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.

Detection of focal source and arrhythmogenic substrate from body surface potentials to guide atrial fibrillation ablation.

Focal sources (FS) are believed to be important triggers and a perpetuation mechanism for paroxysmal atrial fibrillation (AF). Detecting FS and determining AF sustainability in atrial tissue can help guide ablation targeting. We hypothesized that sustained rotors during FS-driven episodes indicate an arrhythmogenic substrate for sustained AF, and that non-invasive electrical recordings, like electrocardiograms (ECGs) or body surface potential maps (BSPMs), could be used to detect FS and AF sustainability. Computer simulations were performed on five bi-atrial geometries. FS were induced by pacing at cycle lengths of 120-270 ms from 32 atrial sites and four pulmonary veins. Self-sustained reentrant activities were also initiated around the same 32 atrial sites with inexcitable cores of radii of 0, 0.5 and 1 cm. FS fired for two seconds and then AF inducibility was tested by whether activation was sustained for another second. ECGs and BSPMs were simulated. Equivalent atrial sources were extracted using second-order blind source separation, and their cycle length, periodicity and contribution, were used as features for random forest classifiers. Longer rotor duration during FS-driven episodes indicates higher AF inducibility (area under ROC curve = 0.83). Our method had accuracy of 90.6±1.0% and 90.6±0.6% in detecting FS presence, and 93.1±0.6% and 94.2±1.2% in identifying AF sustainability, and 80.0±6.6% and 61.0±5.2% in determining the atrium of the focal site, from BSPMs and ECGs of five atria. The detection of FS presence and AF sustainability were insensitive to vest placement (±9.6%). On pre-operative BSPMs of 52 paroxysmal AF patients, patients classified with initiator-type FS on a single atrium resulted in improved two-to-three-year AF-free likelihoods (p-value < 0.01, logrank tests). Detection of FS and arrhythmogenic substrate can be performed from ECGs and BSPMs, enabling non-invasive mapping towards mechanism-targeted AF treatment, and malignant ectopic beat detection with likely AF progression.

Gaussian process manifold interpolation for probabilistic atrial activation maps and uncertain conduction velocity.

In patients with atrial fibrillation, local activation time (LAT) maps are routinely used for characterizing patient pathophysiology. The gradient of LAT maps can be used to calculate conduction velocity (CV), which directly relates to material conductivity and may provide an important measure of atrial substrate properties. Including uncertainty in CV calculations would help with interpreting the reliability of these measurements. Here, we build upon a recent insight into reduced-rank Gaussian processes (GPs) to perform probabilistic interpolation of uncertain LAT directly on human atrial manifolds. Our Gaussian process manifold interpolation (GPMI) method accounts for the topology of the atrium, and allows for calculation of statistics for predicted CV. We demonstrate our method on two clinical cases, and perform validation against a simulated ground truth. CV uncertainty depends on data density, wave propagation direction and CV magnitude. GPMI is suitable for probabilistic interpolation of other uncertain quantities on non-Euclidean manifolds. This article is part of the theme issue 'Uncertainty quantification in cardiac and cardiovascular modelling and simulation'.

Left atrial effective conducting size predicts atrial fibrillation vulnerability in persistent but not paroxysmal atrial fibrillation.

