Electrophysiological and anatomical factors determine arrhythmic risk in acute myocardial ischaemia and its modulation by sodium current availability

Martinez-Navarro, Hector; Zhou, Xin; Bueno‐Orovio, Alfonso; Rodriguez, Blanca

doi:10.1098/rsfs.2019.0124

Cited by 13 publications

(5 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general, hearts with larger global ischemic volumes were more inducible after the pacing protocol. Additonally, pacing from segments with larger percentage of ischemic tissue were also more likely to induce arrhythmia (Oliveira et al, 2018 ; Martinez-Navarro et al, 2019 , 2021 ). This result suggests a mechanistic link between location of pacing site and arrhythmia inducibility in post-MI patients.…”

Section: Resultsmentioning

confidence: 99%

Combined In-silico and Machine Learning Approaches Toward Predicting Arrhythmic Risk in Post-infarction Patients

Maleckar

Myklebust

et al. 2021

Front. Physiol.

View full text Add to dashboard Cite

Background: Remodeling due to myocardial infarction (MI) significantly increases patient arrhythmic risk. Simulations using patient-specific models have shown promise in predicting personalized risk for arrhythmia. However, these are computationally- and time- intensive, hindering translation to clinical practice. Classical machine learning (ML) algorithms (such as K-nearest neighbors, Gaussian support vector machines, and decision trees) as well as neural network techniques, shown to increase prediction accuracy, can be used to predict occurrence of arrhythmia as predicted by simulations based solely on infarct and ventricular geometry. We present an initial combined image-based patient-specific in silico and machine learning methodology to assess risk for dangerous arrhythmia in post-infarct patients. Furthermore, we aim to demonstrate that simulation-supported data augmentation improves prediction models, combining patient data, computational simulation, and advanced statistical modeling, improving overall accuracy for arrhythmia risk assessment.Methods: MRI-based computational models were constructed from 30 patients 5 days post-MI (the “baseline” population). In order to assess the utility biophysical model-supported data augmentation for improving arrhythmia prediction, we augmented the virtual baseline patient population. Each patient ventricular and ischemic geometry in the baseline population was used to create a subfamily of geometric models, resulting in an expanded set of patient models (the “augmented” population). Arrhythmia induction was attempted via programmed stimulation at 17 sites for each virtual patient corresponding to AHA LV segments and simulation outcome, “arrhythmia,” or “no-arrhythmia,” were used as ground truth for subsequent statistical prediction (machine learning, ML) models. For each patient geometric model, we measured and used choice data features: the myocardial volume and ischemic volume, as well as the segment-specific myocardial volume and ischemia percentage, as input to ML algorithms. For classical ML techniques (ML), we trained k-nearest neighbors, support vector machine, logistic regression, xgboost, and decision tree models to predict the simulation outcome from these geometric features alone. To explore neural network ML techniques, we trained both a three - and a four-hidden layer multilayer perceptron feed forward neural networks (NN), again predicting simulation outcomes from these geometric features alone. ML and NN models were trained on 70% of randomly selected segments and the remaining 30% was used for validation for both baseline and augmented populations.Results: Stimulation in the baseline population (30 patient models) resulted in reentry in 21.8% of sites tested; in the augmented population (129 total patient models) reentry occurred in 13.0% of sites tested. ML and NN models ranged in mean accuracy from 0.83 to 0.86 for the baseline population, improving to 0.88 to 0.89 in all cases.Conclusion: Machine learning techniques, combined with patient-specific, image-based computational simulations, can provide key clinical insights with high accuracy rapidly and efficiently. In the case of sparse or missing patient data, simulation-supported data augmentation can be employed to further improve predictive results for patient benefit. This work paves the way for using data-driven simulations for prediction of dangerous arrhythmia in MI patients.

show abstract

Section: Resultsmentioning

confidence: 99%

Combined In-silico and Machine Learning Approaches Toward Predicting Arrhythmic Risk in Post-infarction Patients

Maleckar

Myklebust

et al. 2021

Front. Physiol.

