Tempus AI has announced the publication of a multi-center validation study evaluating its ECG-AF software, an artificial intelligence-enabled tool that received U.S. Food and Drug Administration clearance in 2024 for predicting the one-year risk of atrial fibrillation or atrial flutter (AF). The study, titled “Multi-Center Validation of an Artificial Intelligence-Enabled ECG Model to Predict 1-Year Risk of Atrial Fibrillation or Flutter,” was recently published in Heart Rhythm.
Atrial fibrillation is the most common cardiac arrhythmia and is associated with elevated risks of stroke, heart failure and mortality. Because the condition is often asymptomatic or intermittent, diagnosis can be challenging. The application of AI to electrocardiogram (ECG) interpretation has emerged as a potential approach for identifying patients who may be at increased risk before clinical symptoms become apparent.
The validation study assessed Tempus ECG-AF across three geographically distinct healthcare sites. Researchers aggregated ECG data and conducted manual chart reviews to identify eligible participants. The study focused on patients aged 65 years and older who had no prior history of atrial fibrillation and no pacemaker or implantable defibrillator use.
Endpoints were defined as either a new diagnosis of AF within one year or confirmation of remaining AF-free during one year of follow-up. Among the 4,017 patients included in the analysis, the AI-derived risk score exceeded pre-specified performance thresholds. According to Tempus, the resulting evidence contributed to the FDA clearance of the technology.
Commenting on the findings, Brandon Fornwalt, MD, PhD, Senior Vice President of Cardiology at Tempus and a coauthor of the study, said, “This study marks an important step toward shifting cardiac care from late-stage intervention to early risk detection.”
He added, “The ability of our AI model to consistently predict atrial fibrillation across varied clinical environments highlights its potential as a dependable decision-support tool. We believe this will enable clinicians to surface hidden risks sooner, opening the door to earlier, more targeted diagnosis and care to help minimize serious complications such as stroke and heart failure.”
Tempus noted that ECG-AF was the first FDA-cleared ECG-AI device in its cardiovascular portfolio. The software is designed to analyze resting 12-lead ECG recordings collected in healthcare settings and identify patterns associated with the likelihood of developing atrial fibrillation within the subsequent 12 months.
The publication represents another step in the growing use of AI-enabled clinical decision support tools aimed at identifying cardiovascular risk earlier and supporting more proactive patient management.
Click here for the original news story.
