ECGVEDNET: A Variational Encoder-Decoder Network for ECG Delineation in Morphology Variant ECGs.

Electrocardiogram (ECG) delineation to identify the fiducial points of ECG segments, plays an important role in cardiovascular diagnosis and care. Whilst deep delineation frameworks have been deployed within the literature, several factors still hinder their development: (a) data availability: the capacity of deep learning models to generalise is limited by the amount of available data; (b) morphology variations: ECG complexes vary, even within the same person, which degrades the performance of conventional deep learning models. To address these concerns, we present a large-scale 12-leads ECG dataset, ICDIRS, to train and evaluate a novel deep delineation model-ECGVEDNET. ICDIRS is a large-scale ECG dataset with 156,145 QRS onset annotations and 156,145 T peak annotations. ECGVEDNET is a novel variational encoder-decoder network designed to address morphology variations. In ECGVEDNET, we construct a well-regularized latent space, in which the latent features of ECG follow a regular distribution and present smaller morphology variations than in the raw data space. Finally, a transfer learning framework is proposed to transfer the knowledge learned on ICDIRS to smaller datasets. On ICDIRS, ECGVEDNET achieves accuracy of 86.28%/88.31% within 5/10 ms tolerance for QRS onset and accuracy of 89.94%/91.16% within 5/10 ms tolerance for T peak. On QTDB, the average time errors computed for QRS onset and T peak are -1.86 ± 8.02 ms and -0.50 ± 12.96 ms, respectively, achieving state-of-the-art performances on both large and small-scale datasets. We will release the source code and the pre-trained model on ICDIRS once accepted.

Iatrogenic pacemaker-induced ventricular arrhythmia: a case report.

Background: Minimizing right ventricular (RV) pacing to reduce the progression of heart failure is an established practice. Proprietary algorithms to reduce unnecessary RV pacing have been incorporated into both simple and complex cardiac pacemaker devices, for reducing the possibility of heart failure and arrhythmias. Case summary: We present a case of a 43-year-old male implanted with a dual-chamber primary prevention implantable cardioverter-defibrillator (AUTOGEN EL, Boston Scientific) for sudden cardiac death. At the time of implant, the patient had hypertrophic cardiomyopathy with mild left ventricular (LV) systolic impairment, and sinus rhythm with intact atrioventricular (AV) conduction. The patient developed progression of his disease with symptoms (dyspnoea) and LV impairment. This led to a decision to activate the minimal RV pacing algorithm (RYTHMIQ™). A deterioration in AV conduction caused intrinsic ventricular beats to fall in the atrial blanking period, and subsequent VVI backup pacing resulted in R on T pacing. This induced ventricular arrhythmia. RYTHMIQ™ was subsequently deactivated, and the patient has had no further device-induced arrhythmias. Discussion: Numerous studies have demonstrated the adverse effect of RV pacing on LV function. Minimizing RV pacing is, therefore, encouraged in individuals with intact AV conduction. However, underlying conduction abnormalities must be assessed prior to activating algorithms designed to minimize RV pacing. This case demonstrates the importance of careful intracardiac electrogram interpretation and individual case-based device programming, to avoid device-induced complications.

Non-invasive markers for sudden cardiac death risk stratification in dilated cardiomyopathy.

Dilated cardiomyopathy (DCM) is a common yet challenging cardiac disease. Great strides have been made in improving DCM prognosis due to heart failure but sudden cardiac death (SCD) due to ventricular arrhythmias remains significant and challenging to predict. High-risk patients can be effectively managed with implantable cardioverter defibrillators (ICDs) but because identification of what is high risk is very limited, many patients unnecessarily experience the morbidity associated with an ICD implant and many others are not identified and have preventable mortality. Current guidelines recommend use of left ventricular ejection fraction and New York Heart Association class as the main markers of risk stratification to identify patients who would be at higher risk of SCD. However, when analysing the data from the trials that these recommendations are based on, the number of patients in whom an ICD delivers appropriate therapy is modest. In order to improve the effectiveness of therapy with an ICD, the patients who are most likely to benefit need to be identified. This review article presents the evidence behind current guideline-directed SCD risk markers and then explores new potential imaging, electrophysiological and genetic risk markers for SCD in DCM.

