Kim DG, et al. Yonsei Med J. 2025 Jan;66(1):1-8. https://doi.org/10.3349/ymj.2023.0410

Background/Objectives: Most previous studies using artificial intelligence (AI) to detect left ventricular systolic dysfunction (LVSD) from electrocardiograms (ECGs) relied on data obtained near the time of echocardiography or included patients with known cardiac disease, limiting their specificity for screening. We aimed to evaluate whether AI models could predict future LVSD from ECGs interpreted as normal and recorded one to two years before echocardiography. Methods: We retrospectively analyzed 24,203 sinus rhythm ECGs from 11,131 patients. Two convolutional neural network models (DenseNet-121 and ResNet-101) were trained (70%), validated (10%), and tested (20%) to predict LVSD (defined as ejection fraction ≤50%). Survival analysis was performed using Kaplan–Meier curves and the log-rank test. Results: Of the total population, 2734 patients had LVSD and 8397 had preserved EF. DenseNet-121 and ResNet-101 demonstrated excellent discrimination for LVSD with AUROCs of 0.930 and 0.925, accuracies of 0.887 and 0.860, sensitivities of 0.821 and 0.856, and specificities of 0.908 and 0.861, respectively. In the test set, patients predicted to have LVSD showed a significantly higher risk of echocardiographic LVSD (hazard ratio 9.89, 95% CI 8.20–11.92, p = 0.005) and lower 24-month survival (log-rank p < 0.001). Conclusions: AI-enabled ECG models predicted future LVSD from clinically normal ECGs recorded up to two years prior to imaging. These findings suggest a potential role for AI-ECG in the early detection of subclinical LVSD and improved risk stratification in asymptomatic individuals.

Background/Objectives: Catheter ablation is an effective treatment for atrial fibrillation (AF) but is associated with femoral vascular complications. While anticoagulation therapy has been linked to these complications, specific risk factors remain unclear. This study assessed the incidence and predictors of vascular complications after catheter ablation using systematic duplex ultrasound (DUS) as well as their outcomes. Methods: A single-center observational study was conducted with 404 consecutive AF patients who underwent catheter ablation between March 2023 and February 2024. DUS was performed systematically post-procedure in all patients to identify complications; these were primarily treated with DUS-guided manual compression. Results: Vascular complications were observed in 6.4% of patients, higher than reported in previous studies. Hematomas (3.5%) and arteriovenous fistulas (AVFs, 2.0%) were the most common such complications. Multivariate analysis identified repeat ablation (odds ratio [OR] 3.09, 95% confidence interval [CI] 1.10–8.64, p = 0.03) and months of experience <6 months (OR 3.42, 95% CI 1.36–8.63, p = 0.01) as significant predictors of complications. DUS-guided compression managed most complications successfully, with three pseudoaneurysms resolved through compression and one through embolization. However, AVFs were relatively resistant to conservative management, often necessitating prolonged observation or intervention. Conclusions: Systematic DUS following catheter ablation revealed a higher-than-expected incidence of vascular complications. Repeat ablation and months of experience <6 months are potential predictors of femoral vascular complications. DUS-guided compression is effective for most complications, although AVFs present greater treatment challenges.

Park S, et al. Int J Arrhythm. 2026 ;27:e7. https://doi.org/10.18501/ija.2026.27.e7