.png)
Safety in the healthcare context is patient safety. Whilst we are developing AI/ML systems for diagnosing or treating patients and they have very promising performance, we still need to make sure that they don’t compromise patient safety as well. For example, does the system introduce new hazards, and is the risk associated with the new hazard acceptable, can we mitigate it further?
I'm working on safety assurance of machine learning-based systems in healthcare, especially clinical decision support systems. In order to assure such systems, I have been working on explainable AI as well to understand what the systems have learnt and how it can augment clinicians’ decision-making, thus improving clinician diagnostic performance.
Two interesting use cases I have worked on are recommending doses for sepsis treatment and predicting weaning readiness for patients on mechanical ventilation in ICU.
Currently, there is no agreed optimal treatment for sepsis patients, especially regarding the doses of vasopressor and fluid. So it is possible to use reinforcement learning - a type of machine learning - to learn the optimal treatment based on the episodes where doctors treated sepsis patients in the hospital.
The University of York stands apart from other universities. I think one of the strengths of the University is its expertise in safety assurance. If you are doing such research, this is the best place to come.
In terms of safety assurance, York is a very unique place to be. Especially with the AAIP. It brings all sorts of different expertise together. I think it is a very good and exciting programme. It brings different researchers, different stakeholders, and different disciplines together. We need more of this kind of collaboration in the era of AI.
Centre for Assuring Autonomy