Atrial fibrillation ablation outcome prediction with a machine learning fusion framework incorporating cardiac computed tomography.

BACKGROUND: Structural changes in the left atrium (LA) modestly predict outcomes in patients undergoing catheter ablation for atrial fibrillation (AF). Machine learning (ML) is a promising approach to personalize AF management strategies and improve predictive risk models after catheter ablation by integrating atrial geometry from cardiac computed tomography (CT) scans and patient-specific clinical data. We hypothesized that ML approaches based on a patient's specific data can identify responders to AF ablation. METHODS: Consecutive patients undergoing AF ablation, who had preprocedural CT scans, demographics, and 1-year follow-up data, were included in the study for a retrospective analysis. The inputs of models were CT-derived morphological features from left atrial segmentation (including the shape, volume of the LA, LA appendage, and pulmonary vein ostia) along with deep features learned directly from raw CT images, and clinical data. These were merged intelligently in a framework to learn their individual importance and produce the optimal classification. RESULTS: Three hundred twenty-one patients (64.2 ± 10.6 years, 69% male, 40% paroxysmal AF) were analyzed. Post 10-fold nested cross-validation, the model trained to intelligently merge and learn appropriate weights for clinical, morphological, and imaging data (AUC 0.821) outperformed those trained solely on clinical data (AUC 0.626), morphological (AUC 0.659), or imaging data (AUC 0.764). CONCLUSION: Our ML approach provides an end-to-end automated technique to predict AF ablation outcomes using deep learning from CT images, derived structural properties of LA, augmented by incorporation of clinical data in a merged ML framework. This can help develop personalized strategies for patient selection in invasive management of AF.

Machine Learning-Enabled Multimodal Fusion of Intra-Atrial and Body Surface Signals in Prediction of Atrial Fibrillation Ablation Outcomes.

BACKGROUND: Machine learning is a promising approach to personalize atrial fibrillation management strategies for patients after catheter ablation. Prior atrial fibrillation ablation outcome prediction studies applied classical machine learning methods to hand-crafted clinical scores, and none have leveraged intracardiac electrograms or 12-lead surface electrocardiograms for outcome prediction. We hypothesized that (1) machine learning models trained on electrograms or electrocardiogram (ECG) signals can perform better at predicting patient outcomes after atrial fibrillation ablation than existing clinical scores and (2) multimodal fusion of electrogram, ECG, and clinical features can further improve the prediction of patient outcomes. METHODS: Consecutive patients who underwent catheter ablation between 2015 and 2017 with panoramic left atrial electrogram before ablation and clinical follow-up for at least 1 year following ablation were included. Convolutional neural network and a novel multimodal fusion framework were developed for predicting 1-year atrial fibrillation recurrence after catheter ablation from electrogram, ECG signals, and clinical features. The models were trained and validated using 10-fold cross-validation on patient-level splits. RESULTS: One hundred fifty-six patients (64.5±10.5 years, 74% male, 42% paroxysmal) were analyzed. Using electrogram signals alone, the convolutional neural network achieved an area under the receiver operating characteristics curve (AUROC) of 0.731, outperforming the existing APPLE scores (AUROC=0.644) and CHA2DS2-VASc scores (AUROC=0.650). Similarly using 12-lead ECG alone, the convolutional neural network achieved an AUROC of 0.767. Combining electrogram, ECG, and clinical features, the fusion model achieved an AUROC of 0.859, outperforming single and dual modality models. CONCLUSIONS: Deep neural networks trained on electrogram or ECG signals improved the prediction of catheter ablation outcome compared with existing clinical scores, and fusion of electrogram, ECG, and clinical features further improved the prediction. This suggests the promise of using machine learning to help treatment planning for patients after catheter ablation.

Atrial fibrillation signatures on intracardiac electrograms identified by deep learning.

