Competing Risks for Monomorphic versus Non-Monomorphic Ventricular Arrhythmias in Primary Prevention Implantable Cardioverter Defibrillator Recipients: Global Electrical Heterogeneity and Clinical Outcomes (GEHCO) Study

BACKGROUND AND AIMS

Ablation of monomorphic ventricular tachycardia (MMVT) has been shown to reduce shock frequency and improve survival. We aimed to compare cause-specific risk factors of MMVT and polymorphic ventricular tachycardia (PVT)/ventricular fibrillation (VF) and to develop predictive models.

METHODS

The multicenter retrospective cohort study included 2,668 patients (age 63.1±13.0 y; 23% female; 78% white; 43% nonischemic cardiomyopathy, left ventricular ejection fraction 28.2±11.1%). Cox models were adjusted for demographic characteristics, heart failure severity and treatment, device programming, and ECG metrics. Global electrical heterogeneity was measured by spatial QRS-T angle (QRSTa), spatial ventricular gradient elevation (SVGel), azimuth, magnitude (SVGmag), and sum absolute QRST integral (SAIQRST). We compared the out-of-sample performance of the lasso and elastic net for Cox proportional hazards and the Fine-Gray competing risk model.

RESULTS

During a median follow-up of 4 years, 359 patients experienced their first sustained MMVT with appropriate ICD therapy, and 129 patients had their first PVT/VF with appropriate ICD shock. The risk of MMVT was associated with wider QRSTa (HR 1.16; 95%CI 1.01-1.34), larger SVGel (HR 1.17; 95%CI 1.05-1.30), and smaller SVGmag (HR 0.74; 95%CI 0.63-0.86) and SAIQRST (HR 0.84; 95%CI 0.71-0.99). The best-performing 3-year competing risk Fine-Gray model for MMVT (ROC(t)AUC 0.728; 95%CI 0.668-0.788) identified high-risk (> 50%) patients with 75% sensitivity, 65% specificity, and PVT/VF prediction model had ROC(t)AUC 0.915 (95%CI 0.868-0.962), both satisfactory calibration.

CONCLUSION

We developed and validated models to predict the competing risks of MMVT or PVT/VF that could inform procedural planning and future RCTs of prophylactic VT ablation.

Spatially Conserved Spiral Wave Activity During Human Atrial Fibrillation

BACKGROUND

Atrial fibrillation is the most common cardiac arrhythmia in the world and increases the risk for stroke and morbidity. During atrial fibrillation, the electric activation fronts are no longer coherently propagating through the tissue and, instead, show rotational activity, consistent with spiral wave activation, focal activity, collision, or partial versions of these spatial patterns. An unexplained phenomenon is that although simulations of cardiac models abundantly demonstrate spiral waves, clinical recordings often show only intermittent spiral wave activity.

METHODS

In silico data were generated using simulations in which spiral waves were continuously created and annihilated and in simulations in which a spiral wave was intermittently trapped at a heterogeneity. Clinically, spatio-temporal activation maps were constructed using 60 s recordings from a 64 electrode catheter within the atrium of N=34 patients (n=24 persistent atrial fibrillation). The location of clockwise and counterclockwise rotating spiral waves was quantified and all intervals during which these spiral waves were present were determined. For each interval, the angle of rotation as a function of time was computed and used to determine whether the spiral wave returned in step or changed phase at the start of each interval.

RESULTS

In both simulations, spiral waves did not come back in phase and were out of step." In contrast, spiral waves returned in step in the majority (68%; P=0.05) of patients. Thus, the intermittently observed rotational activity in these patients is due to a temporally and spatially conserved spiral wave and not due to ones that are newly created at the onset of each interval.

CONCLUSIONS

Intermittency of spiral wave activity represents conserved spiral wave activity of long, but interrupted duration or transient spiral activity, in the majority of patients. This finding could have important ramifications for identifying clinically important forms of atrial fibrillation and in guiding treatment.

Comparative arrhythmia patterns among patients on tyrosine kinase inhibitors

BACKGROUND

Tyrosine kinase inhibitors (TKIs) are widely used in the treatment of hematologic malignancies. Limited studies have shown an association between treatment-limiting arrhythmias and TKI, particularly ibrutinib, a Bruton's tyrosine kinase (BTK) inhibitor. We sought to comprehensively assess the arrhythmia burden in patients receiving ibrutinib vs non-BTK TKI vs non-TKI therapies.

METHODS

We performed a retrospective analysis of consecutive patients who received long-term cardiac event monitors while on ibrutinib, non-BTK TKIs, or non-TKI therapy for a hematologic malignancy between 2014 and 2022.

RESULTS

One hundred ninety-three patients with hematologic malignancies were included (ibrutinib = 72, non-BTK TKI = 46, non-TKI therapy = 75). The average duration of TKI therapy was 32 months in the ibrutinib group vs 64 months in the non-BTK TKI group (p = 0.003). The ibrutinib group had a higher prevalence of atrial fibrillation (n = 32 [44%]) compared to the non-BTK TKI (n = 7 [15%], p = 0.001) and non-TKI (n = 15 [20%], p = 0.002) groups. Similarly, the prevalence of non-sustained ventricular tachycardia was higher in the ibrutinib group (n = 31, 43%) than the non-BTK TKI (n = 8 [17%], p = 0.004) and non-TKI groups (n = 20 [27%], p = 0.04). TKI therapy was held in 25% (n = 18) of patients on ibrutinib vs 4% (n = 2) on non-BTK TKIs (p = 0.005) secondary to arrhythmias.

CONCLUSIONS

In this large retrospective analysis of patients with hematologic malignancies, patients receiving ibrutinib had a higher prevalence of atrial and ventricular arrhythmias compared to those receiving other TKI, with a higher rate of treatment interruption due to arrhythmias.

Race, Sex, and Age Disparities in the Performance of ECG Deep Learning Models Predicting Heart Failure

BACKGROUND

Deep learning models may combat widening racial disparities in heart failure outcomes through early identification of individuals at high risk. However, demographic biases in the performance of these models have not been well-studied.

METHODS

This retrospective analysis used 12-lead ECGs taken between 2008 and 2018 from 326 518 patient encounters referred for standard clinical indications to Stanford Hospital. The primary model was a convolutional neural network model trained to predict incident heart failure within 5 years. Biases were evaluated on the testing set (160 312 ECGs) using the area under the receiver operating characteristic curve, stratified across the protected attributes of race, ethnicity, age, and sex.

