Delineation of intracavitary electrograms for the automatic quantification of decrement-evoked potentials in the coronary sinus with deep-learning techniques.

Cardiac arrhythmias cause depolarization waves to conduct unevenly on the myocardial surface, potentially delaying local components with respect to a previous beat when stimulated at faster frequencies. Despite the diagnostic value of localizing the distinct local electrocardiogram (EGM) components for identifying regions with decrement-evoked potentials (DEEPs), current software solutions do not perform automatic signal quantification. Electrophysiologists must manually measure distances on the EGM signals to assess the existence of DEEPs during pacing or extra-stimuli protocols. In this work, we present a deep learning (DL)-based algorithm to identify decrement in atrial components (measured in the coronary sinus) with respect to their ventricular counterparts from EGM signals, for disambiguating between accessory pathways (APs) and atrioventricular re-entrant tachycardias (AVRTs). Several U-Net and W-Net neural networks with different configurations were trained on a private dataset of signals from the coronary sinus (312 EGM recordings from 77 patients who underwent AP or AVRT ablation). A second, separate dataset was annotated for clinical validation, with clinical labels associated to EGM fragments in which decremental conduction was elucidated. To alleviate data scarcity, a synthetic data augmentation method was developed for generating EGM recordings. Moreover, two novel loss functions were developed to minimize false negatives and delineation errors. Finally, the addition of self-attention mechanisms and their effect on model performance was explored. The best performing model was a W-Net model with 6 levels, optimized solely with the Dice loss. The model obtained precisions of 91.28%, 77.78% and of 100.0%, and recalls of 94.86%, 95.25% and 100.0% for localizing local field, far field activations, and extra-stimuli, respectively. The clinical validation model demonstrated good overall agreement with respect to the evaluation of decremental properties. When compared to the criteria of electrophysiologists, the automatic exclusion step reached a sensitivity of 87.06% and a specificity of 97.03%. Out of the non-excluded signals, a sensitivity of 96.77% and a specificity of 95.24% was obtained for classifying them into decremental and non-decremental potentials. Current results show great promise while being, to the best of our knowledge, the first tool in the literature allowing the delineation of all local components present in an EGM recording. This is of capital importance at advancing processing for cardiac electrophysiological procedures and reducing intervention times, as many diagnosis procedures are performed by comparing segments or late potentials in subsequent cardiac cycles.

Intracoronary tenecteplase versus abciximab as adjunctive treatment during primary percutaneous coronary intervention in patients with anterior myocardial infarction.

AIMS: We sought to compare the effects of intracoronary administration of a fibrinolytic drug (tenecteplase) to those of a glycoprotein IIb/IIIa inhibitor (abciximab) in patients with ST-elevation myocardial infarction (STEMI) undergoing primary percutaneous coronary intervention (PPCI). METHODS AND RESULTS: In this pilot trial, 76 patients (59 male) with anterior STEMI were randomised to intracoronary infusion of reduced-dose tenecteplase or abciximab during PPCI. Angiography was repeated at 48 hours to assess corrected TIMI frame count (cTFC) and TIMI myocardial perfusion grade (TMPG). The primary endpoint was infarct size as assessed by cardiac MRI. The abciximab group showed lower cTFC (median 14.1 [IQR 9.4-17.1]) than the tenecteplase group (18.2 [10.0-28.2]) (p=0.02), and the proportion of patients with TMPG grade 2/3 was higher in the abciximab group (90.3% vs. 67.7%; p=0.03). Major cardiac and cerebrovascular event rates did not differ; however, notably, 2/38 patients in the tenecteplase group experienced subacute stent thrombosis. At four months, there were no significant differences in infarct size between the tenecteplase and abciximab groups (17.0 g [9.6-27.5] vs. 21.1 g [11.3-35.0], p=0.33). CONCLUSIONS: Intracoronary administration of tenecteplase did not reduce infarct size compared to abciximab in STEMI patients undergoing PPCI. Tenecteplase exhibited poorer myocardial reperfusion and might be associated with increased subacute stent thrombosis.

Repeated procedures at the generator pocket are a determinant of implantable cardioverter-defibrillator infection.

BACKGROUND: Rates of cardiac-device infections have increased in recent years, but the current incidence and risk factors for infection in patients with implantable cardioverter-defibrillators (ICDs) are not well known. HYPOTHESIS: The increasing number of ICD infections is related to accumulated pocket manipulations over time. METHODS: This single-center, prospective study included patients that underwent ICD implantation from 2008 to 2015. The endpoint was time to infection. Multivariate analysis was performed to identify independent risk factors related to infection. RESULTS: The study included a total of 570 patients, of whom 419 (73.5%) underwent a first implantation. Mean age was 59 ± 14 years, and 80% were male. During a median follow-up of 36 months (interquartile range, 18-61 months; 1887 patient-years), infection was identified in 26 patients (4.56%), an incidence of 14.9 × 1000 patient-years. Median time to infection was 9.7 months (interquartile range, 1.35-23.4 months), and 38.5% were late infections (beyond 12 months of follow-up). In patients with replacement implants, the incidence was 3-fold higher than in first implantations (27.7 vs 9.1 × 1000 patient-years; P = 0.002). Cox regression identified 2 independent predictors of ICD infection: cumulative number of interventions at the generator pocket (hazard ratio: 1.92, 95% confidence interval: 1.42-2.6, P < 0.001) and pocket hematoma (hazard ratio: 7.0, 95% confidence interval: 2.7-17.9, P < 0.0001). CONCLUSIONS: The incidence of infection in ICD patients is greater than previously reported, largely due to late infections. Each new cumulative intervention at the same generator pocket nearly doubles the risk of infection.

Electroanatomical mapping of the esophagus in circumferential pulmonary vein isolation.

A virtual reconstruction of the geometry of the esophagus was produced using an electroanatomical mapping system and a specially designed catheter in 20 consecutive patients undergoing circumferential pulmonary vein isolation. The course of the esophagus, its motion and its proximity to the predicted lines of application of radiofrequency energy to the left atrium were evaluated. Thirteen (65%) were located centrally (i.e. >10 mm from the ostium), 69 (30%) laterally (i.e. <10 mm from the ostium) and 1 (5%) obliquely. No movements larger than 10 mm occurred during the procedure. Conventionally, the radiofrequency ablation lines are configured such that, in 50% of patients, radiofrequency energy is applied to areas adjacent to the esophagus. In order to decrease the potential risk associated with this procedure, either the position of the ablation lines was altered to bring them closer to the ostium (by 15%) or the power was reduced (by 35%). Although there was no significant movement of the esophagus during the ablation procedure, its course was variable. Consequently, the ablation strategy was altered in a substantial number of cases.

Unusual tachycardia association in a patient without structural heart disease.

We report an unusual association of persistent atrial flutter and bundle branch re-entrant ventricular tachycardia in a young patient without structural heart disease. Atrial flutter masked the infra-Hisian conduction disease, was fundamentally dependent on a long PR interval, and could be a possible trigger of ventricular tachycardia.