Available
Project number:
2025_107
Start date:
October 2025
Project themes:
Main supervisor:
Professor of Medical Bioinformatics
Co-supervisor:
Associate Professor Richard Beare
Additional Information:
Students recruited to this studentship must spend in the region of 12 months at Monash University in Melbourne, Australia, with the named supervisor(s) as part of the research and training programme.
Detecting Frailty in electronic records using AI based approaches for Natural Language Processing and Large Language Models (LLM) on real world clinical text from multiple countries
Background – Frailty is a state that affects many older people, typified by fatigue, reduced and/or slow mobility, altered cognition, muscle weakness, weight loss and increased physiological vulnerability. Identifying frailty in hospitals is therefore important so that appropriate clinical care can be provided to an older person. Although there are several frailty scales and indices available, the implementation of these in a routine and hospital-wide fashion is not feasible given logistics and resources required. Electronic records therefore provide an opportunity to potentially capture frailty using routinely recorded information. There is an electronic frailty index that can be generated from structured electronic data, but it is likely that it does not capture everyone with frailty. Information recorded in clinical notes is likely to provide data that can enhance our ability to accurately and routinely capture frailty, in addition to structured data.
Novelty and Importance – Very few if any groups in the world have used unstructured data to capture clinical concepts such as frailty. If these data can be successfully used to identify frailty, and be implemented in routine systems, then clinical care for older people in hospitals can be vastly improved. This project, enabled through the CogStack programme (cogstack.org) will provide access to unprecedented amounts of longitudinal EHR data in both major UK and Australian hospitals through partnership with the National Centre for Healthy Ageing, and Monash Partners related hospital-network.
Aims and Objectives – To develop (train and validate) AI based natural language processing techniques to reliably capture frailty from unstructured data in electronic health records
Planned Research Methods – 1. Identify cohorts with validated measure of frailty, who have electronic health data available, including electronic frailty index based on structured data 2. Expert clinician supported identification of potential text-based concepts in unstructured data that may be indicators of frailty 3. Application of natural language processing techniques and models to unstructured data to capture and classify presence of frailty. 4. Measures of accuracy and agreement of structured and unstructured models (and their combination) against clinical frailty measure. 5. Develop methods to train data against degree of frailty. 6. Perform validation studies in independent cohort. Apply methods to a number of clinical priority areas.
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