Rapid prediction of prosthetic heart valve haemodynamic performance using physics-informed machine learning

The project aims to create rapid and scalable deep learning-based simulation techniques for predicting the haemodynamic performance of transcatheter aortic valve (TAV) implants. TAVs are the de facto treatment for severe aortic valve stenosis in patients with med-/high-surgical risk. Yet, various clinical and technological challenges prevent uptake of the procedure in a wider spectrum of patients. Computational modelling tools can allow performance of TAVs in so-far untested scenarios (low-risk groups, bicuspid anatomy, etc.) to be assessed non-invasively and safely. Such capabilities underpin the emerging concept of in-silico trials (ISTs).
Complex interactions of blood flow and valves necessitate use of fluid-structure interaction models for haemodynamic assessment. FSI models are expensive, and, like all computational techniques, can encounter convergence problems especially in complex scenarios. This is problematic for ISTs, where large simulation cohorts are required to run quickly and automatically. Recent research demonstrates the feasibility of accelerating computational multiphysics via learning-based approaches. So-called physics-informed neural networks (PINNs) are particularly attractive as they guarantee predictions conform to physical laws, rather than proceeding from data observations only. They may also alleviate training data requirements by imposing strong regularisation. The project will build on our existing efforts to develop distinct structural- and flow-based PINN models.
The aim is to produce efficient and automated FSI simulation tools that will enable TAV haemodynamic performance to be predicted in simulation studies involving potentially thousands of virtual patients.

The CDT will address the continued need of the UK for highly trained graduates in Fluid Dynamics and deliver impact through the novel research conducted by CDT students. The impact and benefits will reach multiple stakeholders.

Impacts on Skills and People:

Key beneficiaries of the CDT will be the alumni of our current and future programme and the organisations who employ them. Through the technical and professional development training, and the CDT environment, our graduates will have expertise in fundamental theory, analytical and numerical approaches, experimental techniques and application, and in-depth technical knowledge in their PhD area. Moreover they will have leadership, communication, responsible innovation and team working skills, combined with experience of working with academic and industry partners in a diverse and cross-disciplinary environment. This breadth and depth sets our CDT graduates apart from their peers, and positions them to become future leaders in industry, society and academia across a range of sectors. They will obtain the underpinning skills, and long term support through our Alumni Association, to drive future innovation across multiple sectors and act as life-long ambassadors for Fluid Dynamics.

The impact on people and skills will also include staff in our partner organisations in industry and non-profit sectors. Through participation in CDT activities, benefits will include new professional contacts and collaborations and knowledge of cutting edge methods and techniques. Through the CDT and the wider activities of Leeds Institute for Fluid Dynamics (LIFD) we will enhance the skills base in Fluid Dynamics and be the "go to" place to support high level training in end-user organisations.

Impact on Industry and the Economy:

In addition to the availability of trained graduates with excellent technical, professional and personal skills, impacts will arise from the direct innovation in research projects within the CDT. Research outcomes will influence processes, technologies, tools, guidelines and methodologies for our industry partners and other related organisations, leading to economic benefits such as new products, services and spin out companies. For example our current CDT has already led to 2 new patents (BAE Systems), student delivery of consultancy (Akzo Nobel), a flood demonstrator unit (JBA Trust) and a new method for hydraulic analysis (Hydrotec). Partners will also gain an enhanced reputation through being involved in successful and novel project outcomes. Skilled graduates and technology enhancement are key to economic growth, and our CDT will contribute to challenge areas such as energy, transport, the environment, the health sector, as well as those with chronic skills shortage such as the nuclear industry. Many of our partners are non-profit organisations, particularly in the environment and health sectors (e.g. NHS, PHE, Met Office). Impacts here derive through skilled graduates with the training and awareness to apply their expertise in organisations that deal with complex problems of societal importance, and novel research at the interface of disciplines. The cross-disciplinary nature of the CDT particularly supports this.

Impact on Society:

Beyond those who partner directly, many of the research projects have potential to lead to innovations with direct societal benefits (e.g. new techniques for detecting or controlling disease, new innovations in controlling flood risk or pollution, new insights into forecasting extreme weather). Beneficiaries here include professional bodies and government agencies who set policy, define guidance or influence the direction of innovation and research in the UK. The benefits to society will also stem from enhanced public awareness of Fluid Dynamics, both benefiting general public knowledge of science and inspiring the next generation (from all sectors of society) to undertake STEM careers.