Search Menu
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information
Search Scholarly Publications

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

Journal Article · · Frontiers in Physiology
 [1];  [2];  [2];  [2];  [3];  [4]
  1. Univ. della Svizzera Italiana (Switzerland); Euler Institute, Università della Svizzera italiana, Lugano, Switzerland
  2. Univ. della Svizzera Italiana (Switzerland)
  3. Univ. of Pennsylvania, Philadelphia, PA (United States)
  4. Pontifica Universidad Catolica de Chile, Santiago (Chile); Millennium Nucleus for Cardiovascular Magnetic Resonance, Santiago (Chile)
+ Show Author Affiliations

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.

Research Organization:
Raytheon Technologies Corp., Waltham, MA (United States); Univ. of Pennsylvania, Philadelphia, PA (United States)
Sponsoring Organization:
USDOE Advanced Research Projects Agency - Energy (ARPA-E); USDOE Office of Science (SC); US Air Force Office of Scientific Research (AFOSR)
Grant/Contract Number:
AR0001201; SC0019116
OSTI ID:
1981097
Journal Information:
Frontiers in Physiology, Journal Name: Frontiers in Physiology Vol. 13; ISSN 1664-042X
Publisher:
Frontiers Media S.A.Copyright Statement
Country of Publication:
United States
Language:
English

References (38)

Predicting drug-induced arrhythmias by multiscale modeling
  • Sahli Costabal, Francisco; Yao, Jiang; Kuhl, Ellen
  • International Journal for Numerical Methods in Biomedical Engineering, Vol. 34, Issue 5 https://doi.org/10.1002/cnm.2964
journal March 2018
Fast uncertainty quantification of activation sequences in patient-specific cardiac electrophysiology meeting clinical time constraints: Fast uncertainty quantification in cardiac electrophysiology
  • Quaglino, A.; Pezzuto, S.; Koutsourelakis, P. S.
  • International Journal for Numerical Methods in Biomedical Engineering, Vol. 34, Issue 7 https://doi.org/10.1002/cnm.2985
journal April 2018
Enabling forward uncertainty quantification and sensitivity analysis in cardiac electrophysiology by reduced order modeling and machine learning journal May 2021
Classifying Drugs by their Arrhythmogenic Risk Using Machine Learning journal March 2020
Multi-fidelity classification using Gaussian processes: Accelerating the prediction of large-scale computational models journal December 2019
A technique for measuring anisotropy in atrial conduction to estimate conduction velocity and atrial fibre direction journal January 2019
Embedding high-dimensional Bayesian optimization via generative modeling: Parameter personalization of cardiac electrophysiological models journal May 2020
Computationally guided personalized targeted ablation of persistent atrial fibrillation journal August 2019
Non-Pulmonary Vein Triggers of Atrial Fibrillation Are Likely to Arise from Low-Voltage Areas in the Left Atrium journal August 2019
Spontaneous Initiation of Atrial Fibrillation by Ectopic Beats Originating in the Pulmonary Veins journal September 1998
Approaches to Catheter Ablation for Persistent Atrial Fibrillation journal May 2015
Predicting the output from a complex computer code when fast approximations are available journal March 2000
Characterizing the arrhythmogenic substrate in personalized models of atrial fibrillation: sensitivity to mesh resolution and pacing protocol in AF models journal March 2021
Synergistic antiarrhythmic effect of inward rectifier current inhibition and pulmonary vein isolation in a 3D computer model for atrial fibrillation journal March 2021
Regression and Classification Using Gaussian Process Priors book August 1999
Gaussian process manifold interpolation for probabilistic atrial activation maps and uncertain conduction velocity
  • Coveney, Sam; Corrado, Cesare; Roney, Caroline H.
  • Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 378, Issue 2173 https://doi.org/10.1098/rsta.2019.0345
journal May 2020
Active Learning with Gaussian Processes for Object Categorization conference January 2007
A Comparison of Monodomain and Bidomain Reaction-Diffusion Models for Action Potential Propagation in the Human Heart journal December 2006
Probabilistic Interpolation of Uncertain Local Activation Times on Human Atrial Manifolds journal January 2020
An explicit link between Gaussian fields and Gaussian Markov random fields: the stochastic partial differential equation approach: Link between Gaussian Fields and Gaussian Markov Random Fields journal August 2011
Real-time interactive simulations of large-scale systems on personal computers and cell phones: Toward patient-specific heart modeling and other applications journal March 2019
A Fast Iterative Method for Solving the Eikonal Equation on Tetrahedral Domains journal January 2013
Multifidelity Information Fusion Algorithms for High-Dimensional Systems and Massive Data sets journal January 2016
Geodesics in heat journal September 2013
Ionic mechanisms underlying human atrial action potential properties: insights from a mathematical model journal July 1998
Initiation of Atrial Fibrillation by Ectopic Beats Originating From the Pulmonary Veins journal November 1999
Heart Disease and Stroke Statistics—2021 Update: A Report From the American Heart Association journal February 2021
Left Atrial Appendage Electrical Isolation Reduces Atrial Fibrillation Recurrences journal January 2021
Particle Learning of Gaussian Process Models for Sequential Design and Optimization journal January 2011
Virtual Electrophysiological Study of Atrial Fibrillation in Fibrotic Remodeling journal February 2015
Deep learning-based reduced order models in cardiac electrophysiology journal October 2020
Active Learning with Statistical Models journal January 1996
Anatomically-Induced Fibrillation in a 3D Model of the Human Atria conference December 2018
Strictly and non-strictly positive definite functions on spheres journal September 2013
Patient-Specific Identification of Atrial Flutter Vulnerability–A Computational Approach to Reveal Latent Reentry Pathways journal January 2019
Epicardial Fibrosis Explains Increased Endo–Epicardial Dissociation and Epicardial Breakthroughs in Human Atrial Fibrillation journal February 2020
A Reproducible Protocol to Assess Arrhythmia Vulnerability in silico: Pacing at the End of the Effective Refractory Period journal April 2021
Fast Posterior Estimation of Cardiac Electrophysiological Model Parameters via Bayesian Active Learning journal October 2021

Similar Records

Related Subjects

59 BASIC BIOLOGICAL SCIENCES
Gaussian processes
Riemannian manifolds
active learning
atrial fibrillation
cardiac electrophysiology
machine learning