BACKGROUND: Automatic detection of atrial fibrillation (AF) by cardiac devices is increasingly common yet suboptimally groups AF, flutter or tachycardia (AT) together as 'high rate events'. This may delay or misdirect therapy. OBJECTIVE: We hypothesized that deep learning (DL) can accurately classify AF from AT by revealing electrogram (EGM) signatures. METHODS: We studied 86 patients in whom the diagnosis of AF or AT was established at electrophysiological study (25 female, 65 ± 11 years). Custom DL architectures were trained to identify AF using N = 29,340 unipolar and N = 23,760 bipolar EGM segments. We compared DL to traditional classifiers based on rate or regularity. We explained DL using computer models to assess the impact of controlled variations in shape, rate and timing on AF/AT classification in 246,067 EGMs reconstructed from clinical data. RESULTS: DL identified AF with AUC of 0.97 ± 0.04 (unipolar) and 0.92 ± 0.09 (bipolar). Rule-based classifiers misclassified ∼10-12% of cases. DL classification was explained by regularity in EGM shape (13%) or timing (26%), and rate (60%; p < 0.001), and also by a set of unipolar EGM shapes that classified as AF independent of rate or regularity. Overall, the optimal AF 'fingerprint' comprised these specific EGM shapes, >15% timing variation, <0.48 correlation in beat-to-beat EGM shapes and CL < 190 ms (p < 0.001). CONCLUSIONS: Deep learning of intracardiac EGMs can identify AF or AT via signatures of rate, regularity in timing or shape, and specific EGM shapes. Future work should examine if these signatures differ between different clinical subpopulations with AF.

Three dimensional reconstruction to visualize atrial fibrillation activation patterns on curved atrial geometry.

BACKGROUND: The rotational activation created by spiral waves may be a mechanism for atrial fibrillation (AF), yet it is unclear how activation patterns obtained from endocardial baskets are influenced by the 3D geometric curvature of the atrium or 'unfolding' into 2D maps. We develop algorithms that can visualize spiral waves and their tip locations on curved atrial geometries. We use these algorithms to quantify differences in AF maps and spiral tip locations between 3D basket reconstructions, projection onto 3D anatomical shells and unfolded 2D surfaces. METHODS: We tested our algorithms in N = 20 patients in whom AF was recorded from 64-pole baskets (Abbott, CA). Phase maps were generated by non-proprietary software to identify the tips of spiral waves, indicated by phase singularities. The number and density of spiral tips were compared in patient-specific 3D shells constructed from the basket, as well as 3D maps from clinical electroanatomic mapping systems and 2D maps. RESULTS: Patients (59.4±12.7 yrs, 60% M) showed 1.7±0.8 phase singularities/patient, in whom ablation terminated AF in 11/20 patients (55%). There was no difference in the location of phase singularities, between 3D curved surfaces and 2D unfolded surfaces, with a median correlation coefficient between phase singularity density maps of 0.985 (0.978-0.990). No significant impact was noted by phase singularities location in more curved regions or relative to the basket location (p>0.1). CONCLUSIONS: AF maps and phase singularities mapped by endocardial baskets are qualitatively and quantitatively similar whether calculated by 3D phase maps on patient-specific curved atrial geometries or in 2D. Phase maps on patient-specific geometries may be easier to interpret relative to critical structures for ablation planning.

Machine Learned Cellular Phenotypes in Cardiomyopathy Predict Sudden Death.

RATIONALE: Susceptibility to VT/VF (ventricular tachycardia/fibrillation) is difficult to predict in patients with ischemic cardiomyopathy either by clinical tools or by attempting to translate cellular mechanisms to the bedside. OBJECTIVE: To develop computational phenotypes of patients with ischemic cardiomyopathy, by training then interpreting machine learning of ventricular monophasic action potentials (MAPs) to reveal phenotypes that predict long-term outcomes. METHODS AND RESULTS: We recorded 5706 ventricular MAPs in 42 patients with coronary artery disease and left ventricular ejection fraction ≤40% during steady-state pacing. Patients were randomly allocated to independent training and testing cohorts in a 70:30 ratio, repeated K=10-fold. Support vector machines and convolutional neural networks were trained to 2 end points: (1) sustained VT/VF or (2) mortality at 3 years. Support vector machines provided superior classification. For patient-level predictions, we computed personalized MAP scores as the proportion of MAP beats predicting each end point. Patient-level predictions in independent test cohorts yielded c-statistics of 0.90 for sustained VT/VF (95% CI, 0.76-1.00) and 0.91 for mortality (95% CI, 0.83-1.00) and were the most significant multivariate predictors. Interpreting trained support vector machine revealed MAP morphologies that, using in silico modeling, revealed higher L-type calcium current or sodium-calcium exchanger as predominant phenotypes for VT/VF. CONCLUSIONS: Machine learning of action potential recordings in patients revealed novel phenotypes for long-term outcomes in ischemic cardiomyopathy. Such computational phenotypes provide an approach which may reveal cellular mechanisms for clinical outcomes and could be applied to other conditions.

