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.

Inflammatory Status Assessment by Machine Learning Techniques to Predict Outcomes in Patients with Symptomatic Aortic Stenosis Treated by Transcatheter Aortic Valve Replacement.

(1) Background: Although transcatheter aortic valve replacement (TAVR) significantly improves long-term outcomes of symptomatic severe aortic stenosis (AS) patients, long-term mortality rates are still high. The aim of our study was to identify potential inflammatory biomarkers with predictive capacity for post-TAVR adverse events from a wide panel of routine biomarkers by employing ML techniques. (2) Methods: All patients diagnosed with symptomatic severe AS and treated by TAVR since January 2016 in a tertiary center were included in the present study. Three separate analyses were performed: (a) using only inflammatory biomarkers, (b) using inflammatory biomarkers, age, creatinine, and left ventricular ejection fraction (LVEF), and (c) using all collected parameters. (3) Results: A total of 338 patients were included in the study, of which 56 (16.5%) patients died during follow-up. Inflammatory biomarkers assessed using ML techniques have predictive value for adverse events post-TAVR with an AUC-ROC of 0.743 and an AUC-PR of 0.329; most important variables were CRP, WBC count and Neu/Lym ratio. When adding age, creatinine and LVEF to inflammatory panel, the ML performance increased to an AUC-ROC of 0.860 and an AUC-PR of 0.574; even though LVEF was the most important predictor, inflammatory parameters retained their value. When using the entire dataset (inflammatory parameters and complete patient characteristics), the ML performance was the highest with an AUC-ROC of 0.916 and an AUC-PR of 0.676; in this setting, the CRP and Neu/Lym ratio were also among the most important predictors of events. (4) Conclusions: ML models identified the CRP, Neu/Lym ratio, WBC count and fibrinogen as important variables for adverse events post-TAVR.

Heart rate variability and microvolt T wave alternans changes during ajmaline test may predict prognosis in Brugada syndrome.

PURPOSE: Drug-induced type I Brugada syndrome (BrS) is associated with a ventricular arrhythmia (VA) rate of 1 case per 100 person-years. This study aims to evaluate changes in electrocardiographic (ECG) parameters such as microvolt T wave alternans (mTWA) and heart rate variability (HRV) at baseline and during ajmaline testing for BrS diagnosis. METHODS: Consecutive patients diagnosed with BrS during ajmaline testing with 5-year follow-up were included in this study. For comparison, a negative ajmaline control group and an isoproterenol control group were also included. ECG recordings during ajmaline or isoproterenol test were divided in two timeframes from which ECG parameters were calculated: a 5-min baseline timeframe and a 5-min drug timeframe. RESULTS: A total of 308 patients with BrS were included, 22 (0.7%) of which suffered VAs during follow-up. One hundred patients were included in both isoproterenol and negative ajmaline control groups. At baseline, there was no difference in ECG parameters between control groups and patients with BrS, nor between BrS with and without VAs. During ajmaline testing, BrS with VAs presented longer QRS duration [159 ± 34 ms versus 138 (122-155) ms, p = 0.006], higher maximum mTWA [33.8 (14.0-114) µV versus 8.00 (3.67-28.2) µV, p = 0.001], and lower power in low frequency band [25.6 (5.8-53.8) ms2 versus 129.5 (52.7-286) ms2, p < 0.0001] when compared to BrS without VAs. CONCLUSIONS: Ajmaline induced important HRV changes similar to those observed during isoproterenol. Increased mTWA was observed only in patients with BrS. BrS with VAs during follow-up presented worse changes during ajmaline test, including lower LF power and higher maximum mTWA which were independent predictors of events.

Hybrid-Approach Ablation in Drug-Refractory Arrhythmogenic Right Ventricular Cardiomyopathy.

Management of ventricular arrhythmias (VAs) beyond implantable cardioverter-defibrillator positioning in patients with arrhythmogenic right ventricular cardiomyopathy (ARVC) is challenging. Catheter ablation of the ventricular substrate often requires a combination of endocardial and epicardial approaches, with disappointing outcomes due to the progressive nature of the disease. We report the Universitair Ziekenhuis Brussel experience through a case series of 16 patients with drug-refractory ARVC, who have undergone endocardial and/or epicardial catheter ablation of VAs with a thoracoscopic hybrid-approach. After a mean follow-up time of 5.16 years (SD 2.9 years) from the first hybrid-approach ablation, VA recurrence was observed in 5 patients (31.25%): among these, patients 4 patients (80%) received a previous ablation and 1 of 11 patients (9.09%) who had a hybrid ablation as first approach had a VA recurrence (80% vs 9.09%; log-rank p = 0.04). Despite the recurrence rate of arrhythmic events, all patients had a significant reduction in the arrhythmic burden after ablation, with a mean of 4.65 years (SD 2.9 years) of freedom from clinically significant arrhythmias, defined as symptomatic VAs or implantable cardioverter-defibrillator-delivered therapies. In conclusion, our case series confirms that management of VAs in patients with ARVC is difficult because patients do not always respond to antiarrhythmic medications and can require multiple invasive procedures. A multidisciplinary approach involving cardiologists, cardiac surgeons, and cardiac electrophysiologists, together with recent cardiac mapping techniques and ablation tools, might mitigate these difficulties and improve outcomes.

