FDA Clears AI Heart Failure Detector
FDA has cleared an Anumana 510(k) for ECG-AI LEF, an artificial intelligence (AI)-powered medical device to detect low ejection fraction (LEF) in patients at risk of heart failure. The device was developed in partnership with Mayo Clinic, and it screens for LEF using data from a routine 12-lead electrocardiogram (ECG), the company says. “Based on pioneering research from Mayo Clinic, the algorithm has been developed utilizing over 100,000 ECG and echocardiogram data pairs from unique patients and has been clinically tested in more than 25 studies involving more than 40,000 patients in the U.S. and internationally,” it adds.
Anumana says ECG-AI LEF was clinically validated in a multi-site, retrospective clinical study involving 16,000 racially diverse patients, “achieving its primary endpoint with an 84.5% sensitivity and 83.6% specificity.” Additionally, it says, a Mayo study called EAGLE, evaluated the use of an investigational version of the algorithm in routine clinical care of 22,641 adults by 120 primary care teams from 45 clinics or hospitals. That study demonstrated that ECG-AI LEF implementation “improved clinician’s ability to diagnosis of LEF by 31% versus standard of care without increasing the overall rate of echocardiogram usage,” it says.