Automated Localization of Focal Ventricular Tachycardia From Simulated Implanted Device Electrograms: A Combined Physics–AI Approach

Monaci, Sofia; Gillette, Karli; Puyol‐Antón, Esther; Rajani, Ronak; King, Andrew P.; Bishop, Martin J.

doi:10.3389/fphys.2021.682446

Cited by 12 publications

(15 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…the origin of the so-called ventricular ectopic beat. Several studies already proved the applicability of machine learning approaches to the problem of localizing the activation wave source with simulated signals, partly by first estimating the activation times on the heart surface, partly by using pacing signals [37,5]. Learning from patient-specific simulated signals is another already used approach which helps to estimate activation times and the location of the activation source on clinical data [17,2].…”

Section: Introductionmentioning

confidence: 99%

“…Besides, simulated data can help to overcome the shortage of clinical data in this field, which often prevents the use of machine learning approaches. Instead of directly estimating a set of coordinates as the origin of the activation, it is also possible to divide the ventricles into segments and predict each segment's probability to contain the activation wave source [28,37,66]. The latter aims at overcoming the problem of inter-patient variability as these segments can be defined on all ventricles.…”

Section: Introductionmentioning

confidence: 99%

“…The latter aims at overcoming the problem of inter-patient variability as these segments can be defined on all ventricles. An alternative to the introduction of ventricular segments are specifically designed machine learning approaches [21] or the use of a ventricular coordinate system [37]. Fully automatic approaches still relying on patient-specific geometries or usable for only one ventricle were successfully implemented in [51,67,65].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Non-invasive Localization of the Ventricular Excitation Origin Without Patient-specific Geometries Using Deep Learning

Pilia¹,

Schuler²,

Rees³

et al. 2022

Preprint

View full text Add to dashboard Cite

Cardiovascular diseases account for 17 million deaths per year worldwide. Of these, 25% are categorized as sudden cardiac death, which can be related to ventricular tachycardia (VT). This kind of arrhythmia can be caused by focal activation sources outside the sinus node. A curative treatment is catheter ablation of these foci in order to inactivate the abnormal triggering activity. However, the localization procedure is usually time-consuming and requires an invasive procedure in the catheter lab. To facilitate and expedite the treatment, we present two novel localization support techniques based on convolutional neural networks (CNNs) addressing these clinical needs. In contrast to existing methods, our approaches were designed to be independent of the patient-specific geometry and directly applicable to surface ECG signals, while also delivering a binary transmural position. Furthermore, one of the method's outputs could be interpreted as several ranked solutions. The CNNs were trained on a data set containing only simulated data and evaluated both on simulated and clinical test data. On simulated data, the median test error was below 3 mm. The median localization error on the unseen clinical (test) data was between 32 mm and 41 mm without optimizing the pre-processing and CNN on the clinical (test) data. Interpreting the output of one of the approaches as ranked solutions, the best median error of the top-3 solutions dropped to 20 mm on the clinical test set. The transmural position was correctly detected in up to 82% of all clinical cases. These results demonstrate a proof of principle to utilize CNNs to localize the activation source without the intrinsic need of patient-specific geometrical information. Furthermore, delivering multiple solutions can help the physician to find the real activation source amongst more than one possible locations. With a further optimization to clinical data, these methods have a high potential to speed up clinical interventions, replace certain steps within those and therefore consequently decrease procedural risk and improve VT patients' outcomes.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Non-invasive Localization of the Ventricular Excitation Origin Without Patient-specific Geometries Using Deep Learning

Pilia¹,

Schuler²,

Rees³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Many studies have also successfully employed ML in arrhythmia risk stratification, including advanced ML-enabled image analysis (Feeny et al, 2020 ; Krittanawong et al, 2020 ; Trayanova, 2021 ). Recently, ML models have been combined with biophysical modeling to assess risk for dangerous arrhythmia as well as to uncover mechanisms of rhythm disturbances and to manage treatment for affected patients (Prakosa et al, 2013 ; Bernard et al, 2018 ; Lozoya et al, 2019 ; Shade et al, 2020 ; Banus et al, 2021 ; Monaci et al, 2021 ; Sermesant et al, 2021 ; Trayanova, 2021 ). Biophysical cardiac computational modeling and ML have also increasingly been combined to focus on drug-induced proarrhythmic risk assessment, as in e.g., Yang et al ( 2020 ) and Sahli-Costabal et al ( 2020 ).…”

Section: Introductionmentioning

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

“…Many studies have also successfully employed ML in arrhythmia risk stratification, including advanced ML-enabled image analysis (Feeny et al, 2020;Krittanawong et al, 2020;Trayanova, 2021). Recently, ML models have been combined with biophysical modeling to assess risk for dangerous arrhythmia as well as to uncover mechanisms of rhythm disturbances and to manage treatment for affected patients (Prakosa et al, 2013;Bernard et al, 2018;Lozoya et al, 2019;Shade et al, 2020;Banus et al, 2021;Monaci et al, 2021;Trayanova, 2021). Biophysical cardiac computational modeling and ML have also increasingly been combined to focus on drug-induced proarrhythmic risk assessment, as in e.g., Yang et al (2020) and Sahli-Costabal et al (2020).…”

Section: Introductionmentioning

confidence: 99%

Data_Sheet_1.pdf

View full text Add to dashboard Cite

Automated Localization of Focal Ventricular Tachycardia From Simulated Implanted Device Electrograms: A Combined Physics–AI Approach

Cited by 12 publications

References 50 publications

Non-invasive Localization of the Ventricular Excitation Origin Without Patient-specific Geometries Using Deep Learning

Non-invasive Localization of the Ventricular Excitation Origin Without Patient-specific Geometries Using Deep Learning

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

Data_Sheet_1.pdf

Contact Info

Product

Resources

About