Funded projects

Background

Epilepsy affects the brain, causing repeated seizures. Epilepsy puts people at greater risk of injury and premature death. It can affect people’s social life, work life and mental health.

People with epilepsy say that the unpredictability of seizures is one of the biggest problems.

Intended outcomes

Dr Brigden’s team is working on technology which can provide a forecast on the likelihood of seizure. The technology aims to improve safety by enabling precautions to be taken during high-risk periods. It can also empower individuals to undertake activities during low-risk periods.

The technology relies on the collection of a range of data through smartwatches and smartphone apps. This data is used as input to the seizure forecasting technology. The technology then uses advanced mathematics to estimate how likely a seizure is in the near future.

The team have developed early versions of the seizure forecasting technology. In this project, they will develop a more finished version of the smartphone app and improve the mathematical models.

Project partners

• University of Bristol
• Neuronostics
• Royal United Hospitals, Bath NHS Foundation Trust
• National Institute for Health and Care Research (NIHR) HealthTech Research Centre in Devices, digital and robotics
• Royal Wolverhampton NHS Trust
• Ulster University
• University of Birmingham
• Garmin Health

Hub Research theme

Smartphone and wearable technologies

Background

Addressing loneliness is a public health priority. People who are often lonely are more likely to develop a range of physical and mental health disorders, including heart disease, dementia and depression. Loneliness can also make people’s existing health conditions worse. Certain groups are particularly at risk of loneliness due to health conditions or caring responsibilities.

Intended outcomes

Dr Grey and her team will work with three groups at greater risk of loneliness but who could benefit from technological innovations:

• Neurodivergent teenagers and young adults
• People with Parkinson’s or dementia
• Informal carers of people with Parkinson’s or dementia

They will co-design technology solutions to help them feel more socially connected. Workshops will identify their specific needs; look at potential ways technology could address these needs; and develop prototype solutions.
This work will provide important evidence on the technology needs of these under-served yet high-risk groups and deliver early-stage solutions for development in future. Dr Grey’s team will share their findings with organisations supporting these groups and with academic and industry communities.

Project partners

• University of Bristol
• University of Bath
• The Care Forum
• Play Well for Life

Hub Research theme

Care outside the hospital

Background

Attention Deficit Hyperactivity Disorder (ADHD) is a neurodevelopmental condition characterised by hyperactivity, impulsivity, and inattention, affecting 5-7% of children / adolescents and 2-5% of adults. Young people aged 16-25 with ADHD face increased risks of negative health, educational, and occupational outcomes.

People with ADHD struggle to access healthcare, with linked economic and social disadvantage. Especially during transition to adult services. Where available, treatments typically focus on assessment/medication, without providing psychoeducation. NHS England recommends using technology to improve access, with smartphone apps potentially providing cost-effective and scalable solutions. However, young people with ADHD need solutions that meet their attentional needs and fulfil NHS requirements. Virtual assistants (VA) can significantly increase app engagement and reduce digital exclusion.

Intended outcomes

This project aims to co-develop an artificial intelligence (AI)-powered virtual assistant for diverse young people with ADHD, that is accessible and usable. A multi-disciplinary team, including experts by experience, will co-develop the VA using the Person-Based-Approach. Dr Price’s team will aim to create a solution that is accessible, inclusive and tailored to the unique needs of individuals with ADHD. Outputs will include a minimal-viable-product to improve young people’s lives, peer-reviewed publications, and an NHS Education England toolkit.

Project partners

• University of Exeter
• Torbay and South Devon NHS Foundation Trust
• NHS Devon Integrated Care Board Strategic Clinical Adviser for Neurodiversity in collaboration with One Devon Neurodiversity Transformation Programme

Hub Research theme

Smartphone and wearable technologies

Background

In the UK, more than 2 million people will fall each year with a quarter of those sustaining a serious injury at an estimated annual cost of £4.4 billion. Detecting fall events and the activities that preceded these falls provides an opportunity to predict and better prevent falls in the future. However, capturing falls and activities in the real world is extremely challenging.

