Evaluating computational efforts and physiological resolution of mathematical models of cardiac tissue

Research on noninvasive electrophysiologic imaging based on cardiac electrophysiology simulation and deep learning methods for the inverse problem

BACKGROUND

The risk stratification and prognosis of cardiac arrhythmia depend on the individual condition of patients, while invasive diagnostic methods may be risky to patient health, and current non-invasive diagnostic methods are applicable to few disease types without sensitivity and specificity. Cardiac electrophysiologic imaging (ECGI) technology reflects cardiac activities accurately and non-invasively, which is of great significance for the diagnosis and treatment of cardiac diseases. This paper aims to provide a new solution for the realization of ECGI by combining simulation model and deep learning methods.

METHODS

A complete three-dimensional bidomain cardiac electrophysiologic activity model was constructed, and simulated electrocardiogram data were obtained as training samples. Particle swarm optimization-back propagation neural network, convolutional neural network, and long short-term memory network were used respectively to reconstruct the cardiac surface potential.

RESULTS

The correlation coefficients between the simulation results and the clinical data range from 75.76 to 84.61%. The P waves, PR intervals, QRS complex, and T waves in the simulated waveforms were within the normal clinical range, and the distribution trend of the simulated body surface potential mapping was consistent with the clinical data. The coefficient of determination R2 between the reconstruction results of all the algorithms and the true value is above 0.80, and the mean absolute error is below 2.1 mV, among which the R2 of long short-term memory network is about 0.99 and the mean absolute error about 0.5 mV.

CONCLUSIONS

The electrophysiologic model constructed in this study can reflect cardiac electrical activity, and contains the mapping relationship between the cardiac potential and the body surface potential. In cardiac potential reconstruction, long short-term memory network has significant advantages over other algorithms.

CLINICAL TRIAL NUMBER

Not applicable.

A probabilistic modeling framework for the prediction of spontaneous premature beats and reentry initiation

BACKGROUND

Spontaneously occurring life-threatening reentrant arrhythmias result when a propagating premature beat encounters a region with significant dispersion of refractoriness. Although localized structural tissue heterogeneities and prescribed cell functional gradients have been incorporated into computational electrophysiologic models, a quantitative framework for the evolution from normal to abnormal behavior that occurs by disease is lacking.

OBJECTIVE

The purpose of this study was to develop a probabilistic modeling framework representing the complex interplay of cell function and tissue structure in health and disease that predicts the emergence of premature beats and the initiation of reentry.

METHODS

An action potential model of the rabbit was developed with data-driven uncertainty characterization as done previously. A novel tissue model using the discrete-cell monodomain equations was developed by implementing cellular uncertainty as a random spatial field.

RESULTS

Cellular action potentials exhibited a wide range of duration and even a variety of behaviors, with 67% exhibiting normal repolarization, 27% displaying early afterdepolarizations, and 6% showing repolarization failure. Nevertheless, simulations in tissue resulted in localized synchronized repolarization. Thus, cellular variability provided "tissue-level robustness," and premature beats and reentry induction were never observed even with abnormalities in cell function (IKr block) or tissue structure (increased tissue resistance). Alterations of both cell function and tissue structure were necessary for the generation of premature beats and arrhythmia initiation.

CONCLUSION

Once extended to whole hearts and validated for a specific context, this modeling framework provides a means to predict the probability of the initiation of life-threatening arrhythmias.

A possible path to persistent re-entry waves at the outlet of the left pulmonary vein

Atrial fibrillation (AF) is the most common form of cardiac arrhythmia, often evolving from paroxysmal episodes to persistent stages over an extended timeframe. While various factors contribute to this progression, the precise biophysical mechanisms driving it remain unclear. Here we explore how rapid firing of cardiomyocytes at the outlet of the pulmonary vein of the left atria can create a substrate for a persistent re-entry wave. This is grounded in a recently formulated mathematical model of the regulation of calcium ion channel density by intracellular calcium concentration. According to the model, the number of calcium channels is controlled by the intracellular calcium concentration. In particular, if the concentration increases above a certain target level, the calcium current is weakened to restore the target level of calcium. During rapid pacing, the intracellular calcium concentration of the cardiomyocytes increases leading to a substantial reduction of the calcium current across the membrane of the myocytes, which again reduces the action potential duration. In a spatially resolved cell-based model of the outlet of the pulmonary vein of the left atria, we show that the reduced action potential duration can lead to re-entry. Initiated by rapid pacing, often stemming from paroxysmal AF episodes lasting several days, the reduction in calcium current is a critical factor. Our findings illustrate how such episodes can foster a conducive environment for persistent AF through electrical remodeling, characterized by diminished calcium currents. This underscores the importance of promptly addressing early AF episodes to prevent their progression to chronic stages.