Prediction Of Early Failure In Electrical Cardioversion Of Atrial Fibrillation Using Refined Multiscale Entropy

In the management of atrial fibrillation (AF), electrical cardioversion (ECV) is a common treatment. Although its initial success rate is high, many patients present AF recurrence after some weeks or months. Hence, being able to identify patients at low chance of mid-term sinus rhythm maintenance is important for a rationale therapeutic strategy. To this end, several parameters assessing fibrillatory (f-) waves have been introduced, however, with limited predictive ability. Moreover, the cardiovascular system exhibits nonlinear dynamics at different time-scales that these indices do not account for. Hence, the present work evaluates the ability of the multiscale entropy (MSE) analysis of the f-waves to improve preoperative forecasts of ECV outcome. Both traditional MSE and a refined version (RMSE) were applied to the main f-waves component obtained for standard lead V1. As a reference, previously proposed predictors were also computed. Results revealed that RMSE was able to anticipate AF recurrence after 1 month of ECV with an accuracy around 78%. Moreover, a Naive Bayes model combining previous parameters and RMSE indices reported a discriminant ability 10% higher than single metrics. It could then be concluded that analysis of nonlinear dynamics at large time-scales can enhance ECV outcome predictions.