Reconstruction of three-dimensional biventricular activation based on the 12-lead electrocardiogram via patient-specific modelling

Harnessing 12-lead ECG and MRI data to personalise repolarisation profiles in cardiac digital twin models for enhanced virtual drug testing

Cardiac digital twins are computational tools capturing key functional and anatomical characteristics of patient hearts for investigating disease phenotypes and predicting responses to therapy. When paired with large-scale computational resources and large clinical datasets, digital twin technology can enable virtual clinical trials on virtual cohorts to fast-track therapy development. Here, we present an open-source automated pipeline for personalising ventricular electrophysiological function based on routinely acquired magnetic resonance imaging (MRI) data and the standard 12-lead electrocardiogram (ECG). Using MRI-based anatomical models, a sequential Monte-Carlo approximate Bayesian computational inference method is extended to infer electrical activation and repolarisation characteristics from the ECG. Fast simulations are conducted with a reaction-Eikonal model, including the Purkinje network and biophysically-detailed subcellular ionic current dynamics for repolarisation. For each patient, parameter uncertainty is represented by inferring an envelope of plausible ventricular models rather than a single one, which means that parameter uncertainty can be propagated to therapy evaluation. Furthermore, we have developed techniques for translating from reaction-Eikonal to monodomain simulations, which allows more realistic simulations of cardiac electrophysiology. The pipeline is demonstrated in three healthy subjects, where our inferred pseudo-diffusion reaction-Eikonal models reproduced the patient's ECG with a median Pearson's correlation coefficient of 0.9, and then translated to monodomain simulations with a median correlation coefficient of 0.84 across all subjects. We then demonstrate our digital twins for virtual evaluation of Dofetilide with uncertainty quantification. These evaluations using our cardiac digital twins reproduced dose-dependent QTc and T peak to T end prolongations that are in keeping with large population drug response data. The methodologies for cardiac digital twinning presented here are a step towards personalised virtual therapy testing and can be scaled to generate virtual populations for clinical trials to fast-track therapy evaluation. The tools developed for this paper are open-source, documented, and made publicly available.

Optimal electrode placements for localizing premature ventricular contractions using a single dipole cardiac source model

INTRODUCTION

The inverse problem of electrocardiography describes non-invasively the electrical activity of the heart using potential recordings from tens to hundreds of torso electrodes. Regrettably, the use of numerous electrodes poses a challenge to its integration into routine clinical practice.

METHODS

Optimal electrode placements, ranging from 8 to 112 electrodes, were derived from the singular values of the transfer matrices computed for all feasible positions of a single dipole cardiac source across 12 patients with unique geometrical characteristics from the Bratislava dataset. The transfer matrices were computed using the boundary element method. Subsequently, these optimal electrode placements were used to compute the inverse solution for localizing the origin of premature ventricular contraction (PVC) with a single dipole cardiac source. The localization error (LE) was computed as the Euclidean distance between the true PVC origin, obtained through an invasive radiofrequency ablation, and the inverse solution. This enabled a direct comparison of LE computed for each optimal electrode placement with that from the full 128-electrode set.

RESULTS

Results showed that subsets of electrodes, particularly 32 to 112, provided comparable localization accuracy (LE of 30.5 ± 15.0 mm and 26.8 ± 12.6 mm) to the full 128-electrode set (LE of 27.2 ± 11.5 mm). High errors were observed with 8 and 16-electrode placements (LE of 48.6 ± 21.3 mm and 41.0 ± 18.3 mm).

CONCLUSION

Precise PVC localization can be achieved using strategically positioned subsets of electrodes, offering advantages in reduced preparation time, enhanced patient comfort, and improved cost-effectiveness of body surface potential mapping.

Characterization of cardiac resynchronization therapy response through machine learning and personalized models

INTRODUCTION

The characterization and selection of heart failure (HF) patients for cardiac resynchronization therapy (CRT) remain challenging, with around 30% non-responder rate despite following current guidelines. This study aims to propose a novel hybrid approach, integrating machine-learning and personalized models, to identify explainable phenogroups of HF patients and predict their CRT response.

METHODS

The paper proposes the creation of a complete personalized model population based on preoperative CRT patient strain curves. Based on the parameters and features extracted from these personalized models, phenotypes of patients are identified thanks to a clustering algorithm and a random forest classification is provided.

