The Alan Turing Institute and the British Heart Foundation (BHF) have awarded funding totalling over £550,000 to six new research projects which aim to generate data science solutions with the potential to transform how we diagnose and treat many heart and circulatory conditions.
According to the British Heart Foundation, coronary heart disease remains the number one cause of early deaths in the UK and healthcare costs as a result of heart and circulatory diseases stand at £7.4 billion per year.
The announcement follows an open funding call for projects, to promote the use of multi-disciplinary research to generate data science solutions to key cardiovascular issues. The projects involve collaborative research between data scientists and cardiovascular investigators.
Six projects were selected which demonstrate maximum impact in the fight against cardiovascular disease. They include exploring the type and frequency of physical activity which is most beneficial for cardiovascular health; analysing how genetic traits can influence an individual’s risk of heart attacks or strokes; developing a risk predictor tool which will predict the risk of heart attacks and bleeding for individual patients in order to tailor treatment following a heart attack; using machine learning to personalise the risk posed by factors such as smoking and high blood pressure to improve the accuracy of intervention and treatment.
The findings of some of the projects will potentially influence practice across the UK, Europe and worldwide.
The projects will be undertaken as part of the Turing’s Health research programme, which aims to accelerate the scientific understanding of human disease and improve human health through data-driven innovation in AI and statistical science.
Professor Metin Avkiran, Associate Medical Director at the British Heart Foundation, said:
“The UK is blessed with many world-class heart and circulatory disease researchers, spanning a wide range of disciplines. But, as we enter the era of digital medicine, there’s a growing need to foster excellence in applying data science solutions to cardiovascular problems. At the BHF, we recognise the enormous potential of data science and want to create an environment where we can realise that potential.
“This funding is a major step towards using data science to make transformational improvements in preventing, detecting and treating heart attacks and strokes, as well as other heart and circulatory diseases.”
The funded projects are:
Around 130 regions of the human genome are now known to influence an individual’s risk of heart attacks or strokes, but current methods lack the ability to show how certain genes are involved. This project involves the development of new fine-mapping learning tools that can deal with the complexities of today’s genetic datasets. This work will aid the understanding of what causes cardiovascular diseases and will help drug-makers identify potential targets to make new treatments, which are more likely to be effective.
Researchers: Leonardo Bottolo (Turing Fellow, University of Cambridge), Adam Butterworth (University of Cambridge), Sylvia Richardson (Turing Fellow, University of Cambridge), James Peters (University of Cambridge).
It is not known exactly how much or what type of physical activity is best for reducing the risk of heart disease, and how often it should be done. This work could help build a better understanding the types and patterns of activity that are beneficial for cardiovascular health using machine learning techniques.
Researchers: Aiden Doherty (University of Oxford), Chris Holmes (Programme Director for Health at the Turing, Turing Fellow, University of Oxford), Tom Gaunt (Turing Fellow, University of Bristol), Louise Millard (University of Bristol), Derrick Bennett (University of Bristol).
This project will use advanced computational techniques to develop, train, and test a risk predictor tool that provides accurate estimates for individual patients following a heart attack. The predictor tool will be able to estimate the risk of major adverse cardiac events and bleeding for an individual patient. Such a tool could support doctors when prescribing drugs to ‘thin’ the blood following a heart attack; to identify patients where a short course of treatment is required to avoid unwanted severe side-effects, or those for whom prolonged treatment is truly in their best interests.
Researchers: Catalina Vallejos (Turing Research Fellow, University of Edinburgh), Nick Mills (University of Edinburgh), Ioanna Manolopoulou (Turing Fellow, UCL), David Newby (University of Edinburgh), Catherine Stables (University of Edinburgh), Chris Russell (Turing Fellow, University of Surrey).
Measurements of certain 'risk factors'—such as older age, being male, smoking, high blood pressure, high cholesterol—are currently used to estimate how likely someone is to develop cardiovascular disease, and to prioritise people for intervention. However, the personalised use of these risk factors could be greatly improved by the application of machine learning methods. These techniques will allow for systematic identification of patients at high risk of future disease, improving the accuracy of intervention and treatment. Such advances will have benefits for both public health and healthcare resource use.
Researchers: Angela Wood (Turing Fellow, University of Cambridge), Emanuele Di Angelantonio (University of Cambridge), Mihaela van der Schaar (Turing Fellow, University of Cambridge).
Most heart attacks and strokes occur when a clot forms inside a blood vessel blocking blood flow, caused when blood cells become active and clump together. The study of blood cells is therefore essential to understand processes leading to heart attack or stroke. This project will use algorithms to analyse cell properties from images of blood cells from 30,000 healthy people. This work aims to improve understanding of blood related risk factors, and possible treatments, for heart attacks and strokes.
Researchers: William Astle (University of Cambridge), John Aston (University of Cambridge).
The processes that keep the heart beating healthily involve chemical signals, i.e. the movement of calcium, which are controlled by specific proteins. Precise modelling of these variable processes has been limited in the past, making it difficult to tailor drug treatments. This project aims to develop new ways of obtaining a more complete statistical description of calcium handling in the heart, in order to better predict the effects of drugs, improve treatments, and understand the conditions that lead to heart disease.
Researchers: Steven Niederer (King’s College London), Mark Girolami (Programme Director for Data-Centric Engineering at the Turing, Imperial), Chris Oates (Data-Centric Engineering Group Leader at the Turing, Turing Fellow, Newcastle University), Pawel Swietach (University of Oxford), Marina Riabiz (King's College London).
Notes to editors:
The Alan Turing Institute
Mary Dolan - Marketing & Communications Manager
The British Heart Foundation
Press office: 020 7554 0164 (07764 290 381 – out of hours)
British Heart Foundation
Heart and circulatory diseases kill 1 in 4 people in the UK. For over 50 years we’ve pioneered research that’s transformed the lives of people living with heart and circulatory conditions. Our work has been central to the discoveries of vital treatments that are changing the fight against heart disease. But so many people still need our help. From babies born with life-threatening heart problems to the many Mums, Dads and Grandparents who survive a heart attack and endure the daily battles of heart failure. Every pound raised, minute of your time and donation to our shops will help make a difference to people’s lives.
Find out more at bhf.org.uk