Machine Learning to Classify Intracardiac Electrical Patterns During Atrial Fibrillation: Machine Learning of Atrial Fibrillation.

BACKGROUND: Advances in ablation for atrial fibrillation (AF) continue to be hindered by ambiguities in mapping, even between experts. We hypothesized that convolutional neural networks (CNN) may enable objective analysis of intracardiac activation in AF, which could be applied clinically if CNN classifications could also be explained. METHODS: We performed panoramic recording of bi-atrial electrical signals in AF. We used the Hilbert-transform to produce 175 000 image grids in 35 patients, labeled for rotational activation by experts who showed consistency but with variability (kappa [κ]=0.79). In each patient, ablation terminated AF. A CNN was developed and trained on 100 000 AF image grids, validated on 25 000 grids, then tested on a separate 50 000 grids. RESULTS: In the separate test cohort (50 000 grids), CNN reproducibly classified AF image grids into those with/without rotational sites with 95.0% accuracy (CI, 94.8%-95.2%). This accuracy exceeded that of support vector machines, traditional linear discriminant, and k-nearest neighbor statistical analyses. To probe the CNN, we applied gradient-weighted class activation mapping which revealed that the decision logic closely mimicked rules used by experts (C statistic 0.96). CONCLUSIONS: CNNs improved the classification of intracardiac AF maps compared with other analyses and agreed with expert evaluation. Novel explainability analyses revealed that the CNN operated using a decision logic similar to rules used by experts, even though these rules were not provided in training. We thus describe a scaleable platform for robust comparisons of complex AF data from multiple systems, which may provide immediate clinical utility to guide ablation. Registration: URL: https://www.clinicaltrials.gov; Unique identifier: NCT02997254. Graphic Abstract: A graphic abstract is available for this article.

Termination of persistent atrial fibrillation by ablating sites that control large atrial areas.

AIMS: Persistent atrial fibrillation (AF) has been explained by multiple mechanisms which, while they conflict, all agree that more disorganized AF is more difficult to treat than organized AF. We hypothesized that persistent AF consists of interacting organized areas which may enlarge, shrink or coalesce, and that patients whose AF areas enlarge by ablation are more likely to respond to therapy. METHODS AND RESULTS: We mapped vectorial propagation in persistent AF using wavefront fields (WFF), constructed from raw unipolar electrograms at 64-pole basket catheters, during ablation until termination (Group 1, N = 20 patients) or cardioversion (Group 2, N = 20 patients). Wavefront field mapping of patients (age 61.1 ± 13.2 years, left atrium 47.1 ± 6.9 mm) at baseline showed 4.6 ± 1.0 organized areas, each separated by disorganization. Ablation of sites that led to termination controlled larger organized area than competing sites (44.1 ± 11.1% vs. 22.4 ± 7.0%, P < 0.001). In Group 1, ablation progressively enlarged unablated areas (rising from 32.2 ± 15.7% to 44.1 ± 11.1% of mapped atrium, P < 0.0001). In Group 2, organized areas did not enlarge but contracted during ablation (23.6 ± 6.3% to 15.2 ± 5.6%, P < 0.0001). CONCLUSION: Mapping wavefront vectors in persistent AF revealed competing organized areas. Ablation that progressively enlarged remaining areas was acutely successful, and sites where ablation terminated AF were surrounded by large organized areas. Patients in whom large organized areas did not emerge during ablation did not exhibit AF termination. Further studies should define how fibrillatory activity is organized within such areas and whether this approach can guide ablation.

