Electrical Cardioversion Outcome Prognosis: A Multivariate Multiscale Entropy Characterization of Atrial Activity in Persistent Atrial Fibrillation

Abstract

Background: Atrial fibrillation (AF) remains a significant cause of stroke, heart failure, and cardiovascular morbidity worldwide. Despite advancements in AF management, electrical cardioversion (ECV) remains the most commonly used technique for sinus rhythm (SR) restoration although presenting a limited success rate in the mid-term along with a high number of side-effects which can lead to an increase in patients health deterioration and, consequently, in healthcare costs. Hence, predicting ECV outcome in the mid-term remains a challenging task. Here, a new framework based on multivariate multiscale entropy (MMSE) characterization of atrial activity is proposed to improve ECV outcome prediction in the mid-term. Methods: 58 patients with persistent AF scheduled for ECV were considered. A 12-Lead standard ECG segment of 1.5 min duration prior to the first electrical shock was analyzed. The atrial activity (AA) is estimated from the 12-lead surface ECG using a QT segment removal algorithm based on QRS complex estimation and pattern recognition techniques. AA is characterized by means of multivariate extensions of traditional indices such as the amplitude of the fibrillatory waves and dominant frequency along with multivariate extensions of complexity measures as multivariate Sample Entropy and finally Multivariate Multiscale Entropy (MMSE). These indices were estimated over 12-lead ECG records from 58 ECV derived patients who were classified based on SR maintenance after 30-day follow up (mid-term evaluation). ECV prognosis was evaluated using ROC curves and Youden’s Criteria for optimal threshold establishment. Performance was compared to that of unidimensional indices. Results: Patients who maintained SR post-ECV exhibited distinct complexity patterns compared to those who relapsed into AF. Specifically, MMSE provided higher discriminant accuracy than traditional unidimensional indices. When considering only the limb leads in the analysis, the best performance was achieved, over 83% accurate classification of SR restoration in the mid-term (Se = 0.74, Sp = 0.85, p ≤ 0.001). Additionally, the accumulated entropy and slope of the MMSE curves, offered robust predictors of ECV outcomes providing better balanced sensitivity and specificity ROC curves. Conclusions: This work highlights the importance of multivariate approaches in AF characterization and provides a comprehensive framework for improving ECV outcome prediction, providing an increase in almost a 30% of correct predictions in the mid-term. Future research should explore the integration of these methods into clinical practice to optimize treatment strategies for AF patients and reduced healthcare costs.