Millions of Americans have atrial fibrillation, but many of them don’t know it.
Atrial fibrillation (AFib) is notoriously hard to diagnose because its symptoms can be intermittent. Between two and six million Americans have AFib. AFib increases the risk of heart failure, blood clots, strokes, and other cardiac events.
Someone with atrial fibrillation may experience symptoms of the condition at irregular times. Typically, a patient with heart problems will undergo an electrocardiogram or EKG. An EKG is a recording of the heart’s electrical activity. A trained expert reviews the results of the test.
However, if the patient isn’t experiencing symptoms at the time of the test, AFib may not be detectable. To combat this, researchers at the Mayo Clinic recently released the results of a study where artificial intelligence was used to look at hundreds of thousands of EKG scans. Artificial intelligence found a way to potentially diagnose atrial fibrillation in as little as 10 seconds.
Applying artificial intelligence to EKG readings allows doctors to detect the signs of atrial fibrillation, even when larger symptoms aren’t occurring while the EKG is recorded.
RELATED: 8 Surprising Factors That Could Be Putting Your Heart At Risk
The Mayo Clinic research team developed artificial intelligence to scour almost 650,000 EKGs taken over 24 years from over 180,000 adult patients.
The AI was able to identify people with potentially undetected atrial fibrillation with 83 percent accuracy by finding signals in the EKG that might have otherwise been invisible to the human eye. Even well-trained experts may miss signs of AFib on an EKG.
The authors of the research say that one day, it may be possible to use AI as a diagnostic test to screen for hypertension, diabetes, or other high-risk diseases.
There are many potential applications for using AI to detect AFib, including predicting the types of
