Jannah Theme License is not validated, Go to the theme options page to validate the license, You need a single license for each domain name.

Artificial intelligence promises to transform heart disease diagnosis

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

The instrument resembles those used in the clinic, which have not been redesigned for about 200 years. This one, however, has a major difference: it uses artificial intelligence to instantly detect heart disease.

The Golborne practice, located above the railway line in London’s affluent Notting Hill district, is one of 200 GP practices in north-west London and Wales to receive an AI stethoscope in the part of the first deployment of this technology in primary care in the United Kingdom. Nearly half of Golborne’s patients are from non-white minority ethnic groups, who tend to face a higher risk of death from heart disease.

The tool has been cleared by medical regulators for use by GPs and will be the first AI product that can be relied upon to prescribe life-saving medications without the need for prior specialist review.

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

If properly designed and tested, AI software can deliver instant results, is inexpensive to deploy at scale, and can help prioritize and triage patients on waiting lists. The speed of the technology could help prevent thousands of excess deaths while providing significant 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 clinical researcher in digital health at Imperial College London, who is overseeing the rollout of the new tool.

The stethoscope hasn’t evolved in the past 200 years, but AI technology could now help speed up the diagnosis and treatment of heart disease.

Experts said the prevalence of heart disease in the UK was probably around double recorded figures.

The goal of the AI ​​stethoscope, designed by Eko, a Mayo Clinic spinoff, is to fill these gaps and save the lives of heart patients who end up needing emergency care in the hospital. “It’s a way to treat patients early while they’re waiting,” Kelshiker said.

For every patient recovered in primary care, before emergency admission, the NHS saves £2,500. “extending this to a single area in North West London. . . will immediately release around £1 million per year for the system,” Kelshiker said.

The traditional procedure is often wrong. General practitioners make the initial diagnosis, using ordinary 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 make patients very ill.

Any diagnosis of heart disease requires a blood test for confirmation as well as a referral to a specialist to perform an EKG or CT scan. Patients cannot be treated without confirmation of these two tests.

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

“There are about 30,000 additional deaths per year, waiting for these kinds of tests. So that’s where the bottleneck is,” Kelshiker said. “People are dying unnecessarily. »

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

Patrik Bachtiger, Mihir Kelshiker, Alexei Peters and Melanie Almonte at Imperial College London
The team behind the use of the AI ​​stethoscope includes Patrik Bachtiger, left, Mihir Kelshiker, Alexei Peters and Melanie Almonte from Imperial College London. © Handout

Yasmin Razak, a senior GP at the clinic, was impressed by the speed and ease of use of the tool, as well as the nuanced measurements made by the software. She has already tried it on a sick patient during a home visit. “We are reaching a larger portion of the population who would normally struggle to access health care,” she said. “It’s possible to do population-wide screening here because it’s primary care first. »

Doctors will need to confirm the diagnosis of IA with a blood test, which usually takes a few weeks locally. Medications can be prescribed immediately.

Traditionally, start-ups had to pilot, fund and test their technology with individual hospitals and NHS trusts, the bodies responsible for providing healthcare in an area.

This slows down the scaling process and can become a barrier to technology adoption, Kelshiker said.

The AI ​​stethoscope, however, is no longer in the trial stage and requires no form filling or paper consent requests, Kelshiker told clinical staff at Golborne, which is in London’s most deprived area and the second most deprived. most deprived in the United Kingdom.

“It’s the same as offering the patient an ECG or an exam with your stethoscope,” he said. “We ask that you use it on every adult who comes to the office. And the reason is to fill the gaps in detection of 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 NHS budget; atrial fibrillation or irregular heartbeat, which is the main cause of stroke; and valvular diseases.

The Eko in clinical studies was able to detect about 85 percent of treatable heart failures in patients. It had a specificity of 93 percent compared to the blood test, meaning that patients with an AI diagnosis almost always also have an abnormal blood test.

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

However, the adoption of the tool by GP practices “speaks for itself”, she said. “I’ve seen the enthusiasm around this stethoscope, everyone sees the value in it, and the GP practices that sign up are usually too busy to make changes, to try new technologies,” he said. -she declared.

“It reconnects GPs to what they love about their work in primary care, which makes a significant difference to the health of their patients. »

Additional reporting by Sarah Neville

Gn En gealth

Back to top button