Explainable localization of premature ventricular contraction using deep learning-based semantic segmentation of 12-lead electrocardiogram.

Background: Predicting the origin of premature ventricular contraction (PVC) from the preoperative electrocardiogram (ECG) is important for catheter ablation therapies. We propose an explainable method that localizes PVC origin based on the semantic segmentation result of a 12-lead ECG using a deep neural network, considering suitable diagnosis support for clinical application. Methods: The deep learning-based semantic segmentation model was trained using 265 12-lead ECG recordings from 84 patients with frequent PVCs. The model classified each ECG sampling time into four categories: background (BG), sinus rhythm (SR), PVC originating from the left ventricular outflow tract (PVC-L), and PVC originating from the right ventricular outflow tract (PVC-R). Based on the ECG segmentation results, a rule-based algorithm classified ECG recordings into three categories: PVC-L, PVC-R, as well as Neutral, which is a group for the recordings requiring the physician's careful assessment before separating them into PVC-L and PVC-R. The proposed method was evaluated with a public dataset which was used in previous research. Results: The evaluation of the proposed method achieved neutral rate, accuracy, sensitivity, specificity, F1-score, and area under the curve of 0.098, 0.932, 0.963, 0.882, 0.945, and 0.852 on a private dataset, and 0.284, 0.916, 0.912, 0.930, 0.943, and 0.848 on a public dataset, respectively. These quantitative results indicated that the proposed method outperformed almost all previous studies, although a significant number of recordings resulted in requiring the physician's assessment. Conclusions: The feasibility of explainable localization of premature ventricular contraction was demonstrated using deep learning-based semantic segmentation of 12-lead ECG.Clinical trial registration: M26-148-8.

Implantable loop recorder uncovered torsades de pointes in long-QT syndrome type 1 with multi cause of syncope.

An implantable loop recorder (ILR) is now widely used for differential diagnosis of unexplained syncope or recurrent syncope with unknown causes. In the inherited arrhythmia syndromes, ILR may be useful for management of the therapeutic strategies; however, there is no obvious evidence to uncover arrhythmic syncope by ILR in long-QT syndrome (LQTS) patients. Here we experienced a 19-year-old female patient with LQTS type 1 who had recurrent syncope even after beta-blocker therapy but no arrhythmias were documented, and some episodes might be due to non-cardiogenic causes. Implantable cardioverter defibrillator (ICD) therapy was also recommended; however, she could not accept ICD but was implanted with ILR for further continuous monitoring. Two years later, she suffered syncope during a brief run, and ILR recorded an electrocardiogram at that moment. Thus a marked QT interval prolongation as well as T-wave alternance resulting in development of torsades de pointes could be detected. Although ILR is just a diagnostic tool but does not prevent sudden cardiac death, most arrhythmic events in LQTS are transient and sometimes hard to be diagnosed as arrhythmic syncope. ILR may provide direct supportive evidence to select the optimal therapeutic strategy in cases where syncope is difficult to diagnose. Learning objective: Long-QT syndrome (LQTS) patients often suffer recurrent syncope even after beta-blocker therapy, but torsades de pointes (TdP) is not always detected by standard 12­lead electrocardiogram or Holter monitoring, and some syncope might be non-cardiogenic. In this case, implantable loop recorder (ILR) documented the evidence of QT interval prolongation and beat-by-beat T-wave alternance subsequent TdP. Thus, ILR may provide useful evidence for the optimal treatment strategy in LQTS cases where syncope is difficult to diagnose.

Clinical Usefulness of the Active Fixation Quadripolar Left Ventricular Lead Compared With the Passive Fixation Quadripolar Lead in Cardiac Resynchronization Therapy.