Prediction of 3-year all-cause and cardiovascular cause mortality in a prospective percutaneous coronary intervention registry: Machine learning model outperforms conventional clinical risk scores.

BACKGROUND AND AIMS: Machine learning (ML) models have been proposed as a prognostic clinical tool and superiority over clinical risk scores is yet to be established. Our aim was to analyse the performance of predicting 3-year all-cause- and cardiovascular cause mortality using ML techniques and compare it with clinical scores in a percutaneous coronary intervention (PCI) population. METHODS: An all-comers patient population treated by PCI in a tertiary cardiovascular centre that have been included prospectively in the local registry between January 2016-December 2017 was analysed. The ML model was trained to predict 3-year mortality and prediction performance was compared with that of GRACE, ACEF, SYNTAX II 2020 and TIMI scores. RESULTS: A total number of 2242 patients were included with 12.1% and 14.9% 3-year cardiovascular and -all-cause mortality, respectively. The area under receiver operator characteristic curve for the ML model was higher than that of GRACE, ACEF, SYNTAX II and TIMI scores: 0.886 vs. 0.797, 0.792, 0.757 and 0.696 for 3-year cardiovascular- and 0.854 vs. 0.762, 0.764, 0.730 and 0.691 for 3-year all-cause mortality prediction, respectively (all p ≤ 0.001). Similarly, the area under precision-recall curve for the ML model was higher than that of GRACE, ACEF, SYNTAX II and TIMI scores: 0.729 vs. 0.474, 0.469, 0.365 and 0.389 for 3-year cardiovascular- and 0.718 vs. 0.483, 0.466, 0.388 and 0.395 for 3-year all-cause mortality prediction, respectively (all p ≤ 0.001). CONCLUSION: The ML model was superior in predicting 3-year cardiovascular- and all-cause mortality when compared to clinical scores in a prospective PCI registry.

Coronary fibromuscular dysplasia with three-vessel involvement: a rare cause of ischaemic dilated cardiomyopathy in a very young male.

Coronary artery disease of non-atherosclerotic aetiology, while rare in incidence, can have a wide aetiology, such as fibromuscular dysplasia, which is a non-inflammatory arteriopathy of numerous histopathological types of fibromuscular tissue accumulation. This brief report describes the case of a 22-year-old male with a recently developed dilated cardiomyopathy and a history of aborted cardiac arrest at the age of 14 years. Coronary angiogram revealed severe three vessels disease, while optical coherence tomography established fibromuscular dysplasia as aetiology. Balloon and stent angioplasty was performed guided by fractional flow reserve with acceptable angiographic result.

SCN5A mutation in Brugada syndrome is associated with substrate severity detected by electrocardiographic imaging and high-density electroanatomic mapping.

BACKGROUND: Brugada syndrome (BrS) is caused by mutations in SCN5A gene in 15%-20% of cases. Previous studies showed worse prognosis in SCN5A mutation carriers (SCN5A+). To date, there are no data on genotype-phenotype correlation with electrocardiographic (ECG) imaging (ECGI) and high-density epicardial electroanatomic map. OBJECTIVE: This study aimed to correlate SCN5A mutation with substrate severity in BrS assessed by ECGI and high-density electroanatomic map. METHODS: All consecutive BrS patients undergoing ECGI and high-density epicardial electroanatomic map with HD Grid Mapping Catheter were retrospectively analyzed. On ECGI, the following parameters were analyzed before and after ajmaline administration: right ventricular outflow tract (RVOT) activation time (RVOT-AT) and RVOT recovery time (RVOT-RT). On electroanatomic map, the parameters analyzed before and after ajmaline were high-frequency potential activation time (HFPat), high-frequency potential duration (HFPd), high-frequency potential amplitude (HFPa), low-frequency potential activation time (LFPat), low-frequency potential duration (LFPd), and low-frequency potential amplitude (LFPa). RESULTS: Thirty-nine BrS patients with ECGI were included. Eight patients (20.5%) were SCN5A+. At baseline ECGI map, mean RVOT-RT was longer in SCN5A+ (P = .024). After ajmaline administration, SCN5A+ patients showed longer RVOT-AT (125.6 vs 100.8 ms; P = .045) and longer RVOT-RT (426.4 vs 397 ms; P = .033). After ajmaline administration, SCN5A+ showed longer HFPat (164.1 vs 119.5 ms; P = .041); longer LFPat (272.7 vs 200.5 ms; P = .018); and longer LFPd (211.9 vs 151.2 ms; P = .033). CONCLUSION: In BrS, SCN5A+ patients compared with SCN5A- patients exhibit marked depolarization and repolarization abnormalities as assessed by ECGI and epicardial high-density electroanatomic map.

