Research projects
While we have several projects we work on, we are excited to share research projects that are cross-institutional and address more complex research challenges.
As all are in early stage of development, we welcome the community and our ecosystem to help influence their direction and partner with us to create flagship and impactful outputs.
Scroll down to see what our researchers are working on.
Problem Fingerprinting
Problem
Actual outputs can differ from our predicted outcomes due to patient demographics, resources, staffing and operations across institutions.
Methods to account for when outputs differ from the prediction are too generalised, strict, or unrealistic. Fairness and reliability are important in clinical decision-making especially when using large medical image datasets.
Research direction
Educate the community on the benefits of causal AI over non-causal AI.
Demonstrate how real-world situations give rise to data shifts and model drifts. Suggest how we can adapt to these changes.
Collaborate with clinical communities to create tools that model dataset cause-effect relationships.
Causal agent
Problem
Large language models are powerful general conversational tools, but they are not yet equipped to act as specialised process-driven assistants—such as tutors, discovery engines, or scientific co-pilots. To enable this, an LLM needs targeted tools, structured memory, and role-specific behaviour.
In healthcare and scientific settings, this gap limits our ability to deliver personalised education, scalable causal discovery, and integrated hypothesis-to-analysis workflows for clinicians and researchers.
Research direction
Build specialised “causal agents” that use tools and memory to act as process-guided assistants.
Integrate all three functions into a unified causal agent.
Chronological Causal Discovery
Problem
Patient data and the healthcare environment change over time. For example, patients visiting hospitals at different times in different health states when hospitals have different equipment. This makes understanding causal relationships in health datasets much more complex.
Research direction
Develop a method for finding cause-effect relationships in irregular and non-stationary time-sensitive data.
Use the method to study large electronic health datasets.
Stress Test Medical AI with Counterfactuals
Problem
Obtaining large and diverse datasets is difficult and often the framework for checking medical AI is fair and unbiased is lacking. This is especially relevant when designing the population sample for clinical trials and processing comprehensive medical imagery datasets.
Research direction
Test medical AI algorithms with ‘what if’ scenarios with different data types.
Simulate real-world changes and challenges.
Productively engage with regulatory bodies and policymakers on regulation and policy issues.
Meta-risk assessment
Problem
Developing accurate and reliable risk models is difficult and most AI methods are simpler non-causal linear models. This difficulty reduces adoption and real impact in everyday healthcare such as cardiovascular disease. The therapy area’s SCORE risk model is simple and doesn’t fully capture cause-effect relationships that could help doctors make smarter and actionable decisions based on the diseases’ underlying factors.
Research direction
Reduce risk prediction uncertainty.
Combine different risk models to increase reliability.
Test approach using Scottish health data.