This project spans 3 different units of assessment at UU (Biomedical Sciences, Computing and Psychology) and involves an industrial partner (GMI, Dublin) who will provide on-site internships for the PhD researcher.
Background:
Depression is a complex heterogeneous disorder. In severe depressive episodes, patients experience feelings of hopelessness/worthlessness, and suicide is a prominent risk. As the leading cause of global disability[1], 300 million people are affected by depression and public health figures indicate depression accounts for 76.4 million years lost to disability; more than any other condition[2]. NI has one of the highest rates of depression in Europe with a lifetime prevalence rate of 16.3%[3] and continues to have the highest rate of suicide of any UK country, at 16.5/100,000 (NISRA, reported by BBC News). NI has a 20-25% higher prevalence rate of mental health problems than the rest of the UK, with associated costs of £3.5 billion. The cost of depression to the UK economy is £70-£100 billion/year. In the UK, depression is predominantly diagnosed by general practitioners in primary care, but diagnosis and treatment selection is largely subjective, and reliant on patient self-report and clinical judgment and experience. Recent advancements have prompted the investigation of patients clinical and physiological profiles to determine biological features (biomarkers) that can be used to identify mental health disorders such as depression. However, there is a huge need to further investigate various biomarkers and intelligently combine these to develop a robust clinical diagnosis tool, which would allow clinicians to effectively diagnose and stratify patients with depression, and ultimately determine the most stratified/personalised treatment.
Dataset:
NICSM have recently procured access to the UK Biobank dataset, including imaging, genomic, biochemical, diagnosis, medication/treatment, demographic/local-environment data of 500,000 participants. Approximately 20,000 of these participants are diagnosed with depression according to International Classification of Diseases Tenth Revision (ICD10).
Method:
This project will investigate the use of medical imaging, specifically, structural Magnetic Resonance Imaging (MRI), to identify neuro-biomarkers (neuromarkers) within the brain that can be used, in combination with existing genetic biomarker approaches (e.g. polygenic risk scoring), to classify major depressive disorder within a patient into specific endotypes for stratified/personalised diagnosis and treatment. A deep-learning model, specifically a convolutional neural network (CNN), will be developed to extract key features from the MRI data, which can be used to identify and classify neuromarkers for depression. Using a cognitive analytic approach, supervised machine learning methodology will be used to analyse correlations between these neuromarkers, genetic biomarkers and phenotypic information to develop a robust diagnosis system to clinically identify endotypes of depression.
Project tasks to be performed by the PhD student:
1. Extract depression cohort from UK Biobank dataset using ICD10 and validated clinical questionnaires and associated genetic and medical imaging data;
2. Perform image data processing (dimensionality reduction, structural analysis, etc.) to determine imaging signatures (neuromarkers) predictive of depression;
3. Using the combination of genetic biomarkers, phenotypic information and acquired neuromarkers, perform big data cognitive analytics to clinically identify endotypes of depression.
References:
1. World Health Organization. (2018). Depression. [online] Available at: http://www.who.int/mediacentre/factsheets/fs369/en/.
2. Global Burden of Disease Study 2013 Collaborators. (2015). Global, regional, and national incidence, prevalence, and years lived with disability for 301 acute and chronic diseases and injuries in 188 countries, 1990-2013: a systematic analysis for the Global Burden of Disease Study 2013. Lancet (London, England), 386 (9995), 743-800.
3. Bunting, BP, Murphy, SD, O'Neill, SM & Ferry, FR. (2012). 'Lifetime prevalence of mental health disorders and delay in treatment following initial onset: evidence from the Northern Ireland Study of Health and Stress', Psychol Med, vol. 42, no. 8, pp.1727-39.
Other Project Specific Requirements:
Degree/MSc in Stratified Medicine, Bioinformatics, Biomedical Sciences, Computer Science, Computer Engineering, or another relevant field. Experience in tools/languages such as MATLAB, R, Python, Linux, or C\C++. Desirable - understanding/experience in machine learning, image processing.
Researcher will be based at C-TRIC (Altnagelvin Hospital site).
Prospective candidate:
The project will be entirely computational. Thus, we are seeking a student having a strong interest in computational approaches evidenced by good programming skills (preferable in Linux, MATLAB, C/C++, Python or R) and knowledge in biomedical/biological sciences, computational biology and statistics. However, students from more biology oriented background but strong interest to learn bioinformatics and programming are also encouraged to apply. Appropriate training will be provided during the course of PhD study. For any informal enquiry and/or to discuss more about the project, please contact the lead supervisor or any member of the supervisory team. Contact details of the supervisory team are mentioned on the right hand side of this webpage.
Applicants should hold, or expect to obtain, a First or Upper Second Class Honours Degree in a subject relevant to the proposed area of study.
We may also consider applications from those who hold equivalent qualifications, for example, a Lower Second Class Honours Degree plus a Master’s Degree with Distinction.
In exceptional circumstances, the University may consider a portfolio of evidence from applicants who have appropriate professional experience which is equivalent to the learning outcomes of an Honours degree in lieu of academic qualifications.
If the University receives a large number of applicants for the project, the following desirable criteria may be applied to shortlist applicants for interview.
The University offers the following levels of support:
The scholarship will cover tuition fees at the Home rate and a maintenance allowance of £19,000 (tbc) per annum for three years (subject to satisfactory academic performance).
This scholarship also comes with £900 per annum for three years as a research training support grant (RTSG) allocation to help support the PhD researcher.
Due consideration should be given to financing your studies. Further information on cost of living
Submission deadline
Friday 7 February 2020
12:00AM
Interview Date
9 to 20 March
Preferred student start date
Mid September 2020
Telephone
Contact by phone
Email
Contact by email