Ruminations

Scanning with Artificial Intelligence

"If you are able to identify inflammation in the arteries of the heart then you can say which arteries ... will cause heart attacks. With the new technology that we have we can achieve this by analyzing simple CT scans."
"[Until now physicians could only see the] tip of the iceberg [with respect to heart risks]."
"It [new scans to detect alterations to blood vessels] is massively important because it will direct treatment and it will save lives."
"A machine can read the scan and give you the accurate information. It can give you the specific risk of the patient. It can tell you that you need treatment or you don't need treatment."
"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, ultimately saving lives."
"We genuinely believe this technology could be saving lives within the next year."
Professor Charalambos Antoniades, Oxford Division of Cardiovascular Medicine

"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 revolutionize 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 personalized care for people with suspected coronary artery disease."
Professor Metin Avkiran, Associate Medical Director, British Heart Foundation

A breakthrough scan can predict the risk of heart attacks up to nine years in advance, experts claim Credit: Getty - Contributor

A new study funded by the British Heart Foundation and published in the European Heart Journal holds great promise in helping to avert heart attacks in potentially huge numbers of people susceptible to heart disease. In Britain alone it is estimated that 350000 people annually could receive benefits from the new protocol which was found to be close to 90 percent accurate.

Oxford University researchers used artificial intelligence to peer "beneath the surface" of CT scans to identify changes to heart-supplying blood vessels.

The new scan protocol could be in operation in at least two years -- doing its part to make certain that high-risk patients are prescribed specific treatments designed for their needs and which are meant to avert potential heart problems. People between the ages 40 to 70 experiencing chest pains, or those who are considered on the basis of conditions such as obesity, smoking or diabetes to be at high risk will be offered the scans.

At the present time, the success rate with routine CT scans reflecting blockages for people experiencing chest pains has been found to be useful in around 25 percent of cases. Most of these patients are sent home without treatment, while some are offered surgery. Many of the patients will at a later date have a heart attack and it is foreseen that the new technology, able to detect a dangerous buildup of fat and scarring around the heart up to nine years before dangerous levels are reached, will be of enormous help in deterring such heart attacks.

In the case of those patients considered to fall into a high-risk category, medication and closer monitoring can be prescribed in prevention of a deadly episode occurring. Deaths from heart attacks and other heart complications remain the number one killer of people on a global scale. Should the new AI-assisted scan prove to have the utility and accuracy that the study indicates, it would represent a great leap forward in decreasing the numbers dying of heart attack.