SET
TrueBeat: Interpretable and Trustworthy AI for Early Arterial Fibrillation Diagnosis
✓ Fully Funded
⏰ Closing Soon
🎓 Biomedical Engineering
🎓 Cardiology
🎓 Computer Science
🎓 Electrical Engineering
🎓 Electronic Engineering
🎓 Health Informatics
🎓 Machine Learning
machine learning
AI healthcare
signal processing
ECG
atrial fibrillation
wearable technology
Fully funded PhD developing interpretable AI models for early detection of atrial fibrillation using ECG data.
Project Description
This PhD project focuses on developing interpretable, robust, and energy-efficient AI models for early detection of atrial fibrillation (AF) using ECG data.
The research will involve signal processing for ECG denoising, development of advanced AI models (including CNNs, LSTMs, and Transformers), and implementation of explainable AI techniques to improve clinical interpretability. The project will also address model generalisation across datasets and wearable devices, and explore green AI approaches for computational efficiency.
The candidate will contribute to building a real-time AF detection prototype system, supporting improved early diagnosis and clinical decision-making.
Entry Requirements
Bachelor’s and postgraduate degree in relevant field (e.g. Biomedical Engineering, Computer Science)
• Experience in Python/MATLAB, machine learning, or signal processing
• Strong analytical and programming skills
• Interest in AI for healthcare and wearable technologies
• English language proficiency (if required)
• Experience in Python/MATLAB, machine learning, or signal processing
• Strong analytical and programming skills
• Interest in AI for healthcare and wearable technologies
• English language proficiency (if required)
How to Apply
Apply via SETU online application portal with all required documents.
Eligibility
UK/Home
EU
International
Supervisor Profile
DB
Dr Bhaskar Murari; Dr Arun Sankar; Dr Ondrej Kucera
South East Technological University (Waterford), Research Support Unit
Related Opportunities
MUM
MUM
MUM
UCL