MS2-06 - Uncertainty Quantification and Machine Learning for Fluid-Structure Interaction in Cardiovascular Problems

A. Harish (Department of Mechanica, University of Manchester (UK)) *, E. Manchester (Department of Mechanica, University of Manchester (UK)) , A. Revell (Department of Mechanica, University of Manchester (UK)) , S. Rogers ( Division of Cardiovascular Sciences, University of Manchester (UK))

Cardiovascular diseases (CVD) screening has improved significantly over the last decade and evidence shows that this also reduces the probability of cardiovascular events (CVE). CT/MRI are expensive, involve radiation or nephrotoxic contrast and are not suitable for mass screening. Ultrasound is cheaper but not cost-effective as it requires skilled operators, of which there is a shortage. For successful ultrasound-based screening, there must be technological developments that improve value and suitability. The improvements in Computational Fluid Dynamic (CFD) modelling have rendered it as a potential capable tool that could eventually help personalize development of markers and predictors of CVE risk. CFD itself is computationally slow, resource-intensive and cannot be directly deployed for usage by clinicians. Additionally, there are several uncertain quantities in the biological system that present a significant challenge towards high-fidelity modelling efforts. Thus, coupling CFD with uncertainty quantification (UQ) and machine learning (ML) could enable the introduction of personalized screening that is good value-for-money. This mini symposium focuses on bringing together the latest developments in the areas of application of ML and UQ for flow and fluid-structure interaction related problems related to cardiovascular engineering. The topics of interest include, but not limited to the development of novel and application of existing techniques in ML and UQ towards improving the understanding of CVE prediction, coupling of existing tools with data-driven techniques, novel imaging and post-processing techniques towards determining flow.