RESULTS

A close match was observed between the 162 experimental and simulated myocardial strain curves, with a mean RMSE of 4.48% (±1.08) for the 162 patients. Five phenogroups of personalized models were identified from the clustering, with response rates ranging from 52% to 94%. The classification results show a mean area under the curves (AUC) of 0.86 ± 0.06 and provided a feature importance analysis with 22 features selected. Results show both regional myocardial contractility (from 22.5% to 33.0%), tissue viability and electrical activation delays importance on CRT response for each HF patient (from 55.8 ms to 88.4 ms).

DISCUSSION

The patient-specific model parameters' analysis provides an explainable interpretation of HF patient phenogroups in relation to physiological mechanisms that seem predictive of the CRT response. These novel combined approaches appear as promising tools to improve understanding of LV mechanical dyssynchrony for HF patient characterization and CRT selection.

Toward Enabling Cardiac Digital Twins of Myocardial Infarction Using Deep Computational Models for Inverse Inference

Cardiac digital twins (CDTs) have the potential to offer individualized evaluation of cardiac function in a non-invasive manner, making them a promising approach for personalized diagnosis and treatment planning of myocardial infarction (MI). The inference of accurate myocardial tissue properties is crucial in creating a reliable CDT of MI. In this work, we investigate the feasibility of inferring myocardial tissue properties from the electrocardiogram (ECG) within a CDT platform. The platform integrates multi-modal data, such as cardiac MRI and ECG, to enhance the accuracy and reliability of the inferred tissue properties. We perform a sensitivity analysis based on computer simulations, systematically exploring the effects of infarct location, size, degree of transmurality, and electrical activity alteration on the simulated QRS complex of ECG, to establish the limits of the approach. We subsequently present a novel deep computational model, comprising a dual-branch variational autoencoder and an inference model, to infer infarct location and distribution from the simulated QRS. The proposed model achieves mean Dice scores of 0.457 ±0.317 and 0.302 ±0.273 for the inference of left ventricle scars and border zone, respectively. The sensitivity analysis enhances our understanding of the complex relationship between infarct characteristics and electrophysiological features. The in silico experimental results show that the model can effectively capture the relationship for the inverse inference, with promising potential for clinical application in the future. The code is available at https://github.com/lileitech/MI_inverse_inference.

Computational modeling of cardiac electrophysiology and arrhythmogenesis: toward clinical translation

The complexity of cardiac electrophysiology, involving dynamic changes in numerous components across multiple spatial (from ion channel to organ) and temporal (from milliseconds to days) scales, makes an intuitive or empirical analysis of cardiac arrhythmogenesis challenging. Multiscale mechanistic computational models of cardiac electrophysiology provide precise control over individual parameters, and their reproducibility enables a thorough assessment of arrhythmia mechanisms. This review provides a comprehensive analysis of models of cardiac electrophysiology and arrhythmias, from the single cell to the organ level, and how they can be leveraged to better understand rhythm disorders in cardiac disease and to improve heart patient care. Key issues related to model development based on experimental data are discussed, and major families of human cardiomyocyte models and their applications are highlighted. An overview of organ-level computational modeling of cardiac electrophysiology and its clinical applications in personalized arrhythmia risk assessment and patient-specific therapy of atrial and ventricular arrhythmias is provided. The advancements presented here highlight how patient-specific computational models of the heart reconstructed from patient data have achieved success in predicting risk of sudden cardiac death and guiding optimal treatments of heart rhythm disorders. Finally, an outlook toward potential future advances, including the combination of mechanistic modeling and machine learning/artificial intelligence, is provided. As the field of cardiology is embarking on a journey toward precision medicine, personalized modeling of the heart is expected to become a key technology to guide pharmaceutical therapy, deployment of devices, and surgical interventions.

Digital Twinning of Cardiac Electrophysiology Models From the Surface ECG: A Geodesic Backpropagation Approach

The eikonal equation has become an indispensable tool for modeling cardiac electrical activation accurately and efficiently. In principle, by matching clinically recorded and eikonal-based electrocardiograms (ECGs), it is possible to build patient-specific models of cardiac electrophysiology in a purely non-invasive manner. Nonetheless, the fitting procedure remains a challenging task. The present study introduces a novel method, Geodesic-BP, to solve the inverse eikonal problem. Geodesic-BP is well-suited for GPU-accelerated machine learning frameworks, allowing us to optimize the parameters of the eikonal equation to reproduce a given ECG. We show that Geodesic-BP can reconstruct a simulated cardiac activation with high accuracy in a synthetic test case, even in the presence of modeling inaccuracies. Furthermore, we apply our algorithm to a publicly available dataset of a biventricular rabbit model, with promising results. Given the future shift towards personalized medicine, Geodesic-BP has the potential to help in future functionalizations of cardiac models meeting clinical time constraints while maintaining the physiological accuracy of state-of-the-art cardiac models.

