AI heart attack scans could become commonplace shortly

A team from Oxford University believes that technology that may reveal secret CT scan data may be able to save lives

In the UK, an artificial intelligence system that can identify people who are at risk of heart attacks up to ten years in advance may soon be put into use. The National Institute for Health and Care Excellence (Nice) is now reviewing this technology, which has the potential to save many lives each year. An announcement about the NHS’s acceptance of this technology is expected by the end of the year.

Researchers working on the project are also creating AI algorithms to predict stroke risk and identify people who may have illnesses like diabetes.

The head of the Orfan (Oxford Risk Factors And Non-Invasive Imaging) project, Prof. Charalambos Antoniades, said, “This technology has been trialled at multiple UK hospitals with highly promising outcomes.” “Upon nationwide implementation, it could prevent numerous early heart attacks or heart disease-related deaths.”

More than 300,000 Britons, according to Antoniades, get severe chest pains every year and get CT scans to check for heart problems such artery blockages. Less than 20% of those who underwent scanning, however, had major coronary artery constriction or other blockages.

“At least 80% of the remaining people show no anomalies. “They are reassured and sent home, frequently without prescription drugs,” said Antoniades, the University of Oxford’s Chair in Cardiovascular Medicine. “Yet, these reassurances are frequently unfounded.”

As a matter of fact, about two thirds of those who are considered “safe” suffer from major, and occasionally deadly, cardiac events like heart attacks. “Clearly, signals indicating real danger have eluded us in our scans,” he said. “This constitutes a substantial healthcare issue, and we are convinced that AI is the ideal technology to address it.”

The study, which was just published in The Lancet, was carried out by a group from Oxford University’s Radcliffe Department of Medicine with the goal of finding anomalies that are missed by routine CT (computed tomography) scans. With this knowledge, physicians might provide patients with preventive care, such anti-inflammatory drugs.

One major problem, according to Antoniades, was that CT scans were unable to identify arterial damage brought on by inflammation. “Our innovation was using AI to enhance our CT scan images and uncover hidden information, which allowed us to see the full amount of the damage. This was not something we could see before, but we can now.”

This approach uses data on the characteristics of coronary plaques and changes in the adipose tissue surrounding inflammatory arteries to provide important new information about the state of our heart arteries. “Essentially, these readings indicate the absolute risk of a patient experiencing a fatal cardiac event over the next 10 years,” he said.

These risk variables were first identified using case studies conducted in the United States. However, 40,000 patients from UK hospitals have now been used to validate the data.

Our results were clear-cut. Individuals who had high levels of inflammation in their coronary arteries were also shown to be extraordinarily vulnerable to serious cardiac problems, including heart attacks. We have discovered a way to identify the unseen elements that lead to heart attacks.

The British Heart Foundation funded the study, which showed that in 45% of cases, doctors changed a patient’s course of treatment based on information gleaned from AI analysis. High dosages of statins or medications like colchicine, which are known to lower the risk of cardiovascular disease, are among these treatments.

Antoniades added, “We also intend to increase the implementation of this technology that was developed in the UK in the US, where the Food and Drug Administration is now reviewing it, and in Europe, where it has already received approval for clinical usage.