Ultrasound-guided versus fluoroscopy-guided axillary vein puncture for cardiac implantable electronic device implantation: a meta-analysis enrolling 1257 patients.

INTRODUCTION: Ultrasound-guided (Echo-AVP) and Fluoroscopy-guided Axillary Vein Puncture (Fluoro-AVP) are both acknowledged as safe and effective techniques for transvenous implantation of leads for cardiac implantable electronic devices (CIEDs). Nonetheless, it is still debated which of the two techniques has a better safety and efficacy profile. Therefore, we performed a meta-analysis to evaluate the efficacy and safety of Echo-AVP versus Fluoro-AVP for CIEDs implantation. METHODS: We systematically searched Medline, Embase and Cochrane electronic databases up to May 15th, 2024, for studies that evaluated the efficacy and safety of Echo-AVP and Fluoro-AVP reporting at least one clinical outcome of interest. The primary efficacy endpoint was acute procedural success and the primary safety endpoint was a composite endpoint of pneumothorax, pocket hematoma/bleeding, pocket infection and inadvertent arterial puncture. The effect size was estimated using a random-effect model as Odds Ratio (OR) and Mean Difference (MD) with relative 95% Confidence Interval (CI). RESULTS: Overall, 4 studies were included, which enrolled 1257 patients (Echo-AVP: 373 patients; Fluoro-AVP: 884 patients). Echo-AVP led to a significant reduction in the primary safety endpoint (OR: 0.41; p = 0.0009), risk of inadvertent arterial puncture (OR: 0.29; p = 0.003) and fluoroscopy time ( MD: -105.02; p = 0.008). No differences were found between Echo-AVP and Fluoro-AVP for acute procedural success (OR: 0.77; p = 0.27), pneumothorax (OR: 0.66; p = 0.60), pocket hematoma/bleeding (OR: 0.68; p = 0.30), pocket infection (OR: 0.66; p = 0.60), procedural time (MD: 1.99; p = 0.65), success rate at first attempt (OR: 1.25; p = 0.34) and venous access time (MD: -0. 25; p = 0.99). CONCLUSION: Echo-AVP proved to reduce significantly the primary safety endpoint, inadvertent arterial puncture and fluoroscopy time compared to Fluoro-AVP.

Multielectrode catheter-based pulsed field ablation of persistent and long-standing persistent atrial fibrillation.

AIMS: Rhythm control of non-paroxysmal atrial fibrillation (AF) is significantly more challenging, as a result of arrhythmia perpetuation promoting atrial substrate changes and AF maintenance. We describe a tailored ablation strategy targeting multiple left atrial (LA) sites via a pentaspline pulsed field ablation (PFA) catheter in persistent AF sustained beyond 6 months (PerAF > 6 m) and long-standing persistent AF (LSPAF). METHODS AND RESULTS: The ablation protocol included the following stages: pulmonary vein antral and posterior wall isolation plus anterior roof line ablation (Stage 1); electrogram-guided substrate ablation (Stage 2); atrial tachyarrhythmia regionalization and ablation (Stage 3). Seventy-two [age:68 ± 10years, 61.1%males; AF history: 25 (18-45) months] patients with PerAF > 6 m (52.8%) and LSPAF (47.2%) underwent their first PFA via the FarapulseTM system. LA substrate ablation (Stage 1 and 2) led to AF termination in 95.8% of patients. AF organized into a left-sided atrial flutter (AFlu) in 46 (74.2%) patients. The PFA catheter was used to identify LA sites showing diastolic, low-voltage electrograms and entrainment from its splines was performed to confirm the pacing site was inside the AFlu circuit. Left AFlu termination was achieved in all cases via PFA delivery. Total procedural and LA dwell times were 112 ± 25 min and 59 ± 22 min, respectively. Major complications occurred in 2 (2.8%) patients. Single-procedure success rate was 74.6% after 14.9 ± 2.7 months of follow-up; AF-free survival was 89.2%. CONCLUSION: In our cohort, PFA-based AF substrate ablation led to AF termination in 95.8% of cases. Very favourable clinical outcomes were observed during >1 year of follow-up.