Quest for the ideal assessment of electrical ventricular dyssynchrony in cardiac resynchronization therapy

This paper reviews the literature on assessing electrical dyssynchrony for patient selection in cardiac resynchronization therapy (CRT). The guideline-recommended electrocardiographic (ECG) criteria for CRT are QRS duration and morphology, established through inclusion criteria in large CRT trials. However, both QRS duration and LBBB morphology have their shortcomings. Over the past decade, various alternative measures of ventricular dyssynchrony have been proposed, ranging from simple options such as vectorcardiography (VCG), ultra-high frequency ECG, and electrical dyssynchrony mapping to more advanced techniques such as ECG imaging electro-anatomic mapping. Despite promising results, none of these methods have yet been widely adopted in daily clinical practice. The VCG is a relatively cost-effective option for potential clinical implementation, as it can be reconstructed from the standard 12‑lead ECG. With the emergence of conduction system pacing, in addition to predicting the outcome of conventional biventricular CRT, the assessment of electrical dyssynchrony holds promise for defining and optimizing the type of resynchronization strategy. Additionally, artificial intelligence has the potential to reveal unknown features for CRT outcomes, and computer models can provide deeper insights into the underlying mechanisms of these features.

Developing Cardiac Digital Twins at Scale: Insights from Personalised Myocardial Conduction Velocity

Large-cohort studies using cardiovascular imaging and diagnostic datasets have assessed cardiac anatomy, function, and outcomes, but typically do not reveal underlying biological mechanisms. Cardiac digital twins (CDTs) provide personalized physics- and physiology-constrained in-silico representations, enabling inference of multi-scale properties tied to these mechanisms. We constructed 3464 anatomically-accurate CDTs using cardiac magnetic resonance images from UK biobank and personalised their myocardial conduction velocities (CVs) from electrocardiograms (ECG), through an automated framework. We found well-known sex-specific differences in QRS duration were fully explained by myocardial anatomy, as CV remained consistent across sexes. Conversely, significant associations of CV with ageing and increased BMI suggest myocardial tissue remodelling. Novel associations were observed with left ventricular ejection fraction and mental-health phenotypes, through a phenome-wide association study, and CV was also linked with adverse clinical outcomes. Our study highlights the utility of population-based CDTs in assessing intersubject variability and uncovering strong links with mental health.

Left ventricular endocardial activation maps during right ventricular pacing in pediatric patients

BACKGROUND

Cardiac pacing from right ventricular (RV) sites may cause electromechanical ventricular dyssynchrony. Invasive and noninvasive mapping studies showed left ventricular (LV) activation sequence in adults. Aim of this study was to seek out the LV endocardial activation (LVEA) in pediatric patients who underwent RV pacing.

METHODS

Single-center, prospective study conducted on pediatric patients who underwent left sided catheter ablation of accessory pathways with the Carto Univu mapping system. After successful ablation procedures, LVEA was recorded by the ablation catheter during sinus rhythm (SR) and during para-hisian (PHP), midseptum (MSP), and apical (RVAP) pacing.

RESULTS

Seventeen patients, 13 males, aged 12 (10-15) years, registered LV activation maps and times (LVAT). SR showed significantly shorter LVAT than during pacing. LVAT of PHP was shorter than MSP, while there were not significant differences among PHP and MSP versus RVAP. In SR initial LV endocardial activation occurred in two midseptum sites, inferior-posterior and superior-anterior. During PHP, initial activation occurred at parahisian basal septum, rapidly followed by midseptum as in SR. During MSP and RVAP initial activation occurred at midseptum and apex, respectively. From all initial sites, the excitation spreads toward the base of the lateral LV free wall. A mild linear correlation was found between QRS duration and LVAT for MSP and for PHP.

CONCLUSIONS

In pediatric patients LVEA maps during RV pacing showed that the shortest LVAT was obtained with PHP. The LV activation pattern seemed similar in sinus rhythm, PHP and MSP, from midseptum to LV lateral base.