Intended outcomes

The primary goal of the project is to determine the feasibility of identifying the movement, interaction with objects and direction of visual attention of older adults in free living, ecologically valid scenarios, from a range of wall mounted and person worn video camera set ups combined with data from body worn inertial measurement units (IMUs).

The project will combine academic and clinical expertise to consider the most effective methods to detect fall events and the activities that preceded these falls. These methods will underpin groundbreaking future work towards predicting and avoiding falls in the future.

Project partners

• University of Exeter
• University of Bristol
• University of Plymouth
• JockeyCam Ltd
• University of Bath
• Bristol Health Partners Academic Science Centre

Hub Research theme

Frailty, fall prediction and fall prevention

Background

Heart failure is a serious condition affecting millions worldwide, leading to high rates of illness, hospitalisations, and death. Patients from ethnic minorities are disproportionately affected, more frequently experiencing hospitalisations and deaths. Cardiac rehabilitation is proven to improve quality of life and reduce hospital visits. However, participation rates remain low, especially among South Asian patients despite their increased need for such care.

Intended outcomes

The REACH-HF programme, currently used in the NHS, offers a home-based alternative to traditional, hospital-based rehabilitation. It includes paper manuals, exercise DVDs, and support from health professionals, involving both patients and caregivers.

Dr van Beurden’s team developed a digital version called D:REACH-HF. An initial study revealed challenges in usability for patients, caregivers, and health professionals. Also, South Asian participants were underrepresented in the development and testing phases.

This project aims to improve D:REACH-HF by making it easier to use and more suitable for patients from diverse ethnic backgrounds. The team will focus on enhancing support for older patients and their caregivers, and ensuring the platform better assists health professionals in delivering the programme. The project will include collaboration with patients and health professionals to ensure the technology meet their needs.

Project partners

• University of Exeter
• South Asian Health Action
• University Hospitals Plymouth NHS Trust
• Health and Care Innovations

Hub Research theme

Care outside the hospital

Background

Stress is a global problem that negatively affects mental and physical health. Stress can increase the risk of disease and has been linked with illnesses such as anxiety, depression, and heart disease. The ability to detect and measure stress can lead to better understanding of its effect on mental and physical health.

Intended outcomes

Dr Clarke’s team will create an ear-based device that can measure how the body changes during stress. Smart earphones can complement or replace smartwatches and can sense a wide variety of bodily changes whilst being less susceptible to movement artefacts which can degrade the quality and validity of the readings.

The team will collect data to train and test a machine learning model that will be able to predict different stress levels. By doing so, it will be possible to detect and measure stress during everyday life, such as when listening to music or at work. This will help to increase understanding of how stress impacts people with, and contributes towards, chronic diseases.

Project partners

• University of Bath
• Royal United Hospitals, Bath NHS Foundation Trust
• TOBI Technologies

Hub Research theme

Smartphone and wearable technologies

Background

The world’s population is aging rapidly. Projections indicate that by 2050, one in six people will be 65+. Many in this group have unique health needs and require careful coordination of a substantial number of resources, especially during their final year of life.

The need for palliative care, which focuses on improving quality of life for those with serious illnesses has been overlooked in many pathways. Unfortunately, older adults often lack integrated care due to gaps between hospital services, primary care, and palliative support.

Intended outcomes

Professor Gartner’s team aims to address this issue through a mathematical modelling approach focussing on the inter-connectedness of palliative care with hospital and primary care services.

The project aims to identify when individuals require palliative care and how to deliver it effectively within the existing healthcare system. This includes creating coordinated care plans with input from doctors, nurses, and other professionals.

Project partners

• Cardiff University
• TEC Cymru
• Bristol, North Somerset and South Gloucestershire Integrated Care Board
• NHS Wales: Aneurin Bevan University Health Board
• NHS Wales: Cardiff and Vale University Health Board
• Velindre Cancer Centre
• Digital Health and Care Wales

Hub Research theme

Service and resource planning

Background

Approximately a third of pregnancies experience complications that can result in restricted growth of an unborn baby, premature birth, stillbirth or maternal death. In these circumstances, a placenta will be reviewed by a specialist pathologist to determine underlying causes and inform clinical care so as to reduce risk in future pregnancies. However, a nationwide shortage of specialist pathologists is leading to huge delays and backlogs in analysing placentas, compromising care that could minimise risk of harm to mother and baby in future pregnancies.