BACKGROUND: The multiple wavelets and functional re-entry hypotheses are mechanistic theories to explain atrial fibrillation (AF). If valid, a chamber's ability to support AF should depend upon the left atrial size, conduction velocity (CV), and refractoriness. Measurement of these parameters could provide a new therapeutic target for AF. We investigated the relationship between left atrial effective conducting size (LAECS ), a function of area, CV and refractoriness, and AF vulnerability in patients undergoing AF ablation. METHODS AND RESULTS: Activation mapping was performed in patients with paroxysmal (n = 21) and persistent AF (n = 18) undergoing pulmonary vein isolation. Parameters used for calculating LAECS were: (a) left atrial body area (A); (b) effective refractory period (ERP); and (c) total activation time (T). Global CV was estimated as √A/T . Effective atrial conducting size was calculated as LAECS=A/(CV×ERP) . Post ablation, AF inducibility testing was performed. The critical LAECS required for multiple wavelet termination was determined from computational modeling. LAECS was greater in patients with persistent vs paroxysmal AF (4.4 ± 2.0 cm vs 3.2 ± 1.4 cm; P = .049). AF was inducible in 14/39 patients. LAECS was greater in AF-inducible patients (4.4 ± 1.8 cm vs 3.3 ± 1.7 cm; P = .035, respectively). The difference in LAECS between inducible and noninducible patients was significant in patients with persistent (P = .0046) but not paroxysmal AF (P = .6359). Computational modeling confirmed that LAECS > 4 cm was required for continuation of AF. CONCLUSIONS: LAECS measured post ablation was associated with AF inducibility in patients with persistent, but not paroxysmal AF. These data support a role for this method in electrical substrate assessment in AF patients.

Variability in pulmonary vein electrophysiology and fibrosis determines arrhythmia susceptibility and dynamics.

Success rates for catheter ablation of persistent atrial fibrillation patients are currently low; however, there is a subset of patients for whom electrical isolation of the pulmonary veins alone is a successful treatment strategy. It is difficult to identify these patients because there are a multitude of factors affecting arrhythmia susceptibility and maintenance, and the individual contributions of these factors are difficult to determine clinically. We hypothesised that the combination of pulmonary vein (PV) electrophysiology and atrial body fibrosis determine driver location and effectiveness of pulmonary vein isolation (PVI). We used bilayer biatrial computer models based on patient geometries to investigate the effects of PV properties and atrial fibrosis on arrhythmia inducibility, maintenance mechanisms, and the outcome of PVI. Short PV action potential duration (APD) increased arrhythmia susceptibility, while longer PV APD was found to be protective. Arrhythmia inducibility increased with slower conduction velocity (CV) at the LA/PV junction, but not for cases with homogeneous CV changes or slower CV at the distal PV. Phase singularity (PS) density in the PV region for cases with PV fibrosis was increased. Arrhythmia dynamics depend on both PV properties and fibrosis distribution, varying from meandering rotors to PV reentry (in cases with baseline or long APD), to stable rotors at regions of high fibrosis density. Measurement of fibrosis and PV properties may indicate patient specific susceptibility to AF initiation and maintenance. PV PS density before PVI was higher for cases in which AF terminated or converted to a macroreentry; thus, high PV PS density may indicate likelihood of PVI success.

Patient-specific simulations predict efficacy of ablation of interatrial connections for treatment of persistent atrial fibrillation.

AIMS: Treatments for persistent atrial fibrillation (AF) offer limited efficacy. One potential strategy aims to return the right atrium (RA) to sinus rhythm (SR) by ablating interatrial connections (IAC) to isolate the atria, but there is limited clinical data to evaluate this ablation approach. We aimed to use simulation to evaluate and predict patient-specific suitability for ablation of IAC to treat AF. METHODS AND RESULTS: Persistent AF was simulated in 12 patient-specific geometries, incorporating electrophysiological heterogeneity and fibres, with IAC at Bachmann's bundle, the coronary sinus, and fossa ovalis. Simulations were performed to test the effect of left atrial (LA)-to-RA frequency gradient and fibrotic remodelling on IAC ablation efficacy. During AF, we simulated ablation of one, two, or all three IAC, with or without pulmonary vein isolation and determined if this altered or terminated the arrhythmia. For models without structural remodelling, ablating all IAC terminated RA arrhythmia in 83% of cases. Models with the LA-to-RA frequency gradient removed had an increased success rate (100% success). Ablation of IACs is less effective in cases with fibrotic remodelling (interstitial fibrosis 50% success rate; combination remodelling 67%). Mean number of phase singularities in the RA was higher pre-ablation for IAC failure (success 0.6 ± 0.8 vs. failure 3.2 ± 2.5, P < 0.001). CONCLUSION: This simulation study predicts that IAC ablation is effective in returning the RA to SR for many cases. Patient-specific modelling approaches have the potential to stratify patients prior to ablation by predicting if drivers are located in the LA or RA. We present a platform for predicting efficacy and informing patient selection for speculative treatments.

