EU approval for new AI heart attack prediction technology from Oxford-based Caristo


Caristo Diagnostics, a spinout from the Department of Cardiovascular Medicine, Oxford University, which has developed a vascular imaging technology platform that can predict risk of major cardiometabolic diseases, has received it’s CE mark accreditation, meaning it can be used by doctors across the UK and Europe, and can be rolled out across the NHS.

CaRi-Heart transforms the diagnostic accuracy of routine CT scans and can predict a patient’s risk of a heart attack – years in advance.

This follows Caristo completing a multi-million-pound investment round last month, led by BGF and existing investors including Oxford Sciences Innovation (OSI), Longwall Ventures and the Oxford Technology & Innovation Fund (OTIF).

The first-of-its-kind technology, CaRi-Heart, was developed by Caristo Diagnostics and has the power to detect ‘invisible’ risk in people with possible heart disease by using routine heart scans already performed in clinical practice.

Those identified at high risk of a future heart attack can be given personalised medication and monitored more closely to prevent a life-threatening event.

Each year in the UK there are hundreds of thousands of hospital visits for people experiencing chest pain. A coronary CT angiogram (CCTA) scan is the first-line test for patients with angina and is used to check for any narrowed or blocked segments in blood vessels that supply the heart. Every year around 350,000 people in the UK have a CCTA scan. However, 75 per cent of these scans do not show significant narrowing of the arteries and so people are sent home without treatment, yet some of them will have a heart attack at some point in the future. Until now, there has been no way for doctors to detect all the underlying red flags that could lead to a future heart attack.

CaRi-Heart is a new technology that performs a deeper dive into the CCTA scans to reveal the ‘red flags’ beneath their surface, identifying the ‘ticking time bomb’ arteries that cause heart attacks. It works by using AI and deep-learning technology to produce a Fat Attenuation Index Score (FAI-Score®), which accurately measures inflammation of blood vessels in and around the heart.

The scientific work that underpins Caristo Diagnostics was initially carried out by BHF researchers at the University of Oxford. Caristo supported the work through a number of translational awards, aimed at developing new technologies for direct patient benefit.

The technology was validated in a landmark BHF-funded study involving around 4,000 patients who were followed up for nine years after their original CCTA scan. They found that people with an abnormal FAI were up to nine times more likely to die of a heart attack in the next nine years than those with normal FAI readings. The study also showed that at least one third of patients who underwent a routine CCTA and were initially considered low risk had a much higher risk after CaRi-Heart® was applied to their scan. The patients would have therefore received a more targeted treatment based on the new technology.

Now, the researchers are looking at ways to use this ground-breaking technology to better predict an individual’s risk of developing stroke and diabetes by analysing routine CT scans. They are also directing their expertise towards the Covid-19 pandemic by developing an AI tool to specifically identify Covid-19 patients who are at high risk of having a future heart attack or stroke.

Caristo also has a pipeline of other products under development that build on the important biological discoveries made in Oxford. They have received funding from NIHR (NHS AI award), Horizon 2020, and the British Heart Foundation to develop products that predict stroke, atrial fibrillation, and diabetes risk, respectively. They hope to bring all of these products to patients in the next few years.