An artificial intelligence-enabled electrocardiogram algorithm for the prediction of left atrial low-voltage areas in persistent atrial fibrillation.

OBJECTIVES: We aimed to construct an artificial intelligence-enabled electrocardiogram (ECG) algorithm that can accurately predict the presence of left atrial low-voltage areas (LVAs) in patients with persistent atrial fibrillation. METHODS: The study included 587 patients with persistent atrial fibrillation who underwent catheter ablation procedures between March 2012 and December 2023 and 942 scanned images of 12-lead ECGs obtained before the ablation procedures were performed. Artificial intelligence-based algorithms were used to construct models for predicting the presence of LVAs. The DR-FLASH and APPLE clinical scores for LVA prediction were calculated. We used a receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis to evaluate model performance. RESULTS: The data obtained from the participants were split into training (n = 469), validation (n = 58), and test sets (n = 60). LVAs were detected in 53.7% of all participants. Using ECG alone, the deep learning algorithm achieved an area under the ROC curve (AUROC) of 0.752, outperforming both the DR-FLASH score (AUROC = 0.610) and the APPLE score (AUROC = 0.510). The random forest classification model, which integrated a probabilistic deep learning model and clinical features, showed a maximum AUROC of 0.759. Moreover, the ECG-based deep learning algorithm for predicting extensive LVAs achieved an AUROC of 0.775, with a sensitivity of 0.816 and a specificity of 0.896. The random forest classification model for predicting extensive LVAs achieved an AUROC of 0.897, with a sensitivity of 0.862, and a specificity of 0.935. CONCLUSION: The deep learning model based exclusively on ECG data and the machine learning model that combined a probabilistic deep learning model and clinical features both predicted the presence of LVAs with a higher degree of accuracy than the DR-FLASH and the APPLE risk scores.

Pulsed field ablation of superior vena cava in paroxysmal atrial fibrillation: a case report.

Paroxysmal atrial fibrillation originates most commonly in the pulmonary veins. However, the superior vena cava has proved to be arrhythmogenic in some cases. Pulsed field ablation, an emerging ablation technology, selectively affects myocardial tissue. Herein, we present a case of paroxysmal atrial fibrillation in a 64-year-old man who was admitted to our hospital for pulsed field ablation. The tachycardia was recurrent despite four successful pulmonary vein isolations. The superior vena cava was determined to be involved in arrhythmogenesis. The atrial fibrillation terminated immediately after the pulsed field ablation discharge at the superior vena cava.

Paroxysmal Atrial Fibrillation Originating From the Inferior Vena Cava: A Case Report and Literature Review.

Atrial fibrillation is a common arrhythmia, but atrial fibrillation originating in the inferior vena cava is extremely rare. Here, we present a case of a 51-year-old woman with symptomatic paroxysmal atrial fibrillation, who was admitted to the Second Affiliated Hospital of Dalian Medical University and underwent radiofrequency ablation. The atrial fibrillation persisted despite pulmonary vein isolation. The inferior vena cava was then identified not only as a trigger but also as the driver to maintain atrial fibrillation, and tachycardia terminated successfully by discharging at the inferior vena cava. Furthermore, we performed a literature review of five previous case reports on this subject.

Premature atrial complexes can predict atrial fibrillation in ischemic stroke patients: A systematic review and meta-analysis.

BACKGROUND AND PURPOSE: Several studies have explored premature atrial complexes (PACs) as high-risk factors for atrial fibrillation (AF) in ischemic stroke patients; however, the results were controversial. The aim of this systematic review and meta-analysis was to examine whether PACs can predict AF in ischemic stroke patients. METHODS: We comprehensively searched the published literature in PubMed, Embase, and Wiley-Cochrane library databases from inception through August 18, 2020. Pooled odds ratios (ORs) and 95% confidence intervals (CIs) were analyzed by the fixed-effect model or the random-effect model based on heterogeneity. RESULTS: We identified 12 eligible studies including 2340 stroke patients with a mean age of 65.9 years. PACs were highly associated with AF occurrence in stroke (pooled OR: 4.16, 95% CI: 3.06-5.65) and cryptogenic stroke patients (pooled OR: 3.72, 95% CI: 2.66-5.20). Subgroup analysis showed PAC presence and frequent PACs were correlated with stroke in AF patients (pooled OR: 3.72, 95% CI: 1.65-8.36 and pooled OR: 5.12, 95% CI: 3.12-8.41, respectively). Frequent PACs were identified as the risks for asymptomatic AF (OR: 6.18, 95% CI: 3.23-11.83) and future AF occurrence (OR: 3.71, 95% CI: 2.62-5.26) in stroke patients. The definition of frequent PACs was inconsistent, and was >70 beats/24 h based on Holter monitoring. CONCLUSIONS: PACs confer high risks for asymptomatic AF and future AF occurrence in stroke patients.

Usefulness of ECG to differentiate apical hypertrophic cardiomyopathy from non-ST elevation acute coronary syndrome.

BACKGROUND: Apical hypertrophic cardiomyopathy (ApHCM) is a phenotypic variant of nonobstructive HCM. ApHCM is characterized by left ventricular hypertrophy involve the distal apex. The electrocardiographic character of ApHCM can mimic non-ST elevation acute coronary syndrome (NSTEACS), triggering a series of studies and treatments that may be unnecessary. This study aimed to clarify the electrocardiogram (ECG) differences between the two diseases. METHODS: Initial ECG recordings of 41 patients with ApHCM and 72 patients with NSTEACS were analyzed retrospectively. We analyzed the voltage of negative T (neg T) and R wave, the change of ST-segment as well as the number of leads with neg T wave in the 12-lead ECGs. RESULTS: Across the 12-lead ECGs, the magnitude of R wave significantly differed between ApHCM and NSTEACS in 10 leads excluding leads aVR and V1. ApHCM was associated with a greater maximal amplitude of R wave in lead V5 (3.13 ± 1.08 vs. 1.38 ± 0.73 mV, P <  0.001). The magnitude of T wave significantly differed between ApHCM and NSTEACS in 10 leads excluding leads II and V1. ApHCM was associated with a greater maximal amplitude of neg T wave in lead V4 (0.85 ± 0.69 vs. 0.35 ± 0.23 mV, P <  0.001). The frequency of giant neg T (1mv or more) wave was higher in ApHCM (36.5% vs. 0%, P <  0.001). The magnitude of ST-segment deviation significantly differed between ApHCM and NSTEACS in 10 leads excluding leads aVF and V2. ApHCM was associated with a greater maximal amplitude of ST-segment depression in lead V5 (0.19 ± 0.07 vs. 0.03 ± 0.06 mV, P <  0.001). The number of leads with neg T wave also differed between ApHCM and NSTEACS (6.75 ± 1.42 vs. 6.08 ± 1.51, P = 0.046). The sum of R wave in lead V5, neg T wave in lead V6 and ST-segment depression in lead V4 > 2.585 mV identified ApHCM with 90.2% sensibility and 87.5% specificity, representing the highest diagnostic accuracy. CONCLUSIONS: Compared with NSTEACS patients, ApHCM patients presented higher R and neg T wave voltage as well as a greater ST-segment depression in the 12-lead ECG. The ECG characteristics can help to differentiate ApHCM from NSTEACS in clinical setting.