Ajmaline-Induced Abnormalities in Brugada Syndrome: Evaluation With ECG Imaging.

Background The rate of sudden cardiac death (SCD) in Brugada syndrome (BrS) is ≈1%/y. Noninvasive electrocardiographic imaging is a noninvasive mapping system that has a role in assessing BrS depolarization and repolarization abnormalities. This study aimed to analyze electrocardiographic imaging parameters during ajmaline test (AJT). Methods and Results All consecutive epicardial maps of the right ventricle outflow tract (RVOT-EPI) in BrS with CardioInsight were retrospectively analyzed. (1) RVOT-EPI activation time (RVOT-AT); (2) RVOT-EPI recovery time, and (3) RVOT-EPI activation-recovery interval (RVOT-ARI) were calculated. ∆RVOT-AT, ∆RVOT-EPI recovery time, and ∆RVOT-ARI were defined as the difference in parameters before and after AJT. SCD-BrS patients were defined as individuals presenting a history of aborted SCD. Thirty-nine patients with BrS were retrospectively analyzed and 12 patients (30.8%) were SCD-BrS. After AJT, an increase in both RVOT-AT [105.9 milliseconds versus 65.8 milliseconds, P<0.001] and RVOT-EPI recovery time [403.4 milliseconds versus 365.7 milliseconds, P<0.001] was observed. No changes occurred in RVOT-ARI [297.5 milliseconds versus 299.9 milliseconds, P=0.7]. Before AJT no differences were observed between SCD-BrS and non SCD-BrS in RVOT-AT, RVOT-EPI recovery time, and RVOT-ARI (P=0.9, P=0.91, P=0.86, respectively). Following AJT, SCD-BrS patients showed higher RVOT-AT, higher ∆RVOT-AT, lower RVOT-ARI, and lower ∆RVOT-ARI (P<0.001, P<0.001, P=0.007, P=0.002, respectively). At the univariate logistic regression, predictors of SCD-BrS were the following: RVOT-AT after AJT (specificity: 0.74, sensitivity 1.00, area under the curve 0.92); ∆RVOT-AT (specificity: 0.74, sensitivity 0.92, area under the curve 0.86); RVOT-ARI after AJT (specificity 0.96, sensitivity 0.58, area under the curve 0.79), and ∆RVOT-ARI (specificity 0.85, sensitivity 0.67, area under the curve 0.76). Conclusions Noninvasive electrocardiographic imaging can be useful in evaluating the results of AJT in BrS.

High-density epicardial mapping in Brugada syndrome: Depolarization and repolarization abnormalities.

BACKGROUND: The pathogenesis of Brugada syndrome (BrS) and consequently of abnormal electrograms (aEGMs) found in the epicardium of the right ventricular outflow tract (RVOT-EPI) is controversial. OBJECTIVE: The purpose of this study was to analyze aEGM from high-density RVOT-EPI electroanatomic mapping (EAM). METHODS: All patients undergoing RVOT-EPI EAM with the HD-Grid catheter for BrS were retrospectively included. Maps were acquired before and after ajmaline, and all patients had concomitant noninvasive electrocardiographic imaging with annotation of RVOT-EPI latest activation time (RVOTat). High-frequency potentials (HFPs) were defined as ventricular potentials occurring during or after the far-field ventricular EGM showing a local activation time (HFPat). Low-frequency potentials (LFPs) were defined as aEGMs occurring after near-field ventricular activation showing fractionation or delayed components. Their activation time from surface ECG was defined as LFPat. RESULTS: Fifteen consecutive patients were included in the study. At EAM before ajmaline, 7 patients (46.7%) showed LFPs. All patients showed HFPs before and after ajmaline and LFPs after ajmaline. Mean HFPat (134.4 vs 65.3 ms, P <.001), mean LFPat (224.6 vs 113.6 ms, P <.001), and mean RVOTat (124.8 vs 55.9 ms, P <.001) increased after ajmaline. RVOTat correlated with HFPat before (ρ = 0.76) and after ajmaline (ρ = 0.82), while RVOTat was shorter than LFPat before (P <.001) and after ajmaline (P <.001). BrS patients with history of aborted sudden cardiac death had longer aEGMs after ajmaline. CONCLUSION: Two different types of aEGMs are described from BrS high-density epicardial mapping. This might correlate with depolarization and repolarization abnormalities.