Rationale and study design of the MINERVA study: Multicentre Investigation of Novel Electrocardiogram Risk markers in Ventricular Arrhythmia prediction-UK multicentre collaboration.

INTRODUCTION: The purpose of this study is to assess the ability of two new ECG markers (Regional Repolarisation Instability Index (R2I2) and Peak Electrical Restitution Slope) to predict sudden cardiac death (SCD) or ventricular arrhythmia (VA) events in patients with ischaemic cardiomyopathy undergoing implantation of an implantable cardioverter defibrillator for primary prevention indication. METHODS AND ANALYSIS: Multicentre Investigation of Novel Electrocardiogram Risk markers in Ventricular Arrhythmia prediction is a prospective, open label, single blinded, multicentre observational study to establish the efficacy of two ECG biomarkers in predicting VA risk. 440 participants with ischaemic cardiomyopathy undergoing routine first time implantable cardioverter-defibrillator (ICD) implantation for primary prevention indication are currently being recruited. An electrophysiological (EP) study is performed using a non-invasive programmed electrical stimulation protocol via the implanted device. All participants will undergo the EP study hence no randomisation is required. Participants will be followed up over a minimum of 18 months and up to 3 years. The first patient was recruited in August 2016 and the study will be completed at the final participant follow-up visit. The primary endpoint is ventricular fibrillation or sustained ventricular tachycardia >200 beats/min as recorded by the ICD. The secondary endpoint is SCD. Analysis of the ECG data obtained during the EP study will be performed by the core lab where blinding of patient health status and endpoints will be maintained. ETHICS AND DISSEMINATION: Ethical approval has been granted by Research Ethics Committees Northern Ireland (reference no. 16/NI/0069). The results will inform the design of a definitive Randomised Controlled Trial (RCT). Dissemination will include peer reviewed journal articles reporting the qualitative and quantitative results, as well as presentations at conferences and lay summaries. TRIAL REGISTRATION NUMBER: NCT03022487.

Regional fractionation and dominant frequency in persistent atrial fibrillation: effects of left atrial ablation and evidence of spatial relationship.

AIMS: The aim was to study regional fractionation and dominant frequency (DF) to determine if any relationship exists between the two parameters and also to assess the impact of limited left atrial ablation. METHODS AND RESULTS: Patients undergoing catheter ablation of persistent AF using three-dimensional navigation were studied. Regional left atrial electrograms were analysed in the frequency domain by assessing DF and organization index (OI), and for degree of fractionation [using complex fractionated electrograms (CFE)-mean] before and after circumferential pulmonary vein and left atrial roof ablation. Twenty-three patients with persistent AF were studied. After ablation, global CFE-mean increased [100 ± 5 to 147 ± 11 ms (P= 0.0003)], DF decreased [6.1 ± 0.2 to 5.3 ± 0.2 Hz (P= 0.0003)], and OI was unchanged [0.27 ± 0.01 to 0.26 ± 0.02, (P= 0.70)]. Comparing sites close to and distant from ablation lines, percentage change in CFE-mean was 94 ± 10 vs. 37 ± 6% (P< 0.0001), DF change was -13 ± 3 vs.-12 ± 2% (P= 0.98), and OI change was 3 ± 6 vs. 10 ± 5% (P= 0.75), respectively. There was modest correlation between CFE-mean and DF points prior to ablation (r = -0.33, P< 0.0001) which was reduced following left atrial ablation (r = -0.24, P= 0.005). CONCLUSIONS: Left atrial ablation reduces global left atrial DF and decreases the degree of fractionation. Complex fractionated electrograms-mean and DF appear to share only modest spatial correlation and are affected to different extents by ablation, suggesting that they are either separate entities or reflect different components of the same substrate.