Focal Pulsed Field Ablation for Premature Ventricular Contractions: A Multicenter Experience.

BACKGROUND: Pulsed field ablation (PFA) is a novel technology for catheter-based atrial arrhythmia treatment. Evidence of its application for ventricular arrhythmia ablation is still limited. In this study, we describe the feasibility and efficacy of focal PFA for premature ventricular contraction (PVC) ablation. METHODS: A prospective cohort of 20 patients referred for PVC ablation at 2 centers was enrolled, regardless of the presence of structural heart disease, PVC morphology, or previous ablation attempts. All procedures were performed using the CENTAURI System in combination with contact force sensing catheters and 3-dimensional electroanatomical mapping systems. Energy output and the number of applications were left to the operator's discretion. RESULTS: Eleven (55%) procedures were conducted under general anesthesia, 6 (30%) under deep sedation, and 3 (15%) under light sedation. Muscular contraction was observed in one case (5%). Median procedural and fluoroscopy times were 95.5 and 6.55 minutes, respectively. The median number of PFA applications was 8 with a median contact force of 10g. A statistically significant (76%) reduction was observed in mean peak-to-peak bipolar electrogram voltage before and after ablation (0.707 versus 0.098 mV; P=0.008). Ventricular irritative firing was observed in 11 (55%) patients after PFA. The median follow-up was 120 days. Acute procedural success was achieved in 17 of 20 (85% [95% CI, 0.70-1]) patients. Two of the patients with procedural failure had late success with >80% clinical PVC burden suppression during follow-up, and 2 of 17 patients with acute success had late PVC recurrence, which accounts for a total of 17 of 20 (85% [95% CI, 0.70-1]) patients with chronic success. Transient ST-segment depression occurred in 1 patient, and the right bundle branch block was induced in 2 others (permanently only in one case). CONCLUSIONS: PVC ablation using a focal PFA is feasible, effective, and safe, with promising acute and long-term results in several ventricular locations. Irritative firing is frequently observed. Coronary evaluation should be considered when targeting the outflow tract.

Enhancing origin prediction: deep learning model for diagnosing premature ventricular contractions with dual-rhythm analysis focused on cardiac rotation.

AIMS: Several algorithms can differentiate inferior axis premature ventricular contractions (PVCs) originating from the right side and left side on 12-lead electrocardiograms (ECGs). However, it is unclear whether distinguishing the origin should rely solely on PVC or incorporate sinus rhythm (SR). We compared the dual-rhythm model (incorporating both SR and PVC) to the PVC model (using PVC alone) and quantified the contribution of each ECG lead in predicting the PVC origin for each cardiac rotation. METHODS AND RESULTS: This multicentre study enrolled 593 patients from 11 centres-493 from Japan and Germany, and 100 from Belgium, which were used as the external validation data set. Using a hybrid approach combining a Resnet50-based convolutional neural network and a transformer model, we developed two variants-the PVC and dual-rhythm models-to predict PVC origin. In the external validation data set, the dual-rhythm model outperformed the PVC model in accuracy (0.84 vs. 0.74, respectively; P < 0.01), precision (0.73 vs. 0.55, respectively; P < 0.01), specificity (0.87 vs. 0.68, respectively; P < 0.01), area under the receiver operating characteristic curve (0.91 vs. 0.86, respectively; P = 0.03), and F1-score (0.77 vs. 0.68, respectively; P = 0.03). The contributions to PVC origin prediction were 77.3% for PVC and 22.7% for the SR. However, in patients with counterclockwise rotation, SR had a greater contribution in predicting the origin of right-sided PVC. CONCLUSION: Our deep learning-based model, incorporating both PVC and SR morphologies, resulted in a higher prediction accuracy for PVC origin, considering SR is particularly important for predicting right-sided origin in patients with counterclockwise rotation.

Shortened radiofrequency delivery time to optimize efficiency and safety of pulmonary vein isolation with the radiofrequency balloon: insights from the COLLABORATE registry.

