Machine learning methods for locating re-entrant drivers from electrograms in a model of atrial fibrillation.
Ontology highlight
ABSTRACT:
SUBMITTER: McGillivray MF
PROVIDER: S-EPMC5936952 | biostudies-literature | 2018 Apr
REPOSITORIES: biostudies-literature
Publications
Machine learning methods for locating re-entrant drivers from electrograms in a model of atrial fibrillation.
McGillivray Max Falkenberg MF Cheng William W Peters Nicholas S NS Christensen Kim K
Royal Society open science 20180418 4
Mapping resolution has recently been identified as a key limitation in successfully locating the drivers of atrial fibrillation (AF). Using a simple cellular automata model of AF, we demonstrate a method by which re-entrant drivers can be located quickly and accurately using a collection of indirect electrogram measurements. The method proposed employs simple, out-of-the-box machine learning algorithms to correlate characteristic electrogram gradients with the displacement of an electrogram reco ...[more]
Similar Datasets
Project description:AimsAtrial fibrillation (AF) is sustained by re-entrant activation patterns. Ablation strategies have been proposed that target regions of tissue that may support re-entrant activation patterns. We aimed to characterize the tissue properties associated with regions that tether re-entrant activation patterns in a validated virtual patient cohort.Methods and resultsAtrial fibrillation patient-specific models (seven paroxysmal and three persistent) were generated and validated against local activation time (LAT) measurements during an S1-S2 pacing protocol from the coronary sinus and high right atrium, respectively. Atrial models were stimulated with burst pacing from three locations in the proximity of each pulmonary vein to initiate re-entrant activation patterns. Five atria exhibited sustained activation patterns for at least 80 s. Models with short maximum action potential durations (APDs) were associated with sustained activation. Phase singularities were mapped across the atria sustained activation patterns. Regions with a low maximum conduction velocity (CV) were associated with tethering of phase singularities. A support vector machine (SVM) was trained on maximum local conduction velocity and action potential duration to identify regions that tether phase singularities. The SVM identified regions of tissue that could support tethering with 91% accuracy. This accuracy increased to 95% when the SVM was also trained on surface area.ConclusionIn a virtual patient cohort, local tissue properties, that can be measured (CV) or estimated (APD; using effective refractory period as a surrogate) clinically, identified regions of tissue that tether phase singularities. Combing CV and APD with atrial surface area further improved the accuracy in identifying regions that tether phase singularities.
| S-EPMC7943361 | biostudies-literature
Project description:Introduction: Catheter ablation (CA) is a common treatment for atrial fibrillation (AF), but the knowledge of optimal ablation sites, and hence clinical outcomes, are suboptimal. Increasing evidence suggest that ablation strategies based on patient-specific substrates information, such as distributions of fibrosis and atrial wall thickness (AWT), may be used to improve therapy. We hypothesized that competing influences of large AWT gradients and fibrotic patches on conductive properties of atrial tissue can determine locations of re-entrant drivers (RDs) sustaining AF. Methods: Two sets of models were used: (1) a simple model of 3D atrial tissue slab with a step change in AWT and a synthetic fibrosis patch, and (2) 3D models based on patient-specific right atrial (RA) and left atrial (LA) geometries. The latter were obtained from four healthy volunteers and two AF patients, respectively, using magnetic resonance imaging (MRI). A synthetic fibrotic patch was added in the RA and fibrosis distributions in the LA were obtained from gadolinium-enhanced MRI of the same patients. In all models, 3D geometry was combined with the Fenton-Karma atrial cell model to simulate RDs. Results: In the slab, RDs drifted toward, and then along the AWT step. However, with additional fibrosis, the RDs were localized in regions between the step and fibrosis. In the RA, RDs drifted toward and anchored to a large AWT gradient between the crista terminalis (CT) region and the surrounding atrial wall. Without such a gradient, RDs drifted toward the superior vena cava (SVC) or the tricuspid valve (TSV). With additional fibrosis, RDs initiated away from the CT anchored to the fibrotic patch, whereas RDs initiated close to the CT region remained localized between the two structures. In the LA, AWT was more uniform and RDs drifted toward the pulmonary veins (PVs). However, with additional fibrotic patches, RDs either anchored to them or multiplied. Conclusion: In the RA, RD locations are determined by both fibrosis and AWT gradients at the CT region. In the LA, they are determined by fibrosis due to the absence of large AWT gradients. These results elucidate mechanisms behind the stabilization of RDs sustaining AF and can help guide ablation therapy.
