Predicting left ventricular contractile function via Gaussian process emulation in aortic-banded rats

被引:34
作者
Longobardi, S. [1 ]
Lewalle, A. [1 ]
Coveney, S. [2 ,3 ]
Sjaastad, I [4 ,5 ]
Espe, E. K. S. [4 ,5 ]
Louch, W. E. [4 ,5 ]
Musante, C. J. [6 ]
Sher, A. [6 ]
Niederer, S. A. [1 ]
机构
[1] Kings Coll London, Sch Biomed Engn & Imaging Sci, London, England
[2] Univ Sheffield, Insigneo Inst In Silico Med, Sheffield, S Yorkshire, England
[3] Univ Sheffield, Dept Comp Sci, Sheffield, S Yorkshire, England
[4] Univ Oslo, Inst Expt Med Res, Oslo, Norway
[5] Univ Oslo, KG Jebsen Ctr Cardiac Res, Oslo, Norway
[6] Pfizer Worldwide Res Dev & Med, Cambridge, MA USA
来源
PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES | 2020年 / 378卷 / 2173期
基金
英国工程与自然科学研究理事会;
关键词
Gaussian process; history matching; global sensitivity analysis; three-dimensional bi-ventricular model; aortic-banded rat; SENSITIVITY-ANALYSIS; ANIMAL-MODELS; UNCERTAINTY; MYOCARDIUM;
D O I
10.1098/rsta.2019.0334
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Cardiac contraction is the result of integrated cellular, tissue and organ function. Biophysical in silico cardiac models offer a systematic approach for studying these multi-scale interactions. The computational cost of such models is high, due to their multi-parametric and nonlinear nature. This has so far made it difficult to perform model fitting and prevented global sensitivity analysis (GSA) studies. We propose a machine learning approach based on Gaussian process emulation of model simulations using probabilistic surrogate models, which enables model parameter inference via a Bayesian history matching (HM) technique and GSA on whole-organ mechanics. This framework is applied to model healthy and aortic-banded hypertensive rats, a commonly used animal model of heart failure disease. The obtained probabilistic surrogate models accurately predicted the left ventricular pump function (R-2 = 0.92 for ejection fraction). The HM technique allowed us to fit both the control and diseased virtual bi-ventricular rat heart models to magnetic resonance imaging and literature data, with model outputs from the constrained parameter space falling within 2 SD of the respective experimental values. The GSA identified Troponin C and cross-bridge kinetics as key parameters in determining both systolic and diastolic ventricular function. This article is part of the theme issue 'Uncertainty quantification in cardiac and cardiovascular modelling and simulation'.
引用
收藏
页数:14
相关论文
共 32 条
[1]   Bayesian History Matching of Complex Infectious Disease Models Using Emulation: A Tutorial and a Case Study on HIV in Uganda [J].
Andrianakis, Ioannis ;
Vernon, Ian R. ;
McCreesh, Nicky ;
McKinley, Trevelyan J. ;
Oakley, Jeremy E. ;
Nsubuga, Rebecca N. ;
Goldstein, Michael ;
White, Richard G. .
PLOS COMPUTATIONAL BIOLOGY, 2015, 11 (01)
[2]  
Camacho P, 2016, AM J CARDIOVASC DIS, V6, P70
[3]   Gaussian process emulation of dynamic computer codes [J].
Conti, S. ;
Gosling, J. P. ;
Oakley, J. E. ;
O'Hagan, A. .
BIOMETRIKA, 2009, 96 (03) :663-676
[4]   Fitting two human atrial cell models to experimental data using Bayesian history matching [J].
Coveney, Sam ;
Clayton, Richard H. .
PROGRESS IN BIOPHYSICS & MOLECULAR BIOLOGY, 2018, 139 :43-58
[5]   Parameter estimation in cardiac ionic models [J].
Dokos, S ;
Lovell, NH .
PROGRESS IN BIOPHYSICS & MOLECULAR BIOLOGY, 2004, 85 (2-3) :407-431
[6]   Compensatory and decompensatory alterations in cardiomyocyte Ca2+ dynamics in hearts with diastolic dysfunction following aortic banding [J].
Gattoni, Sara ;
Roe, Asmund Treu ;
Aronsen, Jan Magnus ;
Sjaastad, Ivar ;
Louch, William E. ;
Smith, Nicolas P. ;
Niederer, Steven A. .
JOURNAL OF PHYSIOLOGY-LONDON, 2017, 595 (12) :3867-3889
[7]   Cell-Specific Cardiac Electrophysiology Models [J].
Groenendaal, Willemijn ;
Ortega, Francis A. ;
Kherlopian, Armen R. ;
Zygmunt, Andrew C. ;
Krogh-Madsen, Trine ;
Christini, David J. .
PLOS COMPUTATIONAL BIOLOGY, 2015, 11 (04)
[8]   PASSIVE MATERIAL PROPERTIES OF INTACT VENTRICULAR MYOCARDIUM DETERMINED FROM A CYLINDRICAL MODEL [J].
GUCCIONE, JM ;
MCCULLOCH, AD ;
WALDMAN, LK .
JOURNAL OF BIOMECHANICAL ENGINEERING-TRANSACTIONS OF THE ASME, 1991, 113 (01) :42-55
[9]  
Herman J., 2017, J Open Source Software, V2, DOI [DOI 10.21105/JOSS.00097, 10.21105/joss.00097]
[10]   Constitutive modelling of passive myocardium: a structurally based framework for material characterization [J].
Holzapfel, Gerhard A. ;
Ogden, Ray W. .
PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES, 2009, 367 (1902) :3445-3475