News

AI promises to transform diagnosis of heart disease

Doctors and nurses at the Golborne Medical Centre, in one of the UK’s most deprived areas, crowd together in a small examination room, eager to try out a new stethoscope.

The instrument looks similar to the ones in use at the clinic, which have not been redesigned for about 200 years. This one however has a significant difference: it uses artificial intelligence to detect heart disease instantly.

The Golborne practice, which lies over the railway track from London’s affluent Notting Hill neighbourhood, is one of 200 GP surgeries in north-west London and Wales to receive an AI stethoscope in the UK’s first deployment of the technology in primary care. Nearly half of Golborne’s patients come from non-white minority ethnic groups, who tend to face a higher risk of death from heart disease.

The tool has been licensed by medical regulators for use by general physicians and will be the first AI product that can be relied on to prescribe life-saving medication without the need for a specialist review first.  

AI diagnostics promise to be a game-changer for the UK’s National Health Service and its staff, who are working under enormous strain. As the health service heads into what is expected to be one of its toughest winters, figures in October showed that people were waiting for a near record 7.7mn non-emergency appointments.

If properly designed and tested, AI software can give instant results, is cheap to deploy at scale, and can help prioritise and triage patients on waiting lists. The speed of the technology could help avoid thousands of excess deaths while offering big savings to overburdened health services.

“There are around 300,000 patients on diagnostic waiting lists for heart conditions,” said Mihir Kelshiker, an NHS cardiologist and a clinical fellow in digital health at Imperial College London who is overseeing the deployment of the new tool.

The stethoscope has not evolved over the past 200 years, but now AI technology could help speed up the diagnosis and treatment of heart disease

Experts said that the prevalence of heart disease in the UK was likely to be about double the numbers recorded.

The goal of the AI stethoscope, designed by Mayo Clinic spin-off Eko, is to close these gaps and save the lives of heart patients who end up needing emergency care in hospital. “This is a route to treating patients early while they wait,” said Kelshiker.  

For every patient picked up in primary care, before emergency admission, the NHS saves £2,500. “Scaling that across just one sector in north-west London . . . will immediately unlock around £1mn per year for the system,” said Kelshiker. 

The traditional procedure is often flawed. GPs carry out the first diagnosis, using regular stethoscopes and their clinical judgment. However, common symptoms of heart failure, such as fatigue and abdominal bloating, are very general and often missed during routine 10-minute appointments, which can result in patients becoming very sick.

Any heart condition diagnosis needs a blood test for confirmation as well as a referral to a specialist to perform an electrocardiogram, or a scan. Patients cannot be treated without confirmation from both those tests.

Although the diagnoses are meant to be made within six to eight weeks, it currently takes, on average, eight to 12 months to see a cardiologist in the UK.

“There are around 30,000 excess deaths per year, while they are waiting for these sorts of tests. So that’s where the bottleneck is,” said Kelshiker. “People are dying needlessly.” 

At the Golborne clinic in November, Patrik Bachtiger, an NHS doctor in acute medicine and a digital health researcher, demonstrated the AI stethoscope on Ronald, a patient recovering from a heart attack. Bachtiger, who is Kelshiker’s partner on the project, placed the mouth of the stethoscope on Ronald’s chest for 15 seconds, while the underlying algorithms analysed his heart rhythm and uploaded the results online instantly.

The team behind the push to use the AI stethoscope include Patrik Bachtiger, left, Mihir Kelshiker, Alexei Peters and Melanie Almonte at Imperial College London © Handout

Yasmin Razak, the senior GP at the clinic, was impressed by the tool’s speed and ease of use, and the nuanced measurements made by the software. She has already tried it on a sick patient during a home visit. “We are reaching more of the population who would ordinarily struggle to access healthcare,” she said. “There is potential to do population-level screening here, because it has come to primary care first.”

Doctors will need to confirm the AI diagnosis with a blood test, which usually takes a couple of weeks to complete locally. The drugs can be prescribed straightaway. 

Traditionally start-ups have had to pilot, fund and test their technology with individual hospitals and NHS trusts, the bodies responsible for providing healthcare across a region.

This slows the process to scale up and can become a barrier to adopting the technology, said Kelshiker. 

The AI stethoscope though is no longer at a trial stage and needs no form filling or paper consent requests, Kelshiker told the clinical staff at Golborne, which is in the most deprived ward in London and the second-most deprived in the UK.

“It is the same as offering the patient an ECG or examination with your stethoscope,” he said. “We would ask that you use this on every and any adult that comes into the practice. And the reason for that is to close the detection gap for these heart diseases.”

In 15 seconds, the Eko stethoscope can detect three types of heart disease: heart failure, which accounts for up to 4 per cent of the annual budget of the NHS; atrial fibrillation or irregular heartbeat, which is the biggest cause of stroke; and valvular heart disease.

The Eko in clinical studies was able to detect about 85 per cent of treatable heart failure in patients. It had a 93 per cent specificity against the blood test, which means patients with an AI diagnosis almost always have an abnormal blood test as well.

Razak, who has been using the Eko stethoscope for a few weeks, said the AI version feels less traditional in its design, compared with the others she has used, which might give older physicians reason to pause. It also requires a mobile device to pair with, and regular charging — extra steps she and others will have to get used to.

However, the uptake of the tool across GP practices “speaks for itself”, she said. “I’ve seen the excitement around this stethoscope, everyone sees the value, and the GP surgeries signing up are ones that are normally too busy to make change happen, to try new technology,” she said.

“It is reconnecting GPs to what they love about their jobs in primary care, which is making meaningful differences to their patients’ health.”

Additional reporting from Sarah Neville

Articles You May Like

The second coming of Ed Miliband
Kansas lawmakers fall short in attempt to override tax cut veto
What we must still learn about the great inflation disaster
Chicago’s assistant finance commissioner finds ‘heart, struggle and empathy’ in finance
G7 to target sixfold expansion of electricity storage