Determinants of new wavefront locations in cholinergic atrial fibrillation.

AIMS: Atrial fibrillation (AF) wavefront dynamics are complex and difficult to interpret, contributing to uncertainty about the mechanisms that maintain AF. We aimed to investigate the interplay between rotors, wavelets, and focal sources during fibrillation. METHODS AND RESULTS: Arrhythmia wavefront dynamics were analysed for four optically mapped canine cholinergic AF preparations. A bilayer computer model was tuned to experimental preparations, and varied to have (i) fibrosis in both layers or the epicardium only, (ii) different spatial acetylcholine distributions, (iii) different intrinsic action potential duration between layers, and (iv) varied interlayer connectivity. Phase singularities (PSs) were identified and tracked over time to identify rotational drivers. New focal wavefronts were identified using phase contours. Phase singularity density and new wavefront locations were calculated during AF. There was a single dominant mechanism for sustaining AF in each of the preparations, either a rotational driver or repetitive new focal wavefronts. High-density PS sites existed preferentially around the pulmonary vein junctions. Three of the four preparations exhibited stable preferential sites of new wavefronts. Computational simulations predict that only a small number of connections are functionally important in sustaining AF, with new wavefront locations determined by the interplay between fibrosis distribution, acetylcholine concentration, and heterogeneity in repolarization within layers. CONCLUSION: We were able to identify preferential sites of new wavefront initiation and rotational activity, in order to determine the mechanisms sustaining AF. Electrical measurements should be interpreted differently according to whether they are endocardial or epicardial recordings.

Modelling methodology of atrial fibrosis affects rotor dynamics and electrograms.

AIMS: Catheter ablation is an effective technique for terminating atrial arrhythmia. However, given a high atrial fibrillation (AF) recurrence rate, optimal ablation strategies have yet to be defined. Computer modelling can be a powerful aid but modelling of fibrosis, a major factor associated with AF, is an open question. Several groups have proposed methodologies based on imaging data, but no comparison to determine which methodology best corroborates clinically observed reentrant behaviour has been performed. We examined several methodologies to determine the best method for capturing fibrillation dynamics. METHODS AND RESULTS: Patient late gadolinium-enhanced magnetic resonance imaging data were transferred onto a bilayer atrial computer model and used to assign fibrosis distributions. Fibrosis was modelled as conduction disturbances (lower conductivity, edge splitting, or percolation), transforming growth factor-ß1 ionic channel effects, myocyte-fibroblast coupling, and combinations of the preceding. Reentry was induced through pulmonary vein ectopy and the ensuing rotor dynamics characterized. Non-invasive electrocardiographic imaging data of the patients in AF was used for comparison. Electrograms were computed and the fractionation durations measured over the surface. Edge splitting produced more phase singularities from wavebreaks than the other representations. The number of phase singularities seen with percolation was closer to the clinical values. Addition of fibroblast coupling had an organizing effect on rotor dynamics. Simple tissue conductivity changes with ionic changes localized rotors over fibrosis which was not observed with clinical data. CONCLUSION: The specific representation of fibrosis has a large effect on rotor dynamics and needs to be carefully considered for patient specific modelling.

A Review of Personalised Cardiac Computational Modelling Using Electroanatomical Mapping Data.

Computational models of cardiac electrophysiology have gradually matured during the past few decades and are now being personalised to provide patient-specific therapy guidance for improving suboptimal treatment outcomes. The predictive features of these personalised electrophysiology models hold the promise of providing optimal treatment planning, which is currently limited in the clinic owing to reliance on a population-based or average patient approach. The generation of a personalised electrophysiology model entails a sequence of steps for which a range of activation mapping, calibration methods and therapy simulation pipelines have been suggested. However, the optimal methods that can potentially constitute a clinically relevant in silico treatment are still being investigated and face limitations, such as uncertainty of electroanatomical data recordings, generation and calibration of models within clinical timelines and requirements to validate or benchmark the recovered tissue parameters. This paper is aimed at reporting techniques on the personalisation of cardiac computational models, with a focus on calibrating cardiac tissue conductivity based on electroanatomical mapping data.

