A smart stethoscope combined with an AI algorithm could enable earlier diagnosis of heart failure and better patient outcomes, all at a lower cost.
Researchers at the National Heart and Lung Institute and Imperial’s Cardiac Engineering Center complete the first-ever NHS study to assess artificial intelligence (AI) technology for the detection of failure heart rate at the point of care.
Heart failure is a condition in which the heart cannot pump blood efficiently. It carries a higher risk of death than most cancers and is increasingly common, affecting 2% of the UK population and consuming 4% of the NHS budget.
This tool can save the NHS time and money and unlock major benefits for patients through early diagnosis Doctor Patrik Bachtiger
Reliable diagnosis of heart failure is a major challenge for general practitioners because symptoms, such as shortness of breath, are associated with many other conditions. Most heart failure patients are diagnosed in hospital after a series of tests, highlighting the need for a point-of-care screening tool.
The study published in The Lancet Digital Health and led by Professor Nicholas Peters, Head of Cardiac Electrophysiology, recruited more than 1,000 NHS patients at seven sites in North West London, including Imperial College Healthcare hospitals. NHS Trust (ICHNT).
Using a “smart” stethoscope – the Eko DUO device – which records electrocardiograms (ECGs) as well as heart sounds, the researchers applied the new AI algorithm that determines in 15 seconds whether the action pumping capacity of their heart is weakened, providing an immediate diagnosis of heart failure.
The study team found that the AI ââtechnology exhibited 91% sensitivity and 80% specificity compared to routine diagnostic tests which are invasive and expensive.
Dr Patrik Bachtiger, NHLI digital health clinical researcher and lead author of the paper, said: âThis superhuman ability to screen patients at any point of care, including general surgery, can overcome reality. unacceptable% of patients with heart failure are currently diagnosed during emergency hospitalization. The current clinical journey is simply missing too many patients, leaving them undiagnosed until they are seriously ill. This tool can save the NHS time and money and bring major benefits to patients through early diagnosis and initiation of effective treatments. “
“Game change for general practitioners”
Early diagnosis is a key determinant of the effectiveness of heart failure treatments on which symptoms, quality of life and survival depend. A lack of effective tools for GPs to confirm or rule out heart failure leads to late diagnosis, significantly higher NHS costs and earlier death in 80% of cases.
Professor Nicholas Peters said: âThis tool is a game-changer because our study shows that general practitioners will be able to use it in a way that matches how they examine patients to reliably rule out or rule out heart failure. that time. The result will be earlier diagnosis and treatment, avoidance of unnecessary and costly tests in those in whom heart failure is ruled out, and therefore allow better and more cost-effective health care.
NHSX AI Award in Health and Care
This research is among the first to be funded by the NIHR and the NHSX Artificial Intelligence in Health and Care Award. The award aims to accelerate the testing and evaluation of the most promising AI technologies that meet the strategic goals set out in the NHS long-term plan.
Commenting on the next steps, Professor Peters said: âThis study lays the foundation for the deployment of this AI technology to unlock the clinical and economic benefits of early diagnosis. We will now begin the study to prove the magnitude of this benefit in numerous urban and rural GP practices across the UK, with the aim of producing evidence for widespread adoption by the NHS. “
Point-of-Care Screening for Heart Failure with Reduced Ejection Fraction Using Artificial Intelligence in ECG-Activated Stethoscope Exam in London, UK: A Prospective, Observational, and multicentric â- by Bachtiger et al is published in The Lancet Digital Health.