AI to Improve Diagnosis of Atrial Fibrillation

Abnormal heart rhythms frequently arise from—and contribute to—structural abnormalities in the heart. Atrial fibrillation is a specific type of abnormal rhythm that may not be consistently present, often eluding detection during routine medical evaluations. In atrial fibrillation, the synchronization between the heart's upper and lower chambers can intermittently fail, complicating its diagnosis for healthcare professionals. While some individuals experience no symptoms from atrial fibrillation, others may suffer from heart palpitations, fatigue, shortness of breath, dizziness, and other issues that disrupt their everyday activities. If not addressed, atrial fibrillation can lead to severe complications such as stroke and heart failure. Now, researchers have developed an artificial intelligence (AI) program that is capable of identifying atrial fibrillation by analyzing images from echocardiograms—a common diagnostic test that utilizes sound waves to produce images of the heart.

A research team at Cedars-Sinai (Los Angeles, CA, USA) hypothesized that an AI tool designed to interpret echocardiograms could assist medical professionals in recognizing early, subtle cardiac changes in patients with undetected arrhythmias. They trained this AI system using over 100,000 video echocardiograms from patients diagnosed with atrial fibrillation. The system was able to differentiate between echocardiograms depicting normal sinus rhythm and those illustrating irregular rhythms. Additionally, it successfully predicted which patients currently in sinus rhythm were at risk of developing or having a recurrence of atrial fibrillation within the next 90 days. This AI model's performance in assessing the images surpassed traditional methods that predict risk based solely on established risk factors.

“We were able to show that a deep learning algorithm we developed could be applied to echocardiograms to identify patients with a hidden abnormal heart rhythm disorder called atrial fibrillation,” said Neal Yuan, MD, a staff scientist with the Smidt Heart Institute and first and corresponding author of the study. “Atrial fibrillation can come and go, so it might not be present at a doctor’s appointment. This AI algorithm identifies patients who might have atrial fibrillation even when it is not present during their echocardiogram study.”

Related Links:
Cedars-Sinai

Visit expo >

Gold Member

STI Test

Vivalytic Sexually Transmitted Infection (STI) Array

Flocked Fiber Swabs
Puritan® patented HydraFlock®

New

Ultra-Flat DR Detector

meX+1717SCC

New

Table-Top Reader

FCR PRIMA T2