We are searching data for your request:
Upon completion, a link will appear to access the found materials.
Technology and AI are increasingly being used to improve our lives, especially in the medical field. Sometimes it's even better than the doctors themselves.
Now, researchers at the University of Oxford have used machine learning to help estimate the health of arteries and have developed a new biomarker to predict heart disease, and prevent future heart attacks.
The researchers claim it can identify people at risk five years before it strikes.
RELATED: NEW STUDY SHOWS DIASTOLIC AND SYSTOLIC BLOOD PRESSURE INDICATE HEART ATTACK RISKS
The typical procedure for those with chest pain is to conduct CCTA or coronary CT angiogram — an imaging test to check the arteries. "If there is no significant narrowing of the artery, which accounts for 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," the press release claims.
Prof. Charalambos Antoniades, Professor of Cardiovascular Medicine and BHF Senior Clinical Fellow at the University of Oxford notes, "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."
This means that just a CCTA test may not be enough and that's where the new AI-based technology comes in, saving lives.
The new biomarker 'fingerprint' is called fat radiomic profile (FRP) and was developed using machine learning. It detects biological 'red flags' in the perivascular space lining of blood vessels. Signs of inflammation, scarring, or any change in these blood vessels can point to the possibility of future heart attacks.
Prof. Antoniades and his team used fat biopsies from 167 patients undergoing heart surgery for this study. Analyzing the expression of genes that indicated changes, they also took note of an increase in inflammation, and scarring and matched them to CCTA scans, to find out perivascular fat changes in the blood vessels.
Then, from a big pool of 5487 individuals, they took CCTA scans of 101 patients, "who went on to have a heart attack or cardiovascular death within 5 years of having a CCTA with matched controls who did not, to understand the changes in the perivascular space which indicate that someone is at higher risk of a heart attack." The changes in the perivascular space lining were then used to predict the risks with machine learning.
They tested the FRP again with 1,575 individuals in another trial and found it was very effective, with higher prediction rates than the current systems in place.
The study notes that with additional CCTA scans, the new technology can become better, with more accurate results — improving 'core knowledge.'
The hope is that the study will help bring awareness, and ultimately, help revolutionize the health care system with this new tool. The plan is to roll out the AI-based technology to health care professionals across the U.K. in routine NHS practice, in conjunction with CCTA tests.
According to the British Heart Foundation's Associate Medical Director, Metin Avkiran, "Every 5 minutes, someone is admitted to a UK hospital due to a heart attack." To avoid such dismal statistics, this revolutionary AI-based technology can help "personalize care" and prevent heart attacks.
Prof. Antoniades notes that "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, ultimately saving lives."
"We genuinely believe this technology could be saving lives within the next year," he declared.
The findings were published in the European Heart Journal, and the study was funded by the British Heart Foundation.