AIMS: Previous clinical studies on pulmonary vein isolation (PVI) with a radiofrequency balloon (RFB) reported safe and effective procedures using conventional ablation settings with 20/60 s RF delivery via posterior/anterior (PST/ANT) electrodes. The latest evidence suggests that reducing the application time to 15 s (s) on the posterior wall when facing the oesophageal region is as effective as applying 20 s. To prospectively assess whether reducing RF time on PST/ANT segments to 15/45 s can ensure sufficient quality of lesion metrics and compare the new shortened ablation settings with the conventional one in terms of safety, and effectiveness at 1-year. METHODS AND RESULTS: A total of 641 patients from seven European centres were enrolled in a collaborative registry, with 374 in the conventional RF delivery group and 267 in the shortened RF delivery group. Procedural outcomes, lesion metrics, and safety profiles were assessed and compared between the groups. Freedom of any atrial tachycarrythmias at one year was 85.4% and 88.2% in the SHRT and CONV groups, respectively. The shortened RF delivery strategy was associated with significantly shorter procedure times (median 63.5 vs. 96.5 min, P < 0.001) and shortened fluoroscopy exposure (median 10.0 vs. 14.0 min, P < 0.001) compared to conventional delivery. Efficacy metrics, including first-pass isolation rates and time to isolation, were comparable between groups. Shortened RF delivery was associated with a lower incidence of procedural complications (1.4% vs. 5.3%, P = 0.04) and optimized thermal characteristics. CONCLUSION: Analyses from the COLLABORATE registry demonstrate that shortening RF energy delivery times to 15/45 s (PST/ANT) during PVI with the RFB resulted in comparable freedom from recurrent atrial tachyarrhythmia compared to conventional delivery times with comparable efficiency and safety.

Atrial fibrillation burden: Stepping beyond the categorical characterization.

Traditional classifications categorize atrial fibrillation (AF) into paroxysmal, persistent, or permanent, but recent advancements in monitoring have revealed AF as a continuous variable, challenging existing paradigms. AF burden, defined basically as the amount of time spent in AF during a monitored period, has emerged as a crucial metric. This review assesses the evolving landscape of AF burden and its measurement methods, diagnostic modalities, and impact on outcomes. Guidelines suggest individualized approaches, combining AF burden with clinical scores (CHA2DS2-VASc), but studies have challenged this. Addressing the impact of AF burden on patients' quality of life before or after ablation is also crucial. Although continuous monitoring technologies offer promising avenues, the field faces challenges, such as defining clinically relevant thresholds. Future research should focus on refining these, designing trials centered around AF burden, and evaluating the efficacy of interventions in reducing AF burden, ultimately paving the way for personalized management strategies.

Distance-dependent neuromodulation effect during thermal ablation for atrial fibrillation.

INTRODUCTION: Thermal atrial fibrillation (AF) ablation exerts an additive treatment effect on the cardiac autonomic nervous system (CANS). This effect is mainly reported during ablation of the right superior pulmonary vein (RSPV), modulating the right anterior ganglionated plexus (RAGP), which contains parasympathetic innervation to the sinoatrial node in the epicardial fat pad between RSPV and superior vena cava (SVC). However, a variable response to neuromodulation after ablation is observed, with little to no effect in some patients. Our objective was to assess clinical and anatomic predictors of thermal ablation-induced CANS changes, as assessed via variations in heart rate (HR) postablation. METHODS: Consecutive paroxysmal AF patients undergoing first-time PV isolation by the cryoballoon (CB) or radiofrequency balloon (RFB) within a 12-month time frame and with preprocedural cardiac computed tomography (CT), were evaluated. Preablation and 24-h postablation electrocardiograms in sinus rhythm were collected and analyzed to assess HR. Anatomic evaluation by CT included the measurement of the shortest distance between the SVC and RSPV ostium (RSPV-SVC distance). RESULTS: A total of 97 patients (CB, n = 50 vs. RFB, n = 47) were included, with similar baseline characteristics between both groups. A significant HR increase postablation (ΔHR ≥ 15 bpm) occurred in a total of 37 patients (38.1%), without difference in number of patients between both thermal ablation technologies (CB, 19 [51%]), RFB, 18 [49%]). Independent predictors for increased HR were RSPV-SVC distance (odds ratio [OR]: 0.49, CI: 0.34-0.71, p value < .001), and age (OR: 0.94, CI: 0.89-0.98, p value = .003). CONCLUSIONS: Thermal balloon-based PV isolation influences the CANS through its effect on the RAGP, especially in younger patients and patients with shorter RSPV-SVC distance.

