NIHR Oxford Biomedical Research Centre

Enabling translational research through partnership

MENUMENU
  • About
    • About the NIHR Oxford Biomedical Research Centre
    • A Guide to What We Do
    • Activities during COVID-19
    • Strategic Partnership Board
    • Steering Committee
    • Promoting Equality, Diversity and Inclusion in Research
    • Current Vacancies
    • Contact Us
    • Stay in Touch
  • Research
        • OUR 20 RESEARCH THEMES

        • Antimicrobial Resistance and Modernising Microbiology
        • Cardiovascular
        • Clinical Informatics and Big Data
        • Diabetes and Metabolism
        • Gastroenterology and Mucosal Immunity
        • Genomic Medicine
        • Haematology and Stem Cells
        • Imaging
        • Molecular Diagnostics
        • Multi-Modal Cancer Therapies
        • Multi-Morbidity and Long-Term Conditions
        • Musculoskeletal
        • Neurological Conditions
        • Obesity, Diet and Lifestyle
        • Partnerships for Health, Wealth and Innovation
        • Respiratory
        • Stroke and Vascular Dementia
        • Surgical Innovation and Evaluation
        • Technology and Digital Health
        • Vaccines for Emerging and Endemic Diseases
        • Oxford Biomedical Research Centre activities during COVID-19
  • Patient & Public Involvement
    • About Patient and Public Involvement
      • Our Work with Patients and the Public
      • Learn More About Our Research
      • Patient Involvement Blog
      • External Links
    • For Patients, Carers and the Public
      • Current Listings for Involvement
      • REGISTER INTEREST
      • Patient and Public Involvement Workshops
    • PPI Resources for Researchers
      • PPI Strategy
      • A Researcher’s Guide to PPI
      • PPI Resources for Researchers
      • PPI Briefing Notes
      • PPI Case Studies
      • PPI Advisory Group
      • PPI Events for Researchers
      • Post a PPI Listing
      • Public Engagement for Researchers
      • Public Engagement Case Studies
  • Training Hub
    • Training Hub
    • Fellowships
    • Funding Opportunities
    • Clinical Researchers and Scientists
    • Nurses, Midwives and Allied Health Professionals
    • Next Generation Leaders Programme
    • Useful Links
    • Training and Education Resources
    • Upcoming Training Events & Courses
  • Industry
    • Collaborate with Oxford BRC
    • What Can We Do For Your Organisation?
    • Who Do We Work With?
    • IP and Licensing
    • Contacts for Industry
  • Videos
  • News
  • Events

News

You are here: Home > Cardiovascular > AI identifies ‘fingerprint’ that predicts heart attack risk

AI identifies ‘fingerprint’ that predicts heart attack risk

4 September 2019 · Listed under Cardiovascular

Oxford researchers have developed a new biomarker – derived through artificial intelligence analysis of routine CT scans – that can identify people at high risk of a fatal heart attack at least five years before it strikes.

The researchers, who are supported by the NIHR Oxford Biomedical Research Centre, developed the new fat radiomic profile (FRP) biomarker, using machine learning.

This FRP ‘fingerprint’ detects biological ‘red flags’ in the perivascular space lining the vessels that supply blood to the heart. It identifies inflammation, scarring and changes to these blood vessels, which can all indicate a future heart attack.

When someone goes to hospital with chest pain, a standard component of care is to have a coronary CT angiogram (CCTA), a scan of the coronary arteries, to check for any narrowed or blocked segments.

If there is no significant narrowing of the artery, which is the case in about 75 per cent of scans, people are sent home. Yet some of them will still have a heart attack at some point in the future. There are no methods used routinely by doctors that can spot all of the underlying red flags for a future heart attack.

The findings from the study, which was also funded by the British Heart Foundation (BHF), were being presented at the European Society of Cardiology (ESC) Congress in Paris and published in the European Heart Journal.

Prof Charalambos Antoniades and his team used fat biopsies from 167 people undergoing cardiac surgery. They analysed the expression of genes associated with inflammation, scarring and new blood vessel formation, and matched these to the CCTA scan images to determine which features best indicate changes to the fat surrounding the heart vessels, called perivascular fat.

They then compared the CCTA scans of 101 people, from a pool of 5,487 individuals, who went on to have a heart attack or cardiovascular death within five years of having a CCTA with matched controls who did not, to understand the changes in the perivascular space that  indicate that someone is at higher risk of a heart attack.

Using machine learning, they developed the FRP fingerprint that captures the level of risk. The more heart scans that are added, the more accurate the predictions will become, and the more information that will become ‘core knowledge’.

They tested the performance of this perivascular fingerprint in 1,575 people and found that the FRP was far more effective at predicting heart attacks that any of the tools currently used in clinical practice. The team plan to roll this powerful technology out to health care professionals in the next year, with the hope that it will be included in routine NHS practice alongside CCTA scans in the next 2 years.

Prof Antoniades said: “Just because someone’s scan of their coronary artery shows there’s no narrowing, that does not mean they are safe from a heart attack.

“By harnessing the power of AI, we’ve developed a fingerprint to find ‘bad’ characteristics around people’s arteries. This has huge potential to detect the early signs of disease, and to be able to take all preventative steps before a heart attack strikes. We genuinely believe this technology could be saving lives within the next year.”

Professor Metin Avkiran, Associate Medical Director at the British Heart Foundation, said:  “Every five minutes, someone is admitted to a UK hospital due to a heart attack. This research is a powerful example of how innovative use of machine learning technology has the potential to revolutionise how we identify people at risk of a heart attack and prevent them from happening. “This is a significant advance. The new ‘fingerprint’ extracts additional information about underlying biology from scans used routinely to detect narrowed arteries. Such AI-based technology to predict an impending heart attack with greater precision could represent a big step forward in personalised care for people with suspected coronary artery disease.”

← Heart failure care must address patients’ broader health if survival rates are to improve
Oxford haematologists win national awards to further their research →

News

  • Classification system uncovers new information about ovarian cancers 18 January 2021
  • Ancient gene mutation found to cause rare hereditary condition 18 January 2021
  • Oxford study confirms medium-term impact of COVID-19 11 January 2021
See full news archive

News Categories

Month Archives

Subscribe to the Oxford BRC Newsletter

Keep informed about the work of the Oxford BRC by subscribing to our Mailchimp e-newsletter. It is produced bimonthly and delivers news and information about upcoming events straight to your inbox.

Subscribe Now

Oxford BRC on Social Media

  • Facebook
  • Twitter
  • YouTube

Feedback

We’d love to hear your feedback. Please contact us at obrcenquiries@ouh.nhs.uk

  • Sitemap
  • Data Control and Privacy
  • Accessibility
  • Our Partners
  • Disclaimer
  • Contact

Copyright © 2021 NIHR Oxford Biomedical Research Centre

Cookies

This site uses cookies See our data control and privacy page