RISK CDT - Development of a clinical tool for management of thoracic aortic emergencies through risk prediction modelling

PLEASE APPLY ONLINE TO THE SCHOOL OF ENGINEERING, PROVIDING THE PROJECT TITLE, NAME OF THE PRIMARY SUPERVISOR AND SELECT THE PROGRAMME CODE "EGPR" (PHD - SCHOOL OF ENGINEERING)

This is a project within the multi-disciplinary EPSRC and ESRC Centre for Doctoral Training (CDT) on Quantification and Management of Risk & Uncertainty in Complex Systems & Environments, within the Institute for Risk and Uncertainty. The studentship is granted for 4 years and includes, in the first year, a Master in Decision Making under Risk & Uncertainty. The project includes extensive collaboration with prime industry to build an optimal basis for employability.

Liverpool Heart and Chest Hospital (LHCH) is one of the largest specialist heart and chest hospitals in the UK. Together with a growing team of researchers at the University of Liverpool vascular surgeons at LHCH are addressing one of the biggest challenges that they face, namely aortic dissection, through state-of-the-art research.

Aortic dissection is an emergency condition which involves a splitting of the wall of the aorta and typically results in immediate death. For those patients who survive the initial tear, the mortality rate is 1% per hour over the first 48 hours. Treatment involves immediate surgery with replacement of the ascending aorta to prevent complications from rupture or dissection into the heart. Vascular surgeons have the option to carry out two different procedures each with their pros and cons. Given the high risk of mortality even after surgery, a personalised medicine approach is needed. Your PhD project will utilise extensive datasets to allow vascular surgery to be better guided for each patient using risk and uncertainty analysis.

The overarching aim of this PhD project is to design bespoke patient specific management algorithms for patients with aortic emergencies, based on a risk analysis. The risk analysis will be informed by a range of data including clinical history and radiological imaging data. You will have access to a clinical dataset from over 2000 patients. The approach taken will be with the use of advanced statistical modelling methods and machine learning techniques. Ultimately you will produce a software tool that can easily be used by surgeons to guide the management of patients as well as by the industrial partner, Vascutek Terumo, who may use the information to modify surgical products to improve patient outcomes.

You will work with and have access to a multidisciplinary team with expertise in vascular surgery, bioengineering, biochemistry, medical device manufacture and statistical modelling. You will have opportunities of training in machine learning and related techniques in our cutting-edge research centres.

YOUR PHD TASKS/RESPONSIBILITIES
Your PhD will require the successful completion of a Masters of Research, attendance to a highly structured PhD Training Programme and submission of a PhD thesis.
Your PhD will focus on:
• Identifying risk factors for various surgical procedures used to treat aortic dissection with the use of statistical modelling and machine learning.
• Development of algorithms that can be used to guide patient specific aortic surgery.
• Development of algorithms that can be used to guide the development of medical devices manufactured by Vascutek Terumo for aortic dissection.
• Dissemination of results via publication in high quality cardiovascular journals.

WHO ARE WE LOOKING FOR?
Essential requirements:
• A numerate background – e.g., a Master’s degree in computer science, mathematics, engineering, medical image analysis or related discipline.
• Highly motivated, with a strong interest in the application of statistical analysis to healthcare and cardiovascular disease.
• Excellent English written and verbal communications skills
• Experience with computer programming skills (e.g., Matlab, R, Python).
Desirable skills:
• Experience in statistics/machine learning.
• Experience in biostatistics data analysis.
• Experience in writing publications in peer reviewed scientific journals.