Surface ECG and intracardiac spectral measures predict atrial fibrillation recurrence after catheter ablation

Combination of frequency- and time-domain characteristics of the fibrillatory waves for enhanced prediction of persistent atrial fibrillation recurrence after catheter ablation

Catheter ablation (CA) remains the cornerstone alternative to cardioversion for sinus rhythm (SR) restoration in patients with atrial fibrillation (AF). Unfortunately, despite the last methodological and technological advances, this procedure is not consistently effective in treating persistent AF. Beyond introducing new indices to characterize the fibrillatory waves (f-waves) recorded through the preoperative electrocardiogram (ECG), the aim of this study is to combine frequency- and time-domain features to improve CA outcome prediction and optimize patient selection for the procedure, given the absence of any study that jointly analyzes information from both domains. Precisely, the f-waves of 151 persistent AF patients undergoing their first CA procedure were extracted from standard V1 lead. Novel spectral and amplitude features were derived from these waves and combined through a machine learning algorithm to anticipate the intervention mid-term outcome. The power rate index (φ), which estimates the power of the harmonic content regarding the dominant frequency (DF), yielded the maximum individual discriminant ability of 64% to discern between individuals who experienced a recurrence of AF and those who sustained SR after a 9-month follow-up period. The predictive accuracy was improved up to 78.5% when this parameter φ was merged with the amplitude spectrum area in the DF bandwidth (A M S A L F ) and the normalized amplitude of the f-waves into a prediction model based on an ensemble classifier, built by random undersampling boosting of decision trees. This outcome suggests that the synthesis of both spectral and temporal features of the f-waves before CA might enrich the prognostic knowledge of this therapy for persistent AF patients.

Predictive value of interatrial block on electrocardiogram among obese patients undergoing atrial fibrillation ablation

BACKGROUND

Determine a predictive value of interatrial block (IAB) on atrial fibrillation (AF) ablation outcomes in obese patients.

METHODS

Medical records were retrospectively reviewed for 205 consecutive patients with body mass indices (BMI) ≥ 30 kg/m2 who underwent initial AF ablation. Evidence of partial IAB defined as P-wave duration (PWD) ≥ 120 ms and advanced IAB with PWD ≥ 120 ms and biphasic or negative P-wave in inferior leads was examined from sinus electrocardiograms (ECGs) within 1-year pre-ablation. The primary outcome was recurrent atrial arrhythmia after 3-month blanking period post-ablation.

RESULTS

The mean BMI was 36.9 ± 5.7 kg/m2. Partial IAB and advanced IAB were observed in 155 (75.61%) and 42 (20.49%) patients, respectively. During the median follow-up of 1.35 (interquartile range 0.74, 2.74) years, 115 (56.1%) patients had recurrent atrial arrhythmias. In multivariable analysis adjusting for age, gender, persistent AF, use of antiarrhythmic drugs (AADs), left atrial volume index (LAVI), partial IAB, and advanced IAB were independent predictors of recurrent arrhythmia with hazard ratio (HR) of 2.80 (95% confidence interval [CI] 1.47-6.05; p = 0.001) and HR 1.79 (95% CI 1.11-2.82; p = 0.017), respectively. The results were similar in a subgroup analysis of patients who had no severe left atrial enlargement and a subgroup analysis of patients who were not on AADs.

CONCLUSIONS

IAB is highly prevalent in patients with obesity and AF. Partial IAB, defined as PWD ≥ 120 ms, and advanced IAB with evidence of biphasic P-wave in inferior leads were independently associated with increased risk of recurrent arrhythmia after AF ablation. Its predictive value is independent of other traditional risk factors, LAVI, or use of AADs.

