Key result
A hybrid optimization strategy using forward-mode automatic differentiation estimated simulated left ventricle elastances with mean absolute percentage errors ranging from 6.67% to 14.14%.
Why the study?
The study evaluated a parameter discovery approach using a lumped parameter cardiovascular model and optimization to approximate cardiac parameters, including simulated left ventricle elastances.
Does a hybrid optimization strategy with forward-mode automatic differentiation improve the estimation of simulated left ventricle elastance compared to finite difference approaches using synthetic noninvasive data?
Does a hybrid optimization strategy with forward-mode automatic differentiation improve the estimation of simulated left ventricle elastance compared to finite difference approaches using synthetic noninvasive data?
A hybrid optimization strategy using forward-mode automatic differentiation accurately estimates simulated left ventricle elastance from synthetic noninvasive data, potentially offering a novel computational approach for noninvasive cardiac parameter assessment.
No takes yet. Share an insight, caveat, or question.
Hypothesis-generating for noninvasive LV elastance estimation in models; leaves open clinical validation in patient data.
Laubscher et al. (2022) studied Simulated aortic stenosis and mitral regurgitation. Hybrid optimization strategy with forward-mode automatic differentiation vs. 1st order optimization with automatic differentiation and finite difference approaches was evaluated on Mean absolute percentage errors in parameter estimation. A hybrid optimization strategy using forward-mode automatic differentiation estimated simulated left ventricle elastances with mean absolute percentage errors ranging from 6.67% to 14.14%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: