Primary supervisor
Jesmin NaharResearch area
Data Science and Artificial IntelligenceBackground
Colorectal cancer is a major health challenge, and early detection and accurate risk assessment are important for improving clinical outcomes. The increasing availability of clinical, demographic, lifestyle, laboratory, imaging and longitudinal health data provides opportunities to apply Artificial Intelligence (AI) and Machine Learning (ML) to colorectal cancer research.
Research Aim
This PhD research aims to develop and evaluate explainable AI and machine-learning approaches for early detection, risk stratification and prognostic prediction of colorectal cancer, with a focus on supporting personalised clinical decision-making.
Research Approach
The research will investigate clinical, demographic, lifestyle, laboratory, medical imaging and, where available, longitudinal patient data. Machine-learning and deep-learning techniques will be developed and compared for cancer-risk prediction, classification and prognostic modelling.
Explainable and Multimodal AI
Explainable AI (XAI) methods will be investigated to identify important clinical and predictive factors contributing to model decisions. Where appropriate, multimodal approaches will explore the integration of different data sources to improve prediction and generalisability.
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 validation and performance evaluation
- Explainable AI (XAI) and interpretable machine learning
- Temporal and longitudinal data analysis is desirable
- Healthcare, clinical or biomedical data analysis
- Medical imaging and/or multimodal data analysis is desirable
- Research methodology, critical thinking and scientific communication
- Responsible and ethical AI in healthcare