A 3D-CNN with temporal-attention block to predict the recurrence of atrial fibrillation based on body-surface potential mapping signals

Catheter ablation has become an important treatment for atrial fibrillation (AF), but its recurrence rate is still high. The aim of this study was to predict AF recurrence using a three-dimensional (3D) network model based on body-surface potential mapping signals (BSPMs). BSPMs were recorded with a 128-lead vest in 14 persistent AF patients before undergoing catheter ablation (Maze-IV). The torso geometry was acquired and meshed by point cloud technology, and the BSPM was interpolated into the torso geometry by the inverse distance weighted (IDW) method to generate the isopotential map. Experiments show that the isopotential map of BSPMs can reflect the propagation of the electrical wavefronts. The 3D isopotential sequence map was established by combining the spatial–temporal information of the isopotential map; a 3D convolutional neural network (3D-CNN) model with temporal attention was established to predict AF recurrence. Our study proposes a novel attention block that focuses the characteristics of atrial activations to improve sampling accuracy. In our experiment, accuracy (ACC) in the intra-patient evaluation for predicting the recurrence of AF was 99.38%. In the inter-patient evaluation, ACC of 3D-CNN was 81.48%, and the area under the curve (AUC) was 0.88. It can be concluded that the dynamic rendering of multiple isopotential maps can not only comprehensively display the conduction of cardiac electrical activity on the body surface but also successfully predict the recurrence of AF after CA by using 3D isopotential sequence maps.

Preoperative Prediction of Catheter Ablation Outcome in Persistent Atrial Fibrillation Patients through Spectral Organization Analysis of the Surface Fibrillatory Waves

Catheter ablation (CA) is a commonly used treatment for persistent atrial fibrillation (AF). Since its medium/long-term success rate remains limited, preoperative prediction of its outcome is gaining clinical interest to optimally select candidates for the procedure. Among predictors based on the surface electrocardiogram, the dominant frequency (DF) and harmonic exponential decay (γ) of the fibrillatory waves (f-waves) have reported promising but clinically insufficient results. Hence, the main goal of this work was to conduct a broader analysis of the f-wave harmonic spectral structure to improve CA outcome prediction through several entropy-based measures computed on different frequency bands. On a database of 151 persistent AF patients under radio-frequency CA and a follow-up of 9 months, the newly introduced parameters discriminated between patients who relapsed to AF and those who maintained SR at about 70%, which was statistically superior to the DF and approximately similar to γ. They also provided complementary information to γ through different combinations in multivariate models based on lineal discriminant analysis and report classification performance improvement of about 5%. These results suggest that the presence of larger harmonics and a proportionally smaller DF peak is associated with a decreased probability of AF recurrence after CA.

Prediction of Atrial Fibrillation Using Machine Learning: A Review

There has been recent immense interest in the use of machine learning techniques in the prediction and screening of atrial fibrillation, a common rhythm disorder present with significant clinical implications primarily related to the risk of ischemic cerebrovascular events and heart failure. Prior to the advent of the application of artificial intelligence in clinical medicine, previous studies have enumerated multiple clinical risk factors that can predict the development of atrial fibrillation. These clinical parameters include previous diagnoses, laboratory data (e.g., cardiac and inflammatory biomarkers, etc.), imaging data (e.g., cardiac computed tomography, cardiac magnetic resonance imaging, echocardiography, etc.), and electrophysiological data. These data are readily available in the electronic health record and can be automatically queried by artificial intelligence algorithms. With the modern computational capabilities afforded by technological advancements in computing and artificial intelligence, we present the current state of machine learning methodologies in the prediction and screening of atrial fibrillation as well as the implications and future direction of this rapidly evolving field.

Atrial Remodeling in Atrial Fibrillation. Comorbidities and Markers of Disease Progression Predict Catheter Ablation Outcome

Atrial fibrillation is the most common supraventricular arrhythmia affecting an increasing proportion of the population in which mainstream therapy, i.e. catheter ablation, provides freedom from arrhythmia in only a limited number of patients. Understanding the mechanism is key in order to find more effective therapies and to improve patient selection. In this review, the structural and electrophysiological changes of the atrial musculature that constitute atrial remodeling in atrial fibrillaton and how risk factors and markers of disease progression can predict catheter ablation outcome will be discussed in detail.

ECG-Based Indices to Characterize Persistent Atrial Fibrillation Before and During Stepwise Catheter Ablation

Background: Consistently successful patient outcomes following catheter ablation (CA) for treatment of persistent atrial fibrillation (pers-AF) remain elusive. We propose an electrocardiogram (ECG) analysis designed to (1) refine selection of patients most likely to benefit from ablation, and (2) examine the temporal evolution of AF organization indices that could act as clinical indicators of ongoing ablation effectiveness and completeness.

