New horizons in big data: from surgery risk to Covid-19

It may sound like something from the future, but the BHF has been funding research into artificial intelligence for many years to help improve the diagnosis and treatment of heart and circulatory diseases.

Scans, such as electrocardiograms (ECG), echocardiograms or cardiac MRI, are a particularly rich source of data that can improve diagnosis and guide treatment.

In the 1970s, BHF Professor Veitch Lawrie and Professor Peter Macfarlane in Glasgow first developed methods for automated interpretation of ECGs using computers. Their work led in the 1980s to the “Glasgow Program”, used for the automated analysis of ECGs. It’s still used around the world for more than 20 million ECGs every year.

At the BHF, we’re committed to using data science to find new ways of diagnosing and treating the millions of people living with heart and circulatory diseases in the UK.

In 2017, we joined forces with the Alan Turing Institute, named after the British mathematician and pioneer of computing science. Our BHF-Turing grants bring together data scientists and cardiovascular scientists to solve cardiovascular problems that could be solved with data science techniques, such as machine learning or artificial intelligence. We have funded 12 BHF-Turing projects so far, with a total of £644,000.

Using data to understand risk from surgery

In one project, BHF Professor Gianni Angelini, a heart surgeon at the University of Bristol, and Professor Chris Holmes, a statistician at the University of Oxford, are leading a team of doctors and data scientists to improve risk prediction in people having heart surgery. People who require open heart surgery must be informed about the risks related to the operation. Currently, heart surgeons in the UK calculate the risk using a mathematical model called EuroSCORE. But this model is no longer considered to be accurate in the UK, due to improvements in anaesthetics, surgical and post-operative care. EuroSCORE tends to overestimate the risk of death, which means patients or surgeons may choose not to go ahead with surgery that in reality would have a good chance of success.

The team will apply a type of artificial intelligence called machine learning to a large dataset of all patients undergoing major heart surgery in the UK to create an improved risk prediction score. This will help surgeons better identify patients who are likely to have successful heart surgery.

The BHF Data Science Centre

To untap the potential to improve health through big data, in 2019 we committed up to £10 million to set up the BHF Data Science Centre, in partnership with Health Data Research UK. By helping to bring together large sets of data and applying the latest ways to analyse them with tools like artificial intelligence, the BHF Data Science Centre is a part of the UK’s support for cutting-edge science that will transform patient care.

Patients and the public are important partners in ensuring we achieve this ambition. To deliver on the enormous potential of digital medicine, we need to earn and keep public trust in the safety and security of their data and show the life-saving difference that its use in research will make. The Centre has established a Public and Patient Involvement and Engagement panel and will ensure that there is patient and public representation across its activities.

More recently, the BHF Data Science Centre has contributed to the fight against Covid-19. During the pandemic, the Centre established the CVD-COVID-UK consortium to work specifically in this area. The Centre also works with the Strategic Advisory Group for Emergencies (SAGE) and regularly provides SAGE with updates on the prioritised health data research related to Covid-19. And it is currently using UK-wide data to identify which genetic, demographic and lifestyle factors related to heart and circulatory health are linked to your level of risk from Covid-19.

First published 1st June 2021