Preprocedure Application of Machine Learning and Mechanistic Simulations Predicts Likelihood of Paroxysmal Atrial Fibrillation Recurrence Following Pulmonary Vein Isolation

Abstract

Background - Pulmonary vein isolation (PVI) is an effective treatment strategy for patients with atrial fibrillation (AF), but many experience AF recurrence and require repeat ablation procedures. The goal of this study was to develop and evaluate a methodology which combines machine learning (ML) and personalized computational modeling to predict, prior to PVI, which patients are most likely to experience AF recurrence after PVI. Methods - This single-center retrospective proof-of-concept study included 32 patients with documented paroxysmal AF who underwent PVI and had pre-procedural late gadolinium enhanced magnetic resonance imaging (LGE-MRI). For each patient, a personalized computational model of the left atrium simulated AF induction via rapid pacing. Features were derived from pre-PVI LGE-MRI images and from results of simulations (SimAF). The most predictive features were used as input to a quadratic discriminant analysis ML classifier, which was trained, optimized, and evaluated with 10-fold nested cross validation to predict the probability of AF recurrence post-PVI. Results - In our cohort, the ML classifier predicted probability of AF recurrence with an average validation sensitivity and specificity of 82% and 89%, respectively, and a validation AUC of 0.82. Dissecting the relative contributions of SimAF and raw images to the predictive capability of the ML classifier, we found that when only features from SimAF were used to train the ML classifier, its performance remained similar (validation AUC=0.81). However, when only features extracted from raw images were used for training, the validation AUC significantly decreased (0.47). Conclusions - ML and personalized computational modeling can be used together to accurately predict, using only pre-PVI LGE-MRI scans as input, whether a patient is likely to experience AF recurrence following PVI, even when the patient cohort is small.

Computational modeling identifies embolic stroke of undetermined source patients with potential arrhythmic substrate

“…As in previous studies ( Ali et al, 2019 ; Shade et al, 2020 ), our models do not differentiate between cell- or tissue-scale properties of atrial electrophysiology between patients with paroxysmal and persistent forms of AFib. Likewise, our approach to characterizing potential arrhythmia propensity in ESUS patients assumes cell- and tissue-scale remodeling based on experimental and clinical data from the AFib milieu.…”

The 4S-AF Scheme (Stroke Risk; Symptoms; Severity of Burden; Substrate): A Novel Approach to In-Depth Characterization (Rather than Classification) of Atrial Fibrillation

“…45 The rapidly advancing technologies such as machine learning may also enhance the characterization of correlates for atrial structure in the risk assessment of AF recurrence. 46 With increasing evidence about the clinical application of the recently proposed concept of atrial cardiomyopathy, 47 the assessment, classification, and staging of the atrial disease may become the cornerstone of the Su domain in the 4S-AF scheme.…”

Computational Modeling Identifies Embolic Stroke of Undetermined Source Patients with Potential Arrhythmic Substrate

“…As in previous studies (23, 24), our models do not differentiate between cell-or tissue-scale properties of atrial electrophysiology between patients with paroxysmal and persistent forms of AFib. Likewise, our approach to characterizing potential arrhythmia propensity in ESUS patients assumes cell- and tissue-scale remodeling based on experimental and clinical data from the AFib milieu.…”

“…As in previous studies (25,26), our models do not differentiate between cell-or tissue-scale properties of atrial electrophysiology between patients with paroxysmal and persistent forms of AFib.…”