivity and positive predictive value were 89.4% and 97.8%, respectively. Episode and duration F1 scores (range 0-100) exceeded 70 for all 14 rhythms (including noise) that were evaluated. F1 scores for 11 rhythms exceeded 80, 7 exceeded 90, and 5 including atrial fibrillation/flutter, ventricular tachycardia, ventricular bigeminy, ventricular trigeminy, and third-degree heart block exceeded 95. CONCLUSION: The BeatLogic platform represents the next stage of advancement for algorithmic ECG interpretation. This comprehensive platform performs beat detection, beat classification, and rhythm detection/classification with greatly improved performance over the current state of the art, with comparable or improved performance over previously published algorithms that can accomplish only 1 of these 3 tasks.

A robust algorithm for heart rate variability time series artefact correction using novel beat classification.

Purpose: Heart rate variability is a commonly used measurement to evaluate functioning of autonomic nervous system, psychophysiological stress, and exercise intensity and recovery. HRV measurements contain artefacts such as extra, missed or misaligned beat detections, which can produce significant distortion on HRV parameters. In this paper, a robust automatic method for artefact detection from HRV time series is proposed. Methods: The proposed detection method is based on time-varying thresholds estimated from distribution of successive RR-interval differences combined with a novel beat classification scheme. The method is validated using simulated extra, missed and misaligned beat detections as well as real artefacts such as atrial and ventricular ectopic beats. Results: The sensitivity of the algorithm to detect simulated missed/extra beats was 100%. The sensitivity to detect real atrial and ventricular ectopic beats was 96.96%, the corresponding specificity being 99.94%. The mean error in HRV parameters after correction was <2% for missed and extra beats as well as for misaligned beats generated with large displacement factors. Misaligned beats with smallest displacement factor were the most difficult to detect and resulted in largest HRV parameter errors after correction, largest errors being <8%. Conclusions: The HRV artefact correction algorithm presented in this study provided comparable specificity and better sensitivity to detect ectopic beats as compared to state-of-the-art algorithms. The proposed algorithm detects abnormal beats with high accuracy, is relatively easy to implement, and secures reliable HRV analysis by reducing the effect of possible artefacts to tolerable level.

Isolated Non-Compacted Myocardium: Should We Consider the Presence of Extrasystoles as the Initial Manifestation?

Ventricular non-compaction occurs due to failure in myocardial morphogenesis during the fetal period. Patients can have heart failure, as well as systemic complications due to thromboembolism and cardiac arrhythmias. Early diagnosis is essential. We present the case of an asymptomatic 49-year-old woman who initially manifested ventricular extrasystoles and heart failure with reduced ejection fraction and a myocardial noncompaction diagnosis

"Pseudo" Hisian extrasystole arising from the proximal portion of the left bundle branch.

The diagnosis of a Hisian extrasystole is based on simple electrocardiographic features and both an extrasystole arising from the His-Bundle ("true" Hisian extrasystole) and also one from the proximal portion of the bundle branch ("pseudo" Hisian extrasystole) would be diagnosed as Hisian extrasystoles [1]. Here we report a case of "pseudo" Hisian extrasystole arising from the proximal portion of the left bundle branch and the successful catheter ablation was achieved in the right coronary cusp.

Ectopic Beats: Insights from Timing and Morphology.

Premature complexes are electrical impulses arising from atrial, junctional, or ventricular tissue, leading to premature heart beats. Premature atrial beats are much more frequent than those arising in the atrioventricular junction but less frequent than premature beats from the ventricles. Although they are usually benign and highly prevalent in the general population, they could trigger sustained supraventricular and ventricular arrhythmias, and cause cardiomyopathies. The aim of this article was to review the main electrocardiology features of premature complexes and discuss their implications in clinical practice.

Double ventricular response in dual AV nodal pathways mimicking interpolated premature beat.

Double ventricular response in dual atrioventricular (AV) nodal pathways can result in nonreentrant supraventricular tachycardia. Since this condition was first described in 1979, around 20 cases have been reported. Here, we present the case of a patient with a confirmed diagnosis of double ventricular response in dual AV nodal pathways resembling an interpolated premature beat who underwent successful radiofrequency ablation of the slow pathway.

Influence of irregular heart rhythm on radiation exposure, image quality and diagnostic impact of cardiac computed tomography angiography in 4,339 patients. Data from the German Cardiac Computed Tomography Registry.