The evolving state of cardiac resynchronization therapy and conduction system pacing: 25 years of research at EP Europace journal

Cardiac resynchronization therapy (CRT) was proposed in the 1990s as a new therapy for patients with heart failure and wide QRS with depressed left ventricular ejection fraction despite optimal medical treatment. This review is aimed first to describe the rationale and the physiologic effects of CRT. The journey of the landmark randomized trials leading to the adoption of CRT in the guidelines since 2005 is also reported showing the high level of evidence for CRT. Different alternative pacing modalities of CRT to conventional left ventricular pacing through the coronary sinus have been proposed to increase the response rate to CRT such as multisite pacing and endocardial pacing. A new emerging alternative technique to conventional biventricular pacing, conduction system pacing (CSP), is a promising therapy. The different modalities of CSP are described (Hirs pacing and left bundle branch area pacing). This new technique has to be evaluated in clinical randomized trials before implementation in the guidelines with a high level of evidence.

Combination of personalized computational modeling and machine learning for optimization of left ventricular pacing site in cardiac resynchronization therapy

Introduction: The 30-50% non-response rate to cardiac resynchronization therapy (CRT) calls for improved patient selection and optimized pacing lead placement. The study aimed to develop a novel technique using patient-specific cardiac models and machine learning (ML) to predict an optimal left ventricular (LV) pacing site (ML-PS) that maximizes the likelihood of LV ejection fraction (LVEF) improvement in a given CRT candidate. To validate the approach, we evaluated whether the distance D_PS between the clinical LV pacing site (ref-PS) and ML-PS is associated with improved response rate and magnitude. Materials and methods: We reviewed retrospective data for 57 CRT recipients. A positive response was defined as a more than 10% LVEF improvement. Personalized models of ventricular activation and ECG were created from MRI and CT images. The characteristics of ventricular activation during intrinsic rhythm and biventricular (BiV) pacing with ref-PS were derived from the models and used in combination with clinical data to train supervised ML classifiers. The best logistic regression model classified CRT responders with a high accuracy of 0.77 (ROC AUC = 0.84). The LR classifier, model simulations and Bayesian optimization with Gaussian process regression were combined to identify an optimal ML-PS that maximizes the ML-score of CRT response over the LV surface in each patient. Results: The optimal ML-PS improved the ML-score by 17 ± 14% over the ref-PS. Twenty percent of the non-responders were reclassified as positive at ML-PS. Selection of positive patients with a max ML-score >0.5 demonstrated an improved clinical response rate. The distance D_PS was shorter in the responders. The max ML-score and D_PS were found to be strong predictors of CRT response (ROC AUC = 0.85). In the group with max ML-score > 0.5 and D_PS< 30 mm, the response rate was 83% compared to 14% in the rest of the cohort. LVEF improvement in this group was higher than in the other patients (16 ± 8% vs. 7 ± 8%). Conclusion: A new technique combining clinical data, personalized heart modelling and supervised ML demonstrates the potential for use in clinical practice to assist in optimizing patient selection and predicting optimal LV pacing lead position in HF candidates for CRT.

Localization of the ventricular pacing site from BSPM and standard 12-lead ECG: a comparison study

Inverse ECG imaging methods typically require 32-250 leads to create body surface potential maps (BSPM), limiting their routine clinical use. This study evaluated the accuracy of PaceView inverse ECG method to localize the left or right ventricular (LV and RV, respectively) pacing leads using either a 99-lead BSPM or the 12-lead ECG. A 99-lead BSPM was recorded in patients with cardiac resynchronization therapy (CRT) during sinus rhythm and sequential LV/RV pacing. The non-contrast CT was performed to localize precisely both ECG electrodes and CRT leads. From a BSPM, nine signals were selected to obtain the 12-lead ECG. Both BSPM and 12-lead ECG were used to localize the RV and LV lead, and the localization error was calculated. Consecutive patients with dilated cardiomyopathy, previously implanted with a CRT device, were enrolled (n = 19). The localization error for the RV/LV lead was 9.0 [IQR 4.8-13.6] / 7.7 [IQR 0.0-10.3] mm using the 12-lead ECG and 9.1 [IQR 5.4-15.7] / 9.8 [IQR 8.6-13.1] mm for the BSPM. Thus, the noninvasive lead localization using the 12-lead ECG was accurate enough and comparable to 99-lead BSPM, potentially increasing the capability of 12-lead ECG for the optimization of the LV/RV pacing sites during CRT implant or for the most favorable programming.

