NDORMS DPhil & MSc by Research
Novel solutions for managing and curating big clinical data regularly collected in NHS Primary Care setting
The amount of clinical data digitally collected and stored is vast and is expanding rapidly, offering unique opportunities to promote health and wellbeing. As a consequence, big clinical data is considered now one of the driving forces in clinical research.
While statistical packages struggle to handle the multi-dimensionality and volume of big clinical data, medical statistics is catalyzed by investigating new powerful and time-consuming methods, such as machine learning techniques and prediction models. To fill up this gap in the research chain, Health Data Science is advancing fast to convert big clinical data into information, which can successfully be analyzed by advanced statistical methods to produce medical evidence. To achieve this objective, a multidisciplinary approach has become necessary where principal investigators, medical researchers and statisticians rely on high-level information technologists. To improve the clinical research process, novel programming solutions are needed for managing and curating multi-dimensional clinical data effectively, consistently and efficiently by full automation.
A promising approach for observational research studies is to develop specialized and sophisticated programming solutions with embedded data quality rules for error detection to produce selective and high-quality information ready for statistical analyses. This can be tailored for different clinical research designs, including case-control, cohort and cross-sectional studies.
The overall aim of this research project is to design an innovative computing solution to develop and validate automatic methods and data quality algorithms for the management and curation of big health data for observational clinical research. Routinely collected NHS primary care data from the UK Clinical Practice Research Datalink (CPRD) will be used for this purpose.
- Fan W, Data Quality: From Theory to Practice, ACM SIGMOD, Vol. 44, Issue 3, 2015, pp. 7-18. DOI=https://dx.doi.org/10.1145/2854006.2854008
- Cook JA and Collins GS, The rise of big clinical databases, BJS, Vol. 102, Issue 2, 2015, pp. e93 - e101, DOI=https://doi.org/10.1002/bjs.9723
- Lee CH, Yoon H-J, Medical big data: promise and challenges, Kidney Research and Clinical Practice, Vol. 36, Issue 1, pp. 3-11, 2017, DOI=http://doi.org/10.23876/j.krcp.2017.36.1.3
DETAILS OF THE RESEARCH GROUP
The DPhil will be jointly supervised by Dr Antonella Delmestri and Associate Prof Prieto-Alhambra, who are both part of the NDORMS Big Health Data Research within the Centre for Statistics in Medicine (CSM).
Dr Antonella Delmestri is a Senior Database Manager with vast and long term expertise in Big Health Data, Computer Science and Software Engineering. She has an outstanding publication history in epidemiology, randomized controlled clinical trials and computer science.
Prof Daniel Prieto-Alhambra has published extensively in the field of pharmaco epidemiology, and is recognized internationally as an authority on use of routinely collected data for musculoskeletal pharmaco and device epidemiology.
Current DPhil Students within the Big Health Data Research group: 7
The Botnar Research Centre plays host to the University of Oxford's Institute of Musculoskeletal Sciences, which enables and encourages research and education into the causes of musculoskeletal disease and their treatment. Training will be provided in techniques including the Real World Epidemiology Oxford Summer School and the UK Research in Musculoskeletal Epidemiology (UK-RIME) training. In addition, courses from the Oxford University Computer Science and Software Engineering Departments on key computing skills will be available.
A core curriculum of lectures will be taken in the first term to provide a solid foundation in a broad range of subjects including musculoskeletal biology, inflammation, epigenetics, translational immunology, data analysis and the microbiome.
Students will attend regular seminars within the department and those relevant in the wider University.
Students will be expected to present data regularly in the departmental PGR seminars, in the Big Health Data Research and to attend external conferences to present their research globally.
Students will also have the opportunity to work closely with other researchers within CSM.
Students will have access to various courses run by the Medical Sciences Division Skills Training Team and other departments. All students are required to attend a 2 - day Statistical and Experimental Design course at NDORMS.
This multidisciplinary project will be the first of a new research programme, led by the Big Health Data Research group. The aim of this programme is to investigate how the use of full automation for the management and curation of Big Health Data can benefit reproducibility, consistency, reliability, quality and efficiency of epidemiology research.
Students applying for this project are expected to have a degree in Computer Science, Software Engineering, Medical/Health Informatics or similar.
How to Apply
The department accepts applications throughout the year but it is recommended that, in the first instance, you contact the relevant supervisors or the Graduate Studies Officer, Sam Burnell (firstname.lastname@example.org), who will be able to advise you of the essential requirements.
Interested applicants should have or expect to obtain a first or upper second class BSc degree or equivalent, and will also need to provide evidence of English language competence. The application guide and form is found online and the DPhil or MSc by research will commence in October 2019.
For further information, please visit http://www.ox.ac.uk/admissions/graduate/applying-to-oxford