A team of researchers from the University of Edinburgh and Heriot-Watt University are developing artificial intelligence (AI) and social work robots to detect urinary tract infections (UTIs) earlier.
Image credit: the national robotarium
The FEATHER project aims to reduce the number of serious adverse effects that can result from late or misdiagnosis and to reduce the amount of antibiotics prescribed while clinicians await laboratory results.
The groundbreaking research has received £1.1 million from the UK government through the Engineering and Physical Sciences Research Council, part of UK Research and Innovation, and the National Institute for Health and Care Research (NIHR).
UTIs affect 150 million people worldwide each year, making it one of the most common types of infection. When diagnosed early, it can be treated with antibiotics. If left untreated, UTIs can lead to sepsis, kidney damage, and even death.
Diagnosis, however, can be difficult with laboratory analysis, a process taking up to 48 hours, providing the only definitive result. Early signs of a UTI can also be difficult to recognize as symptoms vary depending on age and existing health conditions. There is no single sign of infection, but a collection of symptoms that can include pain, temperature, frequency of urination, changes in sleep patterns, and tremors.
UTIs are particularly difficult to diagnose in people receiving formal care, and there is significant antibiotic overtreatment in this group as clinicians wait for lab results to return.
To address these concerns, researchers from the University of Edinburgh and Heriot-Watt University are working with two industrial partners in the care sector. Scotland’s National Respite Centre, Leuchie House, and Blackwood Homes and Care are providing user insights to help researchers develop machine learning methods and interactions for social service robots to enable earlier detection of potential infection and trigger an alert for investigation by a clinician.
The project will collect continuous data on the daily activities of individuals in their homes via sensors that could help detect changes in behavior or activity levels and trigger interaction with a social worker robot. The FEATHER platform will combine and analyze these data points to flag potential signs of infection before an individual or career is aware there is a problem. Behavioral changes could include the use of a kettle, a change in walking pace, cognitive function through interaction with a social service robot, or a change in sleep patterns.
The AI and implementation aspects of the project will be led by Professor Kia Nazarpour, Dr Nigel Goddard and Dr Lynda Webb from the University of Edinburgh. Aspects of human-robot interaction will be led by Professor Lynne Baillie, assisted by Dr. Mauro Dragone, from Heriot-Watt University.
Professor Kia Nazarpour, Project Leader and Professor of Digital Health at the University of Edinburgh’s School of Computing, said: “This unique data platform will help individuals, careers and clinicians recognize the signs of potential urinary tract infections much sooner, helping with necessary medical examinations and examinations. Earlier detection enables rapid treatment, improves patient outcomes, reduces the number of people presenting to A&E and reduces costs for the NHS.
“We also believe it will help minimize the amount of antibiotics that are necessarily prescribed as cover while awaiting lab results. As the second most common reason for antibiotics being prescribed, infection contributes significantly to the problem. of growing concern of drug-resistant bacteria, and there is widespread benefit to society in implementing better diagnostics.
Professor Lynne Baillie, National Robotarium Lead on Human-Robot Interaction, Assistive Living and Health, said: “We hope this work will create an additional structured support mechanism for people who live independently. Studies show that there is a significant association between delirium and urinary tract infections in the elderly, and while it is possible for careers to pick up on these signs, we should not rely on observations alone. We work with stakeholders to co-design robot interaction and data collection for machine learning methods to better support longer and healthier independent living.
“Working sensitively and supportively with this vulnerable social group is of utmost importance. By developing the technology in the new Assisted Living Lab at the National Robotarium, we are able to test it in a realistic social care setting.
Kitty Walker, a care recipient and regular guest at Leuchie House, said: ‘The impact of having a UTI can be much more serious than many people realize. Generally my speech is affected which can make it difficult to communicate with people as I normally would. On a more serious note, I have been hospitalized in the past after a late diagnosis of a UTI led to a seizure and required mouth-to-mouth resuscitation.”
It often takes a long time to receive a full diagnosis and receive the correct antibiotics to fight the infection. In the meantime, I am usually prescribed a general antibiotic until my results come back. Being able to spot the early indicators that I have a UTI would take away any anxiety I might feel when I know there is a problem and help reduce the number of different antibiotics I need to take.
Kitty Walker, care recipient and regular guest, Leuchie House
UK Government Minister for Scotland Malcolm Offord said: “Data and AI have the potential to transform the diagnosis and treatment of so many diseases and improve patient outcomes.
“This research will make a big difference in detecting UTIs as soon as possible, and I am happy that residents of the care sector in Scotland are among the first to benefit.
“The UK government is providing £1.1 million in research funding for this project, and through the City Deal we are investing £21 million in the new National Robotorium facilities at Heriot-Watt University.”
Scottish Government Business Minister Ivan McKee said: “I am delighted to see this groundbreaking and innovative work being done in Scotland. By enabling earlier diagnosis and treatment of UTIs, this AI and robotics research can make a vital contribution to improving the provision of health and social care in Scotland, while ensuring the protection of the dignity of individuals.
“The National Robotarium and its Assisted Living Lab will be a key asset for Scotland and the UK, helping people to live well and independently in their communities as they age. The Scottish Government is investing £1.4m in the National Robotarium as part of our wider investment under the £1.3bn agreement for the Edinburgh and South East Region Scotland.
Colin Foskett, Head of Innovation and Research at Blackwood Homes and Care, said: “Understanding how casework AI can be used to better detect UTIs has the potential to improve health and outcomes. well-being of our customers. Early detection of UTIs could prevent hospital admissions, associated decline, and ensure people can continue to live independently for longer.
Building on our existing collaborations with the University of Edinburgh and Heriot-Watt University, this exciting new project will co-design and co-create new products and services with our customers, staff and academic partners. We look forward to exploring this emerging technology and are excited to see the potential of AI for the future of independent living.
Mark Bevan, CEO of Leuchie House, said: ‘The personal, health and financial cost of UTIs is enormous, costing the NHS at least £500million last year, devastating people’s lives and adding great complexity to the provision of increasingly complex adult care.
“Leuchie House is uniquely placed as a national hub with unparalleled access to customers who trust us to manage the sharing of their healthcare data and experience.
“This groundbreaking partnership with guests University of Edinburgh and Heriot-Watt University is just one example of how we are reaching out from our base in East Lothian to improve the lives of people in across Scotland and beyond, developing important new knowledge through our partners’ practical experience and research expertise.
#social #work #robots #early #detection #urinary #tract #infections