Novel non-invasive ECG imaging method based on the 12-lead ECG for reconstruction of ventricular activation: A proof-of-concept study

Aim

Current non-invasive electrocardiographic imaging (ECGi) methods are often based on complex body surface potential mapping, limiting the clinical applicability. The aim of this pilot study was to evaluate the ability of a novel non-invasive ECGi method, based on the standard 12-lead ECG, to localize initial site of ventricular activation in right ventricular (RV) paced patients. Validation of the method was performed by comparing the ECGi reconstructed earliest site of activation against the true RV pacing site determined from cardiac computed tomography (CT).

Methods

This was a retrospective study using data from 34 patients, previously implanted with a dual chamber pacemaker due to advanced atrioventricular block. True RV lead position was determined from analysis of a post-implant cardiac CT scan. The ECGi method was based on an inverse-ECG algorithm applying electrophysiological rules. The algorithm integrated information from an RV paced 12-lead ECG together with a CT-derived patient-specific heart-thorax geometric model to reconstruct a 3D electrical ventricular activation map.

Results

The mean geodesic localization error (LE) between the ECGi reconstructed initial site of activation and the RV lead insertion site determined from CT was 13.9 ± 5.6 mm. The mean RV endocardial surface area was 146.0 ± 30.0 cm² and the mean circular LE area was 7.0 ± 5.2 cm² resulting in a relative LE of 5.0 ± 4.0%.

Conclusion

We demonstrated a novel non-invasive ECGi method, based on the 12-lead ECG, that accurately localized the RV pacing site in relation to the ventricular anatomy.

Credibility assessment of patient-specific computational modeling using patient-specific cardiac modeling as an exemplar

Reliable and robust simulation of individual patients using patient-specific models (PSMs) is one of the next frontiers for modeling and simulation (M&S) in healthcare. PSMs, which form the basis of digital twins, can be employed as clinical tools to, for example, assess disease state, predict response to therapy, or optimize therapy. They may also be used to construct virtual cohorts of patients, for in silico evaluation of medical product safety and/or performance. Methods and frameworks have recently been proposed for evaluating the credibility of M&S in healthcare applications. However, such efforts have generally been motivated by models of medical devices or generic patient models; how best to evaluate the credibility of PSMs has largely been unexplored. The aim of this paper is to understand and demonstrate the credibility assessment process for PSMs using patient-specific cardiac electrophysiological (EP) modeling as an exemplar. We first review approaches used to generate cardiac PSMs and consider how verification, validation, and uncertainty quantification (VVUQ) apply to cardiac PSMs. Next, we execute two simulation studies using a publicly available virtual cohort of 24 patient-specific ventricular models, the first a multi-patient verification study, the second investigating the impact of uncertainty in personalized and non-personalized inputs in a virtual cohort. We then use the findings from our analyses to identify how important characteristics of PSMs can be considered when assessing credibility with the approach of the ASME V&V40 Standard, accounting for PSM concepts such as inter- and intra-user variability, multi-patient and “every-patient” error estimation, uncertainty quantification in personalized vs non-personalized inputs, clinical validation, and others. The results of this paper will be useful to developers of cardiac and other medical image based PSMs, when assessing PSM credibility.

Patient-specific models are computational models that have been personalized using data from a patient. After decades of research, recent computational, data science and healthcare advances have opened the door to the fulfilment of the enormous potential of such models, from truly personalized medicine to efficient and cost-effective testing of new medical products. However, reliability (credibility) of patient-specific models is key to their success, and there are currently no general guidelines for evaluating credibility of patient-specific models. Here, we consider how frameworks and model evaluation activities that have been developed for generic (not patient-specific) computational models, can be extended to patient specific models. We achieve this through a detailed analysis of the activities required to evaluate cardiac electrophysiological models, chosen as an exemplar field due to its maturity and the complexity of such models. This is the first paper on the topic of reliability of patient-specific models and will help pave the way to reliable and trusted patient-specific modeling across healthcare applications.

Synchronization of repolarization after cardiac resynchronization therapy: A combined clinical and modeling study

INTRODUCTION

The changes in ventricular repolarization after cardiac resynchronization therapy (CRT) are poorly understood. This knowledge gap is addressed using a multimodality approach including electrocardiographic and echocardiographic measurements in patients and using patient-specific computational modeling.

