About the Project
Respiratory diseases affect a person’s ability to breathe normally. Acute respiratory infections are common, particularly in young children and older adults. Examples of acute respiratory infections include COVID-19, influenza (flu), pneumonia, respiratory syncytial virus (RSV) and Streptococcus pneumonia. The NHS was under unprecedented pressure as a result of the compound effects of the ongoing COVID-19 pandemic, NHS staff absences and vacancies, and the cost-of-living crisis. There were increases in the incidence and severity of respiratory syncytial virus (RSV) in parts of the United States and Europe and other respiratory illnesses such as Streptococcus A and these impacted in the UK too. RSV in adults alone is estimated to result in approximately 487,000 GP episodes, 18,000 hospitalisations and nearly 8,500 deaths per season. Annually respiratory illness cost the UK at least £11 billion. There is considerable policy interest in understanding who might be most at risk of poor health or hospitalisation in winter to predict and manage demand on health and care services. Better understanding of these risks is also essential for targeted preventive actions (such as vaccination, antiviral/antibiotics treatment, monoclonal antibody treatment, optimising care for individual with pre-existing conditions).

Our primary aim is to derive and validate a risk prediction model via systematic evaluation of various machine learning-based algorithms (supervised learning) for adults with winter respiratory infections with a particular focus on those who experience sever outcomes resulting in hospitalisation or death.

Supervisors:

· Dr Ting Shi, Usher Institute, Edinburgh Medical School, The University of Edinburgh

· Professor Aziz Sheikh, Usher Institute, Edinburgh Medical School, The University of Edinburgh

· Dr Syed Ahmar Shah, Usher Institute, Edinburgh Medical School, The University of Edinburgh

In collaboration with:

· Dr Antonia Ho, School of Infection and Immunity, University of Glasgow.

Requirements

A strong academic track record with a 2:1 or higher in a relevant undergraduate degree or its equivalent if outside the UK. It is also desirable for the candidate to have evidence of strong performance in a relevant postgraduate degree. Candidates with qualifications in mathematics / computer science and a health-related discipline are particularly encouraged to apply, but it would be possible for those with cognate disciplines to also make the transition to health data science. We welcome applications from candidates from diverse backgrounds.

Essential attributes:

· A strong quantitative background and desire to apply these techniques to healthcare

· Good written and oral communication skills

· Evidence of independent research skills relevant to the project

· Strong motivation

· Good time management

· Demonstrable ability to work independently as part of a distributed team

Desirable attributes:

Demonstrable experience in one or more of the following:

· Programming in MATLAB/Python/R or a comparable language

· Previous research experience with healthcare datasets or electronic health records.

Following interview, the selected candidate will need to apply and be accepted for a place on the Usher Institute PhD programme. Details about the PhD programme can be found here: https://www.ed.ac.uk/studying/postgraduate/degrees/index.php?r=site/view&id=924

Application Procedures:

This 4 year PhD project is part of a competition funded by EASTBIO BBSRC Doctoral Training Partnership (DTP) http://www.eastscotbiodtp.ac.uk/how-apply-0.

EASTBIO Application and Reference Forms can be downloaded via http://www.eastscotbiodtp.ac.uk/how-apply-0

Please send your completed EASTBIO Application Form along with a copy of your academic transcripts to Ting.shi@ed.ac.uk

You should also ensure that two references have been send to Ting.shi@ed.ac.uk by the deadline using the EASTBIO Reference Form.

The closing date for applications is: 27th November 2023

Interviews will be held during 5-9th February 2024.