Search

Background Brugada syndrome (BrS) has been associated with sudden cardiac death in otherwise healthy subjects, and drug‐induced BrS accounts for 55% to 70% of all patients with BrS. This study aims to develop a deep convolutional neural network and evaluate its performance in recognizing and predicting BrS diagnosis. Methods and Results Consecutive patients who underwent ajmaline testing for BrS following a standardized protocol were included. ECG tracings from baseline and during ajmaline were transformed using wavelet analysis and a deep convolutional neural network was separately trained to (1) recognize and (2) predict BrS type I pattern. The resultant networks are referred to as BrS‐Net. A total of 1188 patients were included, of which 361 (30.3%) patients developed BrS type I pattern during ajmaline infusion. When trained and evaluated on ECG tracings during ajmaline, BrS‐Net recognized a BrS type I pattern with an AUC‐ROC of 0.945 (0.921–0.969) and an AUC‐PR of 0.892 (0.815–0.939). When trained and evaluated on ECG tracings at baseline, BrS‐Net predicted a BrS type I pattern during ajmaline with an AUC‐ROC of 0.805 (0.845–0.736) and an AUC‐PR of 0.605 (0.460–0.664). Conclusions BrS‐Net, a deep convolutional neural network, can identify BrS type I pattern with high performance. BrS‐Net can predict from baseline ECG the development of a BrS type I pattern after ajmaline with good performance in an unselected population.

Background: Brugada syndrome (BrS) has been associated with sudden cardiac death in otherwise healthy subjects, and drug-induced BrS accounts for 55% to 70% of all patients with BrS. This study aims to develop a deep convolutional neural network and evaluate its performance in recognizing and predicting BrS diagnosis., Methods and Results: Consecutive patients who underwent ajmaline testing for BrS following a standardized protocol were included. ECG tracings from baseline and during ajmaline were transformed using wavelet analysis and a deep convolutional neural network was separately trained to (1) recognize and (2) predict BrS type I pattern. The resultant networks are referred to as BrS-Net. A total of 1188 patients were included, of which 361 (30.3%) patients developed BrS type I pattern during ajmaline infusion. When trained and evaluated on ECG tracings during ajmaline, BrS-Net recognized a BrS type I pattern with an AUC-ROC of 0.945 (0.921-0.969) and an AUC-PR of 0.892 (0.815-0.939). When trained and evaluated on ECG tracings at baseline, BrS-Net predicted a BrS type I pattern during ajmaline with an AUC-ROC of 0.805 (0.845-0.736) and an AUC-PR of 0.605 (0.460-0.664)., Conclusions: BrS-Net, a deep convolutional neural network, can identify BrS type I pattern with high performance. BrS-Net can predict from baseline ECG the development of a BrS type I pattern after ajmaline with good performance in an unselected population.

Introduction: The clinical utility of inferolateral early repolarisation (ER) and late potentials (LP) in children with Brugada Syndrome (BrS) has not been previously evaluated. The aim of this study was to determine the prevalence of electrocardiographic (ECG) abnormalities in children with BrS, and to investigate their relationship with clinical outcomes.Methods: 43 patients with BrS and 47 controls aged ≤18 undergoing systematic clinical and ECG evaluation, including signal-averaged ECG (SAECG) and pharmacological provocation testing, between 2003 and 2019 were included.Results: Four patients with BrS (9%) presented with a spontaneous type 1 Brugada pattern; the remaining 39 (91%) were diagnosed following ajmaline provocation testing. Twelve BrS patients (28%) had late potentials (LP) on SAECG compared to 1 (2%) in controls (p = 0.001). LP were more common in 5 patients with a high-risk phenotype (60% vs 24%) but this was not statistically significant. Twelve patients with BrS (28%) had inferolateral early repolarisation (ER) and 2 (5%) had fractionated QRS (f-QRS), but there were no statistically-significant differences with controls in these parameters. A significant arrhythmia (non-sustained ventricular tachycardia or atrial fibrillation) was seen in 4 patients (9%).Conclusions: This study shows a high prevalence of SAECG abnormalities in children with BrS compared with controls, but this was not significantly associated with a high-risk phenotype. [ABSTRACT FROM AUTHOR]

An association between arrhythmogenic right ventricular dysplasia–cardiomyopathy (ARVD/C) and Brugada syndrome can be supposed according to several case reports.In order to examine a possible link between ARVD/C and Brugada syndrome, systematic ajmaline testing with 1 mg/kg body weight intravenously, was done in 55 patients (32 males, mean age 46.7±12.3 years) with ISFC/ESC criteria of ARVD/C. In nine patients ajmaline testing could demonstrate coved ST segment elevation of at least 2 mm in at least two right precordial leads. Three of these patients had recurrent syncopes. Electrophysiological study revealed non-sustained ventricular tachycardia with left bundle branch block configuration and inferior axis in only one case. Systematic ajmaline testing could demonstrate a definite link between ARVD/C and Brugada syndrome. [Copyright &y& Elsevier]