View full text Add to dashboard Cite

show abstract

“…The presence of MI scars creates regions of slow conduction in the heart, which can lead to arrhythmia [ 47 ]. To measure conduction delay caused by the patch, we computed the change in right epicardial activation time (REAT) in the model (measured as the time from stimulation to activation of the top right corner) and used this value to evaluate the impact of different parameters in our model.…”

Section: Methodsmentioning

confidence: 99%

Modelling the interaction between stem cells derived cardiomyocytes patches and host myocardium to aid non-arrhythmic engineered heart tissue design

et al. 2022

View full text Add to dashboard Cite

Application of epicardial patches constructed from human-induced pluripotent stem cell- derived cardiomyocytes (hiPSC-CMs) has been proposed as a long-term therapy to treat scarred hearts post myocardial infarction (MI). Understanding electrical interaction between engineered heart tissue patches (EHT) and host myocardium represents a key step toward a successful patch engraftment. EHT retain different electrical properties with respect to the host heart tissue due to the hiPSC-CMs immature phenotype, which may lead to increased arrhythmia risk. We developed a modelling framework to examine the influence of patch design on electrical activation at the engraftment site. We performed an in-silico investigation of different patch design approaches to restore pre-MI activation properties and evaluated the associated arrhythmic risk. We developed an in silico cardiac electrophysiology model of a transmural cross section of host myocardium. The model featured an infarct region, an epicardial patch spanning the infarct region and a bath region. The patch is modelled as a layer of hiPSC-CM, combined with a layer of conductive polymer (CP). Tissue and patch geometrical dimensions and conductivities were incorporated through 10 modifiable model parameters. We validated our model against 4 independent experimental studies and showed that it can qualitatively reproduce their findings. We performed a global sensitivity analysis (GSA) to isolate the most important parameters, showing that the stimulus propagation is mainly governed by the scar depth, radius and conductivity when the scar is not transmural, and by the EHT patch conductivity when the scar is transmural. We assessed the relevance of small animal studies to humans by comparing simulations of rat, rabbit and human myocardium. We found that stimulus propagation paths and GSA sensitivity indices are consistent across species. We explored which EHT design variables have the potential to restore physiological propagation. Simulations predict that increasing EHT conductivity from 0.28 to 1–1.1 S/m recovered physiological activation in rat, rabbit and human. Finally, we assessed arrhythmia risk related to increasing EHT conductivity and tested increasing the EHT Na+ channel density as an alternative strategy to match healthy activation. Our results revealed a greater arrhythmia risk linked to increased EHT conductivity compared to increased Na+ channel density. We demonstrated that our modeling framework could capture the interaction between host and EHT patches observed in in vitro experiments. We showed that large (patch and tissue dimensions) and small (cardiac myocyte electrophysiology) scale differences between small animals and humans do not alter EHT patch effect on infarcted tissue. Our model revealed that only when the scar is transmural do EHT properties impact activation times and isolated the EHT conductivity as the main parameter influencing propagation. We predicted that restoring physiological activation by tuning EHT conductivity is possible but may promote arrhythmic behavior. Finally, our model suggests that acting on hiPSC-CMs low action potential upstroke velocity and lack of IK1 may restore pre-MI activation while not promoting arrhythmia.

show abstract

“…The cardiac structural and functional information from imaging data, such as ultrasound, computed tomography or cardiac magnetic resonance (CMR), could be complementary to the information provided by ECG. Computational models combining ECG and imaging data can be used to estimate ventricular activation properties for therapy guidance and variability interpretation among different patients [22,25]. However, it is complicated to accurately localize RNs, as there is limited knowledge about the actual topology of Purkinje activation networks [16].…”

Section: Introductionmentioning

confidence: 99%

Deep Computational Model for the Inference of Ventricular Activation Properties

Li¹,

Camps²,

Banerjee³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Patient-specific cardiac computational models are essential for the efficient realization of precision medicine and in-silico clinical trials using digital twins. Cardiac digital twins can provide non-invasive characterizations of cardiac functions for individual patients, and therefore are promising for the patient-specific diagnosis and therapy stratification. However, current workflows for both the anatomical and functional twinning phases, referring to the inference of model anatomy and parameter from clinical data, are not sufficiently efficient, robust, and accurate. In this work, we propose a deep learning based patient-specific computational model, which can fuse both anatomical and electrophysiological information for the inference of ventricular activation properties, i.e., conduction velocities and root nodes. The activation properties can provide a quantitative assessment of cardiac electrophysiological function for the guidance of interventional procedures. We employ the Eikonal model to generate simulated electrocardiogram (ECG) with ground truth properties to train the inference model, where specific patient information has also been considered. For evaluation, we test the model on the simulated data and obtain generally promising results with fast computational time.

show abstract

Electrophysiological and anatomical factors determine arrhythmic risk in acute myocardial ischaemia and its modulation by sodium current availability

Cited by 13 publications

References 63 publications

Combined In-silico and Machine Learning Approaches Toward Predicting Arrhythmic Risk in Post-infarction Patients

Combined In-silico and Machine Learning Approaches Toward Predicting Arrhythmic Risk in Post-infarction Patients

Modelling the interaction between stem cells derived cardiomyocytes patches and host myocardium to aid non-arrhythmic engineered heart tissue design

Deep Computational Model for the Inference of Ventricular Activation Properties

Contact Info

Product

Resources

About