Modelling the Heart's Hidden Hero: The Right Ventricle
Continuing the quest to unlock the mysteries of right ventricular function through machine learning and computational modeling
Our understanding of heart mechanics is constantly evolving, from the times of Leonardo da Vinci, who first illustrated the heart's anatomy in detail, to the times of Inge Edler, who in the 1950s pioneered the use of echocardiography to visualize the heart's movements in real time. After half a millennia, we are still improving our understanding of heart mechanics, albeit by means not available to da Vinci and Edler. While the left ventricle (LV) has been the focus of extensive research, the right ventricle (RV) remains significantly understudied. RV dysfunction is strongly associated with poor outcomes in diseases such as pulmonary hypertension and right heart failure, highlighting the urgent need for better insight into its function. This proposal aims to use finite element modeling (FEM) and machine learning (ML) for a better understanding of RV dysfunction.
Goal
The main goal of the project is to model the RV and determine whether current biomarkers, like strain and myocardial work, can reliably assess RV performance. This can be achieved by a combination of ML and FEM. The model paves the way for improved diagnosis and treatment of RV-related conditions and development of RV-specific biomarkers.
Learning outcome
- Ability to break down complex systems into simplified, manageable models and apply mathematical and computational techniques to solve important, real-life problems.
- Hands-on experience with the analysis and practical application of the finite element method (FEM), particularly the FEniCSx platform, and machine learning (ML).
- Acquire knowledge of advanced topics related to numerical methods and their implementation in real-world scenarios.
Qualifications
- The student should have a background in applied mathematics, mechanics, physics and/or computer science.
- In particular, knowledge of partial differential equations, numerical methods such as finite element methods, and/or high-level scripting is a must.
- A curious mind and goal-oriented attitude is highly valuable.
Supervisors
- Mohammad Javad Sadeghinia
- Henrik Nicolay Finsberg
- Samuel Wall
