Data-Driven Reduction of a Cardiac Myofilament Model

This manuscript presents a novel, data-driven approach to reduce a detailed cellular model of cardiac myofilament (MF) for efficient and accurate cellular simulations towards cell-to-organ computation. Based on 700 different sarcomere dynamics calculated using Rice model, we show through manifold learning that sarcomere force (SF) dynamics lays surprisingly in a linear manifold despite the non-linear equations of the MF model. Then, we learn a multivariate adaptive regression spline (MARS) model to predict SF from the Rice model parameters and sarcomere length dynamics. Evaluation on 300 testing data showed a prediction error of less than 0.4 nN/mm2 in terms of maximum force amplitude and 0.87 ms in terms of time to force peak, which is comparable to the differences observed with experimental data. Moreover, MARS provided insights on the driving parameters of the model, mainly MF geometry and cell mechanical passive properties. Thus, our approach may not only constitute a fast and accurate alternative to the original Rice model but also provide insights on parameter sensitivity.

[1]  Ulf G. Indahl,et al.  Hierarchical multivariate regression-based sensitivity analysis reveals complex parameter interaction patterns in dynamic models , 2013 .

[2]  Andrew D McCulloch,et al.  Multi-scale computational models of familial hypertrophic cardiomyopathy: genotype to phenotype , 2011, Journal of The Royal Society Interface.

[3]  Donald M Bers,et al.  A mathematical treatment of integrated Ca dynamics within the ventricular myocyte. , 2004, Biophysical journal.

[4]  N P Smith,et al.  Interpreting genetic effects through models of cardiac electromechanics. , 2012, American journal of physiology. Heart and circulatory physiology.

[5]  Steven Niederer,et al.  Efficient Computational Methods for Strongly Coupled Cardiac Electromechanics , 2012, IEEE Transactions on Biomedical Engineering.

[6]  Peter J. Hunter,et al.  Hierarchical Cluster-based Partial Least Squares Regression (HC-PLSR) is an efficient tool for metamodelling of nonlinear dynamic models , 2011, BMC Systems Biology.

[7]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[8]  J. Rice,et al.  Approximate model of cooperative activation and crossbridge cycling in cardiac muscle using ordinary differential equations. , 2008, Biophysical journal.

[9]  Eric A Sobie,et al.  Models of cardiac excitation-contraction coupling in ventricular myocytes. , 2010, Mathematical biosciences.

[10]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[11]  Harald Martens,et al.  Fast and comprehensive fitting of complex mathematical models to massive amounts of empirical data , 2012 .