Key result
The data-driven reduced order method (POD-NN) achieved a computational speed-up of about 4 orders of magnitude compared to the full order model while maintaining comparable accuracy.
Why the study?
The study aimed to solve an optimal blood flow control problem to match blood flow velocity with given measurements across physiological Reynolds numbers in a coronary artery bypass graft.
A data-driven reduced order method using neural networks significantly accelerates patient-specific coronary bypass blood flow simulations while maintaining high accuracy compared to traditional full order models.
Answers are grounded in this paper and cite their sources.
May accelerate preclinical bypass flow modeling; leaves open human validation before clinical use.
We consider an optimal flow control problem in a patient-specific coronary artery bypass graft with the aim of matching the blood flow velocity with given measurements as the Reynolds number varies in a physiological range. Blood flow is modelled with the steady incompressible Navier-Stokes equations. The geometry consists in a stenosed left anterior descending artery where a single bypass is performed with the right internal thoracic artery. The control variable is the unknown value of the normal stress at the outlet boundary, which is need for a correct set-up of the outlet boundary condition. For the numerical solution of the parametric optimal flow control problem, we develop a data-driven reduced order method that combines proper orthogonal decomposition (POD) with neural networks. We present numerical results showing that our data-driven approach leads to a substantial speed-up with respect to a more classical POD-Galerkin strategy proposed in [59], while having comparable accuracy.
No takes yet. Share an insight, caveat, or question.
Balzotti et al. (2022) studied Coronary artery disease (Coronary artery bypass graft) (n=1). Data-driven reduced order method (POD-NN) vs. Full order model (Finite Element Method) and POD-Galerkin strategy was evaluated on Computational speed-up and relative L2 error (accuracy). The data-driven reduced order method (POD-NN) achieved a computational speed-up of about 4 orders of magnitude compared to the full order model while maintaining comparable accuracy.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: