About the Project
This DPhil in Clinical Epidemiology and Medical Statistics is a 3.5-year project on the development and evaluation of agentic artificial intelligence (AI) to support analytical code development for real-world evidence (RWE) studies.
RWE studies using large healthcare databases are widely used to support regulatory decision-making. However, translating a study protocol into reproducible analytical code remains time-consuming and prone to error, requiring codelist and cohort definitions, covariate selection, and a detailed description of statistical analyses, and sensitivity analyses. Regulatory applications place particular importance on the pre-specification, transparency, and reproducibility of these steps, making automation appealing.
Recent advances in large language models (LLMs) have demonstrated their ability to generate code, while agentic AI systems extend this by allowing models to iteratively develop, execute, test, and refine analytical workflows. This project will investigate whether these approaches can automate components of RWE planning and analysis by translating study protocols into executable and reproducible pipelines.
AI-generated analyses will be trained and then tested and benchmarked against code developed by experienced RWE researchers, using new and previously completed RWE studies with validated analytical pipelines and results as ground truth, across different study designs and datasets. Evaluation will consider correctness, reproducibility, adherence to protocol, analytical validity, and efficiency, identifying which tasks can be reliably automated and where human oversight remains necessary. Overall, the project will establish how, when, and where agentic AI can be safely and transparently integrated into regulatory-grade RWE generation.
Supervisors
- Prof. Daniel Prieto-Alhambra https://www.ndorms.ox.ac.uk/team/daniel-prieto-alhambra
- Dr. Martí Català Sabaté https://www.ndorms.ox.ac.uk/team/marti-catala-sabate
- Dr. Xintong Li https://www.ndorms.ox.ac.uk/team/xintong-li
Training
The Health Data Sciences Section is part of the Botnar Research Centre, University of Oxford. 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 epidemiology, biostatistics, common data models, causal inference, and real world evidence methods and data.
A core curriculum of lectures will be taken in the first term to provide a solid foundation in a broad range of subjects, incl. data analysis. Students will also be required to attend regular seminars within the Department and those relevant in the wider University.
Students will be expected to present data regularly in Departmental seminars, the Health Data Sciences Section’s fortnightly lab meeting, and to attend external conferences to present their research globally, with limited financial support from the Department.
Students will also have the opportunity to work closely with our multiple collaborators nationally and internationally, including academic centres of excellence (Harvard University, Universitat Autonoma de Barcelona, Erasmus Medical Centre, among others), regulators (UK MHRA, European Medicines Agency), and industry.
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 (information will be provided once accepted to the programme).
How to Apply
Please contact the relevant supervisor(s), to register your interest in the project, and, if required, the departmental Education Team (graduate.studies@ndorms.ox.ac.uk), who will be able to advise you of the essential requirements for the programme and provide further information on how to make an official application.
Interested applicants should have, or expect to obtain, a first or upper second-class BSc degree or equivalent in a relevant subject and will also need to provide evidence of English language competence (where applicable). The application guide and form is found online and the DPhil or MSc by research will commence in October 2027.
Applications should be made to one of the following programmes using the specified course code. D.Phil in Clinical Epidemiology and Medical Statistics (course code: RD_NNRA1)
For further information, please visit http://www.ox.ac.uk/admissions/graduate/applying-to-oxford.
Applications open mid-September
Application deadline: 12:00 on 1st December
References
Wang SV, Sreedhara SK, Schneeweiss S, et al. Reproducibility of real-world evidence studies using clinical practice data to inform regulatory and coverage decisions. Nat Commun. 2022;13:5126. doi: 10.1038/s41467-022-32310-3.
Kim H, Kim M, Kim S, et al. From study design to executable code: automating target trial emulation with large language models. JAMIA Open. 2026;9(4):ooag131. doi: 10.1093/jamiaopen/ooag131.
Cid Royo A, Elbers JHJ, Weibel D, et al. Real-World Evidence BRIDGE: A Tool to Connect Protocol With Code Programming. Pharmacoepidemiol Drug Saf. 2024;33(12):e70062. doi: 10.1002/pds.70062.
This is a Preview Listing…
You must sign in to see the full job description, and to apply.
Manage / Upgrade this job to a Full Job Listing.
Find Your Best Opportunity
Tell them AcademicJobs.com sent you!