METHODS

In 33 patients electrocardiographic and echocardiographic measurements were performed before and at various intervals after CRT, both during CRT-ON and temporary CRT-OFF. T-wave area was calculated from vectorcardiograms, and reconstructed from the 12-lead electrocardiography (ECG). Computer simulations were performed using a patient-specific eikonal model of cardiac activation with spatially varying action potential duration (APD) and repolarization rate, fit to a patient's ECG.

RESULTS

During CRT-ON T-wave area diminished within a day and remained stable thereafter, whereas QT-interval did not change significantly. During CRT-OFF T-wave area doubled within 5 days of CRT, while QT-interval and peak-to-end T-wave interval hardly changed. Left ventricular (LV) ejection fraction only increased significantly increased after 1 month of CRT. Computer simulations indicated that the increase in T-wave area during CRT-OFF can be explained by changes in APD following chronic CRT that are opposite to the change in CRT-induced activation time. These APD changes were associated with a reduction in LV dispersion in repolarization during chronic CRT.

CONCLUSION

T-wave area during CRT-OFF is a sensitive marker for adaptations in ventricular repolarization during chronic CRT that may include a reduction in LV dispersion of repolarization.

An Integrated Workflow for Building Digital Twins of Cardiac Electromechanics-A Multi-Fidelity Approach for Personalising Active Mechanics

Personalised computer models of cardiac function, referred to as cardiac digital twins, are envisioned to play an important role in clinical precision therapies of cardiovascular diseases. A major obstacle hampering clinical translation involves the significant computational costs involved in the personalisation of biophysically detailed mechanistic models that require the identification of high-dimensional parameter vectors. An important aspect to identify in electromechanics (EM) models are active mechanics parameters that govern cardiac contraction and relaxation. In this study, we present a novel, fully automated, and efficient approach for personalising biophysically detailed active mechanics models using a two-step multi-fidelity solution. In the first step, active mechanical behaviour in a given 3D EM model is represented by a purely phenomenological, low-fidelity model, which is personalised at the organ scale by calibration to clinical cavity pressure data. Then, in the second step, median traces of nodal cellular active stress, intracellular calcium concentration, and fibre stretch are generated and utilised to personalise the desired high-fidelity model at the cellular scale using a 0D model of cardiac EM. Our novel approach was tested on a cohort of seven human left ventricular (LV) EM models, created from patients treated for aortic coarctation (CoA). Goodness of fit, computational cost, and robustness of the algorithm against uncertainty in the clinical data and variations of initial guesses were evaluated. We demonstrate that our multi-fidelity approach facilitates the personalisation of a biophysically detailed active stress model within only a few (2 to 4) expensive 3D organ-scale simulations-a computational effort compatible with clinical model applications.

Modeling the His-Purkinje Effect in Non-invasive Estimation of Endocardial and Epicardial Ventricular Activation

Inverse electrocardiography (iECG) estimates epi- and endocardial electrical activity from body surface potentials maps (BSPM). In individuals at risk for cardiomyopathy, non-invasive estimation of normal ventricular activation may provide valuable information to aid risk stratification to prevent sudden cardiac death. However, multiple simultaneous activation wavefronts initiated by the His-Purkinje system, severely complicate iECG. To improve the estimation of normal ventricular activation, the iECG method should accurately mimic the effect of the His-Purkinje system, which is not taken into account in the previously published multi-focal iECG. Therefore, we introduce the novel multi-wave iECG method and report on its performance. Multi-wave iECG and multi-focal iECG were tested in four patients undergoing invasive electro-anatomical mapping during normal ventricular activation. In each subject, 67-electrode BSPM were recorded and used as input for both iECG methods. The iECG and invasive local activation timing (LAT) maps were compared. Median epicardial inter-map correlation coefficient (CC) between invasive LAT maps and estimated multi-wave iECG versus multi-focal iECG was 0.61 versus 0.31. Endocardial inter-map CC was 0.54 respectively 0.22. Modeling the His-Purkinje system resulted in a physiologically realistic and robust non-invasive estimation of normal ventricular activation, which might enable the early detection of cardiac disease during normal sinus rhythm.

