Available
Project number:
2025_15
Start date:
October 2025
Project themes:
Main supervisor:
Lecturer in Health Data Science and AI
Co-supervisor:
Additional Information:
Advancing Cardiovascular Disease Diagnosis and Medical Report Generation Through Deep Generative Models
Background
Cardiovascular diseases (CVDs) are the leading cause of death globally, contributing to around 32% of annual deaths [1]. Electrocardiograms (ECGs) are pivotal in diagnosing CVDs due to their non-invasive, fast, and cost-effective nature [2]. However, interpreting ECGs requires expert knowledge, and has potential inconsistencies and misdiagnoses among healthcare professionals. This project will leverage deep generative models, specifically transformer architectures, to automatically analyse ECGs and generate comprehensive medical reports.
Novelty & Importance
This research uniquely integrates DL models with LLMs for automated cardiovascular diagnosis and medical report generation. The application of LLMs to extract clinically significant features from ECG data is innovative and represents a major step forward in cardiac diagnostics. By automating both ECG interpretation and report generation, the research aims to enhance diagnostic accuracy and efficiency, improving patient outcomes and making healthcare more accessible.
Aims & Objectives
The primary aim is to develop and evaluate DL models that can autonomously interpret ECGs and generate medical reports. The specific objectives include: (1) Developing models to extract latent features from raw ECG signals and using attention mechanisms to highlight clinically relevant ECG features; (2) Creating transformer-based models that integrate these features with pre-trained LLMs (e.g., BERT) to generate detailed medical reports.
References
[1] Lei Lu, et al., Decoding 2.3 million ECGs: interpretable deep learning for advancing cardiovascular diagnosis and mortality risk stratification, European Heart Journal - Digital Health, 2024.
[2] Y. Shen, et al., AutoNet-Generated Deep Layer-Wise Convex Networks for ECG Classification, IEEE TPAMI, 2024.
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 30 January 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 March 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