Observable Atrial and Ventricular Fibrillation Episode Durations Are Conformant With a Power Law Based on System Size and Spatial Synchronization.

BACKGROUND: Atrial fibrillation (AF) and ventricular fibrillation (VF) episodes exhibit varying durations, with some spontaneously ending quickly while others persist. A quantitative framework to explain episode durations remains elusive. We hypothesized that observable self-terminating AF and VF episode lengths, whereby durations are known, would conform with a power law based on the ratio of system size and correlation length ([Formula: see text]. METHODS: Using data from computer simulations (2-dimensional sheet and 3-dimensional left-atrial), human ischemic VF recordings (256-electrode sock, n=12 patients), and human AF recordings (64-electrode basket-catheter, n=9 patients; 16-electrode high definition-grid catheter, n=42 patients), conformance with a power law was assessed using the Akaike information criterion, Bayesian information criterion, coefficient of determination (R2, significance=P<0.05) and maximum likelihood estimation. We analyzed fibrillatory episode durations and [Formula: see text], computed by taking the ratio between system size ([Formula: see text], chamber/simulation size) and correlation length (xi, estimated from pairwise correlation coefficients over electrode/node distance). RESULTS: In all computer models, the relationship between episode durations and [Formula: see text] was conformant with a power law (Aliev-Panfilov R2: 0.90, P<0.001; Courtemanche R2: 0.91, P<0.001; Luo-Rudy R2: 0.61, P<0.001). Observable clinical AF/VF durations were also conformant with a power law relationship (VF R2: 0.86, P<0.001; AF basket R2: 0.91, P<0.001; AF grid R2: 0.92, P<0.001). [Formula: see text] also differentiated between self-terminating and sustained episodes of AF and VF (P<0.001; all systems), as well as paroxysmal versus persistent AF (P<0.001). In comparison, other electrogram metrics showed no statistically significant differences (dominant frequency, Shannon Entropy, mean voltage, peak-peak voltage; P>0.05). CONCLUSIONS: Observable fibrillation episode durations are conformant with a power law based on system size and correlation length.

High Prevalence of New Clinically Significant Findings in Patients With Embolic Stroke of Unknown Source Evaluated by Cardiac Magnetic Resonance Imaging.

BACKGROUND: Embolic stroke of unknown source (ESUS) accounts for 1 in 6 ischemic strokes. Current guidelines do not recommend routine cardiac magnetic resonance (CMR) imaging in ESUS, and beyond the identification of cardioembolic sources, there are no data assessing new clinical findings from CMR in ESUS. This study aimed to assess the prevalence of new cardiac and noncardiac findings and to determine their impact on clinical care in patients with ESUS. METHODS AND RESULTS: In this prospective, multicenter, observational study, CMR imaging was performed within 3 months of ESUS. All scans were reported according to standard clinical practice. A new clinical finding was defined as one not previously identified through prior clinical evaluation. A clinically significant finding was defined as one resulting in further investigation, follow-up, or treatment. A change in patient care was defined as initiation of medical, interventional, surgical, or palliative care. From 102 patients recruited, 96 underwent CMR imaging. One or more new clinical findings were observed in 59 patients (61%). New findings were clinically significant in 48 (81%) of these patients. Of 40 patients with a new clinically significant cardiac finding, 21 (53%) experienced a change in care (medical therapy, n=15; interventional/surgical procedure, n=6). In 12 patients with a new clinically significant extracardiac finding, 6 (50%) experienced a change in care (medical therapy, n=4; palliative care, n=2). CONCLUSIONS: CMR imaging identifies new clinically significant cardiac and noncardiac findings in half of patients with recent ESUS. Advanced cardiovascular screening should be considered in patients with ESUS. REGISTRATION: URL: https://www.clinicaltrials.gov; Unique identifier: NCT04555538.