RESULTS

There were 59 817 cases of incident heart failure observed within 5 years of ECG collection. The performance of the primary model declined with age. There were no significant differences observed between racial groups overall. However, the primary model performed significantly worse in Black patients aged 0 to 40 years compared with all other racial groups in this age group, with differences most pronounced among young Black women. Disparities in model performance did not improve with the integration of race, ethnicity, sex, and age into model architecture, by training separate models for each racial group, or by providing the model with a data set of equal racial representation. Using probability thresholds individualized for race, age, and sex offered substantial improvements in F1 scores.

CONCLUSIONS

The biases found in this study warrant caution against perpetuating disparities through the development of machine learning tools for the prognosis and management of heart failure. Customizing the application of these models by using probability thresholds individualized by race, ethnicity, age, and sex may offer an avenue to mitigate existing algorithmic disparities.

Advances in cardiac pacing with leadless pacemakers and conduction system pacing

PURPOSE OF REVIEW

The field of cardiac pacing has undergone significant evolution with the introduction and adoption of conduction system pacing (CSP) and leadless pacemakers (LLPMs). These innovations provide benefits over conventional pacing methods including avoiding lead related complications and achieving more physiological cardiac activation. This review critically assesses the latest advancements in CSP and LLPMs, including their benefits, challenges, and potential for future growth.

RECENT FINDINGS

CSP, especially of the left bundle branch area, enhances ventricular depolarization and cardiac mechanics. Recent studies show CSP to be favorable over traditional pacing in various patient populations, with an increase in its global adoption. Nevertheless, challenges related to lead placement and long-term maintenance persist. Meanwhile, LLPMs have emerged in response to complications from conventional pacemaker leads. Two main types, Aveir and Micra, have demonstrated improved outcomes and adoption over time. The incorporation of new technologies allows LLPMs to cater to broader patient groups, and their integration with CSP techniques offers exciting potential.

SUMMARY

The advancements in CSP and LLPMs present a transformative shift in cardiac pacing, with evidence pointing towards enhanced clinical outcomes and reduced complications. Future innovations and research are likely to further elevate the clinical impact of these technologies, ensuring improved patient care for those with conduction system disorders.

Segmenting computed tomograms for cardiac ablation using machine learning leveraged by domain knowledge encoding

Background

Segmentation of computed tomography (CT) is important for many clinical procedures including personalized cardiac ablation for the management of cardiac arrhythmias. While segmentation can be automated by machine learning (ML), it is limited by the need for large, labeled training data that may be difficult to obtain. We set out to combine ML of cardiac CT with domain knowledge, which reduces the need for large training datasets by encoding cardiac geometry, which we then tested in independent datasets and in a prospective study of atrial fibrillation (AF) ablation.

Methods

We mathematically represented atrial anatomy with simple geometric shapes and derived a model to parse cardiac structures in a small set of N = 6 digital hearts. The model, termed "virtual dissection," was used to train ML to segment cardiac CT in N = 20 patients, then tested in independent datasets and in a prospective study.

Results

In independent test cohorts (N = 160) from 2 Institutions with different CT scanners, atrial structures were accurately segmented with Dice scores of 96.7% in internal (IQR: 95.3%-97.7%) and 93.5% in external (IQR: 91.9%-94.7%) test data, with good agreement with experts (r = 0.99; p < 0.0001). In a prospective study of 42 patients at ablation, this approach reduced segmentation time by 85% (2.3 ± 0.8 vs. 15.0 ± 6.9 min, p < 0.0001), yet provided similar Dice scores to experts (93.9% (IQR: 93.0%-94.6%) vs. 94.4% (IQR: 92.8%-95.7%), p = NS).

Conclusions

Encoding cardiac geometry using mathematical models greatly accelerated training of ML to segment CT, reducing the need for large training sets while retaining accuracy in independent test data. Combining ML with domain knowledge may have broad applications.

Optimizing patient selection for primary prevention implantable cardioverter-defibrillator implantation: utilizing multimodal machine learning to assess risk of implantable cardioverter-defibrillator non-benefit

AIMS

Left ventricular ejection fraction (LVEF) is suboptimal as a sole marker for predicting sudden cardiac death (SCD). Machine learning (ML) provides new opportunities for personalized predictions using complex, multimodal data. This study aimed to determine if risk stratification for implantable cardioverter-defibrillator (ICD) implantation can be improved by ML models that combine clinical variables with 12-lead electrocardiograms (ECG) time-series features.

METHODS AND RESULTS

A multicentre study of 1010 patients (64.9 ± 10.8 years, 26.8% female) with ischaemic, dilated, or non-ischaemic cardiomyopathy, and LVEF ≤ 35% implanted with an ICD between 2007 and 2021 for primary prevention of SCD in two academic hospitals was performed. For each patient, a raw 12-lead, 10-s ECG was obtained within 90 days before ICD implantation, and clinical details were collected. Supervised ML models were trained and validated on a development cohort (n = 550) from Hospital A to predict ICD non-arrhythmic mortality at three-year follow-up (i.e. mortality without prior appropriate ICD-therapy). Model performance was evaluated on an external patient cohort from Hospital B (n = 460). At three-year follow-up, 16.0% of patients had died, with 72.8% meeting criteria for non-arrhythmic mortality. Extreme gradient boosting models identified patients with non-arrhythmic mortality with an area under the receiver operating characteristic curve (AUROC) of 0.90 [95% confidence intervals (CI) 0.80-1.00] during internal validation. In the external cohort, the AUROC was 0.79 (95% CI 0.75-0.84).

CONCLUSIONS

ML models combining ECG time-series features and clinical variables were able to predict non-arrhythmic mortality within three years after device implantation in a primary prevention population, with robust performance in an independent cohort.

Quantifying a spectrum of clinical response in atrial tachyarrhythmias using spatiotemporal synchronization of electrograms

AIMS

There is a clinical spectrum for atrial tachyarrhythmias wherein most patients with atrial tachycardia (AT) and some with atrial fibrillation (AF) respond to ablation, while others do not. It is undefined if this clinical spectrum has pathophysiological signatures. This study aims to test the hypothesis that the size of spatial regions showing repetitive synchronized electrogram (EGM) shapes over time reveals a spectrum from AT, to AF patients who respond acutely to ablation, to AF patients without acute response.