BACKGROUND: Coronary computed tomography angiography (coronary CTA) provides non-invasive evaluation of the coronary arteries with high precision for the detection of significant coronary artery disease (CAD). AIM: To investigate whether irregular heart rhythm including atrial fibrillation and premature beats during data acquisition influences (i) radiation and contrast media exposure, (ii) number of non-evaluable coronary segments and (iii) diagnostic impact of coronary CTA. METHODS: Twelve tertiary care centers with ≥64 slice CT scanners and ≥5 years of experience with cardiovascular imaging participated in this registry. Between 2009 and 2014, 4339 examinations were analysed in patients who underwent clinically indicated coronary CTA for suspected CAD. Clinical and epidemiologic data were gathered from all patients. In addition, clinical presentation, heart rate and rhythm during the scan, Agatston score, radiation and contrast media exposure and the diagnostic impact of coronary CTA were systematically analysed. RESULTS: Of 4339 patients in total, 260 (6.0%) had irregular heart rhythm, whereas the remaining 4079 (94.0%) had stable sinus rhythm. Patients with irregular heart rhythm were older (63.2 ± 12.5yrs versus 58.6 ± 11.4yrs. p < 0.001), exhibited a higher rate of pathologic stress tests before CTA (37.1% versus 26.1%, p < 0.01) and higher heart rates during CTA compared to those with sinus rhythm (62.5 ± 11.6bpm versus 58.9 ± 8.5bpm, p < 0.001). Both contrast media exposure and radiation exposure were significantly higher in patients with irregular heart rhythm (90 mL (95%CI = 80-110 mL) versus 80 mL (95%CI = 70-90 mL) and 6.2 mSv (95%CI = 2.5-11.7) versus 3.3 mSv (95%CI = 1.7-6.9), p < 0.001 for both). Coronary CTA excluded significant CAD less frequently in patients with irregular heart rhythm (32.9% versus 44.8%, p < 0.001). This was attributed to the higher rate of examinations with at least one non-diagnostic coronary segment in patients with irregular heart rhythm (10.8% versus 4.6%, p < 0.001). Subsequent invasive angiography could be avoided in 47.2% of patients with irregular heart rhythm compared to 52.9% of patients with sinus rhythm (p = NS), whereas downstream stress testing was recommended in 3.2% of patients with irregular heart rhythm versus 4.0% of patients with sinus rhythm (p = NS). CONCLUSION: A significant number of patients scheduled for coronary CTA have irregular heart rhythm in a real-world clinical setting. In such patients, heart rate during coronary CTA is higher, possibly resulting in (i) higher radiation and contrast agent exposure and (ii) more frequent coronary CTA examinations with at least one non-diagnostic coronary artery segment. However, this does not seem to lead to increased downstream stress testing or subsequent invasive procedures.

[Trigeminy of ventricular bigeminy caused by reentrant mechanism: reentry of reentry]. / Trigeminia de la bigeminia ventricular por mecanismo reentrante: reentrada de la reentrada.

The process that follows an acute myocardial infarction generates an appropriate substrate for the formation of reentry circuits, considered to be the most frequent mechanism of ventricular extrasystoles and tachyarrhythmias. We present the case of a patient with an acute myocardial infarction unusually concurring with ventricular trigeminy coupled to ventricular bigeminated extrasystoles giving rise to a trigeminy sequence over the bigeminy, which indicates the existence of two reentry circuits (reentry of reentry) that trigger ventricular flutter.

Trigeminia de la bigeminia ventricular por mecanismo reentrante: reentrada de la reentrada / Trigeminy of ventricular bigeminy caused by reentrant mechanism: reentry of reentry

El proceso post-infarto agudo de miocardio genera el sustrato apropiado para la formación de circuitos de reentrada, los cuales son considerados como el mecanismo más frecuente de las extrasístoles y taquiarritmias ventriculares. Presentamos el trazado electrocardiográfico de un paciente con infarto agudo de miocardio en quien se observó la inusual concurrencia de una trigeminia ventricular acoplada a extrasístoles ventriculares bigeminadas, que originó una secuencia de trigeminia sobre la bigeminia, evidenciando la existencia de dos circuitos reentrantes (reentrada de la reentrada); después de una dupla de la extrasístole bigeminada se genera un aleteo ventricular.

The process that follows an acute myocardial infarction generates an appropriate substrate for the formation of reentry circuits, considered to be the most frequent mechanism of ventricular extrasystoles and tachyarrhythmias. We present the case of a patient with an acute myocardial infarction unusually concurring with ventricular trigeminy coupled to ventricular bigeminated extrasystoles giving rise to a trigeminy sequence over the bigeminy, which indicates the existence of two reentry circuits (reentry of reentry) that trigger ventricular flutter.

[Malignant bileaflet mitral valve prolapse syndrome in otherwise idiopathic ventricular fibrillation]. / Malignes Mitralklappenprolapssyndrom bei "idiopathischem" Kammerflimmern.

A 32-year-old, otherwise healthy woman was admitted after successful out-of-hospital resuscitation due to ventricular fibrillation. Established cardiac, pulmonary, metabolic, and toxicological causes were excluded. However, persisting (biphasic) negative T waves in the inferior ECG leads and premature ventricular contractions (PVC) were noted. PVC morphology indicated a focus alternating between the posterior papillary muscle/the left posterior fascicle and the left ventricular outflow tract region/anterior papillary muscle. Echocardiography revealed a bileaflet mitral prolapse with mild mitral valve regurgitation. This case is a typical presentation of the recently described malignant bileaflet mitral valve prolapse syndrome. The patient was discharged without overt neurological deficit after implantation of a cardioverter-defibrillator.

