A new artificial intelligence approach developed by researchers at Los Angeles-based Cedars-Sinai's Smit Heart Institute has been shown to be able to detect abnormal heart rhythms associated with atrial fibrillation that may go unnoticed by doctors. It was done.
Why is it important?
Researchers at the Smit Heart Institute say their findings demonstrate the potential for artificial intelligence to be used more widely in cardiac care.
In a recent study published in npj Digital Medicine, clinicians at Cedars-Sinai show how a deep learning model was developed to analyze echocardiogram images in which sound waves show heart rhythm. Masu.
The researchers say they trained the program to study more than 100,000 echocardiogram videos of patients with atrial fibrillation. The model differentiated between echocardiograms showing a heart in sinus rhythm (normal heartbeat) and echocardiograms showing a heart in irregular heart rhythm.
The program was able to predict which patients with sinus rhythm experienced or would develop atrial fibrillation within 90 days, the researchers said, adding that an AI model that evaluated the images They noted that the study performed better than estimating risk based on known risk factors.
“We were able to show that the deep learning algorithm we developed can be applied to echocardiograms to identify patients with a hidden abnormal heart rhythm disorder called atrial fibrillation,” said Smit Heart Institute. Staff Scientist Dr. Neil Yuan explained.
“Atrial fibrillation can come and go, so atrial fibrillation may not be present at the time of presentation. This AI algorithm detects atrial fibrillation even if it is not present during an echocardiogram. identify patients at risk of movement.
bigger trends
Smit Heart Institute is the largest cardiothoracic transplant center in California and the third largest in the United States.
According to the CDC, it is estimated that 12.1 million people in the United States will have atrial fibrillation in 2030. During AFib, the heart's upper ventricle may or may not beat in sync with the lower ventricle, often making it difficult for clinicians to detect the arrhythmia. For some patients, this condition may not cause any symptoms at all.
Researchers say machine learning models trained to analyze echo images could help clinicians detect subtle changes in the heart of patients with undiagnosed arrhythmia early. .
In fact, AI has shown great promise in early detection of atrial fibrillation, as evidenced by similar studies at medical institutions such as Geisinger Hospital and Mayo Clinic.
On record
“We are encouraged that this technology has the potential to detect dangerous conditions that are invisible to the human eye when viewing an echocardiogram,” said Smit Heart Institute cardiologist. said AI researcher Dr. David O'Young. “It may be used in patients who are at risk for atrial fibrillation or who are experiencing symptoms related to atrial fibrillation.”
“The fact that this program predicted which patients had active or hidden atrial fibrillation has tremendous clinical potential,” said Dr. Smit, director of cardiology at the Heart Institute. added Dr. Christine M. Albert. “If we can identify patients with hidden atrial fibrillation, we may be able to treat them before serious cardiovascular events occur.”
Mike Miliard is the Editor-in-Chief of Healthcare IT News
Email the author: mike.miliard@himssmedia.com
Healthcare IT News is a HIMSS publication.
