Providing reliable detection of QRS complexes is key in automated analyses of electrocardiograms (ECG). Accurate and timely R-peak detections provide a basis for ECG-based diagnoses and to synchronize radiologic, electrophysiologic, or other medical devices. Compared with classical algorithms, deep learning (DL) architectures have demonstrated superior accuracy and high generalization capacity. Furthermore, they can be embedded on edge devices for real-time inference. 3D vectorcardiograms (VCG) provide a unifying framework for detecting R-peaks regardless of the acquisition strategy or number of ECG leads. In this article, a DL architecture was demonstrated to provide enhanced precision when trained and applied on 3D VCG, with no pre-processing nor post-processing steps. Experiments were conducted on four different public databases. Using the proposed approach, high F1-scores of 99.80% and 99.64% were achieved in leave-one-out cross-validation and cross-database validation protocols, respectively. False detections, measured by a precision of 99.88% or more, were significantly reduced compared with recent state-of-the-art methods tested on the same databases, without penalty in the number of missed peaks, measured by a recall of 99.39% or more. This approach can provide new applications for devices where precision, or positive predictive value, is essential, for instance cardiac magnetic resonance imaging.

Recently, deep learning (DL) models have been increasingly adopted for automatic analyses of medical data, including electrocardiograms (ECGs). Large, available ECG datasets, generally of high quality, often lack specific distortions, which could be helpful for enhancing DL-based algorithms. Synthetic ECG datasets could overcome this limitation. A generative adversarial network (GAN) was used to synthesize realistic 3D magnetohydrodynamic (MHD) distortion templates, as observed during magnetic resonance imaging (MRI), and then added to available ECG recordings to produce an augmented dataset. Similarity metrics, as well as the accuracy of a DL-based R-peak detector trained with and without data augmentation, were used to evaluate the effectiveness of the synthesized data. Three-dimensional MHD distortions produced by the proposed GAN were similar to the measured ones used as input. The precision of a DL-based R-peak detector, tested on actual unseen data, was significantly enhanced by data augmentation; its recall was higher when trained with augmented data. Using synthesized MHD-distorted ECGs significantly improves the accuracy of a DL-based R-peak detector, with a good generalization capacity. This provides a simple and effective alternative to collecting new patient data. DL-based algorithms for ECG analyses can suffer from bias or gaps in training datasets. Using a GAN to synthesize new data, as well as metrics to evaluate its performance, can overcome the scarcity issue of data availability.

Background: Ventricular arrhythmias (VAs) represent a serious complication of myocardial infarction (MI). Incidence rate of VAs and sudden cardiac death is commonly reported to be lower in women than in men after MI (1,2). While data regarding SCD and VAs after MI in patients with implantable cardioverter defibrillator (ICD) are well described, data regarding the incidence of readmissions for VA in patients without ICD implantation criteria after a first MI are scarce, as well as the impact of sex on their occurrence. Objective: This study aims to investigate the impact of sex on VA occurrences in post-MI patients without ICD implantation criteria. Methods: This study was conducted using the French national health data system using electronic codes for procedures (CCAM) and hospitalizations data (PMSI). The study population consisted of patients discharged after a first MI and without criteria for ICD implantation. Results: Between January 2014 and January 2015, 137,736 patients were hospitalized in France with a diagnosis of first MI and were followed using CCAM and PMSI codes. Among the 112,465 alive at discharge, 6838 patients were excluded due to criteria for the implantation of an ICD for primary or secondary prevention. Of the remaining 105,629 patients, 1600 (1.51%) were rehospitalized for VA with a median delay of 505 days (IQR 110-1208). Men had almost twice the risk of VA than women after initial discharge for MI (OR 1.88, 95% CI 1.65-2.14; p<0.0001). Among the 72,103 men included, 1240 (1.72%) were rehospitalized for VA with a median delay of 514 days (IQR 107-1212). Factors independently associated with VA in men were previous atrial fibrillation (OR 1.91, 95% CI 1.66 - 2.21, p<0.0001), previous vascular disease (OR 1.28, 95% CI 1.10 - 1.50, p=0.002), absence of coronary angioplasty (OR 1.28, 95% CI 1.10 - 1.50, p=0.002), previous diabetes (OR 1.19, 95% CI 1.04 - 1.36, p=0.012), previous hypertension (OR 1.19, 95% CI 1.05 - 1.34, p=0.007), previous or in-hospital congestive heart failure (OR 1.47, 95% CI 1.03-2.08, p=0.032 and OR 1.65, 95% CI 1.32-2.07, p<0.0001), and age (patients between 60 and 79 yo being at the higher risk of VA compared to 80yo patients, p=0.002 and <0.0001 respectively). Among the 33,526 women included, 360 (1.07%) were rehospitalized for VA with a median (IQR) delay of 461 days (116-1159) after MI. Factors independently associated with VA were previous atrial fibrillation (OR 1.68, 95% CI 1.30 - 2.18, p80yo patients, p=0.001). Conclusion: The risk of readmission for VAs after a first MI is significantly lower in women compared to men, with distinct predictive factors. These findings suggest that sex-specific VA risk stratification and management strategies may be warranted after an initial MI.Sexe influence on post-MI VAs occurence