Tempus AI study validates ECG software for AF risk prediction
Tempus AI, Inc. published a multi-site validation study in Heart Rhythm confirming its ECG-AF software accurately predicts one-year risk of atrial fibrillation. The study, involving 4,017 patients across three clinical sites, supported the FDA clearance received in 2024. The technology aims to shift cardiac care to early risk detection.
*this image is generated using AI for illustrative purposes only.
Tempus AI, Inc. announced the publication of a successful multi-site software validation study titled "Multi-Center Validation of an Artificial Intelligence-Enabled ECG Model to Predict 1-Year Risk of Atrial Fibrillation or Flutter" in Heart Rhythm. The study evaluated the Tempus ECG-AF software across three geographically distinct clinical sites, demonstrating the technology's ability to identify patients at risk of atrial fibrillation (AF), a prevalent cardiac arrhythmia associated with increased risks of stroke, heart failure, and death. The resulting data supported Tempus' U.S. Food and Drug Administration clearance of the ECG-AF technology received in 2024.
The application of artificial intelligence to electrocardiogram (ECG) interpretation offers a promising avenue for improving diagnosis, particularly given that AF is frequently asymptomatic and paroxysmal. The study aggregated ECG data and involved manual review of patient charts to identify eligible participants aged 65 and older with no prior AF and no history of pacemaker or defibrillator use.
Study Methodology and Endpoints
The study focused on a specific patient demographic and defined clear endpoints to measure the software's efficacy. The primary goal was to determine if the Tempus ECG-AF software could accurately predict the likelihood of AF development within a specific timeframe.
| Criteria | Details |
|---|---|
| Patient Age | 65 and older |
| Medical History | No prior AF, no pacemaker or defibrillator use |
| Study Endpoints | New AF diagnosis within one year or one year of AF-free follow-up |
| Total Patients Evaluated | 4,017 |
Key Findings and Regulatory Impact
Among the 4,017 patients evaluated, the ECG-AI-derived risk score surpassed pre-specified performance thresholds. "This study marks an important step toward shifting cardiac care from late-stage intervention to early risk detection," said Brandon Fornwalt, MD, PhD, SVP of Cardiology at Tempus and a coauthor of the study. "The ability of our AI model to consistently predict atrial fibrillation across varied clinical environments highlights its potential as a dependable decision-support tool."
The Tempus ECG-AF was the first FDA-cleared ECG-AI device in Tempus' growing portfolio of next-generation devices designed to identify patients at risk for a variety of cardiovascular conditions.
How does Tempus plan to integrate the ECG-AF software into existing clinical workflows across different healthcare systems?
What are the potential reimbursement pathways and cost implications for widespread adoption of this AI-driven screening tool?
Will Tempus pursue similar FDA clearances for AI models targeting other cardiovascular conditions beyond atrial fibrillation?
20
Create Custom Screeners 
Access 200+ Pre-built Filters 
Use 50+ Readymade Screener 
