Parameter estimation for closed-loop lumped parameter models of the systemic circulation using synthetic data

Bjørdalsbakke, Nikolai L; Sturdy, Jacob; Hose, D.R.; Hellevik, Leif Rune

doi:10.1016/j.mbs.2021.108731

Cited by 16 publications

(28 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The synthetic data generated for case study 1, is for healthy heart valves using the nominal parameters listed in tables 1 and 2. To recreate clinical data, normally distributed noise [14] was added to the synthetically generated arterial pressure, chamber volumes and heart valve flow data which forms the set of measurements used to optimise the model parameters. The standard deviation used for noise generation was set to 3% of the mean value for the volume and flow rate measurements and 1% for the arterial pressure measurement.…”

Section: Case Studiesmentioning

confidence: 99%

“…In [13], errors between the predicted LPM outputs and the non-invasive measurements were optimised using the fmincon function in MATLAB. Bjørdalsbakke et al [14] developed a program capable of estimating systemic loop parameters such as systemic compliances, LV elastances (diastolic and systolic), systemic resistance and aorta blood inertia using the trust region reflective algorithm [15] from the free and opensource Python library SciPy. The developed LPM did not consider the pulmonary loop and approximated the systemic loop using a 3-element component.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Non-invasive estimation of left ventricle elastance using a multi-compartment lumped parameter model and gradient-based optimization with forward-mode automatic differentiation

Laubscher¹,

Merwe²,

Liebenberg³

et al. 2022

Preprint

View full text Add to dashboard Cite

Accurate estimates of left ventricle elastances based on non-invasive measurements are required for clinical decision-making during treatment of valvular diseases. The present study proposes a parameter discovery approach based on a lumped parameter model of the cardiovascular system in conjunction with optimization and non-invasive, clinical input measurements to approximate important cardiac parameters, including left ventricle elastances. A subset of parameters of a multi-compartment lumped parameter model was estimated using 1st order Adam gradient descent and hybrid Adam and 2nd order quasi-Newton limited-memory Broyden-Fletcher-Goldfarb-Shanno optimization routines. Forward-mode automatic differentiation was used to estimate the Jacobian matrices and compared to the common finite differences approach. Synthetic data of healthy and diseased hearts were generated as proxies for noninvasive clinical measurements and used to evaluate the algorithm. Twelve parameters including left ventricle elastances were selected for optimization based on 99% explained variation in mean left ventricle pressure and volume. The hybrid optimization strategy yielded the best overall results compared to 1st order optimization with automatic differentiation and finite difference approaches, with mean absolute percentage errors ranging from 6.67% to 14,14%. Errors in left ventricle elastance estimates for simulated aortic stenosis and mitral regurgitation were smallest when including synthetic measurements for arterial pressure and valvular flow rate at approximately 2% and degraded to roughly 5% when including volume trends as well. However, the latter resulted in better tracking of the left ventricle pressure waveforms and may be considered when the necessary equipment is available.

show abstract

Section: Case Studiesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Non-invasive estimation of left ventricle elastance using a multi-compartment lumped parameter model and gradient-based optimization with forward-mode automatic differentiation

Laubscher¹,

Merwe²,

Liebenberg³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In the previous equation, the pressure gradient across the valve Δ ( ) is calculated using Equation (8), where ( ) is the valve upstream static pressure and ( ) is the valve downstream pressure. For example, the aortic valve inlet pressure would be the LV pressure ( ) and the exit pressure the aortic sinus pressure ( ) as shown in Figure 2.…”

Section: Parameters Left Heart Right Heart Atriumsmentioning

confidence: 99%

“…The benefit of this approach is that the true underlying parameters being optimized is known and the obvious disadvantage is that one assumes the model is capable of capturing the dynamics of an actual cardiovascular system. Nonetheless, other published authors have also followed this approach [8].…”

Section: Data and Measurementsmentioning

confidence: 99%

“…Several researchers have recently investigated the efficacy of computational parameter estimation strategies to find unknown physiological parameters of a human cardiovascular system by using clinical measurements, 0-D cardiovascular dynamic models and optimization routines. Bjordalsbakke et al [8] developed a 0-D computer model of a human systemic loop and used non-invasive measurements and the trust region reflective algorithm to estimate various parameters such as systemic compliances and left ventricle elastance. Synthetic data was generated using the 0-D cardiovascular model with known parameters to gauge the accuracy of the parameter estimation workflow.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Inference of Pulmonary Arterial Pressure using Non-invasive Measurements and Scientific Machine Learning Techniques

Laubscher¹,

Merwe²,

Herbst³

et al. 2022

Preprint

View full text Add to dashboard Cite

Reliable quantification of pulmonary arterial pressure is essential in the diagnostic and prognostic assessment of a range of cardiovascular pathologies including rheumatic heart disease, yet an accurate and routinely available method for its quantification remains elusive. This work proposes an approach to infer pulmonary arterial pressure based on scientific machine learning techniques and non-invasive, clinically available measurements. A 0-D multicompartment model of the cardiovascular system was optimized using several optimization algorithms, subject to forward-mode automatic differentiation. Measurement data were synthesized from known parameters to represent the healthy, mitral regurgitant, aortic stenosed and combined valvular disease situations with and without pulmonary hypertension. Eleven model parameters were selected for optimization based on 95 % explained variation in mean pulmonary arterial pressure. A hybrid Adam and limited-memory Broyden-Fletcher-Goldfarb-Shanno optimizer yielded the best results with input data including valvular flow rates, heart chamber volume changes and systematic arterial pressure. Mean absolute percentage errors ranged from 1.8 % to 3.78 % over the simulated test cases. The model was able to capture pressure dynamics under hypertensive conditions with pulmonary arterial systole, diastole, and mean pressure average percentage errors of 1.12 %, 2.49 % and 2.14 %, respectively. The relatively low errors highlight the potential of the proposed model to recover pulmonary pressures for diseased heart valve and pulmonary hypertensive conditions.

show abstract

Local Sensitivity Analysis of a Closed-Loop in Silico Model of the Human Baroregulation

Tlałka,

Saxton,

Halliday

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Parameter estimation for closed-loop lumped parameter models of the systemic circulation using synthetic data

Cited by 16 publications

References 37 publications

Non-invasive estimation of left ventricle elastance using a multi-compartment lumped parameter model and gradient-based optimization with forward-mode automatic differentiation

Non-invasive estimation of left ventricle elastance using a multi-compartment lumped parameter model and gradient-based optimization with forward-mode automatic differentiation

Inference of Pulmonary Arterial Pressure using Non-invasive Measurements and Scientific Machine Learning Techniques

Local Sensitivity Analysis of a Closed-Loop in Silico Model of the Human Baroregulation

Contact Info

Product

Resources

About