Embedding high-dimensional Bayesian optimization via generative modeling: Parameter personalization of cardiac electrophysiological models

Dhamala, Jwala; Bajracharya, Pradeep; Arevalo, Hermenegild; Sapp, John L.; Horáček, B. Milan; Wu, Kathérine C.; Trayanova, Natalia A.; Wang, Linwei

doi:10.1016/j.media.2020.101670

Cited by 21 publications

(11 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The phenomenological Mitchell-Schaeffer model (Mitchell and Schaeffer, 2003), with relatively few parameters, may be a good candidate in this regard (Relan et al, 2010(Relan et al, , 2011Corrado et al, 2017). Clinical data are typically noisy and sparse so recent developments have included a set of approaches that take into account uncertainties in the data to create probabilistic models (Konukoglu et al, 2011;Dhamala et al, 2020), as well as new models designed with uncertainty in mind (Pathmanathan et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

“…Gaussian process (GP) emulators, which provide a prediction and corresponding prediction uncertainty, can be effective emulators of complex computer models (Conti and O'Hagan, 2010). GP emulators have been used for sensitivity analysis (Chang et al, 2015;Coveney and Clayton, 2020) and history matching (Coveney and Clayton, 2018) of cardiac cell models, and for models of cardiac tissue (Dhamala et al, 2020;Lawson et al, 2020) and mechanics (Longobardi et al, 2020). Emulators are conditioned on precalculated simulator data, but since they can make predictions at new inputs they are ideal tools for MCMC.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Bayesian Calibration of Electrophysiology Models Using Restitution Curve Emulators

et al. 2021

View full text Add to dashboard Cite

Calibration of cardiac electrophysiology models is a fundamental aspect of model personalization for predicting the outcomes of cardiac therapies, simulation testing of device performance for a range of phenotypes, and for fundamental research into cardiac function. Restitution curves provide information on tissue function and can be measured using clinically feasible measurement protocols. We introduce novel “restitution curve emulators” as probabilistic models for performing model exploration, sensitivity analysis, and Bayesian calibration to noisy data. These emulators are built by decomposing restitution curves using principal component analysis and modeling the resulting coordinates with respect to model parameters using Gaussian processes. Restitution curve emulators can be used to study parameter identifiability via sensitivity analysis of restitution curve components and rapid inference of the posterior distribution of model parameters given noisy measurements. Posterior uncertainty about parameters is critical for making predictions from calibrated models, since many parameter settings can be consistent with measured data and yet produce very different model behaviors under conditions not effectively probed by the measurement protocols. Restitution curve emulators are therefore promising probabilistic tools for calibrating electrophysiology models.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Bayesian Calibration of Electrophysiology Models Using Restitution Curve Emulators

et al. 2021

View full text Add to dashboard Cite

show abstract

“… Zenker (2010) used importance sampling to estimate model parameters in a cardiovascular model. Dhamala et al (2020) used high-dimensional Bayesian optimization for parameter personalization of a cardiac electrophysiological model. Coveney and Clayton (2018) used history matching to calibrate the maximum conductance of ion channels and exchangers in two detailed models of the human atrial action potential against measurements of action potential biomarkers.…”

Section: Discussionmentioning

confidence: 99%

Uncertainty Quantification of Regional Cardiac Tissue Properties in Arrhythmogenic Cardiomyopathy Using Adaptive Multiple Importance Sampling