Intended outcomes

To address this resource capacity shortage, Professor O’Hara’s team will develop an artificial intelligence (AI) triage system for digital placenta pathology that pre-screens placentas for normality / abnormalities and prioritises high-risk cases for review by the pathologist.

The system will significantly reduce perinatal pathology workload, enabling faster review of priority cases, and guiding treatment that mitigates risk to mother and baby in future pregnancies.

Project partners

• University of Bristol
• Cardiff University
• Great Ormond Street Hospital

Hub Research theme

Service and resource planning

Background

Orthopaedic elective waiting lists are a well-publicised NHS challenge. While currently at record waits, this problem is not new, and one contributing factor is the need to simultaneously manage unpredictable emergency arrivals with scheduled elective care.

Intended outcomes

In South West Ambulatory Orthopaedic Centre (SWAOC) and Royal Devon University Hospital patients of different complexities are scheduled across two sites. Dr Harper’s team will use a computational method to model complex queuing systems. They’ll combine two methods of to create a robust simulation.

Dr Harper’s team will provide a bespoke user-interface for their NHS partners, enabling experimentation with the model. They will investigate reusability of hybrid model components for wider NHS planning.

Project partners

• University of Exeter
• Royal Devon University Hospital
• South West Ambulatory Orthopaedic Centre

Hub Research theme

Service and resource planning

Background

Critical care data is routinely collected as part of patient care, but for privacy reasons this data cannot be easily shared with researchers or between hospitals. Across the NHS large volumes of this data exist but individual datasets are small and not always easy to access due to their complexity.

Intended outcomes

This project develops methods to unlock the value in siloed healthcare data to realise benefits to patients and the NHS. Dr McWilliams’ team will develop a synthetic data generator – an artificial intelligence (AI) model – that can be trained across small datasets without any patient data having to leave its hospital of origin. The model will generate data about ‘synthetic’ adult and neonatal patients which can be used for research such as training predictive models, whilst preserving patient privacy.

Neonatal intensive care unit provides the prototypical use-case. At University Hospitals Bristol and Weston NHS Trust there are only 592 significantly premature ventilated infants in the local dataset. The team will demonstrate how their synthetic data can be used to train a model that predicts successful extubation for these patients. This is a key part of de-escalating care which is poorly predicted by existing clinical tests.

Project partners

• University of Bristol
• University Hospitals Bristol and Weston NHS Trust
• North Bristol NHS Trust
• Royal Cornwall Hospitals NHS Trust
• University of Exeter

Hub Research theme

Service and resource planning

Background

As people get older there is an increasing risk of falls which may result in serious injury, such as a fracture. The risk of falls is due to a range of different factors. Examples include physical fitness, confusion, chronic diseases, medications, as well as the environment such as where a person lives.

Many of these factors are recorded as data in routine electronic healthcare records. Bringing them together and looking at how they change over time, may help to identify a person who is at a higher risk of falls in the future. Risk changes over time, often increasing but can decrease with earlier interventions, so these data offer not only the reduction of risk but also of which ones might be modifiable earlier.

Intended outcomes

Dr Owusu’s team have obtained a national database of 1 million people with heart problems that brings together data from primary care, hospital, accident & emergency, and outpatients, without identifying patients. They want to use these data to develop and test prediction risk models for falls and fracture and understand how this risk might vary with different levels of health severity, and by gender, socio-economic status and ethnicity.

Project partners

• University of Exeter

Hub Research theme

Frailty, fall prediction and fall prevention

Background

Readmission to hospitals leads to adverse consequences for patients and an increased pressure on healthcare systems that are currently stretched beyond what they have ever been. Virtual Wards can be used to prevent readmission. They are an innovative new healthcare setting, designed to support patients who would otherwise be in hospital.