Fiber Organization has Little Effect on Electrical Activation Patterns during Focal Arrhythmias in the Left Atrium.

Over the past two decades there has been a steady trend towards the development of realistic models of cardiac conduction with increasing levels of detail. However, making models more realistic complicates their personalization and use in clinical practice due to limited availability of tissue and cellular scale data. One such limitation is obtaining information about myocardial fiber organization in the clinical setting. In this study, we investigated a chimeric model of the left atrium utilizing clinically derived patient-specific atrial geometry and a realistic, yet foreign for a given patient fiber organization. We discovered that even significant variability of fiber organization had a relatively small effect on the spatio-temporal activation pattern during regular pacing. For a given pacing site, the activation maps were very similar across all fiber organizations tested.

Fiber Organization Has Little Effect on Electrical Activation Patterns During Focal Arrhythmias in the Left Atrium.

Over the past two decades there has been a steady trend towards the development of realistic models of cardiac conduction with increasing levels of detail. However, making models more realistic complicates their personalization and use in clinical practice due to limited availability of tissue and cellular scale data. One such limitation is obtaining information about myocardial fiber organization in the clinical setting. In this study, we investigated a chimeric model of the left atrium utilizing clinically derived patient-specific atrial geometry and a realistic, yet foreign for a given patient fiber organization. We discovered that even significant variability of fiber organization had a relatively small effect on the spatio-temporal activation pattern during regular pacing. For a given pacing site, the activation maps were very similar across all fiber organizations tested.

Quantifying the impact of shape uncertainty on predicted arrhythmias.

BACKGROUND: Personalised computer models are increasingly used to diagnose cardiac arrhythmias and tailor treatment. Patient-specific models of the left atrium are often derived from pre-procedural imaging of anatomy and fibrosis. These images contain noise that can affect simulation predictions. There are few computationally tractable methods for propagating uncertainties from images to clinical predictions. METHOD: We describe the left atrium anatomy using our Bayesian shape model that captures anatomical uncertainty in medical images and has been validated on 63 independent clinical images. This algorithm describes the left atrium anatomy using Nmodes=15 principal components, capturing 95% of the shape variance and calculated from 70 clinical cardiac magnetic resonance (CMR) images. Latent variables encode shape uncertainty: we evaluate their posterior distribution for each new anatomy. We assume a normally distributed prior. We use the unscented transform to sample from the posterior shape distribution. For each sample, we assign the local material properties of the tissue using the projection of late gadolinium enhancement CMR (LGE-CMR) onto the anatomy to estimate local fibrosis. To test which activation patterns an atrium can sustain, we perform an arrhythmia simulation for each sample. We consider 34 possible outcomes (31 macro-re-entries, functional re-entry, atrial fibrillation, and non-sustained arrhythmia). For each sample, we determine the outcome by comparing pre- and post-ablation activation patterns following a cross-field stimulus. RESULTS: We create patient-specific atrial electrophysiology models of ten patients. We validate the mean and standard deviation maps from the unscented transform with the same statistics obtained with 12,000 Monte Carlo (ground truth) samples. We found discrepancies <3% and <2% for the mean and standard deviation for fibrosis burden and activation time, respectively. For each patient case, we then compare the predicted outcome from a model built on the clinical data (deterministic approach) with the probability distribution obtained from the simulated samples. We found that the deterministic approach did not predict the most likely outcome in 80% of the cases. Finally, we estimate the influence of each source of uncertainty independently. Fixing the anatomy to the posterior mean and maintaining uncertainty in fibrosis reduced the prediction of self-terminating arrhythmias from ≃14% to ≃7%. Keeping the fibrosis fixed to the sample mean while retaining uncertainty in shape decreased the prediction of substrate-driven arrhythmias from ≃33% to ≃18% and increased the prediction of macro-re-entries from ≃54% to ≃68%. CONCLUSIONS: We presented a novel method for propagating shape uncertainty in atrial models through to uncertainty in numerical simulations. The algorithm takes advantage of the unscented transform to compute the output distribution of the outcomes. We validated the unscented transform as a viable sampling strategy to deal with anatomy uncertainty. We then showed that the prediction computed with a deterministic model does not always coincide with the most likely outcome. Finally, we found that shape uncertainty affects the predictions of macro-re-entries, while fibrosis uncertainty affects the predictions of functional re-entries.

