Research from Cedars-Sinai shows that a deep learning model could improve AFib detection
A new artificial intelligence approach developed by researchers at the Los Angeles-based Smidt Heart Institute at Cedars-Sinai has been shown to detect abnormal heart rhythms associated with atrial fibrillation that might otherwise go unnoticed by doctors.
WHY IT MATTERS
Researchers at the Smidt Heart Institute say the findings point to the potential for artificial intelligence to be used more widely in heart care.
From a recent study published in npj Digital medicinedoctors at Cedars-Sinai show how the deep learning model was developed to analyze echocardiogram images, where sound waves show the rhythm of the heart.
Researchers trained a program to study more than 100,000 echocardiogram videos of patients with atrial fibrillation, they explain. The model distinguished between echocardiograms that show a heart in sinus rhythm β normal heartbeats β and echocardiograms that show a heart with an irregular heart rhythm.
The program was able to predict which patients with sinus rhythm had experienced or would develop atrial fibrillation within 90 days, they said, noting that the AI ββmodel that evaluated the images outperformed estimating risk based on known risk factors .
βWe were able to demonstrate that a deep learning algorithm we developed can be applied to echocardiograms to identify patients with a hidden abnormal heart rhythm disorder called atrial fibrillation,β explains Dr. Neal Yuan, a staff scientist at the Smidt Heart Institute.
“Atrial fibrillation can come and go,” he added, “so it may not be present at a doctor’s appointment. This AI algorithm identifies patients who may have atrial fibrillation even if it is not present during their echocardiogram exam.”
THE BIG TREND
The Smidt Heart Institute is the largest cardiothoracic transplant center in California and the third largest in the United States.
According to the CDC, an estimated 12.1 million people in the United States will have atrial fibrillation by 2030. During AFib, the upper chambers of the heart sometimes beat in sync with the lower chamber and sometimes not β making the arrhythmia often difficult for doctors to detect. In some patients, the condition causes no symptoms at all.
Researchers say a machine learning model trained to analyze ultrasound images could help doctors detect early and subtle changes in the hearts of patients with undiagnosed arrhythmias.
ON THE RECORD
βWe are encouraged that this technology could detect a dangerous condition that the human eye would not detect while looking at echocardiograms,β said Dr. David Ouyang, a cardiologist and AI researcher at the Smidt Heart Institute. βIt can be used for patients who are at risk for atrial fibrillation or who are experiencing symptoms associated with the condition.β
“The fact that this program predicted which patients had active or occult atrial fibrillation could have enormous clinical applications,” added Dr. Christine M. Albert, chair of the Smidt Heart Institute’s Department of Cardiology, added. βIf we can identify patients with occult atrial fibrillation, we can treat them before they experience a serious cardiovascular event.β
Mike Miliard is editor-in-chief of Healthcare IT News
Email the writer: mike.miliard@himssmedia.com
Healthcare IT News is a HIMSS publication.