This AI tool can predict heart attack risk in individuals up to 10 years in future

This AI tool can predict heart attack risk in individuals up to 10 years in future

Image for representative purpose

Artificial Intelligence could be used to detect potential risks of heart attack in individuals up to 10 years in future, according to a study by researchers at the University of Oxford.

The study focused on improving the accuracy of cardiac CT scans, where it is still a tricky task for experts to predict heart risks and detect the narrowing of arteries.

Prof Charalambos Antoniades, chair of cardiovascular medicine at the BHF and director of the acute multidisciplinary imaging and interventional centre at Oxford, was quoted by the Guardian as saying, “Our study found that some patients presenting in hospital with chest pain – who are often reassured and sent back home – are at high risk of having a heart attack in the next decade, even in the absence of any sign of disease in their heart arteries.”

“Here we demonstrated that providing an accurate picture of risk to clinicians can alter, and potentially improve, the course of treatment for many heart patients,” he added.

Lack of accuracy in CT scans

Approximately 350,000 individuals in the UK undergo CT scans annually. However, the British Heart Foundation (BHF) notes that a considerable number of patients succumb to heart attacks later, which shows the detection of subtle, undetectable narrowings of veins is still a major puzzle.

Watch:Elon Musk's new chatbot, AI decoding pet language, and more

In a study involving data from over 40,000 patients receiving routine cardiac CT scans at eight UK hospitals, researchers observed outcomes over a median follow-up period of 2.7 years.

The AI tool shows promising results

The AI tool developed by scientists was tested on 3,393 patients across nearly eight years, and surprisingly, it accurately predicted the risk of heart attacks.

Doctors were given recommendations for 744 patients based on the assessment by the AI bot, leading to altered treatment plans for 45 per cent of them.

Notably, patients with "significant" artery narrowings were found to be more prone to severe heart attacks.
Surprisingly, twice as many patients with no notable narrowings also experienced heart attacks, occasionally resulting in fatalities.

According to Antoniades, the AI tool is now expected to be implemented across the National Health Service (NHS) facilities in the country.

(With inputs from agencies)