Constructing bilayer and volumetric atrial models at scale.

To enable large in silico trials and personalized model predictions on clinical timescales, it is imperative that models can be constructed quickly and reproducibly. First, we aimed to overcome the challenges of constructing cardiac models at scale through developing a robust, open-source pipeline for bilayer and volumetric atrial models. Second, we aimed to investigate the effects of fibres, fibrosis and model representation on fibrillatory dynamics. To construct bilayer and volumetric models, we extended our previously developed coordinate system to incorporate transmurality, atrial regions and fibres (rule-based or data driven diffusion tensor magnetic resonance imaging (MRI)). We created a cohort of 1000 biatrial bilayer and volumetric models derived from computed tomography (CT) data, as well as models from MRI, and electroanatomical mapping. Fibrillatory dynamics diverged between bilayer and volumetric simulations across the CT cohort (correlation coefficient for phase singularity maps: left atrial (LA) 0.27 ± 0.19, right atrial (RA) 0.41 ± 0.14). Adding fibrotic remodelling stabilized re-entries and reduced the impact of model type (LA: 0.52 ± 0.20, RA: 0.36 ± 0.18). The choice of fibre field has a small effect on paced activation data (less than 12 ms), but a larger effect on fibrillatory dynamics. Overall, we developed an open-source user-friendly pipeline for generating atrial models from imaging or electroanatomical mapping data enabling in silico clinical trials at scale (https://github.com/pcmlab/atrialmtk).

Calibrating cardiac electrophysiology models using latent Gaussian processes on atrial manifolds.

Models of electrical excitation and recovery in the heart have become increasingly detailed, but have yet to be used routinely in the clinical setting to guide personalized intervention in patients. One of the main challenges is calibrating models from the limited measurements that can be made in a patient during a standard clinical procedure. In this work, we propose a novel framework for the probabilistic calibration of electrophysiology parameters on the left atrium of the heart using local measurements of cardiac excitability. Parameter fields are represented as Gaussian processes on manifolds and are linked to measurements via surrogate functions that map from local parameter values to measurements. The posterior distribution of parameter fields is then obtained. We show that our method can recover parameter fields used to generate localised synthetic measurements of effective refractory period. Our methodology is applicable to other measurement types collected with clinical protocols, and more generally for calibration where model parameters vary over a manifold.

A personalized real-time virtual model of whole heart electrophysiology.

Computer models capable of representing the intrinsic personal electrophysiology (EP) of the heart in silico are termed virtual heart technologies. When anatomy and EP are tailored to individual patients within the model, such technologies are promising clinical and industrial tools. Regardless of their vast potential, few virtual technologies simulating the entire organ-scale EP of all four-chambers of the heart have been reported and widespread clinical use is limited due to high computational costs and difficulty in validation. We thus report on the development of a novel virtual technology representing the electrophysiology of all four-chambers of the heart aiming to overcome these limitations. In our previous work, a model of ventricular EP embedded in a torso was constructed from clinical magnetic resonance image (MRI) data and personalized according to the measured 12 lead electrocardiogram (ECG) of a single subject under normal sinus rhythm. This model is then expanded upon to include whole heart EP and a detailed representation of the His-Purkinje system (HPS). To test the capacities of the personalized virtual heart technology to replicate standard clinical morphological ECG features under such conditions, bundle branch blocks within both the right and the left ventricles under two different conduction velocity settings are modeled alongside sinus rhythm. To ensure clinical viability, model generation was completely automated and simulations were performed using an efficient real-time cardiac EP simulator. Close correspondence between the measured and simulated 12 lead ECG was observed under normal sinus conditions and all simulated bundle branch blocks manifested relevant clinical morphological features.