The prevalence of electrocardiogram abnormalities in professional divers.

BACKGROUND: The underwater environment presents physiological challenges for the cardiovascular, renal and pulmonary systems. Increases in external hydrostatic pressure reduce the capacity of the venous compartment and cause blood to move toward the lung. The aim of this study was to evaluate retrospectively electrocardiographic (ECG) changes in a cohort of professional divers. METHODS: Between January 2009 and January 2012, 225 randomly selected professional divers, 204 male (91%) and 21 female (9%) attended our clinic for their biannual diving medical assessment. Their ECG records were evaluated retrospectively. RESULTS: The most common ECG abnormality observed was incomplete right bundle branch block (IRBBB) in 30 divers (13.3%). Eleven divers (4.9%) showed right QRS axis deviation (seven with IRBBB). Six divers had a sinus tachycardia; in four divers there was early repolarization; three divers had ventricular extrasystoles; one diver had ST elevation in lead V3; there was one with sinus arrhythmia and another with T-wave inversion in leads V2, V3 and aVF. These ECG changes were evaluated retrospectively by a cardiologist who made various recommendations for further review including bubble contrast echocardiography for IRBBB. CONCLUSIONS: No serious ECG abnormalities were identified, but IRBBB should be further investigated because of its association with persistent (patent) foramen ovale. Rapid cardiological review of ECGs could be achieved using modern communications technology, such as telecardiography, and further clinical investigations directed by specialist recommendation arranged promptly if indicated.

Hisian extrasystole mimicking second degree atrioventricular block. a case report.

Hisian extrasystoles originate from the His bundle. They are rare and usually misdiagnosed. In fact, they manifest on the EKG, with a p' wave located before, in or after the QRS complex. More rarely, the extrasystole blocks the propagation of the influx to the ventricles simulating a Mobitz II atrioventricular (AV) block. We report the case of a 36-Year-old woman with no medical History, suffering from presyncope and palpitations at rest. Her physical examination and EKG were normal. The 24-hour Holter monitoring showed some long periods with unexpected blocked p waves but with no significant pause. Considering her young age and the absence of causes of AV block, we performed an intracardiac electrophysiological study which showed hisian extrasystoles with normal conduction tissue properties at baseline and under flecainide. The diagnosis of hisian extrasystoles simulating Mobitz II AV block was made. A simple monitoring with beta-blockers therapy was recommended. Hisian extrasystoles may simulate first or second degree AV block with different therapeutic and prognostic implications. Nevertheless, these hisian extrasystoles may be the marker of a vulnerable AV conduction, long-term follow up should be considered.

Further insights into blood pressure induced premature beats: Transient depolarizations are associated with fast myocardial deformation upon pressure decline.

BACKGROUND: An acute increase in blood pressure is associated with the occurrence of premature ventricular complexes (PVCs). OBJECTIVE: We aimed to study the timing of these PVCs with respect to afterload-induced changes in myocardial deformation in a controlled, preclinically relevant, novel closed-chest pig model. METHODS: An acute left ventricular (LV) afterload challenge was induced by partial balloon inflation in the descending aorta, lasting 5-10 heartbeats (8 pigs; 396 inflations). RESULTS: Balloon inflation enhanced the reflected wave (augmentation index 30% ± 8% vs 59% ± 6%; P < .001), increasing systolic central blood pressure by 35% ± 4%. This challenge resulted in a more abrupt LV pressure decline, which was delayed beyond ventricular repolarization (rate of pressure decline 0.16 ± 0.01 mm Hg/s vs 0.27 ± 0.04 mm Hg/ms; P < .001 and interval T-wave to peak pressure 1 ± 12 ms vs 36 ± 9 ms; P = .008), during which the velocity of myocardial shortening at the basal septum increased abruptly (ie, postsystolic shortening) (peak strain rate -0.6 ± 0.5 s(-1) vs -2.5 ± 0.8 s(-1); P < .001). It is exactly at this time of LV pressure decline, with increased postsystolic shortening, and not at peak pressure, that PVCs occur (22% of inflations). These PVCs preferentially occurred at the basal and apical segments. In the same regions, monophasic action potentials demonstrated the appearance of delayed afterdepolarization-like transient depolarizations as origin of PVCs. CONCLUSION: An acute blood pressure increase results in a more abrupt LV pressure decline, which is delayed after ventricular repolarization. This has a profound effect on myocardial mechanics with enhanced postsystolic shortening. Coincidence with induced transient depolarizations and PVCs provides support for the mechanoelectrical origin of pressure-induced premature beats.