Continuous Rhythm Monitoring With Implanted Loop Recorders in Children and Adolescents With Brugada Syndrome.

BACKGROUND: Young (<18 years of age) patients with Brugada syndrome (BrS) are often under-represented in BrS studies and their management, especially related to syncopal episodes, remains unclear. OBJECTIVES: This study sought to describe the arrhythmia prevalence among young patients with BrS undergoing continuous rhythm monitoring by implantable loop recorder (ILR) and to assess the etiology behind syncope of undetermined origin. METHODS: A total of 147 patients with BrS with ILR were enrolled in 12 international centers and divided into pediatric (age <12 years; n = 77, 52%) and adolescents (age 13-18 years; n = 70, 48%). RESULTS: Mean age was 11.3 years, 53 patients (36.1%) were female, and 31 (21.1%) had spontaneous type 1 electrocardiograms. Over a median follow-up of 3.6 years (Q1-Q3: 1.6-4.8 years), an arrhythmic event was recorded in 33 patients (22.4%), mainly of nonventricular origin: 15 atrial (10.2%) and 16 bradyarrhythmic events (10.9%). Ventricular arrhythmias occurred in 4 patients, all with spontaneous BrS, and were fever-related in one-half. Among all patients with recurrence of syncope during follow-up, true arrhythmic syncope was documented in 5 (17.8%), and it was due to bradyarrhythmias or atrial arrhythmias in 3 cases (60%). CONCLUSIONS: Continuous rhythm monitoring with ILRs in young patients with BrS detects a broad range of arrhythmias. Ventricular arrhythmias occur predominantly in patients with spontaneous type 1 electrocardiograms and during fever. Despite the young age, bradyarrhythmias and atrial arrhythmias are frequent and represent the cause of arrhythmic syncope in 60% of patients. Young patients with BrS with syncope of undetermined origin may benefit from ILR implant.

Characterization and Clinical Significance of Hemolysis After Pulsed Field Ablation for Atrial Fibrillation: Results of a Multicenter Analysis.

BACKGROUND: Pulsed field ablation (PFA) is increasingly used in clinical practice for the treatment of atrial fibrillation. While the susceptibility of erythrocytes to electroporation is well established, the effect of cardiac PFA technologies on hemolysis has remained underreported. The aim of this study was to investigate the incidence, severity, and clinical impact of PFA-induced hemolysis. METHODS: We included n=145 patients undergoing atrial fibrillation catheter ablation with a pentaspline PFA catheter (biphasic, bipolar pulses of 2 kV) and n=70 patients receiving radiofrequency ablation (40-90 W) at 4 high-volume European centers. The lesion set comprised pulmonary vein isolation for paroxysmal atrial fibrillation and pulmonary vein isolation±additional lesions for persistent atrial fibrillation. Hemolysis and renal function biomarkers were analyzed in blood samples at baseline, at the end of ablation, and 24 hours after the procedure. RESULTS: Baseline characteristics were well balanced between groups (overall mean 65.7±9.4 years; 69.3% men). The ablation procedures comprised a mean of 61.6±27.4 PFA deliveries and 26.3±15.0 minutes RF duration. Hemolysis was detected in 94.3% versus 6.8% of patients after PFA versus radiofrequency ablation (P<0.001): PFA was associated with significantly lower haptoglobin levels (0.5±0.4 versus 1.0±0.4 g/L), while free plasma hemoglobin (592.8±330.6 versus 147.8±183.0 mg/L), bilirubin (21.3±11.3 versus 14.8±8.8 µmol/L), and LDH (lactate dehydrogenase, 352.7±115.7 versus 253.2±56.5 U/L) were significantly higher after PFA compared with radiofrequency ablation (all P<0.001). Hemolysis correlated with the number of PFA deliveries (r=0.62 [95% CI, 0.33-0.80]; P<0.001), with the highest severity occurring ≥54 PFA deliveries. After PFA, hemoglobinuria occurred in 36.4%, while creatinine increase was higher in patients with baseline glomerular filtration rate <50 mL/min than with baseline glomerular filtration rate >50 mL/min (Δcrea, 27.0±103.1 versus -0.2±12.1 µmol/L; P=0.010). CONCLUSIONS: Intravascular hemolysis is a frequent finding after PFA and increases with the number of PFA deliveries. Until the clinical impact of PFA-associated hemolysis is fully elucidated, a careful titration of PFA deliveries during the ablation procedure is warranted.

