The ExAIDSS project (Explainable AI to ensure trust in clinical Decision Support Systems) is a 5-year research fellowship (March 2023 – March 2028) awarded to Dr Evangelia Kyrmi (QMUL) by the Royal Academy of Engineering. Dr Kyrimi will receive up to £625,000 over the 5-year period to undertake research into XAI.
Objective: Technological breakthroughs have led to the development of sophisticated healthcare systems, but these will only become widely adopted if patients and healthcare professionals have confidence in their recommendations. Without a solution to the problem of user trust and user acceptance of healthcare technologies generally, the undeniable benefits of these systems will never be realised and all our efforts to develop accurate health-AI will be in vain. The ‘right to explanation’ and regulations on algorithmic decision-making already exist. Therefore, the ExAIDSS project focuses on translating causal AI models into explainable AI systems that users can trust and adopt in healthcare. The objectives of the project are:
- Investigate the fundamentals of explanation: Explore fundamental questions that have been neglected, such as what makes an explanation of AI “good”.
- Develop explanation algorithms that incorporate causality: Develop explanation algorithms that produces meaningful causal explanations for various types of reasoning.
- Create user-specific explanation outputs: Design an explanation that recognises who is interacting with it and the dynamics of clinical decision making.
- Create an evaluation protocol: Propose a protocol for evaluating different explanations purposes.
- Integrate the explanation algorithm and representation into existing healthcare digital platforms.