et al. 2021

View full text Add to dashboard Cite

Introduction: Computational models of the cardiovascular system are widely used to simulate cardiac (dys)function. Personalization of such models for patient-specific simulation of cardiac function remains challenging. Measurement uncertainty affects accuracy of parameter estimations. In this study, we present a methodology for patient-specific estimation and uncertainty quantification of parameters in the closed-loop CircAdapt model of the human heart and circulation using echocardiographic deformation imaging. Based on patient-specific estimated parameters we aim to reveal the mechanical substrate underlying deformation abnormalities in patients with arrhythmogenic cardiomyopathy (AC).Methods: We used adaptive multiple importance sampling to estimate the posterior distribution of regional myocardial tissue properties. This methodology is implemented in the CircAdapt cardiovascular modeling platform and applied to estimate active and passive tissue properties underlying regional deformation patterns, left ventricular volumes, and right ventricular diameter. First, we tested the accuracy of this method and its inter- and intraobserver variability using nine datasets obtained in AC patients. Second, we tested the trueness of the estimation using nine in silico generated virtual patient datasets representative for various stages of AC. Finally, we applied this method to two longitudinal series of echocardiograms of two pathogenic mutation carriers without established myocardial disease at baseline.Results: Tissue characteristics of virtual patients were accurately estimated with a highest density interval containing the true parameter value of 9% (95% CI [0–79]). Variances of estimated posterior distributions in patient data and virtual data were comparable, supporting the reliability of the patient estimations. Estimations were highly reproducible with an overlap in posterior distributions of 89.9% (95% CI [60.1–95.9]). Clinically measured deformation, ejection fraction, and end-diastolic volume were accurately simulated. In presence of worsening of deformation over time, estimated tissue properties also revealed functional deterioration.Conclusion: This method facilitates patient-specific simulation-based estimation of regional ventricular tissue properties from non-invasive imaging data, taking into account both measurement and model uncertainties. Two proof-of-principle case studies suggested that this cardiac digital twin technology enables quantitative monitoring of AC disease progression in early stages of disease.

show abstract

“…Alternatively, the computational cost per simulation could be reduced by a faster implementation of the AF model, e.g., based on GPGPU (Kaboudian et al, 2019 ). Additionally, low fidelity models provide an approximation that could be based on simplified physics, e.g., eikonal models (Fu et al, 2013 ; Quaglino et al, 2018 ), reduced-order modeling (Fresca et al, 2020 ; Pagani and Manzoni, 2021 ) or simply on a coarser discretization (Quaglino et al, 2019 ; Dhamala et al, 2020 ).…”

Section: Introductionmentioning

confidence: 99%

Fast Characterization of Inducible Regions of Atrial Fibrillation Models With Multi-Fidelity Gaussian Process Classification

et al. 2022

View full text Add to dashboard Cite

Computational models of atrial fibrillation have successfully been used to predict optimal ablation sites. A critical step to assess the effect of an ablation pattern is to pace the model from different, potentially random, locations to determine whether arrhythmias can be induced in the atria. In this work, we propose to use multi-fidelity Gaussian process classification on Riemannian manifolds to efficiently determine the regions in the atria where arrhythmias are inducible. We build a probabilistic classifier that operates directly on the atrial surface. We take advantage of lower resolution models to explore the atrial surface and combine seamlessly with high-resolution models to identify regions of inducibility. We test our methodology in 9 different cases, with different levels of fibrosis and ablation treatments, totalling 1,800 high resolution and 900 low resolution simulations of atrial fibrillation. When trained with 40 samples, our multi-fidelity classifier that combines low and high resolution models, shows a balanced accuracy that is, on average, 5.7% higher than a nearest neighbor classifier. We hope that this new technique will allow faster and more precise clinical applications of computational models for atrial fibrillation. All data and code accompanying this manuscript will be made publicly available at: https://github.com/fsahli/AtrialMFclass.

show abstract

Embedding high-dimensional Bayesian optimization via generative modeling: Parameter personalization of cardiac electrophysiological models

Cited by 21 publications

References 25 publications

Bayesian Calibration of Electrophysiology Models Using Restitution Curve Emulators

Bayesian Calibration of Electrophysiology Models Using Restitution Curve Emulators

Uncertainty Quantification of Regional Cardiac Tissue Properties in Arrhythmogenic Cardiomyopathy Using Adaptive Multiple Importance Sampling

Fast Characterization of Inducible Regions of Atrial Fibrillation Models With Multi-Fidelity Gaussian Process Classification

Contact Info

Product

Resources

About