PHD Title: Improving respiratory care via statistical modelling of multiple sources of data

Data science and statistics are rapidly transforming the face of health care and are leading to efficiency increases in prevention, diagnosis and treatment for a multitude of diseases. This PhD project will address respiratory disease, using as a case study data from the Morcambe Bay area in the Northwest of England, and will aim to use multiple sources of data to identify factors that may be useful to improve the care of people suffering from respiratory disease in deprived communities.

Respiratory disease remains a leading cause of morbidity and mortality in the UK and has strong links with poor housing, deprivation and health inequalities; this is particularly the case in the Morecambe Bay Area, which contains some of the most deprived communities in the country. Nationally, there is currently considerable focus on the importance of robust recognition and diagnosis of respiratory disease in the primary care setting. This is important not only for correct and timely treatment of individual patients but also to reduce the burden on local health services caused by non-elective admissions and lengthy hospital stays. In addition national policy requires accurate diagnostic coding to inform strategic health planning for respiratory disease. Tasked with addressing these issues, the Morecambe Bay Respiratory Network (MBRN) is the emerging integrated respiratory service in Bay and Health Care Partners.

The three main objectives to the PhD are:

1. Develop statistical models for the spatio-temporal epidemiology of respiratory disease in the MBRN patch. Identify the relationships between incidence of respiratory disease, deprivation and housing in our locality; determine the factors affecting space-time changes in patterns of respiratory disease.

2. Develop machine learning classification algorithms to understand the features of diagnostic quality for the four main chronic respiratory diseases (COPD, Asthma, Bronchiectasis and ILD). Identify areas of good practice and areas that may require improved training in respiratory care and support from population health strategies.

3. Develop statistical models for predicting how well patients control their symptoms and evaluate outcomes 1 year from initial diagnoses. Compare expected to actual outcomes in patients on the MRBN pathway vs control groups in and out of Morecambe Bay, thus evaluating the clinical benefits of MBRN.

The PhD project will be based in the Royal Lancaster Infirmary Business Intelligence/Data Science Unit and at the Data Science Institute (https://www.lancaster.ac.uk/dsi/) at Lancaster University and will form part of the portfolio of research associated with our forthcoming Health Innovation Campus (https://www.lancaster.ac.uk/health-innovation/) and the NIHR Applied Research Collaboration North West Coast (https://www.nihr.ac.uk/explore-nihr/support/collaborating-in-applied-health-research.htm). The supervisory team includes both academic and key clinical partners to ensure the research goals are both intellectually-innovative and of practical relevance and utility to the NHS in our local area and more widely at the national level.

The is an ESRC studentship which will pay UK/EU/Overseas tuition fees and a starting stipend of approx £18,000 per annum. The student will receive advanced training at the machine learning / statistics / epidemiology interface.

The Lancaster University campus is situated in a beautiful 360 acre parkland site at Bailrigg, just 3 miles from Lancaster City Centre. Lancaster University is one of Britain's top universities, with over 12,000 students and 2,500 employees within the Bailrigg campus that is now almost a small town in its own right. For those applicants who enjoy the outdoors, living in Lancaster offers easy access to the Lake District and Yorkshire Dales.

The successful candidate will have a first class Bachelor's degree, or a distinction at Master level in statistics, or in a related discipline with substantial statistical content. They will be highly motivated and capable of independent work. Applicants must have an interest in Health Data Science, together with good interpersonal and communications skills.

Interested and appropriately qualified applicants should contact Professor Jo Knight ([log in to unmask]) or Dr Frank Dondelinger ([log in to unmask]) for further information. Please include an up-to-date CV as an attachment. The project will start in October 2020.
The first round interviews will be held in in late February with second round interviews in late March if required.
 

You may leave the list at any time by sending the command

SIGNOFF allstat

to [log in to unmask], leaving the subject line blank.