BACKGROUND: This study compared the stability of the Medtronic Attain Stability Quad (ASQ), a novel quadripolar active fixation left ventricular (LV) lead with a side helix, to that of conventional quadripolar leads with passive fixation (non-ASQ) and evaluated their LV lead performance.Methods and Results: In all, 183 consecutive patients (69 ASQ, 114 non-ASQ) who underwent cardiac resynchronization therapy (CRT) between January 2018 and June 2021 were enrolled. Complications, including elevated pacing capture threshold (PCT) levels, phrenic nerve stimulation (PNS), and LV lead dislodgement, were analyzed during the postimplantation period until the first outpatient visit after discharge. The frequency of LV lead-related complications was significantly lower in the ASQ than non-ASQ group (14% vs. 30%, respectively; P=0.019). Specifically, LV lead dislodgement occurred only in the non-ASQ group, and elevated PCT levels were significantly lower in the ASQ group (7% vs. 23%; P=0.007). Kaplan-Meier analysis confirmed a significantly lower incidence of LV lead-related complications in the ASQ group (log-rank P=0.005). Cox multivariable regression analysis showed a significant reduction in lead-related complications associated with ASQ (hazard ratio 0.44; 95% confidence interval 0.23-0.83; P=0.011). CONCLUSIONS: The ASQ group exhibited fewer LV lead-related complications requiring reintervention and setting changes than the non-ASQ group. Thus, the ASQ may be a favorable choice for CRT device implantation.

Demonstration of Arrhythmia Substrate-Associated Dispersion of Repolarization by Epicardial Unipolar Mapping in Brugada Syndrome.

BACKGROUND: Epicardial unipolar mapping has not been thoroughly investigated in Brugada syndrome (BrS). OBJECTIVES: This study aims to examine the characteristics of epicardial unipolar potentials in BrS and investigate the differences from overt cardiomyopathy. METHODS: Epicardial mapping was performed in 8 patients with BrS and 6 patients with cardiomyopathy. We investigated the J-wave amplitudes using unipolar recordings at delayed potential (DP) sites via bipolar recordings. The repolarization time (RT) at and around the DP recording sites was measured, and maximum dispersion of the RT divided by the distance was defined as the RT dispersion index. RESULTS: Epicardial mapping at baseline revealed significantly higher J-wave amplitude with bipolar DP in patients with BrS than in patients with cardiomyopathy. J-wave amplitude ≥0.42 mV had 99.1% sensitivity and 100% specificity for diagnosing BrS. The RT dispersion index was significantly higher in patients with BrS than in patients with cardiomyopathy at baseline. In all patients with BrS, coved-type unipolar electrograms without negative T waves (short RT) appeared close to coved-type electrograms with negative T waves (long RT) at the DP recording sites after pilsicainide administration. Thus, a steep RT dispersion was observed in this region, and ventricular arrhythmias emerged from this shorter RT area in all 3 patients with BrS in whom ventricular arrhythmias were induced. CONCLUSIONS: Bipolar DP-related prominent unipolar J waves and steep repolarization gradients may be more specific for characterizing BrS than for overt cardiomyopathy. Ventricular arrhythmias in BrS are associated with a steep repolarization gradient, indicating phase 2 re-entry as a possible cause.

Right Atrial Septal Lead Enhances the Favorable Effects of the Adaptive Cardiac Resynchronization Therapy Algorithm.

The adaptive cardiac resynchronization therapy (CRT) algorithm provides synchronized left ventricular pacing (sLVP). However, ensuring a high sLVP rate is challenging. We assessed the association between the sLVP rate and pacing sites in the right atrium. We evaluated 71 patients who underwent CRT and in whom the adaptive CRT algorithm was applied (53 men; mean age, 66 ± 14 years; median follow-up period, 301 days; IQR: 212-596 days). The atrial pacing leads were positioned in the right atrial (RA) septum in 17 patients (septal group) and in the RA appendage in 54 patients (RA appendage group), with significantly higher sLVP rates in the septal group compared with the RA appendage group (81% ± 30% vs 63% ± 37%; P = 0.045). In patients with first-degree atrioventricular blocks, the sLVP rates tended to be higher in the septal group. Therefore, RA septal pacing increased sLVP rates in patients undergoing CRT.

Effect of adaptive cardiac resynchronization therapy in heart failure patients with pacemaker dependency.

