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.

A group of people attending a workshop or meeting in a conference room, with sticky notes on a large blackboard wall, a presenter standing near a banner that says 'CO-CREATING UNIQUE CAUSAL AI SOLUTIONS FOR HEALTHCARE', and a whiteboard with handwritten notes.
Close-up of a fingerprint on a metallic surface.

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

  1. Educate the community on the benefits of causal AI over non-causal AI.

  2. Demonstrate how real-world situations give rise to data shifts and model drifts. Suggest how we can adapt to these changes.

  3. Collaborate with clinical communities to create tools that model dataset cause-effect relationships.

Close-up of a computer screen displaying Python programming code with color syntax highlighting.

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

  1. Build specialised “causal agents” that use tools and memory to act as process-guided assistants.

  2. Integrate all three functions into a unified causal agent.

Group of medical professionals, including doctors and nurses in scrubs and white coats, walking down a hospital corridor.

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

  1. Develop a method for finding cause-effect relationships in irregular and non-stationary time-sensitive data.

  2. Use the method to study large electronic health datasets.

A doctor or medical professional examining dental X-ray films on a lightbox, pointing at one of the films with his right hand.

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

  1. Test medical AI algorithms with ‘what if’ scenarios with different data types.

  2. Simulate real-world changes and challenges.

  3. Productively engage with regulatory bodies and policymakers on regulation and policy issues.

Medical professional discussing brain scan results with a patient in an office.

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

  1. Reduce risk prediction uncertainty.

  2. Combine different risk models to increase reliability.

  3. Test approach using Scottish health data.