Available
Project number:
2025_06
Start date:
October 2025
Project themes:
Main supervisor:
Professor of AI
Co-supervisor:
Additional Information:
Explainable AI for Accelerometer Data To Detect Neurological Deterioration in Cancer Patients
Background Wearable devices, such as triaxial accelerometers, are increasingly utilized in clinical settings to monitor patient health. In brain tumour patients, these devices combined with deep learning have successfully identified activity patterns linked to treatment effects and predicted clinical deterioration. However, the opaque nature of deep learning models limits their transparency and explainability. ReX, an explainable AI (XAI) tool recently developed and applied to brain imaging, identifies the features responsible for specific classifications. This project aims to expand ReX’s application to medical accelerometer data to uncover clinically relevant features of deterioration in brain tumour patients. Novelty & Importance This project pioneers the integration of ReX with accelerometer data for brain tumour patient care, offering interpretable insights into the factors driving predictions of clinical deterioration. This advancement is essential for clinical adoption, ensuring healthcare professionals can trust and understand AI-driven alerts. By identifying specific activity patterns associated with tumour characteristics, the project advances personalized medicine, enabling tailored interventions for individual patient needs. The novel application of ReX to accelerometer data addresses a significant gap in current AI methodologies, fostering the development of reliable and actionable healthcare solutions. Aims & Objectives The primary aim is to elucidate the prediction of clinical deterioration in brain tumour patients using wearable accelerometer data through the ReX framework. Specific objectives include: Determining the relationships between the anatomical locations of brain tumours and specific activity signals captured by triaxial accelerometers. Adapting and implementing the ReX framework to provide causal explanations for predictions made by deep learning models. Assessing the robustness and clinical relevance of the predictive models and the ReX framework using both existing and newly collected longitudinal medical data. Ensuring that the identified features are clinically meaningful to inform healthcare professionals in decision-making processes.
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
