Reliably diagnosing heart failure in primary-care settings is challenging as the symptoms, such as breathlessness, are associated with many other conditions, researchers note in The Lancet Digital Health.
The new tool can help overcome the "unacceptable reality that 80% of patients with heart failure are currently diagnosed through an emergency hospital admission," Dr. Patrik Bachtiger of Imperial College London, lead author of the paper, said in a news release.
"The current clinical pathway simply misses too many patients, leaving them undiagnosed until very sick. This tool can save time and money for the (National Health Service) and unlock major benefits for patients through early diagnosis and starting effective treatments," Dr. Bachtiger added.
The researchers tested the ability of an AI algorithm applied to a single-lead ECG recorded during ECG-enabled stethoscope examinations to detect left ventricular ejection fraction (LVEF) of 40% or lower in primary care.
The study included 1,050 patients (mean age, 62 years; 51% male) undergoing standard transthoracic ECG; 945 (90%) had LVEF of at least 40% and 105 (10%) had LVEF of 40% or lower.
The study team found that the AI-powered smart stethoscope had 92% sensitivity and 80% specificity for detecting low LVEF.
"This tool is a game-changer because our study shows that GPs will be able to use it in a way that fits how they examine patients to reliably rule in or rule out heart failure at the time," co-author Dr. Nicholas Peters, also with Imperial College London, said in the release.
"The result will be earlier diagnosis and treatment, avoidance of unnecessary and expensive tests in those in whom heart failure is ruled out, and therefore enable better and more cost-effective healthcare," Dr. Peters added.
"This prospective, real-world study provides a practical application of an AI algorithm integrated in a clinical context that produces a potentially actionable result," write the authors of an accompanying comment in the journal.
While this is a "notable advance," the correct base population for screening needs to be determined, they caution.
"Patients in this study were attending for a formal transthoracic echocardiogram, having been referred by clinicians for investigation of symptoms and screening related to heart failure. The use of this technology for patients presenting for primary care versus patients presenting for ECGs or transthoracic echocardiograms would alter the predictive value of the algorithm," write Dr. Christine Shen and Dr. Evan Muse of Scripps Clinic in La Jolla, California.
"In addition to LV function, the hope for future advances is that single-lead ECG inputs into AI algorithms can lead to point-of-care diagnosis and prediction of other arrhythmias, electrolyte imbalances, infiltrative cardiomyopathies, and beyond," they say.
The study was funded by the NHS Accelerated Collaborative, NHSX and the National Institute for Health Research. The authors report no conflicts of interest.
SOURCE: https://bit.ly/3FVbYTL and https://bit.ly/33ye1jh The Lancet Digital Health, online January 5, 2022.
By Reuters Staff
Posted on
site created by:
© 2024 Medicom Medical Publishers. All rights reserved. Terms and Conditions | Privacy Policy