BACKGROUND: An adaptive cardiac resynchronization therapy (aCRT) algorithm allows continuous adjustments of pacing timings of atrioventricular delays by periodic automatic evaluation of electrical conduction. This applies to patients with an atrioventricular block and is effective in cardiac resynchronization therapy (CRT) devices; however, whether this algorithm benefits patients with pacemaker dependency is uncertain. METHODS: This study examined the clinical impact of an aCRT algorithm in patients diagnosed with heart failure with reduced ejection fraction and pacemaker dependency. A total of 359 patients underwent CRT between January 2016 and December 2022. Patients undergoing pacemaker-dependent CRT with the aCRT algorithm function were selected. Sixty-four patients with pacemaker dependency (31 with aCRT algorithm and 33 without) were included. Pacemaker dependency was defined as the absence of spontaneous ventricular activity during the sensing test at VVI 30 bpm or prolonged atrioventricular delay (> 300 ms). The primary endpoint was the composite clinical outcome of all-cause death or hospitalization for heart failure. RESULTS: No significant differences were observed in baseline characteristics between groups. During a median follow-up of 1,067 days (interquartile range 553-1,776 days), aCRT reduced the risk of composite clinical outcomes in patients with pacemaker dependency (log-rank P = 0.028). In addition, using the aCRT algorithm was an independent predictor of the composite clinical outcomes in the multivariate analysis (hazard ratio 0.34, 95% confidence interval: 0.12-0.94, P = 0.038). CONCLUSION: The aCRT algorithm significantly reduced the risk of adverse clinical outcomes in patients with pacemaker dependency. This algorithm may be an important tool for managing such patients.

Evaluation of synchronized left ventricular pacing rate over biventricular pacing in cardiac resynchronization therapy.

BACKGROUND: The adaptive cardiac resynchronization therapy (aCRT) algorithm enables synchronized left ventricular pacing (sLVP) to achieve fusion with intrinsic right ventricular activation. Although sLVP presents benefits over biventricular pacing, the adequate sLVP rate for better clinical outcomes remains unclear. We aimed to assess the association between sLVP rates and clinical outcomes. METHODS: Our study cohort included 271 consecutive patients, who underwent CRT implantation between April 2016 and August 2021. RESULTS: We evaluated 63 patients on whom we applied the aCRT algorithm [48 men, mean age: 64 ±â€¯14 years; median follow-up period: 316 days (interquartile range: 212-809 days)]. At the 6-month follow-up after CRT implantation, the frequency of CRT responders was 71 % (n = 45). The sLVP rate was significantly higher in responders than in non-responders (75 ±â€¯30 % vs. 47 ±â€¯40 %, p = 0.003). Receiver operating characteristics curve analysis revealed that the optimal cut-off value during the sLVP rate was 59.4 % for the prediction of CRT responders (area under the curve, 0.70; sensitivity, 80 %; specificity, 61 %; positive predictive value, 84 %; and negative predictive value, 55 %). Kaplan-Meier analysis demonstrated that the higher-sLVP group (sLVP ≧59.4 %, n = 43) had a better prognosis (cardiac death and heart failure hospitalization) than the lower-sLVP group (sLVP <59.4 %, n = 20) (log-rank p < 0.001). Multivariate Cox hazard analysis revealed that a higher sLVP rate was associated with a good prognosis (p < 0.001). CONCLUSIONS: sLVP was associated with CRT response, and a higher sLVP rate (≧59.4 %) was important for good prognosis in patients with aCRT.

Bipolar Radiofrequency Catheter Ablation for Ventricular Arrhythmias.

A minority of premature ventricular contractions (PVC) and ventricular tachycardias (VT) have an intramural origin, which represents a challenge for conventional radiofrequency ablation. Bipolar ablation has the potential ability to create deeper and more transmural lesions and has been demonstrated to be optimal treatment in these cases. Bipolar ablation carries a relatively low risk of complications and is effective in eliminating or reducing the burden of ventricular arrhythmias. Despite its utility and efficacy, the clinical use of bipolar ablation is limited, and B-RF technology is still investigational and not widely available. This article reviews the technique of bipolar ablation and all its advantages when applied to specific scenarios.