Research
Prediction of physiological states using machine learning
Predicting the future dynamics of physiological systems may allow intervention to terminate undesirable states or prevent their occurrence. In several recent papers, our group uses machine-learning techniques to predict complex time series from cardiac action potentials including experimental datasets with good accuracy and over long times compared to previous approaches. We use echo state networks, a type of reservoir computing, that is more efficient to train that other recurrent neural networks because only the output weights are trained. In the cardiac setting, we can predict several seconds (~20 action potentials) into the future.
Cardiac voltage prediction
- Shahi S, Fenton FH, Cherry EM. A machine-learning approach for long-term prediction of experimental cardiac action potential time series using an autoencoder and echo state networks. Chaos 2022; 32: 063117.
- Shahi S, Marcotte CD, Herndon CJ, Fenton FH, Shiferaw Y, Cherry EM. Long-time prediction of arrhythmic cardiac action potentials using recurrent neural networks and reservoir computing. Frontiers in Physiology 2021; 12: 734178.
Prediction of other systems
- Shahi S, Fenton FH, Cherry EM. Prediction of chaotic time series using recurrent neural networks and reservoir computing techniques: A comparative study. Machine Learning with Applications 2022; 8: 100300.
Estimating physiological system states, dynamics, and model parameter values
Cardiac electrical dynamics within the thickness of the myocardium is difficult to observe directly. Toward this end, our group has developed techniques for estimating these dynamics along with the behavior of unobservable variables using data assimilation. In this approach, we update an estimate of the system and state iteratively by combining observations when available with a prior model forecast from a numerical model, which itself depends on earlier observations. We have shown that our approach using an ensemble Kalman filter is effective and computationally efficient for reconstructing known system states even in the presence of significant model error. We have also applied the technique to predicting the transition of cells from the epithelial to mesenchymal state. In addition, we have used Bayesian approaches, including Hamilton Monte Carlo and Approximate Bayesian Computing Sequential Monte Carlo, to estimate distributions of parameter values of cardiac action potential models fitted to experimental data. Finally, we have also used methods of control theory to analyze the controllability of cardiac cellular electrical dynamics.
Data assimilation: cardiac dynamics
- Marcotte CD, Fenton FH, Hoffman MJ, Cherry EM. Robust data assimilation with noise: Applications to cardiac dynamics. Chaos 2021; 31: 013118.
- Hoffman MJ, Cherry EM. Sensitivity of a data-assimilation system for reconstructing three-dimensional cardiac electrical dynamics. Philosophical Transactions of the Royal Society A 2020; 378: 20190388.
- LaVigne NS, Holt N, Hoffman MJ, Cherry EM. Effects of model error on cardiac electrical wave state reconstruction using data assimilation. Chaos 2017; 27: 093911.
- Hoffman MJ, LaVigne NS, Scorse ST, Fenton FH, Cherry EM. Reconstructing 3D reentrant cardiac electrical wave dynamics using data assimilation. Chaos 2016; 26: 013107.
Data assimilation: epithelial-mesenchymal transition
- Mendez MJ, Hoffman MJ, Cherry EM, Lemmon CA, Weinberg SH. A data-assimilation approach to predict population dynamics during epithelial-mesenchymal transition. Biophysical Journal 2022; 121: 3061-3080.
- Mendez MJ, Hoffman MJ, Cherry EM, Lemmon CA, Weinberg SH. Cell fate forecasting: a data assimilation approach to predict epithelial-mesenchymal transition. Biophysical Journal 2020; 118: 1749-1768.
Bayesian approaches for estimating parameter distributions of action potential models
- Nieto Ramos A, Fenton FH, Cherry EM. Bayesian inference for fitting cardiac models to experiments: Estimating parameter distributions using Hamiltonian Monte Carlo and Approximate Bayesian Computation. Medical & Biological Engineering & Computing 2023; 61: 75-95.
- Nieto Ramos A, Herndon CJ, Fenton FH, Cherry EM. Quantifying distributions of parameters for cardiac action potential models using the Hamiltonian Monte Carlo method. Computing in Cardiology 2021; 48: 9662836.
Controllability of cardiac alternans
- Munoz LM, Ampofo MO, Cherry EM. Controllability of voltage- and calcium-driven alternans in a cardiac ionic model. Computing in Cardiology 2022; 498: 10081785.
