University of York research project part of lecture series and discussions hosted by IIT Mumbai
Researchers at the University of York are investigating the use of artificial intelligence (AI) and robotics to support medics in triaging patients that visit hospital emergency rooms. They are developing a prototype Diagnostic AI System for Robot-Assisted A&E Triage (DAISY) and have created a ‘test-bed’ – a reproduction of an emergency room triage space in one of the labs of the Institute of Safe Autonomy to understand how DAISY might operate in such a space.
The project investigates the use of AI software to collect patient data including symptoms and vital signs such as body temperature and pulse rate, with a ‘social robot’ guiding patients who consent to use this service in the emergency room.
The social robot will provide instructions on how the patients can use the medical equipment to measure their own vital signs. It is hypothesised that the interaction with the robot at the triage stage could make communication more effective, reducing patient waiting time and easing the workload pressures on medics.
The project will be one of the areas discussed at the new President’s Lecture series, in a talk, by Professor Miles Elsden, Director of the University of York’s Institute for Safe Autonomy (UK), hosted by the Indian Institute of Technology in Mumbai this week, where the University’s Vice-Chancellor Professor Charlie Jeffery will also be speaking about how, through projects like this, universities are a force for public good.
The lecture is part of a week-long visit to the country where the Vice-Chancellor and Professor Elsden meet with senior education, government, and industry leaders to discuss future collaborations in the areas of research, teaching, and industry in India.
The project team – led by Professor Radu Calinescu from the University of York’s Department of Computer Science and Institute for Safe Autonomy, and York and Scarborough Teaching Hospitals NHS Foundation Trust Emergency Medicine Consultant Dr Tunde Ashaolu – will work to understand the social, legal, ethical, empathetic, and cultural norms, concerns and tensions associated with the use of AI and social robotics, working closely with clinicians and patients to understand the challenges involved.
Despite the potential of the technology, there are a number of areas that require further research, specifically relating to patient safety, such as the fact that AI cannot pick-up on some human behavioural clues that doctors often use during triage.
Professor Calinescu, the principal investigator of the project, said, “Robotics and AI are already part of many healthcare systems around the world, but mostly in areas related to deliveries and maintenance.
“Looking to the future, we need a better understanding of how they might support medics in their work, including through interacting with patients. This requires the consideration of a range of factors from multiple perspectives – not just the technical capabilities of these technologies, but also how they are perceived by the end-user.”
“We will explore the benefits and limitations of the technology, and how we might provide the stepping stones to solutions capable of making a positive difference to patient care and the working lives of medics.”
The team is also working with experts at the University’s Law School to understand what ethical and legal questions they may need to ask at the design stage of the DAISY system in order for the technology to be trustworthy and accepted by patients and doctors.
Dr Chiara Picardi, lead researcher and co-investigator on the project, said, “The DAISY system will ultimately produce a report based on questions and measurements made of the patient’s health, which will be sent to a senior doctor for the next stages of triage.”
“We ultimately aim to test the prototype in a real hospital setting, but we are still some way from this technology being deployed in triage systems as a standard part of healthcare.”
“Robotics and AI will be a significant part of the future of healthcare, but our work at the moment is focused on the big question of making them safe, effective, and acceptable for the end-user and medics.”
The research, in collaboration with York and Scarborough Teaching Hospitals NHS Foundation Trust and the University of Southampton, is supported by the UKRI Trustworthy Autonomous Systems programme and the Assuring Autonomy International Programme.