Extrapolation of Ventricular Activation Times From Sparse Electroanatomical Data Using Graph Convolutional Neural Networks

Electroanatomic mapping is the gold standard for the assessment of ventricular tachycardia. Acquiring high resolution electroanatomic maps is technically challenging and may require interpolation methods to obtain dense measurements. These methods, however, cannot recover activation times in the entire biventricular domain. This work investigates the use of graph convolutional neural networks to estimate biventricular activation times from sparse measurements. Our method is trained on more than 15,000 synthetic examples of realistic ventricular depolarization patterns generated by a computational electrophysiology model. Using geometries sampled from a statistical shape model of biventricular anatomy, diverse wave dynamics are induced by randomly sampling scar and border zone distributions, locations of initial activation, and tissue conduction velocities. Once trained, the method accurately reconstructs biventricular activation times in left-out synthetic simulations with a mean absolute error of 3.9 ms ± 4.2 ms at a sampling density of one measurement sample per cm2. The total activation time is matched with a mean error of 1.4 ms ± 1.4 ms. A significant decrease in errors is observed in all heart zones with an increased number of samples. Without re-training, the network is further evaluated on two datasets: (1) an in-house dataset comprising four ischemic porcine hearts with dense endocardial activation maps; (2) the CRT-EPIGGY19 challenge data comprising endo- and epicardial measurements of 5 infarcted and 6 non-infarcted swines. In both setups the neural network recovers biventricular activation times with a mean absolute error of less than 10 ms even when providing only a subset of endocardial measurements as input. Furthermore, we present a simple approach to suggest new measurement locations in real-time based on the estimated uncertainty of the graph network predictions. The model-guided selection of measurement locations allows to reduce by 40% the number of measurements required in a random sampling strategy, while achieving the same prediction error. In all the tested scenarios, the proposed approach estimates biventricular activation times with comparable or better performance than a personalized computational model and significant runtime advantages.

Multiparameter optimization of nonuniform passive diffusion properties for creating coarse-grained equivalent models of cardiac propagation

The arrhythmogenic role of discrete cardiac propagation may be assessed by comparing discrete (fine-grained) and equivalent continuous (coarse-grained) models. We aim to develop an optimization algorithm for estimating the smooth conductivity field that best reproduces the diffusion properties of a given discrete model. Our algorithm iteratively adjusts local conductivity of the coarse-grained continuous model by simulating passive diffusion from white noise initial conditions during 3-10 ms and computing the root mean square error with respect to the discrete model. The coarse-grained conductivity field was interpolated from up to 300 evenly spaced control points. We derived an approximate formula for the gradient of the cost function that required (in two dimensions) only two additional simulations per iteration regardless of the number of estimated parameters. Conjugate gradient solver facilitated simultaneous optimization of multiple conductivity parameters. The method was tested in rectangular anisotropic tissues with uniform and nonuniform conductivity (slow regions with sinusoidal profile) and random diffuse fibrosis, as well as in a monolayer interconnected cable model of the left atrium with spatially-varying fibrosis density. Comparison of activation maps served as validation. The results showed that after convergence the errors in activation time were < 1 ms for rectangular geometries and 1-3 ms in the atrial model. Our approach based on the comparison of passive properties (<10 ms simulation) avoids performing active propagation simulations (>100 ms) at each iteration while reproducing activation maps, with possible applications to investigating the impact of microstructure on arrhythmias.

Whole-heart ventricular arrhythmia modeling moving forward: Mechanistic insights and translational applications

Ventricular arrhythmias are the primary cause of sudden cardiac death and one of the leading causes of mortality worldwide. Whole-heart computational modeling offers a unique approach for studying ventricular arrhythmias, offering vast potential for developing both a mechanistic understanding of ventricular arrhythmias and clinical applications for treatment. In this review, the fundamentals of whole-heart ventricular modeling and current methods of personalizing models using clinical data are presented. From this foundation, the authors summarize recent advances in whole-heart ventricular arrhythmia modeling. Efforts in gaining mechanistic insights into ventricular arrhythmias are discussed, in addition to other applications of models such as the assessment of novel therapeutics. The review emphasizes the unique benefits of computational modeling that allow for insights that are not obtainable by contemporary experimental or clinical means. Additionally, the clinical impact of modeling is explored, demonstrating how patient care is influenced by the information gained from ventricular arrhythmia models. The authors conclude with future perspectives about the direction of whole-heart ventricular arrhythmia modeling, outlining how advances in neural network methodologies hold the potential to reduce computational expense and permit for efficient whole-heart modeling.