Predicting Atrial Fibrillation Recurrence by Combining Population Data and Virtual Cohorts of Patient-Specific Left Atrial Models.

BACKGROUND: Current ablation therapy for atrial fibrillation is suboptimal, and long-term response is challenging to predict. Clinical trials identify bedside properties that provide only modest prediction of long-term response in populations, while patient-specific models in small cohorts primarily explain acute response to ablation. We aimed to predict long-term atrial fibrillation recurrence after ablation in large cohorts, by using machine learning to complement biophysical simulations by encoding more interindividual variability. METHODS: Patient-specific models were constructed for 100 atrial fibrillation patients (43 paroxysmal, 41 persistent, and 16 long-standing persistent), undergoing first ablation. Patients were followed for 1 year using ambulatory ECG monitoring. Each patient-specific biophysical model combined differing fibrosis patterns, fiber orientation maps, electrical properties, and ablation patterns to capture uncertainty in atrial properties and to test the ability of the tissue to sustain fibrillation. These simulation stress tests of different model variants were postprocessed to calculate atrial fibrillation simulation metrics. Machine learning classifiers were trained to predict atrial fibrillation recurrence using features from the patient history, imaging, and atrial fibrillation simulation metrics. RESULTS: We performed 1100 atrial fibrillation ablation simulations across 100 patient-specific models. Models based on simulation stress tests alone showed a maximum accuracy of 0.63 for predicting long-term fibrillation recurrence. Classifiers trained to history, imaging, and simulation stress tests (average 10-fold cross-validation area under the curve, 0.85±0.09; recall, 0.80±0.13; precision, 0.74±0.13) outperformed those trained to history and imaging (area under the curve, 0.66±0.17) or history alone (area under the curve, 0.61±0.14). CONCLUSION: A novel computational pipeline accurately predicted long-term atrial fibrillation recurrence in individual patients by combining outcome data with patient-specific acute simulation response. This technique could help to personalize selection for atrial fibrillation ablation.

The inspection paradox: An important consideration in the evaluation of rotor lifetimes in cardiac fibrillation.

Background and Objective: Renewal theory is a statistical approach to model the formation and destruction of phase singularities (PS), which occur at the pivots of spiral waves. A common issue arising during observation of renewal processes is an inspection paradox, due to oversampling of longer events. The objective of this study was to characterise the effect of a potential inspection paradox on the perception of PS lifetimes in cardiac fibrillation. Methods: A multisystem, multi-modality study was performed, examining computational simulations (Aliev-Panfilov (APV) model, Courtmanche-Nattel model), experimentally acquired optical mapping Atrial and Ventricular Fibrillation (AF/VF) data, and clinically acquired human AF and VF. Distributions of all PS lifetimes across full epochs of AF, VF, or computational simulations, were compared with distributions formed from lifetimes of PS existing at 10,000 simulated commencement timepoints. Results: In all systems, an inspection paradox led towards oversampling of PS with longer lifetimes. In APV computational simulations there was a mean PS lifetime shift of +84.9% (95% CI, ± 0.3%) (p < 0.001 for observed vs overall), in Courtmanche-Nattel simulations of AF +692.9% (95% CI, ±57.7%) (p < 0.001), in optically mapped rat AF +374.6% (95% CI, ± 88.5%) (p = 0.052), in human AF mapped with basket catheters +129.2% (95% CI, ±4.1%) (p < 0.05), human AF-HD grid catheters 150.8% (95% CI, ± 9.0%) (p < 0.001), in optically mapped rat VF +171.3% (95% CI, ±15.6%) (p < 0.001), in human epicardial VF 153.5% (95% CI, ±15.7%) (p < 0.001). Conclusion: Visual inspection of phase movies has the potential to systematically oversample longer lasting PS, due to an inspection paradox. An inspection paradox is minimised by consideration of the overall distribution of PS lifetimes.