Automatic and interpretable prediction of the site of origin in outflow tract ventricular arrhythmias: machine learning integrating electrocardiograms and clinical data.

The treatment of outflow tract ventricular arrhythmias (OTVA) through radiofrequency ablation requires the precise identification of the site of origin (SOO). Pinpointing the SOO enhances the likelihood of a successful procedure, reducing intervention times and recurrence rates. Current clinical methods to identify the SOO are based on qualitative analysis of pre-operative electrocardiograms (ECG), heavily relying on physician's expertise. Although computational models and machine learning (ML) approaches have been proposed to assist OTVA procedures, they either consume substantial time, lack interpretability or do not use clinical information. Here, we propose an alternative strategy for automatically predicting the ventricular origin of OTVA patients using ML. Our objective was to classify ventricular (left/right) origin in the outflow tracts (LVOT and RVOT, respectively), integrating ECG and clinical data from each patient. Extending beyond differentiating ventricle origin, we explored specific SOO characterization. Utilizing four databases, we also trained supervised learning models on the QRS complexes of the ECGs, clinical data, and their combinations. The best model achieved an accuracy of 89%, highlighting the significance of precordial leads V1-V4, especially in the R/S transition and initiation of the QRS complex in V2. Unsupervised analysis revealed that some origins tended to group closer than others, e.g., right coronary cusp (RCC) with a less sparse group than the aortic cusp origins, suggesting identifiable patterns for specific SOOs.

Training machine learning models with synthetic data improves the prediction of ventricular origin in outflow tract ventricular arrhythmias.

In order to determine the site of origin (SOO) in outflow tract ventricular arrhythmias (OTVAs) before an ablation procedure, several algorithms based on manual identification of electrocardiogram (ECG) features, have been developed. However, the reported accuracy decreases when tested with different datasets. Machine learning algorithms can automatize the process and improve generalization, but their performance is hampered by the lack of large enough OTVA databases. We propose the use of detailed electrophysiological simulations of OTVAs to train a machine learning classification model to predict the ventricular origin of the SOO of ectopic beats. We generated a synthetic database of 12-lead ECGs (2,496 signals) by running multiple simulations from the most typical OTVA SOO in 16 patient-specific geometries. Two types of input data were considered in the classification, raw and feature ECG signals. From the simulated raw 12-lead ECG, we analyzed the contribution of each lead in the predictions, keeping the best ones for the training process. For feature-based analysis, we used entropy-based methods to rank the obtained features. A cross-validation process was included to evaluate the machine learning model. Following, two clinical OTVA databases from different hospitals, including ECGs from 365 patients, were used as test-sets to assess the generalization of the proposed approach. The results show that V2 was the best lead for classification. Prediction of the SOO in OTVA, using both raw signals or features for classification, presented high accuracy values (>0.96). Generalization of the network trained on simulated data was good for both patient datasets (accuracy of 0.86 and 0.84, respectively) and presented better values than using exclusively real ECGs for classification (accuracy of 0.84 and 0.76 for each dataset). The use of simulated ECG data for training machine learning-based classification algorithms is critical to obtain good SOO predictions in OTVA compared to real data alone. The fast implementation and generalization of the proposed methodology may contribute towards its application to a clinical routine.

Stepwise approach for visualization and reconstruction of pulmonary valve with intracardiac echocardiography.

Ventricular tachycardia and premature ventricular complexes (PVCs) arising from right ventricular outflow tract (RVOT) are the most common type of ventricular arrhythmias (VAs) in patients without structural heart disease. Radiofrequency ablation is now the gold standard of treatment in this setting due to high efficacy rates and optimal safety profile. During the last few years, the pulmonary valve (PV) and the pulmonary artery (PA) have attracted much attention as reliable sites of origin of RVOT-type arrhythmias. In the mean while intracardiac echocardiogram (ICE) has undoubtedly improved our understanding of the cardiac anatomy. Aim of this paper is to provide an illustrated step-by-step guide on how to use ICE with the CARTOSOUND module to visualize and reconstruct 3D shell of the RV, the PV, as well of other contiguous anatomical structures (i.e., the aortic valve and coronary arteries) to perform aware and safe ablation in this region.

The ratio of main pulmonary artery to ascending aorta diameter is associated with the right ventricular outflow tract ventriculararrhythmias.