- Munoz LM, Ampofo MO, Cherry EM. Empirical Gramian based controllability of alternans in a cardiac map model. Computing in Cardiology 2021; 48: 9662867.
- Munoz LM, Ampofo MO, Cherry EM. Controllability of voltage- and calcium-driven cardiac alternans in a map model. Chaos 2021; 31: 023139.
Efficient numerical methods for cardiac tissue modeling and simulation
Our group has developed several techniques for improved numerical methods for simulating cardiac cells and tissue. A recent approach involves using GPU-accelerated computations in a browser-based setting to allow near-real-time simulations. Some previous methods have focused on efficient techniques to use for three-dimensional complex geometries, and others focus on using space-time adaptivity in the computational mesh representing the solution to improve performance.
GPU computing applications
- Berman JP, Kaboudian A, Uzelac I, Iravanian S, Iles T, Iaizzo PA, Lim H, Smolka S, Glimm J, Cherry EM, Fenton FH. Interactive 3D human heart simulations on segmented human MRI hearts. Computing in Cardiology 2021; 48: 9662948.
- Ramirez Ortiz J, Kaboudian A, Uzelac I, Iravanian S, Cherry EM, Fenton FH. Interactive simulation of the ECG: Effects of cell types, distributions, shapes and duration. Computing in Cardiology 2021; 48: 9662928.
- Kaboudian A, Cherry EM, Fenton FH. Real-time interactive simulations of complex ionic cardiac cell models in 2D and 3D heart structures with GPUs on personal computers. Computing in Cardiology 2021; 48: 9662759.
- Kaboudian A, Cherry EM, Fenton FH. Real-time interactive simulations of large-scale systems on personal computers and cell phones: Toward patient-specific heart modeling. Science Advances 2019; 5: eaav6019.
- Kaboudian A, Cherry EM, Fenton FH. Large-scale interactive numerical experiments of chaos, solitons and fractals in real time via GPU in a web browser. Chaos, Solitons & Fractals 2019: 121, 6-29.
Complex geometries
- Xue S, Lim H, Glimm J, Fenton FH, Cherry EM. Sharp boundary electrocardiac simulations. SIAM Journal on Scientific Computing 2016; 38, B100-B117.
- Cherry EM, Fenton FH. Effects of boundaries and geometry on the spatial distribution of action potential duration in cardiac tissue. Journal of Theoretical Biology 2011; 285: 164-176.
- Fenton FH, Cherry EM, Karma A, Rappel WJ. Modeling wave propagation in realistic heart geometries using the phase-field method. Chaos 2005; 15: 013502.
Adaptive mesh refinement
- Cherry EM, Greenside HS, Henriquez CS. Efficient simulation of three-dimensional anisotropic cardiac tissue using an adaptive mesh refinement method. Chaos 2003; 13: 853-865.
- Cherry EM, Greenside HS, Henriquez CS. A space-time adaptive method for simulating complex cardiac dynamics. Physical Review Letters 2000; 84: 1343-1346.
Mathematical models of cardiac cellular and tissue electrophysiology
Our group has contributed to the development of several mathematical models of the electrical behavior of cardiac cells and tissue and tools for parameterizing these models. In addition, we have analyzed the behavior of many different cardiac cell models, including comparisons of models for the same cell types and species. We have also studied the use of delay-differential equations for cardiac cell and tissue modeling.
Model development
- Cherry EM, Fenton FH. Contribution of the Purkinje network to wave propagation in the canine ventricle: Insights from a combined electrophysiological-anatomical model. Nonlinear Dynamics 2012; 68: 365-379.
- Bueno-Orovio A, Cherry EM, Fenton FH. Minimal model for human ventricular action potentials in tissue. Journal of Theoretical Biology 2008; 253: 544-560.
- Cherry EM, Ehrlich JR, Nattel S, Fenton FH. Pulmonary vein reentry—Properties and size matter: Insights from a computational analysis. Heart Rhythm 2007; 4: 1553-1562. (cover)
Model parameterization
- Cairns DI, Fenton FH, Cherry EM. Efficient parameterization of cardiac action potential models using a genetic algorithm. Chaos 2017; 27: 093922.