METHODS AND RESULTS

We studied n = 160 patients (35% women, 65.0 ± 10.4 years) of whom (i) n = 75 had AF terminated by ablation propensity matched to (ii) n = 75 without AF termination and (iii) n = 10 with AT. All patients had mapping by 64-pole baskets to identify areas of repetitive activity (REACT) to correlate unipolar EGMs in shape over time. Synchronized regions (REACT) were largest in AT, smaller in AF termination, and smallest in non-termination cohorts (0.63 ± 0.15, 0.37 ± 0.22, and 0.22 ± 0.18, P < 0.001). Area under the curve for predicting AF termination in hold-out cohorts was 0.72 ± 0.03. Simulations showed that lower REACT represented greater variability in clinical EGM timing and shape. Unsupervised machine learning of REACT and extensive (50) clinical variables yielded four clusters of increasing risk for AF termination (P < 0.01, χ2), which were more predictive than clinical profiles alone (P < 0.001).

CONCLUSION

The area of synchronized EGMs within the atrium reveals a spectrum of clinical response in atrial tachyarrhythmias. These fundamental EGM properties, which do not reflect any predetermined mechanism or mapping technology, predict outcome and offer a platform to compare mapping tools and mechanisms between AF patient groups.

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.

Reduction of artifacts and noise in small electrogram datasets without manual annotation using transfer machine learning

Background/Introduction

Mapping AF is challenging. Monophasic action potentials (MAPs) show that most of the recorded signals are not representing the atrial activity, and arise from far-field or other artifacts. Thus, reducing noise in electrophysiological signals is essential, yet it can be difficult for cross-talk from other chambers and pacing. Strategies to reduce noise include template matching, averaging, and smoothing, but all of them have major limitations. Furthermore, expert interpretation requires knowledge to discriminate signals from noise, but is subjective.

Purpose

We hypothesised a) that atrial and ventricular electrograms with varying artifact and noise can be denoised using autoencoder neural networks (NNs) without requiring manual annotation and in a reproducible manner, and b) we could train these NNs on a large available dataset ventricular signals, then apply transfer learning to the original smaller atrial dataset. We applied this approach to MAPs, which have interpretable shapes and would help identifying local from far-field signals helping in diagnosis, mapping and ablation.

Methods

We first trained with 5706 left and right ventricular MAPs from 42 patients with ischemic cardiomyopathy (age 65±13y; Fig. 1A), with 60% for training, 20% (validation) and 20% (testing). Transfer learning and parameter-tuning were then used to apply this NN to a smaller sample of atrial MAPs (N=641 from 21 patients, 67±5y, 13 women; Fig. 2B, D, F). The autoencoder was used to eliminate pacing artifacts in ventricular MAPs (Fig. 1B, C) and denoise atrial MAPs (Fig. 2C, E, G) by reconstructing key learned features. The accuracy of the reconstruction was evaluated using Pearson Correlation Coefficient (PCC) and a novel similarity coefficient (SC). No manual annotation was required to identify noisy signals.

Results

The trained NN encoder learned key features of ventricular MAPs and reconstructed these clean signals with a SC=0.91±0.16 and PCC=0.99±0.01 (Fig. 1A). With this training, the NN was able to denoise ventricular MAPs with pacing artifact (Fig. 1B, C). After fine-tuning, the NN learned key signal features (upstroke, triangular descent, terminus) and thus reduced diverse noise without specific training or manual annotation. Namely, it was able to reconstruct atrial MAPs eliminating ventricular noise, high frequency noise and truncated signals (Fig. 2).

Conclusions

Machine learned encoder-decoders are powerful tools that can learn essential features of atrial and ventricular signals and hence isolate noise. Transfer learning is effective when large datasets are unavailable for training. This approach can separate atrial beats from far-field ventricular beats and other sources of noise. The ability to eliminate a diverse range of noise improves this approach over existing techniques and may have far-reaching applications in electrophysiology, such as mapping and ablation.

Funding Acknowledgement

Type of funding sources: Public grant(s) – National budget only. Main funding source(s): NIH

Machine learned clusters explain heterogeneity in outcomes from map-guided ablation of Atrial Fibrillation results from the large PROspective STanford AF Registry (ProSTAR)

Background

Several mapping systems are being introduced to guide atrial fibrillation (AF) ablation to patient-specific regions of interest. However, results have been extremely heterogeneous between studies, ranging from very poor to very promising. It is unknown if this reflects specific patient characteristics or procedural factors because most prior series were middle sized (N∼30–100 patients).

Purpose

To study 1 year and 3 year very long-term outcomes from map guided AF-driver ablation in a large patient registry with multiple operators, to identify clinical and procedural features influencing outcomes. In real-world AF patients with diverse comorbidities, we applied a consistent patient-tailored AF mapping and ablation strategy, monitored outcomes carefully and applied statistical and unsupervised machine learning approaches to identify features of success and failure.

Method

We studied 632 consecutive patients (65±10 y, 178 F) undergoing ablation for drug-refractory AF. 59.7% had persistent AF, and 29.9% had prior unsuccessful ablation (median 1 procedure). All patients underwent pulmonary vein isolation (PVI), followed by ablation of AF regions of interest mapped from 64 pole baskets (RhythmView, Abbott, IL), by 11 operators. Patients were followed using ambulatory ECG monitors quarterly for one year, and at the time of symptoms for 3 years.

Results

Fig. 1A shows overall freedom from AF at 1-year of 77.5% (95% CI: 74.2%, 80.9%) and at 3 years of 55.5% (95% CI: 51.2%, 60.1%). Freedom from AF/AT at 1-year was 70.1% (95% CI: 66.5%, 73.8%), and at 3 years was 48.6% (95% CI: 44.3%, 53.3%). Success was higher in patients with procedural termination, first ablation versus prior unsuccessful procedures, for paroxysmal AF than non-paroxysmal AF (1 year: AT/AF freedom 74.9% versus 66.7%, p=0.006), and smaller left atrium. Three clusters (Fig 1B) were identified comprising CHA2DS2VASc score, enlarged LA, prior failed case, presenting rhythm and termination during the procedure (Table 2). At 1 year, freedom from AT/AF was 77.8% (95% CI: 72.2%, 82.1%) for cluster 3 and 56.2% (95% CI: 48.3%, 65.4%) for cluster 1 (Fig. 1B).

Conclusion

In our large registry of N=632 patients undergoing AF-map guided ablations, machine learned clusters identified cohorts with success of 56.2 to 77.8% at 1 year. Future studies should identify if lower success represents technical challenges, such as difficulties in mapping very large atria, or more difficult to treat mechanisms. These results may inform patient inclusion and ablation strategy in upcoming AF treatment trials.

