🧠 Welcome to Causality, Healthcare and AI (CHAI) Lab!
🎯 Our Mission
Our mission is to make data-driven personalised healthcare a reality by uniting clinicians, industry partners, and health providers. Through this collaboration, we develop and apply pioneering causal AI methods to solve real-world health challenges and translate research into direct social impact.
🔍 Our Research Focus
We focus on the intersection of causality, healthcare, and AI, drawing on a blend of theory and practice to solve real-world problems and make an impact in personalised healthcare in the long run. We consider any topic which aligns with our research focus, including but not limited to the following:
- Personalised Treatments - Individualised Treatment Effect Estimation
- Causal Inference
- Causal Discovery from Observational Data at Scale
- Counterfactual Fairness
- Counterfactual Explanations
- Uncertainty Quantification
- Counterfactual Generation & Reasoning
- Causal Benchmarking and Evaluation
- Deep Learning
- Federated Learning
- Continual Learning
- Multimodal AI
- Optimisation
- Domain Adaptation and Out-of-distribution Detection
- Causal Foundation Models
- Applications in Healthcare
📚 Recent Highlights
- I am co-editing a special issue (research topic) on Causal AI for the Frontiers in AI and Frontiers in Big Data journals: Causal AI: Integrating Causality and Machine Learning for Robust Intelligent Systems. Manuscript Summary Submission Deadline 15 November 2025 | Manuscript Submission Deadline 27 February 2026
- We are delighted to share our preprint Beyond Correlations: The Necessity and the Challenges of Causal AI, which serves as an accessible entry point for researchers interested in Causality. It outlines the rationale and motivation for integrating causality into AI, and addresses fundamental questions such as what causal AI is, why it matters, its key challenges, and promising research directions.
- I chaired a session on "Tuning for patient-specific care" at the 47th IEEE EMBC 2025 and also presented a paper, "Individualised Treatment Effects Estimation with Composite Treatments and Composite Outcomes".
📢 Join Us
We are looking for curious, motivated researchers and students to join us in shaping the future of causal AI for healthcare.