Available
Project number:
2025_76
Start date:
October 2025
Project themes:
Main supervisor:
Clinician Scientist
Co-supervisor:
Professor Richard Dobson
Additional Information:
Using Artificial Intelligence Methods to improve the representative nature of Clinical Trial Populations
Background
The clinical relevance of randomised controlled trials (RCT) rely on the trial cohort being representative of the underlying disease population. We have demonstrated the feasibility of using natural language processing (NLP) to evaluate the representativeness of a heart failure RCT cohort compared to a real-world heart failure cohort. This project would involve a continuation of that work, building upon excellent foundations and driving the work forward to bring about real benefit for patients.
Novelty and Importance
The novelty of this project rests on its use of artificial intelligence (AI) methods such as NLP to interrogate electronic health records (EHR) not only to retrospectively assess RCT cohort representativeness but also to develop tools to guide RCT recruitment and randomisation to enhance RCT cohort representativeness. The importance of this study relates to the potential to increase the value, robustness and clinical applicability of RCT data. RCTs are extremely expensive and therefore increasing the clinical relevance of their findings will have great value not only for patients, but also for RCT funding bodies (both commercial and non-commercial).
Aims & Objectives
The project has three main aims:
To develop an automated tool to retrospectively describe the relationship between the recruited RCT cohort in relation to the underlying real-world disease population for any given disease (but with a focus on cardiovascular disease)
To develop a reporting tool to allow for automated reporting of RCT representativeness
To develop a prospective tool for increasing RCT representativeness through optimisation of trial recruitment and randomisation.
References
-Wu J, Biswas D…O’Gallagher K. How representative are heart failure clinical trials? A comparative study using natural language processing. Abstract presented at HealTAC 2024.
-Wu J, Biswas D… O’Gallagher K. Artificial intelligence methods for improved detection of undiagnosed heart failure with preserved ejection fraction. Eur J Heart Fail. 2024;26(2):302–310. doi: 10.1002/ejhf.3115 An example of our use of electronic health record data to detect undiagnosed disease
We are now accepting applications for 1 October 2025
How to apply
Candidates should possess or be expected to achieve a 1st or upper 2nd class degree in a relevant subject including the biosciences, computer science, mathematics, statistics, data science, chemistry, physics, and be enthusiastic about combining their expertise with other disciplines in the field of healthcare.
Important information for International Students:
It is the responsibility of the student to apply for their Student Visa. Please note that the EPSRC DRIVE-Health studentship does not cover the visa application fees or the Immigration Health Surcharge (IHS) required for access to the National Health Service. The IHS is mandatory for anyone entering the UK on a Student Visa and is currently £776 per year for each year of study. Further detail can be found under the International Students tab below.
Next Steps
- Applications submitted by the closing date of Thursday 6 February 2025 will be considered by the CDT. We will contact shortlisted applicants with information about this part of the recruitment process.
- Candidates will be invited to attend an interview. Interviews are projected to take place in April 2025.
- Project selection will be through a panel interview chaired by either Professor Richard Dobson and Professor Vasa Curcin (CDT Directors) followed by informal discussion with prospective supervisors.
- If you have any questions related to the specific project you are applying for, please contact the main supervisor of the project directly.
For any other questions about the recruitment process, please email us at