Funding Acknowledgement

Type of funding sources: Public grant(s) – National budget only. Main funding source(s): National budget only - NIH, R01 HL149134, R01HL83359

Novel electrogram featurization reveals a spectrum of response to ablation from atrial tachycardia to types of atrial fibrillation

Background

Although atrial tachycardia (AT) may interconvert with fibrillation (AF) in many patients, it is undefined if this represents a pathophysiological spectrum of organization, or whether it indicates that AF will respond better to ablation.

Objective

To test the hypothesis that the spatial area within which electrograms (EGMs) repeat in synchronized fashion over time indicates a spectrum from AT, in which areas span the entire atria, to AF, in which areas are limited. We further hypothesized that repetitive areas would be larger in AF patients with acute termination than in those with poor response to ablation.

Methods

We studied N=234 patients (47% women, 64±10Y), of whom (i) N=10 had AT, (ii) N=120 had AF that terminated with ablation (“Term”), (ii) N=104 had AF that did not terminate (“Non-term”). All patients had global left atrial mapping by 64 pole baskets (Abbott, IL). Spatial areas of repetitive activity (REACT) were calculated by correlating unipolar EGMs in 2x2 grids for 4 sec, repeated for the entire atria (Figure 1A, B). We quantified global organization by averaging the REACT map for each patient.

Results

Figure 1C shows progressively decreasing areas of repetitive EGM from AT to AF Term to AF Non-term (p&lt;0.001, ANOVA). Figure 1D shows a case of AT in a 71 YO male and global REACT &gt;0.90, a case of AF REACT 0.45 in a 65 YO male with termination by ablation, and a case of AF with REACT 0.19 in an 85 YO male that did not terminate. Further, ROC analysis of REACT analysis in AF cases predicted termination with an AUC of 0.71.

Conclusion

Spatial areas of repeating electrogram shapes indicates a spectrum from AT to AF with good and AF with poor acute response to ablation. Future studies should investigate whether REACT areas can be identified non-invasively, such as by body surface ECG, to guide ablation or prognosis.

Funding Acknowledgement

Type of funding sources: Public grant(s) – National budget only. Main funding source(s): US National Institutes of Health

Spatiotemporal signatures of response to atrial fibrillation ablation

Background

Atrial fibrillation (AF) can have organized regions, in the form of consistent dominant frequency sites, focal or reentrant sites, but it is unclear how these overlap with or differ from focal atrial tachycardias (AT) or potential drivers. We set out to develop an intuitive method based on fundamental electrogram shape and timing to separate types of AF.

Objective

To test the hypothesis that spatial regions of electrogram (EGM) in AF that show similar shapes over time based on cross-correlation analysis may separate patients with differing response to ablation.

Methods

We recruited N=133 patients (63.8±12.1 Y, 32% women), (i) N=10 had AT, (ii) N=122 AF that was or was not terminated by ablation, and (iii) N=1 pacing. All patients had left atrial mapping by 64 pole baskets. We applied repetitive activity (REACT) mapping that correlates EGMs in contiguous 2x2 regions (Fig. 1A) over 4sec. To calibrate REACT, we introduced simulated variations in shape (gaussian noise) and timing (gaussian delay) to pacing EGMs and computed nomograph over 100 random trials (Fig. 1C).

Results

Fig. 1B shows that REACT in a 71-year-old man with AT is more organized than in a 65 YO man with AF (100% vs 40% mapped field). Overall, REACT was higher in AT than AF (0.63±0.15 vs 0.36±0.22, p&lt;0.001). There were 24 cases in which global REACT between AF and AT groups had the overlapping range of values, indicating organized “islands” in AF analogous to AT. From nomograph in Fig. 1C we identified that this overlap reflects 15 ms variation in cycle length and 20% variation in EGM shape (labelled “x” in Fig. 1C).

Conclusion

Basic electrogram properties in AF of similar shapes in spatial areas over time can separate response to ablation and may represent “islands” of AT. Future studies should investigate the mechanisms for such islands and whether they may be targeted for therapy.

Funding Acknowledgement

Type of funding sources: Public grant(s) – National budget only. Main funding source(s): US National Institutes of Health

Automatic left atrial segmentation from cardiac CT using computer graphics imaging and deep learning

Introduction

Segmenting left atrial (LA) substructures, including the LA body, appendage (LAA), and pulmonary veins (PVs), from computed tomography (CT) is central to electroanatomic mapping for ablation and functional studies in patients with atrial fibrillation (AF). However, this process requires manual outlining which needs special training, is subjective, and is difficult to scale. Computer graphics imaging (CGI) has been applied in media, film, and computer-aided design to reliably segment complex structures using their basic geometric representations.

Purpose

We hypothesized that LA substructures can be “virtually” dissected using CGI to separate geometric contours of the “convex ellipsoid” LA, “tubular” PVs, and “conical” LAA. We further hypothesized that the results of virtual dissection can be used to train a deep learning (DL) model to segment raw CT scans.

Methods

First, a mathematical method based on CGI techniques – erosion and dilation – was developed to “virtually dissect” the convex LA body from the original concave shell in publicly available digital atria with diverse simulated morphologies (Fig. 1A). The PVs and LAA were then automatically revealed and labeled by a 3D subtraction approach. Second, we refined precise LA/PV/LAA boundaries by tuning hyper-parameters from N=5 patient shells (Fig. 1B). Third, we used virtual dissection to train a DL model to segment CTs in N=20 patient atria (Fig. 1C). Finally, we applied this pipeline to segment raw CTs in a validation cohort of N=105 patients (23.8% women, 63.8±10.3Y; Fig. 1D).

Results

Virtual dissection accurately identified LA/PV/LAA boundaries in the training set (Dice coefficients 89–98%). In the independent test cohort (N=105), this automated pipeline accurately segmented raw CTs with Dice 81–95% (Fig. 1D) compared to a panel of experts (p&lt;0.001).

Conclusion

CGI of basic cardiac geometry combined with deep learning in small datasets can accurately segment raw CT scans in large populations. This computational pipeline may automate and simplify cardiac image processing and ablation procedures, and could be applied to the ventricle or other organ systems for diverse therapeutic strategies or to train machine learning.

Funding Acknowledgement

Type of funding sources: Public grant(s) – National budget only. Main funding source(s): National Institutes of Health

Artificial intelligence to reduce artifact in cardiac electrophysiological signals

Background/Introduction

Signals in Electrophysiology cases are often noisy despite laboratory shielding and filtering, and current noise-reduction methods are suboptimal. Template matching can identify a “nearest type” of electrogram, but libraries of signal shapes may be unavailable. Beat averaging can reduce noise but obscures beat-to-beat variations and is not optimal to analyze dynamically changing signals, such as when moving a catheter in the heart. Smoothing reduces noise yet blurs high frequency components.

