AI can help doctors detect abnormal heart rhythms earlier.

An artificial intelligence program developed by investigators at the Summit Heart Institute and Cedars-Sinai colleagues can detect a type of abnormal heart rhythm that goes unnoticed during medical appointments, according to a new study. can't go

Results of the study, published in NPJ Digital Medicinesuggest that AI could one day be used to analyze images from a common imaging test called an echocardiogram, which uses sound waves to capture images of the heart.

Abnormal heart rhythms are often caused by structural abnormalities of the heart. The researchers hypothesized that an AI program trained to analyze echocardiograms could help clinicians detect early, subtle changes in the hearts of patients with undiagnosed arrhythmias.

“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 known as atrial fibrillation. fibrillation,” says Neil Yuan, MD, a staff scientist at the Summit Heart Institute and first corresponding author of the study.

“Atrial fibrillation can come and go, so it may not be present at the doctor's appointment. This AI algorithm identifies patients who may not have atrial fibrillation during an echocardiogram study. It can also be present.”

During atrial fibrillation, the upper chambers of the heart sometimes beat in sync with the lower chambers and sometimes they don't, making it often difficult for clinicians to detect the arrhythmia. In some people, atrial fibrillation causes no symptoms. In others, it can cause heart palpitations, fatigue, shortness of breath, dizziness, and other symptoms that interfere with daily life. If left untreated, atrial fibrillation can lead to stroke and heart failure.

According to the Centers for Disease Control and Prevention (CDC), an estimated 12.1 million people in the United States will have atrial fibrillation in 2030. According to CDC data, deaths related to atrial fibrillation have been increasing for more than two decades.

“We're encouraged that this technology can capture a dangerous situation that the human eye wouldn't when looking at an echocardiogram,” said David Ouyang, MD, a cardiologist and a researcher in the Division of Cardiology at the Summit Heart Institute. ” of Artificial Intelligence in Medicine, and a senior author of the study.

“It can be used for patients who are at risk for atrial fibrillation or who are experiencing symptoms associated with the condition.”

The team trained a program to study more than 100,000 echocardiogram videos from patients with atrial fibrillation. The program distinguishes between echocardiograms that show the heart in sinus rhythm (normal heartbeat periods) and echocardiograms that show the heart in irregular heart rhythms. The program predicted which sinus rhythm patients experienced or would develop atrial fibrillation within 90 days.

A model examining images performed better than estimating risk based on known risk factors.

“The fact that this program can predict which patients have active or latent atrial fibrillation could have many clinical applications,” said Christine M. Albert, MD, MPH, Summit Heart Institute. I chair of the Department of Cardiology and a study author. “Being able to identify patients with hidden atrial fibrillation may allow us to treat them before they experience a serious cardiovascular event.”