Symptom-Free, but Not Risk-Free: New Breakthrough Identifies Atrial Fibrillation in Symptomless Individuals
Researchers at the Smidt Heart Institute at Cedars-Sinai have unveiled a groundbreaking discovery: an artificial intelligence (AI) algorithm capable of detecting abnormal heart rhythms in individuals who exhibit no symptoms.
This AI algorithm, designed to uncover hidden signals within routine medical diagnostic tests, holds immense promise in the prevention of strokes and other cardiovascular complications associated with atrial fibrillation, the most prevalent heart rhythm disorder.
While previous algorithms predominantly targeted white populations, this cutting-edge solution demonstrates remarkable efficacy across diverse patient groups, including U.S. veterans and underserved communities.
Historically, algorithms developed in the past have predominantly focused on applications within white populations. In contrast, this algorithm exhibits versatility, demonstrating effectiveness across diverse settings and patient groups, inlcuding U.S. veterans and marginalized communities.
These significant findings were published today in the reputable, peer-reviewed journal, JAMA Cardiology.
Dr. David Ouyang, a cardiologist at the Smidt Heart Institute, Division of Artificial Intelligence in Medicine, and senior author of the study, emphasized, “This research allows for better identification of a hidden heart condition and informs the best way to develop algorithms that are equitable and generalizable to all patients.”
Alarmingly, an estimated one in three individuals with atrial fibrillation remains unaware of their condition, underscoring the critical need for early detection.
Atrial fibrillation disrupts the heart’s electrical signals, leading to erratic blood flow from the upper to lower chambers. This turbulence can result in blood pooling and clot formation, increasing the risk of ischemic strokes.
The development of the algorithm involved the programming of an artificial intelligence tool to analyze patterns within electrocardiogram (ECG) readings, which monitor the heart’s electrical activity. ECG electrodes, placed on the patient’s body, capture this data.
The AI model underwent rigorous training using nearly one million ECG readings collected between January 1, 1987, and December 31, 2022, from patients across two Veterans Affairs health networks. Impressively, the algorithm accurately predicted cases of atrial fibrillation within 31 days.
Furthermore, when applied to medical records from Cedars-Sinai patients, the AI model consistently and accurately identified instances of atrial fibrillation within the same timeframe.
Dr. Sumeet Chugh, the director of the Division of Artificial Intelligence in Medicine at Cedars-Sinai, remarked, “This study of veterans was geographically and ethnically diverse, indicating that the application of this algorithm could benefit the general population in the U.S.”
The collaborative effort between Cedars-Sinai and the San Francisco and Palo Alto Veterans Affairs hospitals brought together experts such as Dr. Grant Duffy and Dr. John Theurer.
Moving forward, the investigators plan to subject the algorithm to prospective clinical trials to assess its ability to identify individuals at risk of heart attacks and strokes. Additionally, they intend to develop a suite of AI algorithms aimed at addressing complex cardiac conditions.
The study was funded by the National Institutes of Health and the U.S. Department of Veterans Affairs.
Image Credit: iStock