The FDA has cleared an artificial intelligence (AI) algorithm capable of detecting signs of heart failure within seconds using a digital stethoscope during a standard physical examination. Developed by Eko Health in collaboration with the Mayo Clinic, the algorithm focuses on identifying low ejection fraction (EF), a key indicator present in approximately 50% of heart failure cases, potentially transforming heart failure diagnosis in primary care settings.
Low Ejection Fraction Detection
Heart failure with reduced ejection fraction (HFrEF), also known as systolic heart failure, is diagnosed when left ventricular ejection fraction (LVEF) falls to 40% or less, typically requiring hospital assessment. The new AI offers the potential for earlier detection in primary care, facilitating quicker referrals to cardiac specialists, even in asymptomatic patients. Current methods like electrocardiography are often unavailable in primary care due to cost, training requirements, and time constraints.
Clinical Validation and Performance
The Low EF AI was trained using a dataset of over 100,000 ECG and echocardiogram pairs from unique patients. Clinical validation, involving nearly 3,500 subjects across multiple sites, demonstrated the algorithm's ability to detect EF below 40% with a sensitivity of approximately 75% and a specificity of 77.5%. An independent study by clinicians at Imperial College London, published in The Lancet Digital Health, reported a sensitivity of 85% and a specificity of 69.5%.
Expert Commentary
Dr. Paul Friedman, chair of cardiovascular medicine at the Mayo Clinic, emphasized the potential impact: "The ability to identify a hidden, potentially life-threatening heart condition using a tool that primary care and subspecialist clinicians are familiar with – the stethoscope – can help us prevent hospitalisations and adverse events. Importantly, since a stethoscope is small and portable, this technology can be used in urban and remote locations, and hopefully help address care in underserved areas."
Broader Implications for Heart Failure Care
Currently, around 80% of heart failure patients are diagnosed only after emergency hospital admissions. Eko Health, which markets a range of digital stethoscopes, already has two FDA-approved AI algorithms for detecting atrial fibrillation (AF) and structural murmurs associated with valvular heart disease, marketed under the Sensora platform. Connor Landgraf, co-founder and CEO of Eko Health, noted the stethoscope's global reach, estimating it touches the lives of an estimated 1 billion people annually, highlighting the potential for widespread impact.
