Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.

PROJECT TITLE

Novel computational methods for next-generation “digital” clinical trials

SUPERVISORS

DESCRIPTION OF PROJECT

Clinical trials remain the gold standard for evaluating healthcare interventions, yet face increasing challenges in efficiency, cost, and generalizability. The emergence of digital technologies, artificial intelligence (AI), and rich electronic health records (EHR) presents unprecedented opportunities to revolutionize clinical trials methodology. Recent advances in synthetic data generation, automated data quality assessment, and digital identity verification are transforming how we design, conduct, and analyse clinical trials.

The integration of AI and machine learning approaches into clinical trials has opened new frontiers in methodological research, from creating synthetic control arms that could reduce trial size and cost, to developing algorithms for minimising human error and laborious, time and resource intensive trial processes. Furthermore, the standardization and mapping of clinical trial data across different sources, coupled with secure sharing mechanisms, has become crucial for enabling meta-analyses and increasing the value of existing trial data.

This DPhil project offers an exciting opportunity within the Deep Medicine group led by Professor Kazem Rahimi within the Nuffield Department of Women’s and Reproductive Health to advance methodological research for clinical trials. The student will review current methodological challenges and technological solutions, then define specific research questions around key areas such as synthetic trial arm generation, anomaly detection, automated data quality assessment, or privacy-preserving data sharing mechanisms. The project will involve developing and validating novel methodological approaches that combine statistical rigor with modern AI techniques, while ensuring practical applicability in real-world clinical trial settings.

The research will bridge statistical methodology, computer science, and clinical research, potentially exploring areas such as:

  • Development and validation of synthetic control arm generation methods
  • Creation of automated data quality assessment and cleaning pipelines
  • Design of privacy-preserving protocols for clinical trial data sharing
  • Implementation of machine learning approaches for protocol deviation detection and automated quality checks
  • Development of standardized data mapping frameworks across trial databases

The Deep Medicine research group with active leadership in start-up Zeesta.ai (https://www.zeesta.ai/)  has extensive experience in clinical trials methodology and have led or facilitated numerous digital trials. This project will benefit from collaboration with both methodological experts and clinical trials practitioners both in-house at Deep Medicine and global collaborators, ensuring that theoretical advances are grounded in practical needs. The group and department’s strong connections with industry partners and clinical research organizations will provide opportunities to validate new methods in real-world settings.

Candidates should have a strong background in statistics, computer science, or related quantitative fields. Experience with clinical trials, epidemiology, or more generally, healthcare data is advantageous but not required. Programming proficiency and an interest in both theoretical and applied aspects of clinical research methodology are essential.

TRAINING OPPORTUNITIES

The DPhil student will receive comprehensive training in both traditional and cutting-edge aspects of clinical trials methodology. Depending on research direction, this could include:

  • Advanced expert- and data-driven computational methods for clinical trials
  • Modern AI and machine learning techniques applied to clinical trial data
  • Software engineering practices for developing robust, scalable solutions
  • Privacy-preserving computation and secure data sharing methodologies
  • Good Clinical Practice (GCP) and regulatory requirements for clinical trials
  • Practical experience with clinical trial databases and data management systems

The student will join a multidisciplinary team of trialists, statisticians, computer scientists, and clinical researchers, providing exposure to various aspects of clinical trials methodology. They will receive training in academic writing, presenting at international conferences, and publishing in peer-reviewed journals. Opportunities for collaboration with industry partners will provide insight into practical implementation challenges and real-world applications of methodological innovations.

Additionally, the DPhil student will receive training in conducting comprehensive literature reviews, writing academic papers in peer-reviewed journals and conferences, and will work with a strong inter-disciplinary team of AI scientists, epidemiologists, cardiologists, and statisticians to conduct high-quality doctoral studies. 

Funding Information

The position is not currently funded, however, the Deep Medicine group will assist the DPhil candidate in securing funding. 

HOW TO APPLY

To apply for this research degree, please click here.