ABSTRACT
AIMS: Prior case series showed promising results for cardioneuroablation in patients with vagally induced atrioventricular blocks (VAVBs). We aimed to examine the acute procedural characteristics and intermediate-term outcomes of electroanatomical-guided cardioneuroablation (EACNA) in patients with VAVB. METHODS AND RESULTS: This international multicentre retrospective registry included data collected from 20 centres. Patients presenting with symptomatic paroxysmal or persistent VAVB were included in the study. All patients underwent EACNA. Procedural success was defined by the acute reversal of atrioventricular blocks (AVBs) and complete abolition of atropine response. The primary outcome was occurrence of syncope and daytime second- or advanced-degree AVB on serial prolonged electrocardiogram monitoring during follow-up. A total of 130 patients underwent EACNA. Acute procedural success was achieved in 96.2% of the cases. During a median follow-up of 300 days (150, 496), the primary outcome occurred in 17/125 (14%) cases with acute procedural success (recurrence of AVB in 9 and new syncope in 8 cases). Operator experience and use of extracardiac vagal stimulation were similar for patients with and without primary outcomes. A history of atrial fibrillation, hypertension, and coronary artery disease was associated with a higher primary outcome occurrence. Only four patients with primary outcome required pacemaker placement during follow-up. CONCLUSION: This is the largest multicentre study demonstrating the feasibility of EACNA with encouraging intermediate-term outcomes in selected patients with VAVB. Studies investigating the effect on burden of daytime symptoms caused by the AVB are required to confirm these findings.
Subject(s)
Atrioventricular Block , Registries , Humans , Male , Female , Retrospective Studies , Aged , Middle Aged , Treatment Outcome , Atrioventricular Block/physiopathology , Atrioventricular Block/therapy , Atrioventricular Block/surgery , Catheter Ablation/methods , Time Factors , Vagus Nerve Stimulation/methods , Electrophysiologic Techniques, Cardiac , Syncope/etiology , Recurrence , Atrioventricular Node/surgery , Atrioventricular Node/physiopathologyABSTRACT
Atrial fibrillation (AF) is a common cardiac arrhythmia with serious health consequences if not detected and treated early. Detecting AF using wearable devices with photoplethysmography (PPG) sensors and deep neural networks has demonstrated some success using proprietary algorithms in commercial solutions. However, to improve continuous AF detection in ambulatory settings towards a population-wide screening use case, we face several challenges, one of which is the lack of large-scale labeled training data. To address this challenge, we propose to leverage AF alarms from bedside patient monitors to label concurrent PPG signals, resulting in the largest PPG-AF dataset so far (8.5 M 30-second records from 24,100 patients) and demonstrating a practical approach to build large labeled PPG datasets. Furthermore, we recognize that the AF labels thus obtained contain errors because of false AF alarms generated from imperfect built-in algorithms from bedside monitors. Dealing with label noise with unknown distribution characteristics in this case requires advanced algorithms. We, therefore, introduce and open-source a novel loss design, the cluster membership consistency (CMC) loss, to mitigate label errors. By comparing CMC with state-of-the-art methods selected from a noisy label competition, we demonstrate its superiority in handling label noise in PPG data, resilience to poor-quality signals, and computational efficiency.
Subject(s)
Algorithms , Atrial Fibrillation , Photoplethysmography , Signal Processing, Computer-Assisted , Humans , Photoplethysmography/methods , Atrial Fibrillation/physiopathology , Atrial Fibrillation/diagnosis , Clinical Alarms , Machine Learning , Wearable Electronic DevicesABSTRACT
BACKGROUND: Cardioneuroablation has been emerging as a potential treatment alternative in appropriately selected patients with cardioinhibitory vasovagal syncope (VVS) and functional AV block (AVB). However the majority of available evidence has been derived from retrospective cohort studies performed by experienced operators. METHODS: The Cardioneuroablation for the Management of Patients with Recurrent Vasovagal Syncope and Symptomatic Bradyarrhythmias (CNA-FWRD) Registry is a multicenter prospective registry with cross-over design evaluating acute and long-term outcomes of VVS and AVB patients treated by conservative therapy and CNA. RESULTS: The study is a prospective observational registry with cross-over design for analysis of outcomes between a control group (i.e., behavioral and medical therapy only) and intervention group (Cardioneuroablation). Primary and secondary outcomes will only be assessed after enrollment in the registry. The follow-up period will be 3 years after enrollment. CONCLUSIONS: There remains a lack of prospective multicentered data for long-term outcomes comparing conservative therapy to radiofrequency CNA procedures particularly for key outcomes including recurrence of syncope, AV block, durable impact of disruption of the autonomic nervous system, and long-term complications after CNA. The CNA-FWRD registry has the potential to help fill this information gap.