Uploaded July 2024 | Updated November 2026, 4 days ago
Professor Charalambos Antoniades and his team at University of Oxford have developed an artificial intelligence (AI) tool that can predict patients’ risk of having a heart attack up to 10 years before it happens.
Every year in the UK, many patients with chest pain who undergo a cardiac CT scan are reassured and discharged, as there are no clear signs of significant narrowings. Despite this, many of these people go on to have a heart attack in the future. Until recently, it was not possible to identify these at risk patients.
In this British Heart Foundation (BHF) funded study, researchers used a new AI tool trained using invisible information found in changes to the fat around inflamed arteries of the heart, as well as other clinical risk factors. They found that those with the highest levels of inflammation in their blood vessels had a more than 10-fold higher risk of cardiac death compared to those with lower levels of inflammation.
In up to 45 per cent of cases, clinicians altered patients’ treatment plans, indicating that this AI tool could be hugely valuable in guiding how patients with chest pain are managed, ensuring early identification and preventative treatment for those at the highest risk.
This technology is now being used in several NHS hospitals, to identify the patients at risk for heart attacks, guiding the use of preventive treatments to those who need them.
This BHF-funded research project was shortlisted for Research Story of the Year as part the BHF Heart Hero Awards 2024.
All information in this video was correct at the time of publishing.
For more information about the BHF Heart Hero Awards, visit bhf.org.uk/heartheroes
If you’ve been inspired by this research project and would like to help fund our lifesaving science, then please visit bhf.org.uk/hhadonate
Professor Charalambos Antoniades and his team at University of Oxford have developed an artificial intelligence (AI) tool that can predict patients’ risk of having a heart attack up to 10 years before it happens.
Every year in the UK, many patients with chest pain who undergo a cardiac CT scan are reassured and discharged, as there are no clear signs of significant narrowings. Despite this, many of these people go on to have a heart attack in the future. Until recently, it was not possible to identify these at risk patients.
In this British Heart Foundation (BHF) funded study, researchers used a new AI tool trained using invisible information found in changes to the fat around inflamed arteries of the heart, as well as other clinical risk factors. They found that those with the highest levels of inflammation in their blood vessels had a more than 10-fold higher risk of cardiac death compared to those with lower levels of inflammation.
In up to 45 per cent of cases, clinicians altered patients’ treatment plans, indicating that this AI tool could be hugely valuable in guiding how patients with chest pain are managed, ensuring early identification and preventative treatment for those at the highest risk.
This technology is now being used in several NHS hospitals, to identify the patients at risk for heart attacks, guiding the use of preventive treatments to those who need them.
This BHF-funded research project was shortlisted for Research Story of the Year as part the BHF Heart Hero Awards 2024.
All information in this video was correct at the time of publishing.
For more information about the BHF Heart Hero Awards, visit bhf.org.uk/heartheroes
If you’ve been inspired by this research project and would like to help fund our lifesaving science, then please visit bhf.org.uk/hhadonate