| S-EPMC6187302 | biostudies-literature
Project description:BackgroundAdvances 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.MethodsWe 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.ResultsIn 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).ConclusionsCNNs 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.
| S-EPMC7438307 | biostudies-literature
Project description:Anti-arrhythmic drug therapy is a frontline treatment for atrial fibrillation (AF), but its success rates are highly variable. This is due to incomplete understanding of the mechanisms of action of specific drugs on the atrial substrate at different stages of AF progression. We aimed to elucidate the role of cellular, tissue and organ level atrial heterogeneities in the generation of a re-entrant substrate during AF progression, and their modulation by the acute action of selected anti-arrhythmic drugs. To explore the complex cell-to-organ mechanisms, a detailed biophysical models of the entire 3D canine atria was developed. The model incorporated atrial geometry and fibre orientation from high-resolution micro-computed tomography, region-specific atrial cell electrophysiology and the effects of progressive AF-induced remodelling. The actions of multi-channel class III anti-arrhythmic agents vernakalant and amiodarone were introduced in the model by inhibiting appropriate ionic channel currents according to experimentally reported concentration-response relationships. AF was initiated by applied ectopic pacing in the pulmonary veins, which led to the generation of localized sustained re-entrant waves (rotors), followed by progressive wave breakdown and rotor multiplication in both atria. The simulated AF scenarios were in agreement with observations in canine models and patients. The 3D atrial simulations revealed that a re-entrant substrate was typically provided by tissue regions of high heterogeneity of action potential duration (APD). Amiodarone increased atrial APD and reduced APD heterogeneity and was more effective in terminating AF than vernakalant, which increased both APD and APD dispersion. In summary, the initiation and sustenance of rotors in AF is linked to atrial APD heterogeneity and APD reduction due to progressive remodelling. Our results suggest that anti-arrhythmic strategies that increase atrial APD without increasing its dispersion are effective in terminating AF.
| S-EPMC5161306 | biostudies-literature
Project description:Focal sources are potential targets for atrial fibrillation (AF) catheter ablation, but they can be time-consuming and challenging to identify when unipolar electrograms (EGM) are numerous and complex. Our aim was to apply deep learning (DL) to raw unipolar EGMs in order to automate putative focal sources detection. We included 78 patients from the Focal Source and Trigger (FaST) randomized controlled trial that evaluated the efficacy of adjunctive FaST ablation compared to pulmonary vein isolation alone in reducing AF recurrence. FaST sites were identified based on manual classification of sustained periodic unipolar QS EGMs over 5-s. All periodic unipolar EGMs were divided into training (n = 10,004) and testing cohorts (n = 3,180). DL was developed using residual convolutional neural network to discriminate between FaST and non-FaST. A gradient-based method was applied to interpret the DL model. DL classified FaST with a receiver operator characteristic area under curve of 0.904 ± 0.010 (cross-validation) and 0.923 ± 0.003 (testing). At a prespecified sensitivity of 90%, the specificity and accuracy were 81.9 and 82.5%, respectively, in detecting FaST. DL had similar performance (sensitivity 78%, specificity 89%) to that of FaST re-classification by cardiologists (sensitivity 78%, specificity 79%). The gradient-based interpretation demonstrated accurate tracking of unipolar QS complexes by select DL convolutional layers. In conclusion, our novel DL model trained on raw unipolar EGMs allowed automated and accurate classification of FaST sites. Performance was similar to FaST re-classification by cardiologists. Future application of DL to classify FaST may improve the efficiency of real-time focal source detection for targeted AF ablation therapy.
