Primary supervisor
Jesmin NaharCo-supervisors
- Anyone from the Faculty who is interested.
Research area
Data Science and Artificial IntelligenceBackground
Cardiovascular disease is a major global health challenge, and early identification of individuals at increased risk is important for prevention and timely clinical intervention. The increasing availability of electronic health records, clinical measurements, medical imaging and longitudinal health data provides opportunities for Artificial Intelligence (AI) and Machine Learning (ML) to improve cardiovascular risk assessment and prediction.
Research Aim
This PhD research aims to develop and evaluate AI and Machine Learning approaches for early prediction, risk stratification and prognostic modelling of heart disease, with a focus on explainable and personalised clinical decision support.
Research Approach
The research will investigate clinical, demographic, lifestyle, physiological, laboratory and, where appropriate, medical imaging and longitudinal data. A range of machine-learning and deep-learning techniques will be developed and evaluated for cardiovascular disease prediction and risk assessment.
Advanced AI and Decision Support
The research will investigate Explainable AI (XAI) to identify important clinical predictors and improve the interpretability of model predictions. Multimodal and temporal modelling approaches may be explored to integrate different data sources and capture changes in patient risk over time.
Prediction and Prognostic Modelling
The study will investigate models for early disease prediction, risk stratification and prognostic prediction, including the potential forecasting of future cardiovascular events or risk trajectories where suitable longitudinal data are available.
Expected Contribution
The research aims to develop a robust, interpretable and generalisable AI framework for cardiovascular risk prediction and clinical decision support. The study will consider model performance, validation, uncertainty, fairness, generalisability and responsible application of AI in healthcare.
Required knowledge
Required Knowledge
Students should have a strong background in:
- Data Science, Artificial Intelligence and Machine Learning
- Python and/or R programming
- Data preprocessing, feature engineering and statistical analysis
- Supervised and unsupervised machine-learning techniques
- Deep learning and neural networks
- Predictive, risk and prognostic modelling
- Model development, validation and performance evaluation
- Temporal/longitudinal data analysis is desirable
- Medical/clinical data analysis and healthcare applications of AI
- Explainable AI (XAI) and responsible AI principles
- Critical thinking, research methodology and scientific communication
