Research Supervisor Connect
This project aims to develop an AI-empowered digital heart that integrates computational modelling, physiological signal analysis, and machine learning to enable accurate monitoring, diagnosis, and prediction of cardiac conditions. The research will advance digital twin technologies for personalised and intelligent cardiovascular healthcare.
Electrical and Computer Engineering
The project on Development of an AI-Empowered Digital Heart focuses on creating a digital twin of the human heart by combining physiological modelling, multimodal biosignal processing (e.g., ECG, echocardiography, wearable sensors), and advanced artificial intelligence algorithms. The research will develop data-driven and hybrid physics–AI models to simulate cardiac dynamics, detect anomalies, and predict disease progression. A key objective is to enable personalised healthcare by adapting the digital heart to patient-specific data, providing clinicians with actionable insights for early diagnosis, treatment planning, and outcome prediction. The project will also address challenges in real-time data integration, model interpretability, and privacy-preserving data sharing, contributing to the next generation of smart, AI-assisted cardiovascular healthcare systems.
Research Techniques/Methodologies/Technologies
The project will employ machine learning and deep learning methods, digital twin modelling, multimodal data fusion, and advanced signal/image processing. Tools such as Python, MATLAB, and biomedical simulation platforms will be used alongside clinical datasets and wearable IoT devices for validation.
Successful candidates:
Candidates should have a strong background in biomedical engineering, computer science, electrical/electronic engineering, or a related field. Experience in AI/ML, signal or image processing, computational modelling, or healthcare IoT is desirable. Knowledge of cardiovascular physiology or prior work with clinical/biomedical data will be advantageous. Strong analytical, programming, and interdisciplinary research skills are essential.
How to apply:
To apply, please email [email protected] the following:
The opportunity ID for this research opportunity is 3697