| S-EPMC8360838 | biostudies-literature
Project description:Unipolar atrial fibrillation (AF) electrograms (EGMs) require far-field ventricle cancellation to recover hidden atrial activations. Current methods cannot achieve real-time cancellation because of the temporal delay they introduce. We propose a new real-time ventricular cancellation (RVC) method based on causal implementation optimized for real-time functioning. The method is similar to the classical average beat subtraction (ABS) method but it computes the ventricular contribution before the ventricular activation finishes. We compare the proposed method to the ABS on synthetic and real EGM databases for the time and frequency domains. All parameters and their optimal values are analyzed and validated. The RVC method provides a good reconstruction of the unipolar EGMs and a better local activation time detection than the classical approach with average F1scores 0.7307 and 0.7125, respectively. The spectral analysis shows that the average power after ventricular cancellation is reduced for frequency bands between 3 and 5.5 Hz, demonstrating that the proposed method removes the ventricular component present in the unipolar EGM signals compared to the ABS method. The phase mapping analysis on the RVC method presented lower error when comparing the annotated EGM cycles with the phase inversion intervals. In terms of performance ABS and RVC behave similarly, but the real-time capability of the latter justifies its preference over the offline implementations. In the clinical environment other online investigations, e.g., rotational activity assessment, dominant frequency or local activation time mapping, might benefit from the real-time potential of the proposed cancellation method.
| S-EPMC7406791 | biostudies-literature
Project description:BACKGROUND:Atrial Fibrillation is the most common arrhythmia worldwide with a global age adjusted prevalence of 0.5% in 2010. Anticoagulation treatment using warfarin or direct oral anticoagulants is effective in reducing the risk of AF-related stroke by approximately two-thirds and can provide a 10% reduction in overall mortality. There has been increased interest in detecting AF due to its increased incidence and the possibility to prevent AF-related strokes. Inexpensive consumer devices which measure the ECG may have the potential to accurately detect AF but do not generally incorporate diagnostic algorithms. Machine learning algorithms have the potential to improve patient outcomes particularly where diagnoses are made from large volumes or complex patterns of data such as in AF. METHODS:We designed a novel AF detection algorithm using a de-correlated Lorenz plot of 60 consecutive RR intervals. In order to reduce the volume of data, the resulting images were compressed using a wavelet transformation (JPEG200 algorithm) and the compressed images were used as input data to a Support Vector Machine (SVM) classifier. We used the Massachusetts Institute of Technology (MIT)-Beth Israel Hospital (BIH) Atrial Fibrillation database and the MIT-BIH Arrhythmia database as training data and verified the algorithm performance using RR intervals collected using an inexpensive consumer heart rate monitor device (Polar-H7) in a case-control study. RESULTS:The SVM algorithm yielded excellent discrimination in the training data with a sensitivity of 99.2% and a specificity of 99.5% for AF. In the validation data, the SVM algorithm correctly identified AF in 79/79 cases; sensitivity 100% (95% CI 95.4%-100%) and non-AF in 328/336 cases; specificity 97.6% (95% CI 95.4%-99.0%). CONCLUSIONS:An inexpensive wearable heart rate monitor and machine learning algorithm can be used to detect AF with very high accuracy and has the capability to transmit ECG data which could be used to confirm AF. It could potentially be used for intermittent screening or continuously for prolonged periods to detect paroxysmal AF. Further work could lead to cost-effective and accurate estimation of AF burden and improved risk stratification in AF.