Virtual Wards are often used in Early Supported Discharge (ESD), where a patient is discharged from hospital sooner than they would otherwise be, whilst still receiving professional medical care from their home. This can benefit the individual, as well as relieving pressure on beds within a healthcare system.

Intended outcomes

Dr James’ and Mr Shaw’s project will develop a machine learning model to predict a patient’s risk of readmission, that is optimised for South West England. Applying the model to ESD patients, they hope to quantify the effect of Virtual Wards on readmission risk, and model an optimal number of days in hospital before ESD, depending on patient characteristics.

If successful, the model can be used to inform operational decision making within hospitals about which patients are most appropriate to receive ESD. Knowing which patients will benefit most from ESD will ensure the value of Virtual Wards, for patients and healthcare systems, is maximised.

Project partners

• University of Bristol
• Bristol, North Somerset and South Gloucestershire Integrated Care Board
• Sirona Care and Health

Hub Research theme

Service and resource planning

Background

Rheumatic and musculoskeletal disorders (RMDs), affect 1-2% of people and cause joint pain and stiffness. These conditions can get better or worse over time. Currently, patients have regular hospital check-ups, but scheduling is often at the wrong time. Some patients are seen when their condition is stable, while others might wait too long when their condition worsens, due to busy clinics. This means patients are not receiving the best care.

Intended outcomes

Since 2018, North Bristol NHS Trust has used an app to track patient reported disease activity in RMDs. Dr Hamann’s project aims to develop an artificial intelligence (AI) tool that uses this patient reported data to predict when patients need to see a doctor.

The goal is to better manage clinic appointments, ensuring patients get timely care based on their needs, and healthcare resources are used most efficiently.

Project partners

• University of Bristol
• Living With Ltd
• Jean Golding Institute
• AI for Collective Intelligence Research Hub

Hub Research theme

Service and resource planning

Background

In the UK, approximately 2500 people become paralysed annually due to spinal cord injury and about 50% of those exhibit tetraplegia. Also, approximately 25% of people with a disability in the UK have limited, or no, digital capability.

Intended outcomes

This project involves the development of a wearable, form-fitted, tongue-computer interface to allow the tongue to control a computer pointing device, giving computer access to individuals unserved by traditional routes. The tongue-computer interface is intended to improve independence for the user, assisting with care outside the hospital and facilitating remote interaction between professionals and patients.

Tongue-based sensors can provide a high number of control inputs and require low physical effort, compared to other types. The project will include: lab testing and refinement of two types of sensor arrays; refinement of relevant sensor electronics; prototype development for a computer pointing device; and, development of fully-encapsulated sensor and electronics, with a wireless computer link.

Project partners

• University of the West of England
• INSPIRE Foundation

Hub Research theme

Smartphone and wearable technologies

Background

Chronic health conditions are often managed in secondary care services that are facing long waiting lists, limited appointment times, and financial pressures. With the increasing availability of mobile devices including smartphones and wearables, patients can collect vast amounts of patient-generated health data (PGHD) outside of the clinic. This includes symptoms, biometrics and treatment adherence, providing clinicians with a more complete picture of patients’ health.

This data has the potential to support more insightful patient-clinician collaboration based on lived experiences; to enable remote clinical review; and ultimately, to improve the efficiency and quality of care.

Intended outcomes

Clinicians and patients have expressed significant interest in using PGHD to manage their health, yet most attempts to review this data in clinic are unsuccessful. Mr Wragg’s and Professor Sengupta’s project will investigate this problem with a case study in axial spondyloarthritis (axSpA) care.

The team will create a model of how the axSpA care pathway works, including activities, data, and outcomes. They will then evaluate the use of a PGHD dashboard in axSpA care, to understand the barriers surrounding its uptake and impact across all parts of the model. From this, they will create a framework that will enable the systematic evaluation of complex dashboards in real-world clinical workflows.

Project partners

• University of Bristol
• Royal United Hospitals, Bath NHS Foundation Trust
• The Bath Institute for Rheumatic Diseases
• UCB pharmaceuticals
• Inhealthcare

Hub Research theme

Smartphone and wearable technologies