Longitudinal trajectories of renal function, and dynamic prediction of progression to end-stage renal disease: a data-driven analysis and validation using regression and machine learning methods in a bi-national population-based cohort #NDORMS-2020/1

Supervisors

1. Prof Daniel Prieto-Alhambra
2. Dr V Strauss
3. Dr Sara Khalid
4. Dr Danielle Robinson
5. Dr Laurie Tomlinson

Research Project Outline

There is a scarcity of data on the natural history of chronic kidney disease (CKD) in the general population, and on markers of rapid progression to end-stage renal disease (ESRD). We will leverage real world data from large representative population-based electronic medical records to identify clusters of subjects with differential longitudinal trajectories of renal function decline. Secondly, we will study the association between the identified trajectories and the risk of developing ESRD. Finally, we will use regression and machine learning methods to develop and externally validate a dynamic prediction tool for the identification of subjects at high risk of ESRD.

We will extract primary care electronic medical records from the UK Clinical Practice Research Datalink (CPRD GOLD) and the Catalan SIDIAP database (www.sidiap.org), both linked to external sources of hospital and renal unit treatments. Our cohort analysis will include subjects with repeat biochemical measures of renal function. We estimate the number of participants will exceed one million participants.

Using the data available in these databases, we will use statistical and machine learning methods to identify key predictors of CKD progression to ESRD. The key features identified in SIDIAP will be combined in a prediction tool that will be validated externally in the UK CPRD GOLD database. In addition to “baseline” predictors (measured in the year/s before inclusion), we will study the additional value of incorporating repeat subsequent eGFR values measured in the years after the first two measures, in a dynamic prediction analysis.

Essential and Desired Qualifications/Experience

Essential Criteria
• Hold or be about to obtain a first or upper second class BSc degree or a Master degree (or equivalent) in subjects relevant to statistics, epidemiology or data science.
• Experience in data analyses.

Additional Qualifications
• Should have a commitment to research in the applied health sciences.
• A good team player as well as work independently.
• Experience in Pharmacoepidemiology and/or studies using routinely collected health data would be an advantage.

Details of the Research Group

The DPhil will be jointly supervised by Prof Prieto-Alhambra (Professor of Pharmaco- and Device Epidemiology and Theme Lead for Observational Research), Dr Victoria Strauss, Dr Sara Khalid, and Dr Danielle Robinson, all members of the Centre for Statistics in Medicine, NDORMS, University of Oxford; and by Dr Laurie Tomlinson, Wellcome Trust Intermediate Fellow at the London School of Hygiene and Tropical Medicine.

The research will be conducted with the Pharmaco- and Device Epidemiology Research Group (https://www.ndorms.ox.ac.uk/research-groups/Musculoskeletal-Pharmacoepidemiology), at the premises of the Botnar Research Centre, in Oxford, UK. Supervision meetings with Dr Tomlinson will be organized regularly, to be held either in Oxford or in London.

Prof Daniel Prieto-Alhambra (https://www.ndorms.ox.ac.uk/team/daniel-prieto-alhambra) has published extensively in the field of pharmaco-epidemiology, and is recognised internationally as an authority on use of routine data for pharmaco- and device epidemiology and related methods.

Dr Victoria Strauss (https://www.ndorms.ox.ac.uk/team/victoria-strauss) is a Senior Statistician. She has extensive expertise in the use, validation and development of statistical methods, both for the analysis of routinely collected data as well as in randomized clinical trial settings.

Dr Sara Khalid (https://www.ndorms.ox.ac.uk/team/sara-khalid) leads machine learning and Big Data analytics at Prof Prieto-Alhambra’s group. She has an Oxford DPhil in Engineering Science, and has an excellent track record and experience in the use of big data methods including machine learning algorithms.

Dr Danielle Robinson (https://www.ndorms.ox.ac.uk/team/danielle-robinson) is a Post-Doctoral Statistician. She has experience with the analysis and interpretation of renal function over time using data from CPRD and SIDIAP.

Dr Laurie Tomlinson (https://www.lshtm.ac.uk/aboutus/people/tomlinson.laurie) is an honorary Consultant Nephrologist at Brighton and Sussex University Hospitals NHS Trust, and a clinical epidemiologist at the LSHTM, where she works as a Wellcome Trust Intermediate fellow.

Current DPhil Students within the pharmaco-epidemiology research group: 6

Training

Training will be provided in relevant related research methodology, including the handling and analysis of large datasets, and advanced statistical techniques. Attendance at formal training courses will be encouraged, and will include the "Real world epidemiology Oxford summer school" directed by Prof Prieto-Alhambra, and the pre-conference course/s offered by the International Society of Pharmaco-epidemiology, amongst others.

A core curriculum of lectures organized departmentally will be taken in the first term to provide a solid foundation in a broad range of subjects including epidemiology, health economics, and data analysis.

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 ([Email Address Removed]), 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 are found online and the DPhil will commence in October 2020.

For further information, please visit http://www.ox.ac.uk/admissions/graduate/applying-to-oxford and/or contact Prof Prieto-Alhambra ([Email Address Removed])