- CDC
- Heart Failure
- Cardiovascular Clinical Consult
- Adult Immunization
- Hepatic Disease
- Rare Disorders
- Pediatric Immunization
- Implementing The Topcon Ocular Telehealth Platform
- Weight Management
- Monkeypox
- Guidelines
- Men's Health
- Psychiatry
- Allergy
- Nutrition
- Women's Health
- Cardiology
- Substance Use
- Pediatrics
- Kidney Disease
- Genetics
- Complimentary & Alternative Medicine
- Dermatology
- Endocrinology
- Oral Medicine
- Otorhinolaryngologic Diseases
- Pain
- Gastrointestinal Disorders
- Geriatrics
- Infection
- Musculoskeletal Disorders
- Obesity
- Rheumatology
- Technology
- Cancer
- Nephrology
- Anemia
- Neurology
- Pulmonology
FDA Clears First AI-Based Algorithm to Detect Heart Failure during Routine Exams
The Low EF AI is designed to detect low ejection fraction in 15 seconds during a primary care exam.
The US Food and Drug Administration on April 2, 2024, granted clearance to digital health company Eko Health for its artificial intelligence (AI) algorithm for the detection of heart failure during routine physical exams.
Developed in partnership with Mayo Clinic to be used with the company’s cardiac early detection platform (Sensora) and digital stethoscope (Eko), the AI-based algorithm (Low EF AI) is designed to detect low ejection fraction in 15 seconds during a primary care exam, according to a company press release.
“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 hospitalizations and adverse events,” said Paul Friedman, MD, chair of the department of cardiovascular medicine at Mayo Clinic, in the release. “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.”
The clearance was based on data from 3 studies that evaluated the effectiveness of the algorithm. First, findings from a multi-site, prospective study of 3456 patients showed Low EF AI achieved an area under the receiver operating characteristic (AUROC) of 0.835 for detection of left ventricle ejection fraction (LVEF) <40%, and it had 74.7% sensitivity and 77.5% specificity.
The second study was an independent validation of the Low EF AI by the Imperial College London and published in Lancet Digital Health. Researchers reported an AUROC of 0.85 for detection of LVEF <40%, 84.8% sensitivity, and 69.5% specificity when used by over 1050 patients across multiple real-world settings.
The last study was led by the Mayo Clinic and included nearly 1200 pregnant women in Nigeria. Findings showed that the Low EF AI identified twice as many cases of pregnancy-related cardiomyopathy than standard care. Data also showed an AUROC of 0.98, 100% sensitivity, and 79.4% specificity.
The addition of the Low EF AI to Eko's Sensora Cardiac Early Detection Platform enhances its capabilities, complementing existing FDA-cleared algorithms designed to detect atrial fibrillation and structural heart murmurs, commonly associated with valvular heart disease, according to the company’s release.
When low EF is identified during a primary care examination using Sensora, it facilitates prompt referral to the cardiology department for comprehensive diagnostic assessments and treatment evaluation, potentially accelerating access to life-extending treatment, added Eko Health in the statement.
Source: FDA clears first AI to aid heart failure detection during routine check-ups. News release. Eko Health. April 2, 2024. Accessed April 3, 2024. https://www.ekohealth.com/blogs/newsroom/fda-clears-low-ejection-fraction-ai