Wavefront Field Mapping Reveals a Physiologic Network Between Drivers Where Ablation Terminates Atrial Fibrillation.

BACKGROUND: Localized drivers are proposed mechanisms for persistent atrial fibrillation (AF) from optical mapping of human atria and clinical studies of AF, yet are controversial because drivers fluctuate and ablating them may not terminate AF. We used wavefront field mapping to test the hypothesis that AF drivers, if concurrent, may interact to produce fluctuating areas of control to explain their appearance/disappearance and acute impact of ablation. METHODS: We recruited 54 patients from an international registry in whom persistent AF terminated by targeted ablation. Unipolar AF electrograms were analyzed from 64-pole baskets to reconstruct activation times, map propagation vectors each 20 ms, and create nonproprietary phase maps. RESULTS: Each patient (63.6±8.5 years, 29.6% women) showed 4.0±2.1 spatially anchored rotational or focal sites in AF in 3 patterns. First, a single (type I; n=7) or, second, paired chiral-antichiral (type II; n=5) rotational drivers controlled most of the atrial area. Ablation of 1 to 2 large drivers terminated all cases of types I or II AF. Third, interaction of 3 to 5 drivers (type III; n=42) with changing areas of control. Targeted ablation at driver centers terminated AF and required more ablation in types III versus I (P=0.02 in left atrium). CONCLUSIONS: Wavefront field mapping of persistent AF reveals a pathophysiologic network of a small number of spatially anchored rotational and focal sites, which interact, fluctuate, and control varying areas. Future work should define whether AF drivers that control larger atrial areas are attractive targets for ablation.

Online webinar training to analyse complex atrial fibrillation maps: A randomized trial.

BACKGROUND: Specific tools have been recently developed to map atrial fibrillation (AF) and help guide ablation. However, when used in clinical practice, panoramic AF maps generated from multipolar intracardiac electrograms have yielded conflicting results between centers, likely due to their complexity and steep learning curve, thus limiting the proper assessment of its clinical impact. OBJECTIVES: The main purpose of this trial was to assess the impact of online training on the identification of AF driver sites where ablation terminated persistent AF, through a standardized training program. Extending this concept to mobile health was defined as a secondary objective. METHODS: An online database of panoramic AF movies was generated from a multicenter registry of patients in whom targeted ablation terminated non-paroxysmal AF, using a freely available method (Kuklik et al-method A) and a commercial one (RhythmView-method B). Cardiology Fellows naive to AF mapping were enrolled and randomized to training vs no training (control). All participants evaluated an initial set of movies to identify sites of AF termination. Participants randomized to training evaluated a second set of movies in which they received feedback on their answers. Both groups re-evaluated the initial set to assess the impact of training. This concept was then migrated to a smartphone application (App). RESULTS: 12 individuals (median age of 30 years (IQR 28-32), 6 females) read 480 AF maps. Baseline identification of AF termination sites by ablation was poor (40%±12% vs 42%±11%, P = 0.78), but similar for both mapping methods (P = 0.68). Training improved accuracy for both methods A (P = 0.001) and B (p = 0.012); whereas controls showed no change in accuracy (P = NS). The Smartphone App accessed AF maps from multiple systems on the cloud to recreate this training environment. CONCLUSION: Digital online training improved interpretation of panoramic AF maps in previously inexperienced clinicians. Combining online clinical data, smartphone apps and other digital resources provides a powerful, scalable approach for training in novel techniques in electrophysiology.

Characterizing Electrogram Signal Fidelity and the Effects of Signal Contamination on Mapping Human Persistent Atrial Fibrillation.

