RESUMO
Cardiac resynchronization therapy (CRT) can substantially improve dyssynchronous heart failure and reduce mortality. However, about one-third of patients who are implanted, derive no measurable benefit from CRT. Non-response may partly be due to suboptimal activation of the left ventricle (LV) caused by electrophysiological heterogeneities. The goal of this study is to investigate the performance of a newly developed method used to analyze electrical wavefront propagation in a heart model including myocardial scar and compare this to clinical benchmark studies. We used computational models to measure the maximum activation front (MAF) in the LV during different pacing scenarios. Different heart geometries and scars were created based on cardiac MR images of three patients. The right ventricle (RV) was paced from the apex and the LV was paced from 12 different sites, single site, dual-site and triple site. Our results showed that for single LV site pacing, the pacing site with the largest MAF corresponded with the latest activated regions of the LV demonstrated during RV pacing, which also agrees with previous markers used for predicting optimal single-site pacing location. We then demonstrated the utility of MAF in predicting optimal electrode placements in more complex scenarios including scar and multi-site LV pacing. This study demonstrates the potential value of computational simulations in understanding and planning CRT.
Assuntos
Terapia de Ressincronização Cardíaca , Insuficiência Cardíaca , Insuficiência Cardíaca/diagnóstico por imagem , Insuficiência Cardíaca/terapia , Ventrículos do Coração/diagnóstico por imagem , Humanos , Resultado do TratamentoRESUMO
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.