A team of researchers from the University of Edinburgh and Heriot-Watt University are developing artificial intelligence (AI) and socially assistive robots to detect urinary tract infections (UTIs) earlier.
mi_viri Shutterstock
2169431287
UTI
The FEATHER project aims to reduce the number of serious adverse outcomes that can result from late or misdiagnosis and reduce the amount of antibiotics that are prescribed while clinicians wait for lab results.
The research has been awarded £1.1 million from the UK Government by 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 annually, 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 loss of life.
Diagnosis, however, can be difficult with lab analysis, a process taking up to 48 hours, providing the only definitive result. Early signs of a UTI can also be challenging to recognise because symptoms vary according to age and existing health conditions. There is no single sign of infection but a collection of symptoms which may 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 industry partners from 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 socially assistive robots to support earlier detection of a potential infection and raise an alert for investigation by a clinician.
The project will gather continual data about the daily activities of individuals in their home via sensors that could help spot changes in behaviour or activity levels and trigger an interaction with a socially assistive robot. The FEATHER platform will combine and analyse these data points to flag potential infection signs before an individual or carer is aware there is a problem. Behaviour changes could include kettle use, change in walking pace, cognitive function through interaction with a socially assistive robot or a change to 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. The Human Robot Interaction aspects will be led by Professor Lynne Baillie, assisted by Dr. Mauro Dragone, from Heriot-Watt University.
Professor Kia Nazarpour, project lead and Professor of Digital Health at the School of Informatics, University of Edinburgh, said: “This unique data platform will help individuals, carers, and clinicians to recognise the signs of potential urinary tract infections far earlier, helping to prompt the investigations and medical tests needed. Earlier detection makes timely treatment possible, improving outcomes for patients, lowering the number of people presenting at A&E, and reducing costs to the NHS.
“We also believe it will help to minimise the amount of antibiotics that are necessarily prescribed as a cover while waiting for lab results. As the second most common reason for the prescription of antibiotics, the infection makes a significant contribution to the increasingly concerning problem of drug-resistant bacteria, and there is widespread advantage to society in implementing better diagnosis.”
Professor Lynne Baillie, lead for the National Robotarium on Human-Robot Interaction, Assistive Living and Health, added: “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 UTI in older adults and, while it is possible that carers will pick up these signs, we should not be relying on observations alone. We are working with stakeholders to co-design the robot interaction and data collection for the machine learning methods to better support longer and healthier independent living.
“Working sensitively and supportively with this vulnerable social group is of the 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.”
