ESBiomech24 Congress in Edinburgh

PhD Position Scientific Machine Learning and Surrogate Modeling for Cardiovascular Digital Twins @TU Delft

We are looking for a motivated and independent PhD candidate to develop highly efficient and robust surrogate models of a multi-scale cardiovascular ‘digital twin’ modelling platform.

A cardiovascular digital twin is a physics-based computer simulation that models an individual’s health and disease states to aid decision-making. These high-fidelity models are often computationally expensive, limiting their personalization and real-time clinical use. In this project, we aim to develop highly efficient data-driven surrogate models for parametrized partial differential equations, with application to computational cardiology.

In this project, you will combine advanced physics-based models of the human heart and vasculature with the latest breakthroughs in machine learning to develop scalable and robust surrogate models of cardiovascular digital twins. These surrogate models will be used to enhance personalized treatment planning and post-treatment monitoring for patients suffering from circulation overload disorders, specifically systemic hypertension, heart failure (with/without preserved ejection fraction), and hemodynamically complicated atrial septal defects.

The research will be conducted in the Department of BioMechanical Engineering at Delft University of Technology (TU Delft) under the supervision of dr. ir. Mathias Peirlinck. The Peirlinck Lab integrates multimodal experimental data, physics-based modeling, and machine learning techniques to understand, explore, and predict the multiscale behavior of the human heart and cardiovascular system. More information on the research and team can be found on This research is part of the VITAL project (, a large international collaboration developing a comprehensive, clinically validated, multi-scale, multi-organ ‘digital twin’ modelling platform that is driven by and can represent individual patient data acquired both in the clinic and from wearable technology.

Prior experience in both scientific machine learning and numerical analysis of PDEs and ODEs is required. In addition, experience in the field of cardiac modeling, arterial modeling, (soft tissue) biomechanics, and/or electrophysiology will be strongly appreciated. As the successful candidate for this position, you will develop scientific machine learning algorithms, develop and run high-performance computer simulations, construct pipelines for model personalization to structural and functional data, and develop APIs between various software codes. You will actively participate in (bi)weekly lab meetings, write scientific articles and reports, and give presentations and workshops at national and international conferences. Besides your research activities, you will also take part in teaching and supervision activities within the Faculty of Mechanical Engineering of Delft University of Technology and beyond.

More information:

Corporate members of the ESB:

AMTI force and motion logo
Beta CAE logo
BoB Biomechanics logo
Materialise logo
Nobel Biocare logo