Purpose

We set out to test if machine learned autoencoders could reduce noise in single beats without requiring massive training data or beat libraries. Specifically, we hypothesised that noisy electrograms in small datasets of atrial signals could be de-noised using an encoder-decoder neural network (NN) using transfer learning of machines trained to recognize key features in larger datasets of related signals.

Methods

We applied NN to monophasic action potentials (MAPs), because they have visually verifiable shapes. The NN was first trained to reconstruct 5706 left and right ventricular MAPs in 42 patients (67±13y; Fig. 1A). Transfer learning was then used to apply the NN to a much smaller dataset of 641 atrial MAPs in 21 patients (67±5y, 13 women; Fig. 1B, D, F).

Results

NN reconstructed atrial MAPs with a Pearson correlation of 0.87±0.11. After fine-tuning, NN reconstruction accuracy improved dramatically (Pearson 0.99±0.01; p&lt;0.001). In Fig. 1B–G the NN learned key MAP features (upstroke, triangular descent, terminus) and thus could eliminate ventricular artifact and electrical circuit noise without specific training or manual annotation.

Conclusion

Machine learned autoencoders are a novel and powerful approach to de-noise electrophysiological signals in a dynamic, beat-to-beat fashion. The ability to learn fundamental signal features from models trained in large datasets, and apply them via transfer learning to small datasets in different heart chambers may have wide ranging applications for automated signal annotation, mapping and ablation.

Funding Acknowledgement

Type of funding sources: Public grant(s) – National budget only. Main funding source(s): NIH

Abstract P2115: Differential Cardiac Remodeling Profile Of Immunosuppression Drugs

Introduction: Heart transplantation provides lifesaving therapy for patients with end-stage heart failure. The longevity of the therapy is limited by Cardiac Graft Dysfunction (CGD), which is an acquired cardiomyopathy affecting transplanted hearts associated with diastolic and/or systolic dysfunction. Some clinical risk factors for CGD have been identified, but none of them are easily modifiable. An unexplored potential contributor to CGD is the choice of immunosuppression agent used despite multiple clinical reports suggesting reduced adverse cardiac remodeling with mammalian target of rapamycin (mTOR) inhibitors compared to calcineurin inhibitors (CNI). This study examines mechanisms of differential cardiac remodeling effects of CNI versus mTOR inhibitors in a human cellular cardiac model.

Methods/Results: We utilized 3D cardiac spheres composed of induced pluripotent stem cell-derived cardiomyocytes, cardiac fibroblasts, and endothelial cells (cardiac organoids). Cardiac organoids were treated with 5 days of vehicle, tacrolimus (CNI), or sirolimus (mTOR inhibitor). We did not observe a significant difference in surrogates of systolic or diastolic function in treated cardiac organoids. We pursued single cell-RNA sequencing of drug-treated cardiac organoids and identified gene expression changes consistent with increased extracellular matrix deposition and fibroblast activity in response to CNI treatment. In addition, CNI-treated cardiac organoids cellular composition was notable for increased proportion of fibroblasts and less cardiomyocytes compared to mTOR inhibitor-treated cardiac organoids. To validate gene expression changes observed, we treated cardiac fibroblasts with drugs and observed an increase in collagen production in response to CNI treatment and a reduction in fibroblast number and collagen production in response to mTOR inhibitor treatment. Furthermore, we observed increased ATP production in CNI-treated cardiac fibroblasts, but a reduction in mTOR-treated counterparts.

Conclusion: We identify reduced extracellular matrix deposition and cardiac fibroblast proliferation in response to mTOR inhibitor as a potential mechanism for the more favorable remodeling profile observed clinically.

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.

Sleep apnea is associated with stroke in young patients with or without atrial fibrillation:A population study of &gt;2 million individuals

Funding Acknowledgements

Type of funding sources: Public grant(s) – National budget only. Main funding source(s): NIH, R01 HL149134, R01HL83359

Background

Both Sleep Apnea (SA) and Atrial Fibrillation/flutter (AF) are known risk factors for stroke, and both are increasing in prevalence. They are both under-diagnosed in young adults &lt;60 Y. There is an urgent need to define stroke risk portended by SA and AF yet there a paucity of data in adults aged 20-60 years.

Purpose

To define the relationship between stroke, SA, and AF in a very large cohort of 2 million young-middle aged adults aged 20-60 Y in Northern California.

Methods

We probed the Stanford Research Repository of electronic health data from 01/01/2008 to 11/30/2021 for the diagnoses of stroke, transient ischemic attacks, AF and SA using relevant codes (stroke: 433.X, 434.X, 436.X, I63.X, I65.X, I66.X, G45.X, G46.X; AF: I48.X; SA: G47.X, 327.27).

Results

We identified 2267485 patients aged 20-60Y (55% F; 32% White, 12% Asian, 3% Black), of whom SA was diagnosed in 52730 (2.3%), AF in 10230 (0.4%) and incident stroke in 10385 (0.4%) (Figure 1A)

In patients with SA, 1.5% developed incident stroke. Stroke was more common in patients with SA than those without, regardless of co-existing diagnosis of AF; OR with AF: 1.5 [1.3-1.7, p&lt;0.001] and OR without AF: 3.0 [2.8-3.3 p&lt;0.0001]. Risk of stroke with SA than without was noted to be higher in the younger age subgroups (Figure 1B) regardless of AF.

Although AF was more common in patients with SA than without (odds ratio, OR: 10.1 [9.6-10.6, p&lt;0.0001]), the majority of SA patients (63% with CHADS2VASC ≥2) with stroke did not have a diagnosis of AF (75%), of whom 96% were not anticoagulated (Fig 1, left panel). Of the remaining patients with SA and incident stroke, who did have AF (25%), only 26% were taking OACs at the time of stroke despite median CHADS2 VASC score=3 (Fig 1A, left panel).

Finally, 7% of AF patients developed incident stroke. Of these, 73% had CHADS2VASC ≥2, yet 44% were not anticoagulated. Patients with SA comprised a third of all AF patients with stroke and, compared to AF patients with stroke and without SA, had higher CHADS2VASC (median 3 vs 2, p&lt;0.001) and a similarly low use of anticoagulation (56% vs 54% on OAC) (Fig 1A, right panel).