Objective: Determining accurate intracardiac maps of atrial fibrillation (AF) in humans can be difficult, owing primarily to various sources of contamination in electrogram signals. The goal of this study is to develop a measure for signal fidelity and to develop methods to quantify robustness of observed rotational activity in phase maps subject to signal contamination. Methods: We identified rotational activity in phase maps of human persistent AF using the Hilbert transform of sinusoidally recomposed signals, where localized ablation at rotational sites terminated fibrillation. A novel measure of signal fidelity was developed to quantify signal quality. Contamination is then introduced to the underlying electrograms by removing signals at random, adding noise to computations of cycle length, and adding realistic far-field signals. Mean tip number N and tip density δ, defined as the proportion of time a region contains a tip, at the termination site are computed to compare the effects of contamination. Results: Domains of low signal fidelity correspond to the location of rotational cores. Removing signals and altering cycle length accounted for minor changes in tip density, while targeted removal of low fidelity electrograms can result in a significant increase in tip density and stability. Far-field contamination was found to obscure rotation at the termination site. Conclusion: Rotational activity in clinical AF can produce domains of low fidelity electrogram recordings at rotational cores. Observed rotational patterns in phase maps appear most sensitive to far-field activation. These results may inform novel methods to map AF in humans which can be tested directly in patients at electrophysiological study and ablation.

Interaction of Localized Drivers and Disorganized Activation in Persistent Atrial Fibrillation: Reconciling Putative Mechanisms Using Multiple Mapping Techniques.

BACKGROUND: Mechanisms for persistent atrial fibrillation (AF) are unclear. We hypothesized that putative AF drivers and disorganized zones may interact dynamically over short time scales. We studied this interaction over prolonged durations, focusing on regions where ablation terminates persistent AF using 2 mapping methods. METHODS: We recruited 55 patients with persistent AF in whom ablation terminated AF prior to pulmonary vein isolation from a multicenter registry. AF was mapped globally using electrograms for 360±45 cycles using (1) a published phase method and (2) a commercial activation/phase method. RESULTS: Patients were 62.2±9.7 years, 76% male. Sites of AF termination showed rotational/focal patterns by methods 1 and 2 (51/55 vs 55/55; P=0.13) in spatially conserved regions, yet fluctuated over time. Time points with no AF driver showed competing drivers elsewhere or disordered waves. Organized regions were detected for 61.6±23.9% and 70.6±20.6% of 1 minute per method (P=nonsignificant), confirmed by automatic phase tracking (P<0.05). To detect AF drivers with >90% sensitivity, 8 to 32 s of AF recordings were required depending on driver definition. CONCLUSIONS: Sites at which persistent AF terminated by ablation show organized activation that fluctuate over time, because of collision from concurrent organized zones or fibrillatory waves, yet recur in conserved spatial regions. Results were similar by 2 mapping methods. This network of competing mechanisms should be reconciled with existing disorganized or driver mechanisms for AF, to improve clinical mapping and ablation of persistent AF. CLINICAL TRIAL REGISTRATION: URL: http://www.clinicaltrials.gov. Unique identifier: NCT02997254.

Identification and Characterization of Sites Where Persistent Atrial Fibrillation Is Terminated by Localized Ablation.

BACKGROUND: The mechanisms by which persistent atrial fibrillation (AF) terminates via localized ablation are not well understood. To address the hypothesis that sites where localized ablation terminates persistent AF have characteristics identifiable with activation mapping during AF, we systematically examined activation patterns acquired only in cases of unequivocal termination by ablation. METHODS AND RESULTS: We recruited 57 patients with persistent AF undergoing ablation, in whom localized ablation terminated AF to sinus rhythm or organized tachycardia. For each site, we performed an offline analysis of unprocessed unipolar electrograms collected during AF from multipolar basket catheters using the maximum -dV/dt assignment to construct isochronal activation maps for multiple cycles. Additional computational modeling and phase analysis were used to study mechanisms of map variability. At all sites of AF termination, localized repetitive activation patterns were observed. Partial rotational circuits were observed in 26 of 57 (46%) cases, focal patterns in 19 of 57 (33%), and complete rotational activity in 12 of 57 (21%) cases. In computer simulations, incomplete segments of partial rotations coincided with areas of slow conduction characterized by complex, multicomponent electrograms, and variations in assigning activation times at such sites substantially altered mapped mechanisms. CONCLUSIONS: Local activation mapping at sites of termination of persistent AF showed repetitive patterns of rotational or focal activity. In computer simulations, complete rotational activation sequence was observed but was sensitive to assignment of activation timing particularly in segments of slow conduction. The observed phenomena of repetitive localized activation and the mechanism by which local ablation terminates putative AF drivers require further investigation.