Compliance with Guideline-Directed Medical Therapy and Early Implantable Cardioverter-Defibrillator Activation in Heart Failure: A Retrospective Study.

Background: This study was conducted to evaluate compliance with guideline-directed optimal medical therapy (OMT) and its association with early implantable cardioverter-defibrillator (ICD) activation in patients with heart failure and reduced ejection fraction (HFrEF). Methods: Retrospective data from 307 patients who underwent ICD implantation for primary prevention from 2011 to 2017 were collected and analyzed. Results: Among the study participants, only 23.8% received the maximum tolerated dose of OMT prior to ICD implantation, with 59.0% receiving all three OMT medication groups. No significant difference in OMT compliance was found between patients with ischemic cardiomyopathy (ICM) and those with non-ischemic dilated cardiomyopathy (DCM). However, DCM patients received ICDs more frequently at the time of diagnosis than ICM patients (13.8% vs. 0.7%). Early ICD activation (within 3 months) occurred in only one patient who had not received appropriate OMT, representing 0.7% of all ICM patients. Furthermore, early activation was also infrequent in patients who received OMT (2.9% of ICM patients and 2.6% of DCM patients). Echocardiography follow-up data revealed that 20.4% of ICM patients and 29.8% of DCM patients who did not receive OMT before ICD implantation showed improvement in the left ventricular ejection fraction (EF) to 35% or more. Conclusions: This study found suboptimal compliance with OMT prior to ICD implantation in HFrEF patients. The results showed that early ICD activation was rare in all patient groups, especially those who did not receive the prescribed 3 months of OMT. More research is needed to investigate longer waiting periods for the evaluation of potential EF improvement, and to better evaluate the eligibility of HFrEF patients for ICD. The current findings have potential implications for clinical practice and patient outcomes.

Systematic review and meta-analysis of left atrial appendage closure's influence on early and long-term mortality and stroke.

Objective: Left atrial appendage closure (LAAC) concomitant to heart surgery in patients with underlying atrial fibrillation (AF) has gained attention because of long-term reduction of thromboembolic complications. As of mortality benefits in the setting of non-AF, data from both observational studies and randomized controlled trials are conflicting. Methods: On-line databases were screened for studies comparing LAAC versus no LAAC concomitant to other heart surgery. End points assessed were all-cause mortality and stroke at early and longest-available follow-up. Subgroup analyses stratified on preoperative AF were performed. Risk ratios (RR) with 95% CIs served as primary statistics. Results: Electronic search yielded 25 studies (N = 660 [158 patients]). There was no difference between LAAC and no LAAC in terms of early mortality. In the overall population analysis, LAAC reduced long-term mortality (RR, 0.86; 95% CI, 0.74-1.00; P = .05; I 2 = 88%), reduced early stroke risk by 19% (RR, 0.81; 95% CI, 0.72-0.93; P = .002; I 2 = 57%), and reduced late stroke risk by 13% (RR, 0.87; 95% CI, 0.84-0.90; P < .001; I 2 = 58%). Subgroup analysis showed lower mortality (RR, 0.85; 95% CI, 0.72-1.01; P = .06; I 2 = 91%), short-, and long-term stroke risk reduction only in patients with preoperative AF (RR, 0.81; 95% CI, 0.71-0.93; P = .003; I 2 = 71% and RR, 0.87; 95% CI, 0.84-0.91; P < .001; I 2 = 70%, respectively). No benefit of LAAC in patients without AF was found. Conclusions: Concomitant LAAC was associated with reduced stroke rates at early and long-term and possibly reduced all-cause mortality at the long-term follow-up but the benefits were limited to patients with preoperative AF. There is not enough evidence to support routine concomitant LAAC in non-AF settings.