Model analysis
- Elshrif MM, Cherry EM. A quantitative comparison of the behavior of human ventricular cardiac electrophysiology models in tissue. PLoS One 2014; 9: e84401.
- Cherry EM, Evans SJ. Properties of two human atrial cell models in tissue: Restitution, memory, propagation, and reentry. Journal of Theoretical Biology 2008; 254: 674-690.
- Bueno-Orovio A, Cherry EM, Fenton FH. Minimal model for human ventricular action potentials in tissue. Journal of Theoretical Biology 2008; 253: 544-560.
- Fenton FH, Cherry EM. Models of cardiac cell. Scholarpedia 2008; 3: 1868.
- Cherry EM, Hastings HM, Evans SJ. Dynamics of human atrial cell models: Restitution, memory, and intracellular calcium dynamics in single cells. Progress in Biophysics and Molecular Biology 2008; 98: 24-37.
- Cherry EM, Fenton FH. A tale of two dogs: Analyzing two models of canine ventricular electrophysiology. American Journal of Physiology Heart and Circulatory Physiology 2007; 292: H43-55.
Delay-differential equations modeling
- Bechara Rameh R, Cherry EM, Weber dos Santos R. Single-variable delay-differential equation approximations of the FitzHugh-Nagumo and Hodgkin-Huxley models. Communications in Nonlinear Science and Numerical Simulation 2020; 82: 105066.
- Gomes JM, Lobosco M, Weber dos Santos R, Cherry EM. Delay differential equation-based models of cardiac tissue: efficient implementation and effects on spiral-wave dynamics. Chaos 2019; 29: 123128.
- Gomes JM, Weber dos Santos R, Cherry EM. Alternans promotion in cardiac electrophysiology models by delay differential equations. Chaos 2017; 27: 093915.
- Eastman J, Sass J, Gomes JM, Weber dos Santos R, Cherry EM. Using delay differential equations to induce alternans in a model of cardiac electrophysiology. Journal of Theoretical Biology 2016; 404: 262-272.
Mechanisms for cardiac arrhythmias
In our group. we have used computational models together with experimental data to study multiple mechanisms that can give rise to cardiac arrhythmias. Some recent work in this area has focused on dynamical mechanisms that can give rise to alternans and has shown that cardiac tissue can experience multiple transitions as well as significant spatial heterogeneity and memory effects during the transition to fibrillation. We have also studied the effects of complex structures like the cardiac Purkinje system on arrhythmia development.
Arrhythmia mechanisms
- He J, Pertsov AM, Cherry EM, Fenton FH, Roney C, Niederer S, Zhang Z, Mangharam R. Fiber organization has little effect on electrical activation patterns during focal arrhythmias in the left atrium. IEEE Transactions on Biomedical Engineering 2023; 70: 1611-1621.
- Belletti R, Romero L, Martinez-Mateu L, Cherry EM, Fenton FH, Saiz J. Arrhythmogenic effects of genetic mutations affecting potassium channels in human atrial fibrillation: a simulation study. Frontiers in Physiology 2021; 12: 681943.
- Cherry EM. Distinguishing mechanisms for alternans in cardiac cells using constant-diastolic-interval pacing. Chaos 2017; 27: 093902.
- Bueno-Orovio A, Cherry EM, Evans SJ, Fenton FH. Basis for the induction of phase-2 reentry as a repolarization disorder in the Brugada syndrome. BioMed Research International 2015; 197586.
- Gizzi A, Cherry EM, Gilmour RF, Luther S, Filippi S, Fenton FH. Effects of pacing site and stimulation history on alternans dynamics and the development of complex spatiotemporal patterns in cardiac tissue. Frontiers in Cardiac Electrophysiology 2013; 4: 71-1 – 71-20.
- Cherry EM, Fenton FH, Gilmour RF, Jr. Mechanisms of ventricular arrhythmias: A dynamical systems-based perspective. American Journal of Physiology Heart and Circulatory Physiology 2012; 302: H2451-H2463.
- Fenton FH, Cherry EM, Glass L. Cardiac arrhythmia. Scholarpedia 2008; 3: 1665.
