‘Game changer’ AI spots hidden 10-year heart attack risk
Technology that can detect if an individual is at risk of a heart attack within the next 10 years has been hailed as a “game changer” by researchers.
The artificial intelligence (AI) model identifies heart inflammation that does not appear on X-ray CT—combinations of X-rays and computer technology.
It is now being piloted at five hospital trusts in Oxford, Milton Keynes, Leicester, Liverpool and Wolverhampton and backed by NHS England.
A decision on whether it can be used routinely within the health service across the UK is expected within months.
A decision on whether it can be used routinely within the health service across the UK is expected within months.
And the company which developed it, Oxford University spinout Caristo Diagnostics, has revealed it is already starting work on using the same technology to prevent strokes and diabetes.
“This technology is transformative and game changing because for the first time we can detect the biological processes that are invisible to the human eye, which precede the development of narrowings and blockages [within the heart],” said Prof Keith Channon, from the University of Oxford.
As part of the trial, patients with chest pain sent for a standard CT scan have their image read by Caristo Diagnostics’CaRi-Heart AI platform.
Further, the algorithm is reviewed by registered professionals for accuracy in identifying inflammation in the coronary and blockages.
Higher levels of inflammation have been shown, through studies, to link with the higher likelihood of cardiovascular disease and fatal heart attacks.
Conclusion
KreativanSays the British Heart Foundation (BHF) has estimated the number of those suffering from heart disease in the UK at 760 million, while government figures revealed an annual cost to the NHS in England is at £7.4bn
The BHF said around 350,000 patients were referred for a cardiac CT scan annually in the UK.
The Orfan study; it enrolled 40,000 patients and it was published in the Lancet, where 80 percent of the patients were sent back to primary care without a well-outlined prevention or treatment plan.
The researchers said they zeroed in on that cohort, with patients who had inflammation throughout their coronary arteries experiencing a 20 to 30 times increased risk of dying of some sort of cardiovascular event in the next decade.
Of the patients in whom the AI was used, in one trial of the BHF-funded, 45% were given medications to mitigate potential future heart attacks or counseled to take up lifestyle interventions.