GEASI: Geodesic-based earliest activation sites identification in cardiac models

The identification of the initial ventricular activation sequence is a critical step for the correct personalization of patient-specific cardiac models. In healthy conditions, the Purkinje network is the main source of the electrical activation, but under pathological conditions the so-called earliest activation sites (EASs) are possibly sparser and more localized. Yet, their number, location and timing may not be easily inferred from remote recordings, such as the epicardial activation or the 12-lead electrocardiogram (ECG), due to the underlying complexity of the model. In this work, we introduce GEASI (Geodesic-based Earliest Activation Sites Identification) as a novel approach to simultaneously identify all EASs. To this end, we start from the anisotropic eikonal equation modeling cardiac electrical activation and exploit its Hamilton-Jacobi formulation to minimize a given objective function, for example, the quadratic mismatch to given activation measurements. This versatile approach can be extended to estimate the number of activation sites by means of the topological gradient, or fitting a given ECG. We conducted various experiments in 2D and 3D for in-silico models and an in-vivo intracardiac recording collected from a patient undergoing cardiac resynchronization therapy. The results demonstrate the clinical applicability of GEASI for potential future personalized models and clinical intervention.

A novel convolutional neural network for reconstructing surface electrocardiograms from intracardiac electrograms and vice versa

We propose a novel convolutional neural network framework for mapping a multivariate input to a multivariate output. In particular, we implement our algorithm within the scope of 12-lead surface electrocardiogram (ECG) reconstruction from intracardiac electrograms (EGM) and vice versa. The goal of performing this task is to allow for improved point-of-care monitoring of patients with an implanted device to treat cardiac pathologies. We will achieve this goal with 12-lead ECG reconstruction and by providing a new diagnostic tool for classifying five different ECG types. The algorithm is evaluated on a dataset retroactively collected from 14 patients. Correlation coefficients calculated between the reconstructed and the actual ECG show that the proposed convolutional neural network model represents an efficient, accurate, and superior way to synthesize a 12-lead ECG when compared to previous methods. We can also achieve the same reconstruction accuracy with only one EGM lead as input. We also tested the model in a non-patient specific way and saw a reasonable correlation coefficient. The model was also executed in the reverse direction to produce EGM signals from a 12-lead ECG and found that the correlation was comparable to the forward direction. Lastly, we analyzed the features learned in the model and determined that the model learns an overcomplete basis of our 12-lead ECG space. We then use this basis of features to create a new diagnostic tool for classifying different ECG arrhythmia's on the MIT-BIH arrhythmia database with an average accuracy of 0.98.

Computer Modeling of the Heart for ECG Interpretation—A Review

Computer modeling of the electrophysiology of the heart has undergone significant progress. A healthy heart can be modeled starting from the ion channels via the spread of a depolarization wave on a realistic geometry of the human heart up to the potentials on the body surface and the ECG. Research is advancing regarding modeling diseases of the heart. This article reviews progress in calculating and analyzing the corresponding electrocardiogram (ECG) from simulated depolarization and repolarization waves. First, we describe modeling of the P-wave, the QRS complex and the T-wave of a healthy heart. Then, both the modeling and the corresponding ECGs of several important diseases and arrhythmias are delineated: ischemia and infarction, ectopic beats and extrasystoles, ventricular tachycardia, bundle branch blocks, atrial tachycardia, flutter and fibrillation, genetic diseases and channelopathies, imbalance of electrolytes and drug-induced changes. Finally, we outline the potential impact of computer modeling on ECG interpretation. Computer modeling can contribute to a better comprehension of the relation between features in the ECG and the underlying cardiac condition and disease. It can pave the way for a quantitative analysis of the ECG and can support the cardiologist in identifying events or non-invasively localizing diseased areas. Finally, it can deliver very large databases of reliably labeled ECGs as training data for machine learning.

Electro-Mechanical Whole-Heart Digital Twins: A Fully Coupled Multi-Physics Approach

Mathematical models of the human heart are evolving to become a cornerstone of precision medicine and support clinical decision making by providing a powerful tool to understand the mechanisms underlying pathophysiological conditions. In this study, we present a detailed mathematical description of a fully coupled multi-scale model of the human heart, including electrophysiology, mechanics, and a closed-loop model of circulation. State-of-the-art models based on human physiology are used to describe membrane kinetics, excitation-contraction coupling and active tension generation in the atria and the ventricles. Furthermore, we highlight ways to adapt this framework to patient specific measurements to build digital twins. The validity of the model is demonstrated through simulations on a personalized whole heart geometry based on magnetic resonance imaging data of a healthy volunteer. Additionally, the fully coupled model was employed to evaluate the effects of a typical atrial ablation scar on the cardiovascular system. With this work, we provide an adaptable multi-scale model that allows a comprehensive personalization from ion channels to the organ level enabling digital twin modeling.