CE mark accreditation for new AI heart attack prediction technology
A heart attack prediction tool based on artificial intelligence (AI) technology has received EU approval. The tool, CaRi-Heart®, performs an analysis on a coronary CT (CCTA) scan and uses AI and deep-learning technology to produce a Fat Attenuation Index Score (FAI-Score®). The FAI-Score® represents the inflammation of blood vessels in and around the heart. The analysis can be performed on any CT heart scan. The tool can thereby identify people at high risk of a heart attack before it strikes using routine CCTA scans. People identified at high risk can be given a more targeted treatment and monitored more closely to prevent a future heart attack event.
The technology was validated in a study funded by the British Heart Foundation (BHF) . This study followed ~4000 patients for nine years after their CCTA scan. At least one third of patients who underwent a routine CCTA and were initially considered to be at low risk, received a much higher risk score after the AI tool was applied to their CCTA scan. Moreover, patients with an abnormal FAI were up to nine times more likely to die of a heart attack within nine years compared to those with a normal FAI.
Researchers are currently investigating whether this technology can also better predict the risk of developing stroke and diabetes by analyzing routine CT scans. In addition, an AI tool is being developed to identify COVID-19 patients who are at high risk of having a future heart attack or stroke.