High vagal tone predicts pulmonary vein reconnection after cryoballoon ablation for paroxysmal atrial fibrillation.

BACKGROUND: Pulmonary vein (PV) isolation is an established treatment for paroxysmal drug-refractory atrial fibrillation (AF). High parasympathetic tone and reconnection of PVs have demonstrated to be possible culprits of AF recurrence after ablation. Our aim was to investigate the association between parasympathetic tone and reconnected PVs in patients with paroxysmal AF. METHODS: Consecutive patients who underwent a redo catheter ablation procedure for atrial tachyarrhythmia recurrence by means of 3D electroanatomic mapping with documentation of presence or absence of PVs reconnection following an initial procedure of cryoballoon (CB) ablation for symptomatic drug-refractory paroxysmal AF were screened for the study. RESULTS: A total of 92 patients were included, of whom 50 (54.35%) were males. Reconnected PVs were found in 64 (69%) patients. PVs reconnection could be predicted by DC (C-statistic = .770), by SDNNI (C-statistic = .714) and by absolute VLF power (C-statistic = .722), while right-sided PVs reconnection could be better predicted by DC (C-statistic = .848) and by SDNNI (C-statistic = .761). In multivariate binary logistic regression analysis, a DC value ≥6.45 ms and an absolute VLF power value ≥160 ms2 were associated with three times and five times higher odds of PVs reconnection, respectively. On a vein-per-vein analysis, absolute VLF power ≥160 ms2 was associated with three times higher odds, while reaching of -40°C within 60 s was associated with three times lower odds of PVs reconnection. CONCLUSION: High parasympathetic tonus accurately predicts PVs reconnection. On a vein-per-vein analysis, parasympathetic markers along with biophysical parameters predicted PVs reconnection. On a case-by-case analysis, parasympathetic markers were the only predictors of PVs reconnection, thus being a robust PVs reconnection prediction tool.

Comparison between superior vena cava ablation in addition to pulmonary vein isolation and standard pulmonary vein isolation in patients with paroxysmal atrial fibrillation with the cryoballoon technique.

BACKGROUND: Paroxysmal atrial fibrillation (PAF) can be triggered by non-pulmonary vein foci, like the superior vena cava (SVC). The latter is correlated with improved result in terms of freedom from atrial tachycardias (ATs), when electrical isolation of this vessel utilizing radiofrequency energy (RF) is achieved. OBJECTIVES: Evaluate the clinical impact, in patients with PAF, of the SVC isolation (SVCi) in addition to ordinary pulmonary vein isolation (PVI) by means of the second-generation cryoballoon (CB) METHODS: A total of 100 consecutive patients that underwent CB ablation for PAF were retrospectively selected. Fifty consecutive patients received PVI followed by SVCi by CB application, and the following 50 consecutive patients received standard PVI. All patients were followed 12 months. RESULTS: The mean time to SVCi was 36.7 ± 29.0 s and temperature at SVC isolation was - 35 (- 18 to - 40) °C. Real-time recording (RTR) during SVCi was observed in 42 (84.0%) patients. At the end of 12 months of follow-up, freedom from ATs was achieved in 36 (72%) patients in the PVI only group and in 45 (90%) patients of the SVC and PV isolation group (Fisher's exact test p = 0.039, binary logistic regression: p = 0.027, OR = 0.28, 95%CI = 0.09-0.86). In survival analysis, SVC and PV isolation group was also associated with improved freedom from ATs (log-rank test: p = 0.017, Cox regression: p = 0.026, HR = 0.31, 95%CI = 0.11-0.87). CONCLUSION: Superior vena cava isolation with the CB in addition to PVI might improve freedom from ATs if compared to PVI alone at 1-year follow-up.

High parasympathetic activity as reflected by deceleration capacity predicts atrial fibrillation recurrence after repeated catheter ablation procedure.