Leadless pacemakers in patients with different stages of chronic kidney disease: Real-world data from the updated i-LEAPER registry.

BACKGROUND: Limited data are available on leadless pacemaker (LPM) outcomes according to different stages of chronic kidney disease (CKD). OBJECTIVE: The purpose of this study was to investigate differences in the safety and efficacy of LPMs among patients stratified per different stages of renal function. METHODS: Consecutive patients enrolled in the multicenter international i-LEAPER registry (International LEAdless PacemakEr Registry) were analyzed. Patients were divided into 3 groups according to CKD stage. The primary end point was the comparison of LPM-related major complication rate at implantation and during follow-up. Differences in electrical performance were deemed secondary outcomes. RESULTS: Of the 1748 patients enrolled, 33% were in CKD stage G3a/G3b and 9.4% were in CKD stage G4/G5. Patients with CKD presented cardiovascular comorbidities more frequently. During a median follow-up of 39 months (interquartile range [IQR] 18-59 months), major complication rate did not differ between groups (normal kidney function [NKF] group 1.8% vs CKD stage G3a/G3b group 2.9% vs CKD stage G4/G5 group 2.4%; P = .418). All-cause mortality resulted higher in the CKD stage G4/G5 group than in the NKF group (19.5% vs 9.8%; adjusted hazard ratio 1.9; 95% confidence interval 1.25-2.89; P = .003). LPM electrical performance was comparable between groups, except for patients with CKD who showed a slightly higher pacing threshold during 1-month follow-up (NKF group 0.50 V [IQR 0.35-0.70 V] vs G3a/G3b group 0.56 V [IQR 0.38-0.81 V] vs G4/G5 group 0.51 V [0.38-0.84 V] @ 0.24 ms; P < .001). CONCLUSION: In a real-world setting, patients with advanced CKD who underwent LPM implantation were underrepresented. Although all-cause mortality was higher in end-stage CKD, periprocedural complications and LPM performance were overall comparable between NKF and different stages of CKD, except for higher values of pacing threshold in patients with CKD up to first-month follow-up.

Catheter ablation as an adjunctive therapy to ICD implantation in Brugada syndrome.

BACKGROUND: Brugada Syndrome (BrS) is a life-threatening cardiac arrhythmia disorder associated with an increased risk ventricular arrhythmias (VAs) and sudden cardiac death (SCD). Current management primarily relies on implantable cardioverter-defibrillators (ICDs), but patients may experience ICD shocks. Catheter ablation (CA) has emerged as a potential intervention to target the arrhythmogenic substrate. This systematic review aims to evaluate the safety and efficacy of catheter ablation in BrS patients. METHODS AND RESULTS: Studies with BrS patients undergoing catheter ablation for VAs were included. 14 studies that involved a total population of 709 BrS patients, with catheter ablation performed in 528 of them, were included. Catheter ablation resulted in non-inducibility of VAs in 91% (95% CI: 83-99, I2 = 76%) and resolution of Type 1 ECG Brugada pattern in 88% (95% CI: 81-96.2, I2 = 91%) of the patients. After a mean follow-up of 30.7 months, 87% (95% CI: 80-94, I2 = 82%) of patients remained free from VAs. The incidence of VAs during follow-up was significantly lower in the ablation cohort in comparison to the group receiving only ICD therapy (OR = 0.03, 95% CI: 0.01-0.12, I2 = 0%). CONCLUSION: Catheter ablation shows potential as a therapeutic approach to reduce VAs and improve outcomes in BrS patients. While further research with long follow-up period is required to confirm these findings, it represents a valuable tool as an add-on intervention to ICD implantation in BrS patients with high burden of VAs.Protocol registration: CRD42024506439.

Predicting and Recognizing Drug-Induced Type I Brugada Pattern Using ECG-Based Deep Learning.

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.