- Fenton FH, Cherry EM, Hastings HM, Evans SJ. Multiple mechanisms of spiral wave breakup in a model of cardiac electrical activity. Chaos 2002; 12: 852-892.
Purkinje modeling and role in arrhythmias
- Ulysses J, Berg L, Cherry EM, Liu BR, Weber dos Santos R, de Barros BG, Rocha BM, de Queiroz RAB. An optimization-based algorithm for the construction of cardiac Purkinje network models. IEEE Transactions on Biomedical Engineering 2018; 65: 2760-2768.
- Liu BR, Cherry EM. Image-based structural modeling of the cardiac Purkinje network. BioMed Research International 2015; 621034.
- Cherry EM, Fenton FH. Contribution of the Purkinje network to wave propagation in the canine ventricle: Insights from a combined electrophysiological-anatomical model. Nonlinear Dynamics 2012; 68: 365-379.
Termination of fibrillation
Our group has worked on multiple methods for terminating fibrillation experimentally and computationally. On the experimental side, we have applied low-energy techniques to terminate fibrillation effectively and efficiently. We have also developed a new method for guiding a catheter to locate atrial fibrillation sources iteratively. In addition, we have shown how an antiarrhythmic agent terminates fibrillation in equine atria and have quantified mechanisms for defibrillation in a computational model of the ventricles.
Low-energy defibrillation
- Ji YC, Uzelac I, Otani N, Luther S, Gilmour RF, Cherry EM, Fenton FH. Synchronization as a mechanism for low-energy anti-fibrillation pacing. Heart Rhythm 2017; 14: 1254-1262.
- Luther S, Fenton FH, Kornreich BG, Squires A, Bittihn P, Hornung D, Zabel M, Flanders J, Gladuli A, Campoy L, Cherry EM, Luther GE, Hasenfuss G, Krinsky VI, Pumir A, Gilmour RF Jr., Bodenschatz E. Low-energy control of electrical turbulence in the heart. Nature 2011; 475: 235-239.
- Fenton FH, Luther S, Cherry EM, Otani NF, Krinsky V, Pumir A, Bodenschatz E, Gilmour RF Jr. Termination of atrial fibrillation using pulsed low-energy far-field stimulation. Circulation 2009; 120: 467-476.
Catheter guidance algorithm
- Ganesan P, Cherry EM, Huang DT, Pertsov AM, Ghoraani B. Atrial fibrillation source area probability mapping using electrogram patterns of multipole catheters. BioMedical Engineering OnLine 2020; 19: 1-23.
- Ganesan P, Cherry EM, Huang DT, Pertsov AM, Ghoraani B. Locating atrial fibrillation rotor and focal sources using iterative navigation of multipole diagnostic catheters. Cardiovascular Engineering and Technology 2019; 10: 354-366.
- Ganesan P, Salmin A, Cherry EM, Huang DT, Pertsov AM, Ghoraani B. Iterative navigation of multipole diagnostic catheters to locate repeating-pattern atrial fibrillation drivers. Journal of Cardiovascular Electrophysiology 2019; 30: 758-768.
- Ganesan P, Zilouchian H, Cherry EM, Pertsov AM, Ghoraani B. Developing an iterative tracking algorithm to guide a catheter towards atrial fibrillation rotor sources in simulated fibrotic sources. Computing in Cardiology 2018; 45: 129.
- Ganesan P, Cherry EM, Pertsov AM, Ghoraani B. Characterization of electrograms from multi-polar diagnostic catheters during atrial fibrillation. BioMed Research International 2015; 272954.
Computational models of defibrillation
- Bragard J, Elorza J, Cherry EM, Fenton FH. Validation of a computational model of cardiac defibrillation. Computing in Cardiology 2013; 40: 851-854.
- Bragard J, Simic A, Elorza J, Grigoriev RO, Cherry EM, Gilmour RF, Otani NF, Fenton FH. Shock-induced termination of reentrant cardiac arrhythmias: Comparing monophasic and biphasic shock protocols. Chaos 2013; 23: 043119.
Defibrillation via anti-arrhythmic drugs
- Fenton FH, Cherry EM, Kornreich BG. Termination of equine atrial fibrillation by quinidine: an optical mapping study. Journal of Veterinary Cardiology 2008; 10: 87-102. (cover)