PURPOSE: High parasympathetic nervous system (PNS) activity is accurately reflected by deceleration capacity (DC) and is involved in atrial fibrillation (AF) recurrence after catheter ablation procedure. When compared with initial catheter ablation procedure, repeated procedures for AF recurrence are followed by a lower success rates, estimated at 50%. Our objective was to evaluate the impact of PNS activity assessed by DC measured before repeated procedure on AF recurrence after repeated procedure. METHODS: Consecutive patients who underwent an initial catheter ablation procedure for pulmonary vein (PV) isolation and a repeated catheter ablation procedure for AF recurrence were selected. Additional 24-h ambulatory electrocardiographic recording between procedures for DC measurement was required for inclusion. A total of 110 patients were included. Seventy-two patients underwent cryoballoon (CB) ablation and 38 patients underwent radiofrequency (RF) ablation as initial procedure, while all patients underwent RF ablation as repeated procedure. RESULTS: DC was higher in cases with right-sided PV reconnection (p = 0.04, OR = 1.38, 95% CI = 1.08-1.78). In patients with CB ablation as initial procedure, DC was higher in patients with PV reconnection (p = 0.03, OR = 1.29, 95% CI = 1.11-1.70), and the number of reconnected PVs was higher in patients with DC ≥ 7.0 ms (median DC value used for dichotomization, p = 0.02, OR = 2.19, 95% CI = 1.10-4.37). In multivariate Cox regression, DC predicted AF recurrence after repeated ablation (p = 0.004, HR = 1.68, 95% CI = 1.35-1.82). In multivariate binary regression, DC predicted persistent AF type recurrence after repeated ablation (p = 0.01, OR = 1.50, 95% CI = 1.10-2.02). CONCLUSIONS: DC is a novel predictor of AF recurrence and AF recurrence type after repeated catheter ablation procedure. DC may reflect the need of more intensive treatment strategies in patients with high PNS activity.

Safety and feasibility of electrical isolation of the superior vena cava in addition to pulmonary vein ablation for paroxysmal atrial fibrillation using the cryoballoon: lessons from a prospective study.

PURPOSE: The purpose of this study was to evaluate the feasibility and safety of superior vena cava (SVC) isolation in addition to standard pulmonary vein isolation (PVI) using the second-generation cryoballoon (CB) in patients with paroxysmal atrial fibrillation. METHODS: Thirty-seven consecutive patients that underwent CB ablation for paroxysmal atrial fibrillation (PAF) were prospectively enrolled in our study. After PVI the SVC was mapped for potentials. If the SVC exhibited electrical activity, isolation was achieved performing a single 180-s balloon application. RESULTS: Regarding SVC isolation, 180-s freeze in the SVC could be completed in 32 (86.4%) patients, and 5 patients had at least 120 s of freezing application (13.5%). Real-time recording during SVC isolation was observed in 30 (81.0%) patients. The mean time to isolation was 36.9 ± 28.7 s and the temperature at isolation was - 33 (- 15 to - 40) °C. No cases developed persistent phrenic nerve palsy (PNP) or any other complication. CONCLUSIONS: Superior vena cava isolation proved to be safe and feasible with the second generation cryoballoon in a prospective series of patients affected by PAF.

Standardized Quantification of Vagal Denervation by Extracardiac Vagal Stimulation during Second Generation Cryoballoon ablation: a Vein per Vein Analysis.

AIMS: The purpose of this study was to evaluate the contribution in the acute loss in vagal innervation after ablation with the second generation cryoballoon (CB-A) in each distinct pulmonary vein (PV) by means of external cardiac vagal stimulation (ECVS) by positioning a catheter in the internal jugular vein in a cohort of 60 patients. METHODS: Sixty patients, 50 starting from the left superior pulmonary vein (LSPV) and 10 from the right superior pulmonary vein with symptomatic paroxysmal atrial fibrillation (PAF), having undergone ECVS before the first and after each PV ablation by means of CB-A ablation, were included. RESULTS: The ECVS performed pre-ablation provoked cardioinhibitory responses in all cases with mean pause duration of 10251.83 ms ± 2826.23 ms. At the end of the procedure, the vagal reactions (VR) were significantly diminished. Specifically, compared against the initial pause, responses were 8957.06 ± 2711.66 ms (p < 0.01) after left superior PV, 10017.36 ± 9127.0 ms (p = 0.88) after left inferior PV, 6020.16 ± 3780.709 ms (p < 0.001) after right inferior PV and 1687.5 ± 2183.7 ms (p < 0.001) after right superior PV. Noteworthy, if starting with ablation in the RSPV, VR was immediately reduced by 90.34%, 990.7 ± 379.78 ms (p < 0.001) as compared to baseline response. CONCLUSION: Although not directly targeting the ganglion plexuses, AF ablation with the CB-A causes a significant acute loss in parasympathetic innervation. The RSPV showed to be associated with the most significant reduction of acute loss in parasympathetic innervation.