No abstract

The electrical signals triggering the heart's contraction are governed by non-linear processes that can produce complex irregular activity, especially during or preceding the onset of cardiac arrhythmias. Forecasts of cardiac voltage time series in such conditions could allow new opportunities for intervention and control but would require efficient computation of highly accurate predictions. Although machine-learning (ML) approaches hold promise for delivering such results, non-linear time-series forecasting poses significant challenges. In this manuscript, we study the performance of two recurrent neural network (RNN) approaches along with echo state networks (ESNs) from the reservoir computing (RC) paradigm in predicting cardiac voltage data in terms of accuracy, efficiency, and robustness. We show that these ML time-series prediction methods can forecast synthetic and experimental cardiac action potentials for at least 15–20 beats with a high degree of accuracy, with ESNs typically two orders of magnitude faster than RNN approaches for the same network size.

Computational modeling and experimental/clinical prediction of the complex signals during cardiac arrhythmias have the potential to lead to new approaches for prevention and treatment. Machine-learning (ML) and deep-learning approaches can be used for time-series forecasting and have recently been applied to cardiac electrophysiology. While the high spatiotemporal nonlinearity of cardiac electrical dynamics has hindered application of these approaches, the fact that cardiac voltage time series are not random suggests that reliable and efficient ML methods have the potential to predict future action potentials. This work introduces and evaluates an integrated architecture in which a long short-term memory autoencoder (AE) is integrated into the echo state network (ESN) framework. In this approach, the AE learns a compressed representation of the input nonlinear time series. Then, the trained encoder serves as a feature-extraction component, feeding the learned features into the recurrent ESN reservoir. The proposed AE-ESN approach is evaluated using synthetic and experimental voltage time series from cardiac cells, which exhibit nonlinear and chaotic behavior. Compared to the baseline and physics-informed ESN approaches, the AE-ESN yields mean absolute errors in predicted voltage 6–14 times smaller when forecasting approximately 20 future action potentials for the datasets considered. The AE-ESN also demonstrates less sensitivity to algorithmic parameter settings. Furthermore, the representation provided by the feature-extraction component removes the requirement in previous work for explicitly introducing external stimulus currents, which may not be easily extracted from real-world datasets, as additional time series, thereby making the AE-ESN easier to apply to clinical data.

Some of the heart valve diseases can be treated by surgical replacement with either a mechanical or bioprosthetic heart valve (BHV). Recently, tissue-engineered heart valves (TEHVs) have been proposed to be the ultimate solution for treating valvular heart disease. In order to improve the durability and design of artificial heart valves, recent studies have focused on quantifying the biomechanical interaction between the organ, tissue, and cellular –level components in native heart valves. Such data is considered fundamental to designing improved BHVs. Mechanical communication from the larger scales affects active biomechanical processes. For instance any organ-scale motion deforms the tissue, which in turn deforms the interstitial cells (ICs). Therefore, a multiscale solution is required to study the behavior of human aortic valve and to predict local cell deformations. The proposed multiscale finite element approach takes into account large deformations and nonlinear anisotropic hyperelastic material models. In this simulation, the organ scale motion is computed, from which the tissue scale deformation will be extracted. Similarly, the tissue deformation will be transformed into the cell scale. Finally, each simulation is verified against a number of experimental measures.

No abstract