About this role
Key Information
Lead supervisor: Dr Giorgia Bosi
Application deadline: 29 June 2026
Project start date: 01 October 2026
Project duration: 4 years (full-time)
Studentship funding:
Full Home/UK tuition fees (currently £6,400/year) and maintenance stipend (currently £23,805/year) for 3.5 years PhD Project Description
Atrial fibrillation (AF) significantly increases the risk of stroke, yet current risk scores such as CHA₂DS₂ VASc rely solely on comorbidities and demographics, and ignore patient specific LAA anatomy and haemodynamics. However, growing evidence shows that LAA morphology (length, eccentricity, bending, lobes, trabeculae) and the resulting local flow stasis play a central role in thrombus formation. High fidelity fluid–structure interaction (FSI) models are capable of capturing these effects but remain too computationally demanding for clinical use.
This PhD proposes to transform FSI based thrombosis assessment by developing machine learning surrogate models trained on simulations generated from a uniquely rich parametric LAA model, enabling fast and generalisable prediction of haemodynamics across the full spectrum of anatomical variability. This work directly supports more accurate AF stroke risk stratification by incorporating personalised morphological features that CHA₂DS₂ VASc does not capture.
Aims
To build a machine learning–accelerated modelling framework that predicts thrombosis related LAA haemodynamics in seconds, enabling anatomy aware risk assessment for AF patients.
Objectives
Create a parametric FSI dataset spanning full anatomical variability Develop machine learning surrogate models for rapid haemodynamic prediction Quantify how anatomy shapes thrombosis risk
Impact
Beyond the duration of the PhD, this work will form the foundation for the development of a clinically deployable tool capable of integrating patient specific LAA geometry with rapid, ML predicted haemodynamic metrics. Such a framework would enable real time estimation of thrombosis risk and support next generation AF risk stratification, augmenting existing scores such as CHA₂DS₂ VASc with mechanistic, personalised anatomical features.
In the longer term, this approach could be validated on clinical imaging datasets and extended to support decision making in patient selection for anticoagulation or left atrial appendage occlusion. More broadly, the methodology will contribute to scalable cardiovascular digital twin technologies, enabling population level studies and ultimately improving precision medicine approaches in AF.
Person Specification
We are seeking a highly motivated and interdisciplinary candidate with a strong interest in computational modelling, machine learning, and cardiovascular biomechanics. The successful applicant will work at the interface of fluid–structure interaction (FSI), parametric modelling, and artificial intelligence, contributing to the development of next generation tools for personalised stroke risk assessment in atrial fibrillation.
Essential Requirements
Applicants are preferred to have, or be about to receive, a first-class undergraduate and master’s degree (or equivalent) in Mechanical Engineering, Biomedical Engineering, Mathematics, Physics, Computer Science, or a closely related discipline. Strong background in numerical methods and computational modelling (e.g. CFD, FEM, or FSI) Experience with programming (Python, MATLAB, or similar) Experience with machine learning / deep learning (e.g., PyTorch, TensorFlow) Good understanding of mathematics relevant to engineering or machine learning (e.g., linear algebra, differential equations) Excellent analytical, problem solving, and communication skills Ability to work both independently and collaboratively in an interdisciplinary environment
Eligibility & How to Apply
Please visit the UCL website for further details.