Spectral and spatiotemporal variability ECG parameters linked to catheter ablation outcome in persistent atrial fibrillation. (1st September 2017)

• Record Type: Journal Article
• Authors: Hidalgo-Muñoz, Antonio R.; Latcu, Decebal G.; Meo, Marianna; Meste, Olivier; Popescu, Irina; Saoudi, Nadir; Zarzoso, Vicente
• Is Part Of: Computers in biology and medicine. Volume 88(2017)
• Page Start: 126
• Page End: 131
• Publication Date: 2017-09-01
• Subjects: Atrial fibrillation -- Catheter ablation -- ECG -- Logistic regression -- Predictive model -- Spatiotemporal variability -- Spectral feature; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2017.07.004
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: With the increasing prevalence of atrial fibrillation (AF), there is a strong clinical interest in determining whether a patient suffering from persistent AF will benefit from catheter ablation (CA) therapy at long term. This work presents several regression models based on noninvasive measures automatically computed from the standard 12-lead electrocardiogram (ECG) such as AF dominant frequency (DF), spectral concentration and spatiotemporal variability (STV). Sixty-two AF patients referred to CA were enrolled in this study. Forty-seven of them had no recurrence after CA during an average follow-up of 14 ± 8 months. The ECG features were extracted from an ECG recorded before the CA intervention and they were combined by means of logistic regression. The combination of DF and STV values from different precordial leads reached AUC = 0.939, outperforming the best results by using only one kind of features, such as DF (AUC = 0.801), and yielding a global accuracy of 93.5% for discriminating the best long-term responders to CA. These results point out the need to take into consideration the spatial variation of spectral ECG parameters to build predictive models dealing with AF. Highlights: Long-term outcome of catheter ablation in persistent atrial fibrillation is predicted. ECG features include dominant frequency (DF) and spatiotemporal variability (STV). Combining features from multiple ECG leads by logistic regression improves accuracy. Combining two families of multi-lead predictors further boosts performance. Used together, DF and STV yield an accuracy of up to 94%.