EPSRC Seed Corn Projects Round 3

The EPSRC Centre for Predictive Modelling in Healthcare commenced its third round of seed corn projects in April 2018.

Seed corn projects are multidisciplinary research projects that bring together researchers with complimentary expertise, to work on a research problem associated with the expertise of researchers within Centre. A budget of up to £10k is provided for essential consumables for each project.

The projects began with a seed corn incubator event held on 22-23 March 2018 in Torquay, which brought together the research teams and other experts from the University’s commercial team, impact team, public engagement team, and Research Development Managers. Three seed corn projects were funded and a summary of each is provided below:

Dynamic risk prediction models for patients in primary care – pilot study

When patients visit their GP or attend a hospital appointment, clinical staff routinely record health information about the patient. This includes symptoms, diagnoses and test results, enabling NHS clinicians to monitor the condition of the patient. Doctors and nursing staff use their clinical experience to interpret these data. However, it can be difficult to anticipate when patients are at risk of deterioration in their condition. We will analyse the electronic health data for each patient to see if we can uncover patterns. We hope to be able to develop a computer or tablet based tool that will detect changes in the patient’s underlying health and wellbeing at an early stage. This would assist the clinical team in intervening early to ensure the patient receives the most appropriate care and could save lives. We plan to begin by developing a system for older patients and to test it out in a GP surgery setting. This has the potential to reduce unplanned hospital admissions and to help patients manage their condition in the community. If successful, this project could lead to the development of similar tools for patients of all ages.

The project is led by Professor William Henley from the Health Statistics Group at the University of Exeter Medical School, his Medical School colleagues Dr Venura Perera and Professor Chris Hyde and Dr Adam Streeter from the Peninsula School of Medicine and Dentistry. They will team up with Centre Research Fellow Dr Margaritis Voliotis.

Machine learning to optimise DECODE dementia identification clinical software

Many people with dementia are never diagnosed or are diagnosed during the later stages of the condition when a diagnosis may be less helpful. A substantial investment was therefore made in setting up a network of specialist memory clinics across the UK to which patients could be referred by their general practitioners (GPs). However it is a difficult task for GPs to recognise dementia symptoms and respond appropriately in the limited time available. Currently only around half of patients referred to memory clinics have dementia. Waiting times are rapidly increasing as there is simply not enough capacity to see everyone. With the support of the Halpin Trust charity we have developed a DEmentia identification COmputerized DEcision support system (DECODE). We know that our system is considerably more accurate than the current ‘gold standard’ assessment. However new advances in artificial intelligence mean that it should be possible to improve the accuracy of the system even further. Indeed recent publications demonstrate that new approaches to analysing data have the potential to be even more accurate than doctors in detecting conditions such as cancer. The focus of this project is to provide the results that we need to secure major funding to undertake a bigger project. Our ultimate vision is to develop an intelligent system that helps doctors identify people with dementia and reduces unnecessary assessments, benefitting both patients and the NHS.

The project is led Dr David Llewellyn from the University of Exeter Medical School. Project Co-Investigators from the Medical School and Computer Science include Professor William Hamilton, Professor Richard Everson, Professor Edward Keedwell, Dr Sarah Moore and Professor Jonathan Fieldsend. They will team up with Centre Scientific Programmer Dr Diane Fraser and Centre for Biomedical Modelling and Analysis Fellow Dr Ben Evans.

Contribution of GABAergic signalling in the daily electrical excitability of suprachiasmatic nuclei circadian clock neurons

Most of our behaviour, such as our eating habits and sleeping patterns, follows a daily or circadian (24-hour) rhythm. These rhythms are controlled by an electrical “master clock” in the brain that is more active during the day than at night.

We know that the rhythmic activity of the master clock can break down in a number of diseases, during old-age, and when we are exposed to unusual light/dark cycles (e.g. jet-lag, shift-workers). When this occurs the consequences for our mental health and well-being are severe. Remarkably, we still do not know why the rhythms of the master clock break down.

A healthy and rhythmic master clock relies on chemical signals to ensure individual brain cells of the clock are operating in time with each other. In this project, we will be using biology and maths to understand how these chemical signals maintain the clock in a healthy state.

We hope to identify processes within the clock that cause its rhythms to break down. In the future, we would like to use this information to design new therapies that can restore healthy rhythmic activity, which will help to alleviate illnesses known to be associated with circadian rhythm disruption.

The project is led by Dr Mino Belle, from the Institute of Biomedical and Clinical Sciences at the University of Exeter Medical School. He will be working with two Co-Investigators, Dr Casey Diekman from the New Jersey Institute of Technology, USA and Dr Jamie Walker from the University of Exeter. They will work with Centre Research Fellow Dr Leandro Junges and Secondee Dr Francesca Spiga from the University of Bristol.

Leave a Reply