Breakthrough ECG-AI Algorithm Detects Low Ejection Fraction in Patients at Risk of Heart Failure

Even though it might not show symptoms, recognizing and managing LEF is crucial due to the rising incidence of heart failure and its associated health and economic burdens. A breakthrough artificial intelligence (AI)-powered medical device now offers a way to identify LEF in those who may be at risk of heart failure.

Anumana, Inc.’s (Cambridge, MA, USA) ECG-AI LEF is an innovative software-as-a-medical device (SaMD) developed in partnership with Mayo Clinic (Rochester, MN, USA) to detect LEF in adults. It analyzes data from a standard 12-lead electrocardiogram (ECG), a test commonly employed in various healthcare settings. This AI algorithm was created based on groundbreaking Mayo Clinic research and used a dataset of over 100,000 paired ECG and echocardiogram readings from distinct patients. Moreover, its effectiveness has been assessed in over 25 studies, involving more than 40,000 patients, both in the U.S. and internationally.

In a multi-site retrospective study, involving 16,000 patients from diverse ethnic backgrounds, ECG-AI LEF achieved impressive results, boasting 84.5% sensitivity and 83.6% specificity. It also achieved an AUROC score of 0.932, indicating an excellent ability to distinguish between LEF and a higher ejection fraction (EF >40%). This score surpasses the performance of many existing diagnostic tests for heart failure. Additionally, a prospective, randomized, controlled clinical trial involving 22,641 adults and 120 primary care teams across 45 clinics showed a 31% improvement in the diagnosis of LEF when using ECG-AI LEF, without leading to an increase in the use of echocardiograms. Anumana has now secured FDA 510(k) clearance for ECG-AI LEF, confirming its safety and effectiveness.

“Anumana was established in 2021 by nference in partnership with Mayo Clinic to unlock the electrical language of the heart through deep learning and improve disease diagnosis and patient care,” said Murali Aravamudan, co-founder and CEO of Anumana and nference. “In the short time of two years we have secured multiple FDA breakthrough device designations, entered multi-year agreements with three pharma partners, successfully established two new medical procedure codes for ECG AI technology, and now achieved our first FDA breakthrough medical device clearance. This is a significant milestone, and we are excited about the next phase of the journey, deploying our technology in the U.S. and globally to empower clinicians and enhance real-world clinical care.”

Related Links:
Anumana, Inc.
Mayo Clinic