Conclusions

In &gt;2 million young individuals, we uncover a novel association between SA and incident stroke, regardless of the diagnosis of AF. Surprisingly, three quarters of patients with SA developed incident stroke in the absence of AF, and were not anticoagulated. These results underscore the need to screen for AF and sleep apnea in young adults.

Noise reduction in electrophysiological signals using transfer machine learning

Funding Acknowledgements

Type of funding sources: Public grant(s) – National budget only. Main funding source(s): NIH

Background/Introduction

Reducing electrophysiological signal noise is essential for diagnosis, mapping and ablation, yet most approaches are suboptimal. Template matching requires libraries of known signal types, that are difficult to obtain. Beat averaging can reduce noise, yet cannot be applied to single beats and obscures beat-to-beat variations. Beat smoothing can lose critical and subtle signal features. We set out to use neural networks (NN) based on encoder-decoders, which are able to extract key signal features and hence reconstruct them without noise and artifact.

Purpose

We hypothesised that electrograms with varying sources of artifact can be denoised using autoencoder neural networks. We further hypothesised that this could be achieved in a small data set by developing the method in a larger dataset of related signals, then using transfer learning. We tested this approach for atrial monophasic action potentials (MAPs) that have verifiable shapes.

Methods

The NN was first trained with 5706 left and right ventricular MAPs from 42 patients with ischemic cardiomyopathy (age 65±13y; fig 1.A): 60% for training, 20% (validation) and 20% (testing). Transfer learning and parameter-tuning were then used to apply this NN to a smaller sample of atrial MAPs (N=641, 21 patients, 67±5y, 13 women; fig D,F,H).

Results

The autoencoder was able to learn key features of MAPs, and hence reconstruct them without artifacts. NN learned ventricular MAPs with similarity coefficient 0.91±0.16, Pearson correlation 0.99± 0.01 (fig A) and learned key features (upstroke, triangular descent, terminus) to reduce noise (fig B-C). Applying this trained NN to atrial MAPs, the approach automatically eliminated ventricular artifact (fig E), high frequency noise (fig G), truncation (fig I), saturation and other artifacts. After fine-tuning, the NN reconstructed atrial MAPs with Pearson correlation = 0.99±0.01 (p&lt;0.001).

Conclusions

Machine learned encoder-decoders are powerful tools that can automatically eliminate diverse types of noise in single beats by learning essential signal features. Transfer learning makes this possible without large datasets for training, even from signals in a different cardiac chamber. This approach may have far-reaching applications for mapping and ablation.

Defining refractoriness in single atrial beats using autoencoder neural networks

Funding Acknowledgements

Type of funding sources: Public grant(s) – National budget only. Main funding source(s): NIH

Background

Mapping atrial fibrillation (AF) is complicated by signals which may be local or far-field, but which cannot currently be separated. This could be clarified by a knowledge of atrial refractory periods, yet these are difficult to define from monophasic action potentials (MAP) in patients. We hypothesized that transfer learning using an autoencoder neural network (ANN), first trained with less-noisy ventricular signals, can be applied to de-noise and classify atrial MAPs.

Methods

We first developed an ANN to encode MAPs in 5706 ventricular MAPs from N=42 patients (age 65±13y) during pacing (fig1. A-B). This created a latent feature space. We now tuned the ANN to classify atrial MAPs in a different cohort of patients with AF. We used a statistical loss function based on mathematical optimization to evaluate the accuracy of final representations of the MAP and classify the different signals.

Results

The autoencoder ANN reconstructed ventricular MAPs with an average similarity of 0.85 (range 0-1) (an example is shown in fig 1.B). We tested on 3000 atrial MAPs in AF patients (N=21; 67±5y, 13 women). Atrial MAPs were accurately represented (fig 1.E-F) with similarity indices that were higher than those obtained by a panel of 3 experts. Fig. 1 shows the reconstruction of different signals: ventricular MAP (fig 1.A-B), ventricular MAP with pacing artifact (fig. 1.C-D), atrial MAP (transfer learning is assumed in here; fig 1.E-F) and noise or signals with morphologies of no interest (fig 1.G-H). Fig. 2 shows the classification of signals according to the similarity metric that allows distinguishing among the different types of signals without manual annotation (p&lt;0.05 between groups).

Conclusion

Atrial refractory periods can be defined in single beats in AF patients using autoencoder neural networks and transfer learning. This approach can separate atrial beats from far-field ventricular beats and other sources of noise. Future work can study if this approach can be used to improve AF mapping or define novel physiological phenotypes.

Arrhythmia Patterns in Patients on Ibrutinib

Introduction: Ibrutinib, a Bruton's tyrosine kinase inhibitor (TKI) used primarily in the treatment of hematologic malignancies, has been associated with increased incidence of atrial fibrillation (AF), with limited data on its association with other tachyarrhythmias. There are limited reports that comprehensively analyze atrial and ventricular arrhythmia (VA) burden in patients on ibrutinib. We hypothesized that long-term event monitors could reveal a high burden of atrial and VAs in patients on ibrutinib. Methods: A retrospective data analysis at a single center using electronic medical records database search tools and individual chart review was conducted to identify consecutive patients who had event monitors while on ibrutinib therapy. Results: Seventy-two patients were included in the analysis with a mean age of 76.9 ± 9.9 years and 13 patients (18%) had a diagnosis of AF prior to the ibrutinib therapy. During ibrutinib therapy, most common arrhythmias documented were non-AF supraventricular tachycardia (n = 32, 44.4%), AF (n = 32, 44%), and non-sustained ventricular tachycardia (n = 31, 43%). Thirteen (18%) patients had >1% premature atrial contraction burden; 16 (22.2%) patients had >1% premature ventricular contraction burden. In 25% of the patients, ibrutinib was held because of arrhythmias. Overall 8.3% of patients were started on antiarrhythmic drugs during ibrutinib therapy to manage these arrhythmias. Conclusions: In this large dataset of ambulatory cardiac monitors on patients treated with ibrutinib, we report a high prevalence of atrial and VAs, with a high incidence of treatment interruption secondary to arrhythmias and related symptoms. Further research is warranted to optimize strategies to diagnose, monitor, and manage ibrutinib-related arrhythmias.

