Facilitating health and wellbeing by developing systems for early recognition of urinary tract infections - Feather
Lead Research Organisation:
UNIVERSITY OF EDINBURGH
Department Name: School of Informatics
Abstract
Urinary tract infections (UTI) are one of the most common types of infection, impacting more than 92 million people worldwide. When diagnosed early, UTI's can readily be resolved with antibiotics. However, left untreated, it can lead to urosepsis (>1.6 million deaths), kidney damage and ultimately death.
Identifying the early symptoms of a UTI can be challenging, symptoms are different in younger and older people and people with underlying health conditions. In addition, there is no one symptom but a collection of symptoms that indicate a person has a UTI. These include changes to urine: colour, smell, frequency; incontinence, pain, confusion, agitation delirium, temperature, shaking and changes in sleep. This concoction of symptoms is what makes identifying the signs of a UTI difficult for the person concerned and/or their carers.
This project will gather data about the activities of an individual in their home on a continuous basis. By having data on activities of daily living, it is possible to identify changes. The Feather platform will combine these data points to recognise the emergence of a UTI. This is in fact quite difficult for an individual themselves or a carer to see. Thus, the Feather project will be able to raise an alert for investigation of a UTI, before a person could do it themselves, enabling early intervention, to get appropriate treatment quickly. For example, the following can all be indicators of behaviours that are impacted by the symptoms of UTI's, patterns for activities of daily behaviour, e.g. kettle use, change in walking pace, cognitive function through interaction with an intelligent agent, e.g. an embodied robot.
The Feather project could enable a GP to have the time to wait for lab results to urine tests to ensure appropriate prescription of antibiotics, reducing the cost to the NHS of prescriptions and improving outcomes for the patient. Early diagnosis should reduce the number of patients presenting at A&E and reduce the number of cases developing to urosepsis, kidney failure and ultimately death.
Working with stakeholders, we will co-design, co-implement and co-evaluate the Feature project.
Identifying the early symptoms of a UTI can be challenging, symptoms are different in younger and older people and people with underlying health conditions. In addition, there is no one symptom but a collection of symptoms that indicate a person has a UTI. These include changes to urine: colour, smell, frequency; incontinence, pain, confusion, agitation delirium, temperature, shaking and changes in sleep. This concoction of symptoms is what makes identifying the signs of a UTI difficult for the person concerned and/or their carers.
This project will gather data about the activities of an individual in their home on a continuous basis. By having data on activities of daily living, it is possible to identify changes. The Feather platform will combine these data points to recognise the emergence of a UTI. This is in fact quite difficult for an individual themselves or a carer to see. Thus, the Feather project will be able to raise an alert for investigation of a UTI, before a person could do it themselves, enabling early intervention, to get appropriate treatment quickly. For example, the following can all be indicators of behaviours that are impacted by the symptoms of UTI's, patterns for activities of daily behaviour, e.g. kettle use, change in walking pace, cognitive function through interaction with an intelligent agent, e.g. an embodied robot.
The Feather project could enable a GP to have the time to wait for lab results to urine tests to ensure appropriate prescription of antibiotics, reducing the cost to the NHS of prescriptions and improving outcomes for the patient. Early diagnosis should reduce the number of patients presenting at A&E and reduce the number of cases developing to urosepsis, kidney failure and ultimately death.
Working with stakeholders, we will co-design, co-implement and co-evaluate the Feature project.
Publications
Hunter E
(2026)
Physiology of everyday sleep and physical activity: An exploratory mixed-methods study of multi-sensor wearables for infants and toddlers
in Behavior Research Methods
Ju W
(2025)
Smart Wearable TENS Device for Home-Based Overactive Bladder Management.
in IEEE transactions on biomedical circuits and systems
Ju W
(2025)
Benchmarking TENSmini for Neuromodulation via Tibial Nerve Stimulation.
in IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society
Lister E
(2024)
An Open-Source Neurodynamic Model of the Bladder
McConnell-Trevillion A
(2025)
Low-Frequency Tibial Neuromodulation Increases Voiding Activity - a Human Pilot Study and Computational Model
McConnell-Trevillion A
(2024)
Low-Frequency Tibial Neuromodulation Increases Voiding Activity - a Human Pilot Study and Computational Model
| Description | Several methodologies have been deployed in real-life setting that enables continuous gait monitoring as well as human robot interaction |
| Exploitation Route | Part of the work as been adopted by the industry and has enabled other research |
| Sectors | Healthcare |
| Description | The MoveR wearable platform, developed at the University of Edinburgh, is a low-cost digital health device designed for continuous monitoring of human movement and physiology in real-world environments. The system integrates multimodal sensing, including inertial motion tracking, cardiovascular monitoring (PPG), and physiological arousal measurements, combined with real-time machine-learning analytics and a companion mobile application for data capture and feedback. MoveR enables scalable measurement of behaviour and health outside laboratory settings and has been deployed in multiple interdisciplinary research studies in digital health and rehabilitation. The technology has demonstrated translational potential and is currently progressing toward industrial licensing, enabling broader deployment in healthcare and digital health applications. |
| First Year Of Impact | 2025 |
| Sector | Healthcare |
| Description | CHAI - EPSRC AI Hub for Causality in Healthcare AI with Real Data |
| Amount | £10,288,789 (GBP) |
| Funding ID | EP/Y028856/1 |
| Organisation | Engineering and Physical Sciences Research Council (EPSRC) |
| Sector | Public |
| Country | United Kingdom |
| Start | 02/2024 |
| End | 01/2029 |
| Title | System to support data collection of bio-vitals relevant to the detection of urinary tract infection |
| Description | The team at Heriot-Watt University has developed a system to facilitate people's contribution to a dataset used for investigating ways to detect the early outset of urinary tract infection by monitoring a set of bio-vitals. The system combines existing digital healthcare devices and associated mobile apps, with a 3D printed holder for urine advisory strips and with a software pipeline for the secure and anonymous upload and interpretation of heart rate variability, body temperature and urine analysis. |
| Type Of Material | Improvements to research infrastructure |
| Year Produced | 2024 |
| Provided To Others? | No |
| Impact | The secure framework has been approved as a data collection tool by the Ethics committee at Heriot-Watt University and it is being reviewed as part of a NHS ethics application. The framework is being used to collect a small dataset (using up to 20 participants), as a way to validate an UTI model being developed on a much larger, open source dataset, and to build knowledge on the acceptability and feasibility of this type of self-health monitoring, ultimately to inform the design of an easy-to-use integrated system. |
| Title | lower urinary tract simulator |
| Description | This repository contains a Python-based model that simulates the dynamics of the bladder, sphincter, and kidney, using normalised neural signals to predict pressure and volume of the bladder. For more detailed mathematical explanations, please refer to the paper: An Open-Source Neurodynamic Model of the Bladder. DOI: 10.1101/2024.11.21.624716 |
| Type Of Material | Computer model/algorithm |
| Year Produced | 2024 |
| Provided To Others? | Yes |
| Impact | Stochastic Kidney Function: Reflects natural fluctuations in urine production throughout the day, incorporating randomness to account for biological variability. Neural Input Modeling: : Features a built-in parameter-based model to simulate neural signals from the brain. This allows for simple modeling of neurological conditions and their effects on the lower urinary tract, as well as the use of external neural models to stimulate the detrusor and sphincter muscles. |
| URL | https://github.com/MoveR-Digital-Health-and-Care-Hub/lower-urinary-tract-sim |
| Description | Blackwood Homes |
| Organisation | Blackwood |
| Country | United Kingdom |
| Sector | Charity/Non Profit |
| PI Contribution | We have worked with Blackwood Homes to undertake requirements gathering and recruit participants for evaluations of early prototypes of our system. |
| Collaborator Contribution | Blackwood Homes has worked with us to provide data for requirements gathering and recruit participants for evaluations of early prototypes of our system. |
| Impact | Nault, E, Baillie, L & Bettosi, C 2024, Designing a Socially Assistive Robot for the Early Identification of Urinary Tract Infections. in 33rd IEEE International Conference on Robot and Human Interactive Communication (ROMAN). IEEE, pp. 1170-1176, 33rd IEEE International Conference on Robot and Human Interactive Communication 2024, Pasadena, California, United States, 26/08/24. https://doi.org/10.1109/ro- man60168.2024.10731395 |
| Start Year | 2024 |
| Description | Feasibility Of Robotic Assisted Monitoring Of Long Term Condition In Primary Care |
| Organisation | NHS Tayside |
| Country | United Kingdom |
| Sector | Public |
| PI Contribution | NHS Tayside and us have collaborated to scope and write a proposal to the TayTechHealth accelerator Grand Challenge fund. |
| Collaborator Contribution | NHS Tayside and us have collaborated to scope and write a proposal to the TayTechHealth accelerator Grand Challenge fund. |
| Impact | We submitted a proposal, requesting £35,049.30 for Heriot-Watt to develop and test a robotic application to facilitate self-health monitoring. |
| Start Year | 2025 |
| Description | Demonstrations of robotic technology at the National Robotarium for MSc Students from Napier University |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | Local |
| Primary Audience | Postgraduate students |
| Results and Impact | In February 2024, 46 occupational therapy and physiotherapy second-year MSc (pre reg) students attended an immersive workshop to learn about and gain training in various robotic technologies at the National Robotarium. As part of the event, the team at Heriot-Watt University illustrated their work as part of the Feather project and demonstrated the use of the temi robot to help people to measure their body temperature, and measure their heart-rate variability using a wearable device while doing a light exercise under the robot's supervision. |
| Year(s) Of Engagement Activity | 2024 |
| Description | Focus group |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | Local |
| Primary Audience | Study participants or study members |
| Results and Impact | Focus group in care home, including interactive demonstration of robotic technology used to facilitate self-health monitoring using digital healthcare devices to collect evidence for the early detection of urinary tract infection. |
| Year(s) Of Engagement Activity | 2025 |
| Description | Leuchie House Charity Technology Showcase and Fund Raiser |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Public/other audiences |
| Results and Impact | The Leuchie House Charity Technology Showcase and Fundraiser event was to raise awareness of the charitys technology use and how they enganged with technology research, such as this project, that would benefit their patients and carers. They were wishing to raise that awareness with their Patron HRH Princess Anne and their donors. The FEATHER team demoed some early scenarios of use on a robot and answered questions about the research teams engagement with Leuchie House. |
| Year(s) Of Engagement Activity | 2023 |