BACKGROUND: Although outflow tract (OT) ventricular arrhythmias (VAs) are generally regarded as benign, the relationship between circulation pressure and VAs has received considerable attention in recent years. Previous studies have shown that the ratio of main pulmonary artery (MPA) to ascending aorta (AA) diameter is associated with pulmonary pressure. Here, we investigated whether an elevated MPA/AA ratio is associated with right ventricular OT (RVOT) VAs. METHODS: A total of 67 patients with OT VAs (47 patients with RVOT and 20 patients with LVOT) who underwent cardiac multidetector computed tomography and radiofrequency ablation were enrolled in this study. MPA and AA diameters were measured at the level of the bifurcation of the pulmonary artery. According to the MPA/AA ratio, patients were further divided into two groups: the MPA/AA ratio abnormal group (n = 19), which is defined as MPA/AA ratio ≥ 0.9, and the MPA/AA ratio normal group (n = 48) consisting of patients with an MPA/AA ratio < 0.9. RESULTS: Patients with RVOT VAs exhibited an elevated MPA/AA ratio (0.84 ± 0.11 vs. 0.75 ± 0.11, p = 0.006). Furthermore, this MPA/AA ratio was shown to be an independent predictor for RVOT VAs (p = 0.013, 95% confidence interval: 1.016-1.145), with an abnormal MPA/AA ratio increasing the odds of RVOT VAs 5.1-fold in patients with OT VAs. CONCLUSION: Patients with RVOT VAs exhibited significantly higher MPA/AA ratios compared with those LVOT VAs. The MPA/AA ratio was showed to be an independent predictor RVOT VAs.

Automatic annotation of local activation time was improved in idiopathic right ventricular outflow tract ventricular arrhythmia by novel electrogram "Lumipoint" algorithm.

PURPOSE: Precise automatic annotation of local activation time (LAT) is crucial for rapid high-density activation mapping in arrhythmia. However, it is still challenging in voltage-transitional areas where local low-amplitude near-field potentials are often obscured by large far-field potentials. The aim of this study was to explore the viability and validity of automatic identification of the earliest activation (EA) in idiopathic right ventricular outflow tract ventricular arrhythmias (RVOT VAs) using a novel Lumipoint algorithm. METHODS AND RESULTS: Twenty-seven patients with RVOT VAs were mapped with Rhythmia mapping system. Lumipoint algorithms were applied to reannotate the initial activation regions retrospectively. The results showed that LATs were reannotated in 35.0 ± 11.4% points in the initial activation area from bipolar activation breakout time (BBO) to the its 40 ms earlier timepoint. The automatically determined bipolar earliest activation time after Lumipoint reannotation (BEAT-lu: - 111.26 ± 12.13 ms) was significantly earlier than that before (BEAT: - 108.67 ± 12.25 ms, P = 0.000). Compared with manually corrected earliest activation time (EAT), the difference between EAT and BEAT-lu (DEAT-BEAT-lu: 6 (2-7) ms) was significantly smaller than that between EAT and BEAT (DEAT-BEAT/DEAT-UEA: 7 (4-11) ms, P = 0.000). The incidence of EAT and BEAT-lu being the same site was significantly higher than that between EAT and BEAT (48.15% vs 18.52%, P = 0.021). CONCLUSIONS: RVOT VAs often originate from voltage-transitional zone, and automatic annotation of LAT usually located at later high-amplitude far-field potential. Lumipoint algorithms could improve the accuracy of LAT automatic annotation, and it was plausible to ablate RVOT VAs just according to the automatically annotated BEAS-lu.

Recovery of renal dysfunction after catheter ablation of outflow tract ventricular arrhythmias in patients with ventricular premature depolarization-mediated cardiomyopathy.

PURPOSE: Frequent ventricular premature depolarizations (VPDs) may cause cardiomyopathy (VPDCM), which often improves after VPD suppression. This study aimed to evaluate whether ablation of outflow tract ventricular arrhythmias (OT VAs) in patients with VPDCM improves renal in addition to left ventricular (LV) function. METHODS: We retrospectively evaluated 153 patients with OT VAs and examined VPD burden and LV ejection fraction (LVEF), as well as estimated glomerular filtration rate (eGFR) pre- and post-ablation. LV dysfunction was defined as LVEF <50 % and impaired renal function was defined as eGFR of <60 mL/min/1.73m2. RESULTS: Fifty-five patients had VPDCM. During mean follow-up of 14 months, 140 (92 %) were free from arrhythmia. In patients with VPDCM, patients with baseline LVEF 40-50 % had greater improvement in the post-ablation LVEF compared to patients with baseline LVEF <40 % (p < 0.01). At baseline, 36 (72 %) patients had renal dysfunction, 29 (81 %) of whom had improvement in eGFR from baseline after successful ablation from eGFR 51 to 57 mL/min/1.73m2. There was a significant association between cardiac (ΔLVEF ≥10 %) and renal (ΔeGFR ≥10 %) improvement (r = 0.54, p = 0.04). Using logistic regression analysis, procedural success was an independent predictor of improvement of cardiac (odds ratio [OR] = 13.7, p = 0.03) and renal function (OR = 21.0, p = 0.047). CONCLUSIONS: Successful catheter ablation of OT VA reduces VPD burden and is associated with improved cardiac and renal function in patients with VPDCM.