Immediate and Delayed Response of Simulated Human Atrial Myocytes to Clinically-Relevant Hypokalemia

Although plasma electrolyte levels are quickly and precisely regulated in the mammalian cardiovascular system, even small transient changes in K⁺, Na⁺, Ca²⁺, and/or Mg²⁺ can significantly alter physiological responses in the heart, blood vessels, and intrinsic (intracardiac) autonomic nervous system. We have used mathematical models of the human atrial action potential (AP) to explore the electrophysiological mechanisms that underlie changes in resting potential (V_r) and the AP following decreases in plasma K⁺, [K⁺]_o, that were selected to mimic clinical hypokalemia. Such changes may be associated with arrhythmias and are commonly encountered in patients (i) in therapy for hypertension and heart failure; (ii) undergoing renal dialysis; (iii) with any disease with acid-base imbalance; or (iv) post-operatively. Our study emphasizes clinically-relevant hypokalemic conditions, corresponding to [K⁺]_o reductions of approximately 1.5 mM from the normal value of 4 to 4.5 mM. We show how the resulting electrophysiological responses in human atrial myocytes progress within two distinct time frames: (i) Immediately after [K⁺]_o is reduced, the K⁺-sensing mechanism of the background inward rectifier current (I_K1) responds. Specifically, its highly non-linear current-voltage relationship changes significantly as judged by the voltage dependence of its region of outward current. This rapidly alters, and sometimes even depolarizes, V_r and can also markedly prolong the final repolarization phase of the AP, thus modulating excitability and refractoriness. (ii) A second much slower electrophysiological response (developing 5-10 minutes after [K⁺]_o is reduced) results from alterations in the intracellular electrolyte balance. A progressive shift in intracellular [Na⁺]_i causes a change in the outward electrogenic current generated by the Na⁺/K⁺ pump, thereby modifying V_r and AP repolarization and changing the human atrial electrophysiological substrate. In this study, these two effects were investigated quantitatively, using seven published models of the human atrial AP. This highlighted the important role of I_K1 rectification when analyzing both the mechanisms by which [K⁺]_o regulates V_r and how the AP waveform may contribute to "trigger" mechanisms within the proarrhythmic substrate. Our simulations complement and extend previous studies aimed at understanding key factors by which decreases in [K⁺]_o can produce effects that are known to promote atrial arrhythmias in human hearts.

Extent of atrium with 1:1 electrogram activation predicts response to ablation of atrial fibrillation

Funding Acknowledgements

Type of funding sources: Public grant(s) – National budget only. Main funding source(s): US National Institutes of Health

Background

Mechanisms associated with successful termination of persistent atrial fibrillation (AF) are still under debate. We sought to study the association between spatial extent of atrium with organized conduction and AF ablation success. We hypothesized that patients with large areas of atrium having 1:1 electrogram activation akin to ‘atrial tachycardia’ may have a higher likelihood of AF termination by ablation.

Methods

In n = 40 AF patients, n = 20 had termination by ablation ("Term"), and the remaining did not have AF termination by ablation ("Non-term"). Basket catheters (64 poles) were used to record unipolar electrograms (EGMs) in one or both atrium. Ablation targeted localized rotational/focal regions, after which pulmonary vein isolation was performed. Unipolar EGMs of 4sec duration at each 2x2 electrode neighborhood within 8x8 catheter grid were processed using a statistical correlation technique to identify the duration of 1:1 activations. Any EGM activation cycle that had a correlation above 80% was considered to be 1:1. Duration of contiguous 1:1 cycles was determined as percentage of total duration (4 sec).

Results

Spatial area of atrium (percentage of mapping field) and the corresponding 1:1 durations were assessed for patients in Term and Non-term groups. Fig A shows spatial 1:1 maps of a Term and a Non-term patient. Fig B shows examples of 1:1 and non-1:1 EGMs. Patients in Term group had higher average 1:1 atrial area than non-term group for any 1:1 duration (Fig C, 15 ± 22% vs 2 ± 4% with ≥70% 1:1 duration, p = 0.03). Positive and negative predictive values of duration≥70% for AF termination were 64.7%, and 75%, with specificity 60% and sensitivity 78.6%, exceeding clinical risk scores.

Conclusion

Persistent AF atrium shows areas of organized 1:1 conduction. Larger 1:1 atrial areas were identified in patients in whom AF terminated by ablation. Future studies should investigate mechanistic bases of organized conduction in AF. Abstract Figure.

Competing risks in patients with primary prevention implantable cardioverter-defibrillators: Global Electrical Heterogeneity and Clinical Outcomes study

BACKGROUND

Global electrical heterogeneity (GEH) is associated with sudden cardiac death in the general population. Its utility in patients with systolic heart failure who are candidates for primary prevention (PP) implantable cardioverter-defibrillators (ICDs) is unclear.

OBJECTIVE

The purpose of this study was to investigate whether GEH is associated with sustained ventricular tachycardia/ventricular fibrillation leading to appropriate ICD therapies in patients with heart failure and PP ICDs.

METHODS

We conducted a multicenter retrospective cohort study. GEH was measured by spatial ventricular gradient (SVG) direction (azimuth and elevation) and magnitude, QRS-T angle, and sum absolute QRST integral on preimplant 12-lead electrocardiograms. Survival analysis using cause-specific hazard functions compared the strength of associations with 2 competing outcomes: sustained ventricular tachycardia/ventricular fibrillation leading to appropriate ICD therapies and all-cause death without appropriate ICD therapies.

RESULTS

We analyzed 2668 patients (mean age 63 ± 12 years; 624 (23%) female; 78% white; 43% nonischemic cardiomyopathy; left ventricular ejection fraction 28% ± 11% from 6 academic medical centers). After adjustment for demographic, clinical, device, and traditional electrocardiographic characteristics, SVG elevation (hazard ratio [HR] per 1SD 1.14; 95% confidence interval [CI] 1.04-1.25; P = .004), SVG azimuth (HR per 1SD 1.12; 95% CI 1.01-1.24; P = .039), SVG magnitude (HR per 1SD 0.75; 95% CI 0.66-0.85; P < .0001), and QRS-T angle (HR per 1SD 1.21; 95% CI 1.08-1.36; P = .001) were associated with appropriate ICD therapies. Sum absolute QRST integral had different associations in infarct-related cardiomyopathy (HR 1.29; 95% CI 1.04-1.60) and nonischemic cardiomyopathy (HR 0.78; 95% CI 0.62-0.96) (P_interaction = .022).

CONCLUSION

In patients with PP ICDs, GEH is independently associated with appropriate ICD therapies. The SVG vector points in distinctly different directions in patients with 2 competing outcomes.

Non-invasive Spatial Mapping of Frequencies in Atrial Fibrillation: Correlation With Contact Mapping

Introduction: Regional differences in activation rates may contribute to the electrical substrates that maintain atrial fibrillation (AF), and estimating them non-invasively may help guide ablation or select anti-arrhythmic medications. We tested whether non-invasive assessment of regional AF rate accurately represents intracardiac recordings.

