Proposed start date: Preferred, 1st October 2020
This 3.5 year studentship is part of the Healthy Lifespan Institute (HELSI) at The University of Sheffield. HELSI is dedicated to the understanding and prevention of multimorbidity, which is the simultaneous presence of multiple chronic health conditions. Using a multidisciplinary approach, we aim to help people live longer, healthier and more independent lives.
As a student, you will be a valued and active member. You will be part of a wider network of PhD students and will have the chance to influence HELSI, to take part in seminars and events, and to meet leaders in the field.
As people live longer, the number of people with multiple diseases and complex medical needs has dramatically increased. As diseases are treated individually, problems of polypharmacy and high costs appear. In the UK, age-related multimorbidity already costs 45 billions/year and it is on the rise.
The study of multimorbidity is complex, and poses excellent methodological challenges in the analysis of temporal event data sequences.
On the data access and availability side, healthcare providers routinely record longitudinal data for all patient encounters. These datasets are large and underexploited.
On the methodological side, machine learning dominates the formulation of data-driven predictive models and has shown its benefits in a diverse range of applications.
To start unfolding this complexity, this PhD studentship will focus on osteoarthritis (OA), a disease associated with ageing, and a high number of comorbidities.
The hypothesis is that it is possible to identify subgroups of OA patients which will develop one or more comorbidities with a similar longitudinal sequence and that for these subgroups it is possible to identify determinants or predictors of those comorbidities.
-Access and use longitudinal datasets routinely collected data by healthcare systems, at local and UK level: Sheffield Teaching Hospitals NHS Foundation Trust, Rotherham NHS Foundation Trust, SAIL databank, and UK biobank.
-Develop a temporal event data methodology to analyse the historic evolution of patients suffering from OA focusing on key events in the disease progression (comorbidities, medications, social and risk factors) and their relative occurrence in terms of sequential order (patterns) but also temporal (duration).
-Develop machine learning models to analyse longitudinal patient data at various scales to identify patients at higher risk of developing additional comorbidities, or developing too early severe adverse outcomes.
-Focus on the identified subgroups of patients at higher risk, and work together with clinicians and social scientists to develop data-driven hypotheses about possible causal links.
The methodologies developed in this project are generic and applicable to other diseases where the temporal evolution, co-occurrence of other diseases, and polypharmacy are key elements to be considered.
Supervision and Mentorship:
This studentship will be jointly supervised by three senior academics Dr. Maria-Cruz Villa-Uriol and Dr. Mauricio Alvarez (Department of Computer Science, Faculty of Engineering), and Prof. Mark Wilkinson (Oncology & Metabolism, Faculty of Medicine, Dentistry & Health). Access to additional mentorship will be provided.
Candidates must have or expect to achieve, a minimum of an upper-second-class Honours degree (2.1 or above) or a Master’s degree (or equivalent) in Computer Science, Mathematics/Statistics, or related disciplines. Demonstrable knowledge of machine learning is desirable. Previous knowledge of the clinical side of the project is not required, although the candidate should demonstrate an interest in gaining the appropriate knowledge during their PhD. Good analytical thinking, strong programming and interpersonal skills are essential.
If English is not your first language, you must have an IELTS score of 6.5 overall, with no less than 6.0 in each component.
Candidates are strongly encouraged to contact Dr Villa-Uriol ([email protected]
) prior to application.
How to apply:
Please complete a University Postgraduate Research Application form available here: http://www.sheffield.ac.uk/postgraduate/research/apply
Please clearly state the title of this studentship, name Dr Villa-Uriol as the proposed supervisor and select Computer Science as the department.
Your application should include a research proposal, CV, transcripts and two references. The research proposal should outline your reasons for applying for this studentship and how you would approach the research, including details of your skills and experience.