About the Project
Despite major advances in cardiovascular prevention, many patients who experience serious cardiovascular events would not be identified as high risk by current clinical prediction tools. Traditional risk scores primarily rely on factors such as age, blood pressure, cholesterol, smoking status, and diabetes, yet these measures often fail to capture the underlying biological processes that drive disease over time. This challenge is particularly evident in patients with non-traditional…
presentations of cardiovascular disease, including spontaneous coronary artery dissection (SCAD), where conventional risk factors provide limited insight into future risk.
Recent advances in medical imaging, computational modelling, and artificial intelligence have created new opportunities to move beyond population-based risk prediction towards truly personalised cardiovascular assessment. In particular, blood flow patterns within the coronary arteries may provide important information about disease development that traditional clinical measures alone cannot detect.
This PhD project will develop next-generation approaches for personalised cardiovascular risk prediction by combining coronary CT imaging, rapid blood flow modelling, machine learning, and clinical outcome data. The successful candidate will investigate how patient-specific biomechanical markers can improve identification of individuals at risk of cardiovascular events, particularly those that existing risk assessment tools may overlook.
A major objective of the project is to improve equity in cardiovascular care by exploring how advanced risk prediction technologies perform across diverse patient populations, including women and patients presenting with conditions such as SCAD.
The project will build on internationally recognised research programs in cardiovascular imaging, computational haemodynamics, digital twins, and precision cardiovascular medicine, providing access to large clinical datasets and extensive international collaborations.
The Candidate Will
- Develop automated methods for coronary artery reconstruction from CT imaging
- Create fast computational models of coronary blood flow
- Apply machine learning to predict cardiovascular outcomes
- Investigate novel haemodynamic markers of cardiovascular risk
- Study cardiovascular disease mechanisms in patients without traditional risk factors
- Contribute to research in SCAD and women's cardiovascular health
Candidate Requirements
Applicants should have a background in:
- Biomedical engineering
- Data science
- Computer science
- Mathematics or statistics
- Or a related discipline
We are seeking outstanding domestic and international applicants with a strong academic record and demonstrated research potential.
Domestic applicants (Australia and New Zealand) should have:
A Bachelor's degree with First Class Honours (H1) or equivalent, or a Master's degree containing a substantial research thesis/project.
- A minimum WAM of 75% (or equivalent).
- Evidence of research capability through an honours thesis, research project, publication, conference presentation, industry R&D experience, or related research activities.
International applicants should typically have:
- A Bachelor's degree with Honours (or equivalent research-intensive qualification) from a university ranked within the Top 200 globally (QS, Times Higher Education, or Shanghai/ARWU rankings), or the nationally leading research-intensive university in their country.
- Academic performance equivalent to UNSW First Class Honours (H1e).
- Ideally have one or two first-author publications (published, accepted) in high-quality international journals, preferably Q1 journals
- Preferably demonstrated research excellence through publications, conference presentations, awards, or research experience.
Preference may be given to applicants who are already based in Australia or able to commence their studies onshore.
We are committed to building a diverse and inclusive research environment. We particularly encourage applications from women and candidates from Southeast Asia.
University of New South Wales (UNSW) and the Sydney Vascular Modelling Group (SVMG)
The successful candidate will join the University of New South Wales (UNSW Sydney) and the Sydney Vascular Modelling Group (SVMG), an internationally recognised research group at the forefront of cardiovascular engineering, artificial intelligence, computational modelling, digital health, medical devices, and precision cardiovascular medicine.
SVMG brings together engineers, clinicians, data scientists, and industry partners to develop technologies that improve the prediction, diagnosis, and treatment of cardiovascular disease. Our research spans fundamental biomechanics through to clinical translation, commercialisation, and implementation in healthcare.
The successful candidate will be embedded within a highly collaborative, multidisciplinary environment and will have opportunities to work with leading academic, clinical, and industry partners across Australia, Europe, North America, and Asia.
Learn more about our work at:
We are a supportive and ambitious team that values scientific excellence, collaboration, innovation, mentorship, and inclusivity. Our goal is to train not only outstanding researchers but also future leaders in academia, healthcare, and industry.
Application Process
Applicants should send the following to s.beier@unsw.edu.au
- A cover letter outlining their motivation and suitability.
- A CV outlining skills and experience.
- Copies of all academic transcripts.
- Contact details of two referees.
Applications will be considered on a rolling basis until the position is filled.
Funding Notes
The UNSW PhD Scholarship covers both course fees and provides a stipend for living expenses. The total scholarship value is ~AUD$40,000 p.a. and is indexed each year.
More information on UNSW PhD Scholarships can be found here: https://www.unsw.edu.au/research/hdr/scholarships.
By applying for this PhD position, the candidate will also apply for a UNSW PhD Scholarship.