Method: Twelve-lead ECG was continuously recorded in 40 patients (61 ± 8 years) during stepwise CA (step-CA) procedures for treatment of pers-AF (sustained duration 19 ± 11 months). Following standard pre-processing, ECG signals were divided into 10-s epochs and labeled according to their temporal placement: pre-PVI (baseline), dur-PVI (during pulmonary vein isolation), and post-PVI (during complex-fractionated atrial electrograms and linear ablation). Instantaneous frequency (IF), adaptive organization index (AOI), sample entropy (SampEn) and f-wave amplitude (FWA) measures were calculated and analyzed during each of the three temporal steps. Temporal evolution of these measures was assessed using a statistical test for mean value transitions, as an indicator of changes in AF organization. Results were then compared between: (i) patients grouped according to step-CA outcome; (ii) patients grouped according to type of arrhythmia recurrence following the procedure, if applicable; (iii) within the same patient group during the three different temporal steps.

Results: Stepwise CA patient outcomes were as follows: (1) left-atrium (LA) terminated, not recurring (LTN, n = 8), (2) LA terminated, recurring (LTR, n = 20), and (3) not LA terminated, all recurring at follow-up (NLT, n = 12). Among the LTR and NLT patients, recurrence occurred as AF in seven patients and atrial tachycardia or atrial flutter (AT/AFL) in the remaining 25 patients. The ECG measures indicated the lowest level of organization in the NLT group for all ablation steps. The highest organization was observed in the LTN group, while the LTR group displayed an intermediate level of organization. Regarding time evolution of ECG measures in dur-PVI and post-PVI recordings, stepwise ablation led to increases in AF organization in most patients, with no significant differences between the LTN, LTR, and NLT groups. The median decrease in IF and increase in AOI were significantly greater in AT/AFL recurring patients than in AF recurring patients; however, changes in the SampEn and FWA parameters were not significantly different between types of recurrence.

Conclusion: Noninvasive ECG measures, though unable to predict arrhythmia recurrence following ablation, show the lowest levels of AF organization in patients that do not respond well to step-CA. Increasing AF organization in post-PVI may be associated with organized arrhythmia recurrence after a single ablation procedure.

Severe and uniform bi-atrial remodeling measured by dominant frequency analysis in persistent atrial fibrillation unresponsive to ablation

BACKGROUND

High values of ECG and intracardiac dominant frequency (DF) are indicative of significant atrial remodeling in persistent atrial fibrillation (peAF). We hypothesized that patients with peAF unresponsive to ablation display higher ECG and intracardiac DFs than those remaining in sinus rhythm (SR) on the long term.

METHODS

Forty consecutive patients underwent stepwise ablation for peAF (sustained duration 19 ± 11 months). Electrograms were recorded before ablation at 13 left atrium (LA) sites and at the right atrial appendage (RAA) and coronary sinus (CS) synchronously to the ECG. DF was defined as the highest peak within the power spectrum.

RESULTS

peAF was terminated within the LA in 28 patients (left-terminated [LT]), whereas 12 patients remaining in AF after ablation (not left-terminated [NLT]) were cardioverted. Over a mean follow-up of 34 ± 14 months, all 12 NLT patients had a recurrence. Of the LT patients, 71% had a recurrence (20/28, LT_Rec), while 29% remained in SR throughout the follow-up (8/28, LT_SR). DF values and correlations between pairs of LA appendage (LAA), RAA, and CS DFs showed distinctive patterns among the subgroups. The NLT subgroup displayed the highest ECG and intracardiac DFs, with strong intragroup homogeneity between pairs of CS and LAA DFs, and to a lesser extent between pairs of CS and RAA DFs. Conversely, the LT_SR subgroup showed the lowest DFs, with significant intragroup heterogeneity between pairs of CS and both LAA and RAA DFs.

CONCLUSIONS

Patients with peAF unresponsive to ablation show high surface and intracardiac DFs indicative of severe and uniform bi-atrial remodeling.