Methods: In 47 patients with AF (27 persistent, age 63 ± 13 years) we performed 57-lead non-invasive Electrocardiographic Imaging (ECGI) in AF, simultaneously with 64-pole intracardiac signals of both atria. ECGI was reconstructed by Tikhonov regularization. We constructed personalized 3D AF rate distribution maps by Dominant Frequency (DF) analysis from intracardiac and non-invasive recordings.

Results: Raw intracardiac and non-invasive DF differed substantially, by 0.54 Hz [0.13 – 1.37] across bi-atrial regions (R² = 0.11). Filtering by high spectral organization reduced this difference to 0.10 Hz (cycle length difference of 1 – 11 ms) [0.03 – 0.42] for patient-level comparisons (R² = 0.62), and 0.19 Hz [0.03 – 0.59] and 0.20 Hz [0.04 – 0.61] for median and highest DF, respectively. Non-invasive and highest DF predicted acute ablation success (p = 0.04).

Conclusion: Non-invasive estimation of atrial activation rates is feasible and, when filtered by high spectral organization, provide a moderate estimate of intracardiac recording rates in AF. Non-invasive technology could be an effective tool to identify patients who may respond to AF ablation for personalized therapy.

Electrical Substrate Ablation for Refractory Ventricular Fibrillation: Results of the AVATAR Study

[Figure: see text].

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.

Continuous ablation improves lesion maturation compared with intermittent ablation strategies

BACKGROUND

Interrupted ablation is increasingly proposed as part of high-power short-duration radiofrequency ablation (RFA) strategies and may also result from loss of contact from respiratory patterns or cardiac motion. To study the extent that ablation interruption affects lesions.

METHODS

In ex vivo and in vivo experiments, lesion characteristics and tissue temperatures were compared between continuous (group 1) and interrupted (groups 2 and 3) RFA with equal total ablation duration and contact force. Extended duration ablation lesions were also characterized from 1 to 5 minutes.

RESULTS

In the ex vivo study, continuous RFA (group 1) produced larger total lesion volumes compared with each interrupted ablation lesion group (273.8 ± 36.5 vs 205.1 ± 34.2 vs 174.3 ± 32.3 mm³ , all P < .001). Peak temperatures for group 1 were higher at 3 and 5 mm than groups 2 and 3. In vivo, continuous ablation resulted in larger lesions, greater lesion depths, and higher tissue temperatures. Longer ablation durations created larger lesion volumes and increased lesion depths. However, after 3 minutes of ablation, the rate of lesion volume, and depth formation decreased.

CONCLUSIONS

Continuous RFA delivery resulted in larger and deeper lesions with higher tissue temperatures compared with interrupted ablation. This study may have implications for high-power short duration ablation strategies, motivates strategies to reduce variations in ablation delivery, and provides an upper limit for ablation duration beyond which power delivery has diminishing returns.

Noninvasive Assessment of Complexity of Atrial Fibrillation: Correlation With Contact Mapping and Impact of Ablation

BACKGROUND

It is difficult to noninvasively phenotype atrial fibrillation (AF) in a way that reflects clinical end points such as response to therapy. We set out to map electrical patterns of disorganization and regions of reentrant activity in AF from the body surface using electrocardiographic imaging, calibrated to panoramic intracardiac recordings and referenced to AF termination by ablation.

METHODS

Bi-atrial intracardiac electrograms of 47 patients with AF at ablation (30 persistent, 29 male, 63±9 years) were recorded with 64-pole basket catheters and simultaneous 57-lead body surface ECGs. Atrial epicardial electrical activity was reconstructed and organized sites were invasively and noninvasively tracked in 3-dimension using phase singularity. In a subset of 17 patients, sites of AF organization were targeted for ablation.

RESULTS

Body surface mapping showed greater AF organization near intracardially detected drivers than elsewhere, both in phase singularity density (2.3±2.1 versus 1.9±1.6; P=0.02) and number of drivers (3.2±2.3 versus 2.7±1.7; P=0.02). Complexity, defined as the number of stable AF reentrant sites, was concordant between noninvasive and invasive methods (r²=0.5; CC=0.71). In the subset receiving targeted ablation, AF complexity showed lower values in those in whom AF terminated than those in whom AF did not terminate (P<0.01).

CONCLUSIONS

AF complexity tracked noninvasively correlates well with organized and disorganized regions detected by panoramic intracardiac mapping and correlates with the acute outcome by ablation. This approach may assist in bedside monitoring of therapy or in improving the efficacy of ongoing ablation procedures.

Clinical Implications of Ablation of Drivers for Atrial Fibrillation: A Systematic Review and Meta-Analysis

BACKGROUND

The outcomes from pulmonary vein isolation (PVI) for atrial fibrillation (AF) are suboptimal, but the benefits of additional lesion sets remain unproven. Recent studies propose ablation of AF drivers improves outcomes over PVI, yet with conflicting reports in the literature. We undertook a systematic literature review and meta-analysis to determine outcomes from ablation of AF drivers in addition to PVI or as a stand-alone procedure.

METHODS

Database search was done using the terms atrial fibrillation and ablation or catheter ablation and driver or rotor or focal impulse or FIRM (Focal Impulse and Rotor Modulation). We pooled data using random effects model and assessed heterogeneity with I² statistic.

RESULTS

Seventeen studies met inclusion criteria, in a cohort size of 3294 patients. Adding AF driver ablation to PVI reported freedom from AF of 72.5% (confidence interval [CI], 62.1%-81.8%; P<0.01) and from all arrhythmias of 57.8% (CI, 47.5%-67.7%; P<0.01). AF driver ablation when added to PVI or as stand-alone procedure compared with controls produced an odds ratio of 3.1 (CI, 1.3-7.7; P=0.02) for freedom from AF and an odds ratio of 1.8 (CI, 1.2-2.7; P<0.01) for freedom from all arrhythmias in 4 controlled studies. AF termination rate was 40.5% (CI, 30.6%-50.9%) and predicted favorable outcome from ablation(P<0.05).

CONCLUSIONS

In controlled studies, the addition of AF driver ablation to PVI supports the possible benefit of a combined approach of AF driver ablation and PVI in improving single-procedure freedom from all arrhythmias. However, most studies are uncontrolled and are limited by substantial heterogeneity in outcomes. Large multicenter randomized trials are needed to precisely define the benefits of adding driver ablation to PVI.

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.

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.