| S-EPMC6980577 | biostudies-literature
Project description:BACKGROUND:Atrial fibrillation (AF) is the most common sustained heart arrhythmia. However, as many cases are asymptomatic, a large proportion of patients remain undiagnosed until serious complications arise. Efficient, cost-effective detection of the undiagnosed may be supported by risk-prediction models relating patient factors to AF risk. However, there exists a need for an implementable risk model that is contemporaneous and informed by routinely collected patient data, reflecting the real-world pathology of AF. METHODS:This study sought to develop and evaluate novel and conventional statistical and machine learning models for risk-predication of AF. This was a retrospective, cohort study of adults (aged ≥30 years) without a history of AF, listed on the Clinical Practice Research Datalink, from January 2006 to December 2016. Models evaluated included published risk models (Framingham, ARIC, CHARGE-AF), machine learning models, which evaluated baseline and time-updated information (neural network, LASSO, random forests, support vector machines), and Cox regression. RESULTS:Analysis of 2,994,837 individuals (3.2% AF) identified time-varying neural networks as the optimal model achieving an AUROC of 0.827 vs. 0.725, with number needed to screen of 9 vs. 13 patients at 75% sensitivity, when compared with the best existing model CHARGE-AF. The optimal model confirmed known baseline risk factors (age, previous cardiovascular disease, antihypertensive medication usage) and identified additional time-varying predictors (proximity of cardiovascular events, body mass index (both levels and changes), pulse pressure, and the frequency of blood pressure measurements). CONCLUSION:The optimal time-varying machine learning model exhibited greater predictive performance than existing AF risk models and reflected known and new patient risk factors for AF.
| S-EPMC6824570 | biostudies-literature
Project description:Radiofrequency ablation therapy of atrial fibrillation (AF) recently incorporated the analysis of dominant frequency (DF) and/or electrogram fractionation for guidance. However, the relationships between DF, fractionation, and spatiotemporal characteristics of the AF source remain unclear.We hypothesize that a meandering reentrant AF source contributes to the wave fractionation and is reflected in the power spectrum of local electrograms elsewhere in the rotor's surroundings.Meandering rotors as AF sources were simulated in 2-dimensional models of human atrial tissue and recorded in isolated sheep hearts. Nondominant elements of the signals were differentiated from the dominant elements using singular value decomposition, whereby the purely periodic constituent (PC) relating to the rotor's DF was eliminated rendering a residual constituent (RC) that consisted of all other activity.Spectral analysis of the decomposed constituents revealed peaks corresponding to the meandering frequency of the rotor tip, the magnitudes of which were proportional to the size of and the distance to the rotor core. Similar analyses on epicardial optical signals and electrograms from isolated sheep hearts, as well as human complex fractionated atrial electrograms, showed applicability of the approach.Increased meandering of the rotor driving AF reduces activation periodicity and increases fractionation. The spectral manifestation of the rotor activity beyond the meandering region makes it possible to characterize AF source stability, as well as DF in humans using electrode mapping.
| S-EPMC3079377 | biostudies-literature
Project description:Extracellular electrograms recorded during atrial fibrillation (AF) are challenging to interpret due to the inherent beat-to-beat variability in amplitude and duration. Phase mapping represents these voltage signals in terms of relative position within the cycle, and has been widely applied to action potential and unipolar electrogram data of myocardial fibrillation. To date, however, it has not been applied to bipolar recordings, which are commonly acquired clinically. The purpose of this study is to present a novel algorithm for calculating phase from both unipolar and bipolar electrograms recorded during AF. A sequence of signal filters and processing steps are used to calculate phase from simulated, experimental, and clinical, unipolar and bipolar electrograms. The algorithm is validated against action potential phase using simulated data (trajectory centre error <0.8 mm); between experimental multi-electrode array unipolar and bipolar phase; and for wavefront identification in clinical atrial tachycardia. For clinical AF, similar rotational content (R 2 = 0.79) and propagation maps (median correlation 0.73) were measured using either unipolar or bipolar recordings. The algorithm is robust, uses standard signal processing techniques, and accurately quantifies AF wavefronts and sources. Identifying critical sources, such as rotors, in AF, may allow for more accurate targeting of ablation therapy and improved patient outcomes.
| S-EPMC5362653 | biostudies-literature