Dataset Information

Machine learning enables noninvasive prediction of atrial fibrillation driver location and acute pulmonary vein ablation success using the 12-lead ECG.

ABSTRACT:

Background

Atrial fibrillation (AF) is the most common supraventricular arrhythmia, characterized by disorganized atrial electrical activity, maintained by localized arrhythmogenic atrial drivers. Pulmonary vein isolation (PVI) allows to exclude PV-related drivers. However, PVI is less effective in patients with additional extra-PV arrhythmogenic drivers.

Objectives

To discriminate whether AF drivers are located near the PVs vs extra-PV regions using the noninvasive 12-lead electrocardiogram (ECG) in a computational and clinical framework, and to computationally predict the acute success of PVI in these cohorts of data.

Methods

AF drivers were induced in 2 computerized atrial models and combined with 8 torso models, resulting in 1128 12-lead ECGs (80 ECGs with AF drivers located in the PVs and 1048 in extra-PV areas). A total of 103 features were extracted from the signals. Binary decision tree classifier was trained on the simulated data and evaluated using hold-out cross-validation. The PVs were subsequently isolated in the models to assess PVI success. Finally, the classifier was tested on a clinical dataset (46 patients: 23 PV-dependent AF and 23 with additional extra-PV sources).

Results

The classifier yielded 82.6% specificity and 73.9% sensitivity for detecting PV drivers on the clinical data. Consistency analysis on the 46 patients resulted in 93.5% results match. Applying PVI on the simulated AF cases terminated AF in 100% of the cases in the PV class.

Conclusion

Machine learning-based classification of 12-lead-ECG allows discrimination between patients with PV drivers vs those with extra-PV drivers of AF. The novel algorithm may aid to identify patients with high acute success rates to PVI.

SUBMITTER: Luongo G

PROVIDER: S-EPMC8053175 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description: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.