Artificial intelligence could help GPs identify those at the most risk of deadly heart conditions, new research shows.
A Leeds University team developed the tool, which scans GP medical records and alerts doctors to high-risk patients. They can then be called into the surgery to get potentially life-saving treatment.
About eight in ten people with heart and circulatory diseases have at least one other health condition – or so-called co-morbidity.
Scientists trained the programme to look for conditions linked to heart deaths, using health records from 2 million patients.
It identified 400,000 people as being at high risk of dying from a cardiovascular condition such as heart attack or stroke – with three quarters of them dying during a ten-year follow-up.
Artificial intelligence could help GPs identify those at the most risk of deadly heart conditions (stock photo)
For the trial, the AI scanned the records of 82 high-risk patients for symptoms of conditions that lead to heart-related death, including kidney disease and diabetes, by highlighting tell-tale signs, such as breathlessness.
Researchers found the tool identified patients earlier stage and more accurately than current methods, which could lead to improved management of risk factors, ultimately preventing conditions from worsening and reducing the likelihood of heart-related death.
It found many who had undiagnosed conditions or had not received medication that could cut their risk of developing them.
One in five received a diagnosis of kidney disease that would not have been picked up otherwise, according to the findings presented at the European Society of Cardiology congress in London.
More than half of those with high blood pressure were given different medication to better manage their risk of heart-related death.
Dr Ramesh Nadarajah, of the University of Leeds, who co-authored the study, said: ‘Heart-related deaths are often caused by a constellation of factors.
A Leeds University team developed the tool, which scans GP medical records and alerts doctors to high-risk patients (stock photo)
‘This AI uses readily available data to gather new insights that could help healthcare professionals ensure that they are providing timely care for their patients.
‘We hope our research will ultimately benefit patients with heart and circulatory diseases, as well as helping relieve pressure off our NHS systems, as prevention is often cheaper than treatment.’
Researchers said they planned to conduct a larger clinical trial, but hoped the AI tool could be available in the next two years. They anticipate GPs could use it twice a year to monitor patients.
Professor Bryan Williams, chief scientific and medical officer at the British Heart Foundation, which funded the study, said: ‘A quarter of all deaths in the UK are caused by heart and circulatory diseases. This exciting study harnesses ever-evolving AI technology to detect the multitude of conditions that contribute to it.
‘Early diagnosis is key to reducing hospital admissions and heart-related deaths.’
