April 3, 2024 — – Eko Health, a pioneer in applying artificial intelligence (AI) for early detection of heart and lung disease, announced FDA clearance of its low EF detection AI. For the first time, U.S. healthcare providers can now detect low EF, a key heart failure indicator, in her 15 seconds using her Eko stethoscope during a routine physical exam. This breakthrough in early detection is both an important medical innovation and a new era in cardiovascular disease discovery.

More than 6 million people in the United States live with heart failure, and half of them experience heart failure with reduced ejection fraction (HFrEF), a condition in which the heart is unable to pump blood effectively. 1 Traditional heart failure detection tools, such as echocardiography, are often unavailable in primary care settings because they are expensive, require specialized training, and take significant time. As a result, many cases of heart failure go undiagnosed until symptoms require a visit to a specialist or emergency hospital, leading to poor patient outcomes and increased healthcare costs. 2 Eko’s Low EF AI challenges this by incorporating rapid and accessible low ejection fraction detection into the system. Stethoscope testing is performed at the forefront of medical care.

“The ability to identify hidden and potentially life-threatening cardiac conditions using a stethoscope, a familiar tool for primary care and subspecialist clinicians, can help prevent hospitalizations and adverse events.” said Dr. Paul Friedman, director of the department. He received his doctorate in cardiovascular medicine from the Mayo Clinic in Rochester. “Importantly, because the stethoscope is small and portable, this technology can be used in urban and remote areas, and is expected to help address care in underserved areas. .”

Low EF AI will be added to Eko’s SENSORA Cardiac Early Detection Platform. This is the latest advancement in a platform that already has FDA-cleared algorithms to identify AFib and structural heart murmurs, which are often indicators of valvular heart disease. When primary care testing using SENSORA detects low EF, referral to cardiology for thorough diagnostic testing and treatment evaluation can expedite access to life-sustaining treatment.

“As the most recognizable symbol of healthcare, the stethoscope touches an estimated one billion lives around the world each year,” said Connor Landgraf, co-founder and CEO of Eko Health. “With Eko’s Low EF AI, we have turned a medical icon into an AI-powered early heart failure detection tool, saving millions of lives in a fraction of the time and cost of echocardiography. We are honored to collaborate with Mayo Clinic on this groundbreaking initiative. ”

Clinical development and validation highlights:

• Robust AI Training and Validation: Eko’s Low EF AI is trained on a proprietary dataset of over 100,000 ECG and echocardiogram pairs from unique patients and a multi-institutional study of 3,456 patients. It was clinically validated in a prospective clinical study and achieved an AUROC of 0.835. Detection of LVEF <40%, sensitivity 74.7%, specificity 77.5%. It shows a strong ability to distinguish between low EF and normal EF.3.
• Independent validation by Imperial College London: An independent validation of the Low EF AI by Imperial College London published in Lancet Digital Health showed an AUROC of 0.85, sensitivity of 84.8%, and specificity of 69.5% for detection of LVEF <40%. , reported when introduced at the University of London. He has worked with over 1,050 patients in multiple real-world settings. This validation led NHS England and Imperial College London to expand the rollout of Eko to more than 100 clinics across London and Wales. Four
• Proven effectiveness in pregnant women: In a Mayo Clinic-led clinical study of approximately 1,200 pregnant women in Nigeria, it identified twice as many cases of pregnancy-related cardiomyopathy than standard of care, with an AUROC of 0.98 and a sensitivity of 100.0%. The effectiveness of AI was highlighted with this excellent value. The specificity was 79.4%, indicating great potential to aid in the detection and appropriate management of cardiomyopathy in pregnant women and reduce the associated disease burden and mortality risk. Five

For more information, please visit www.ekohealth.com.

Click here for detailed coverage of the ACC24 conference.

References:

Centers for Disease Control and Prevention. (January 5, 2023). heart failure. https://www.cdc.gov/heartdisease/heart_failure.htm

Bachtiger P, Kelshiker MA, Petri CF, et al. (2023). Survival and health economic outcomes in heart failure diagnosed at admission versus heart failure in the community: A propensity-matched analysis. BMJ Health & Care Informatics, 30:e100718. doi: 10.1136/bmjhci-2022-100718

FDA 510(k) Overview, K233409

Bachtiger, P., et al. (2022). Point-of-care screening for heart failure with reduced ejection fraction using artificial intelligence during his ECG-enabled stethoscope examination in London, UK: a prospective observational multicenter study. Lancet Digital Health, 4(2).

Adinsewo DA. (November 13, 2023).Screening for peripartum cardiomyopathy using an artificial intelligence-enhanced digital stethoscope: a randomized clinical trial [Conference Presentation and Abstract]. AHA 2023, Philadelphia, Pennsylvania, USA.