Blab AI
Tempus Publishes Multi-Center Validation of AI-Enabled ECG Tool for Atrial Fibrillation Risk Prediction
In a striking new study, Tempus AI, Inc. confirmed that its AI‑enabled electrocardiogram (ECG) software—Tempus ECG‑AF—delivers reliable risk predictions across diverse clinical settings. The research, published in the peer‑reviewed journal Heart Rhythm, evaluated the tool at three geographically distinct sites and found it consistently surpassed the performance thresholds that earned the U.S. Food and Drug Administration (FDA) clearance in 2024.
Tempus, a precision‑medicine company founded in 2015 and listed on Nasdaq as TEM, received 510(k) clearance for ECG‑AF in 2024. The approval allows the device to be marketed as a medical device that uses artificial intelligence to forecast a patient’s one‑year risk of atrial fibrillation (AF) or atrial flutter before any clinical diagnosis.
The validation study, titled “Multi‑Center Validation of an Artificial Intelligence‑Enabled ECG Model to Predict 1‑Year Risk of Atrial Fibrillation or Flutter,” enrolled 4,017 patients aged 65 and older who had no prior history of AF, atrial flutter, pacemaker, or defibrillator implantation. ECG data from each site were aggregated, and patient charts were manually reviewed to confirm eligibility. The primary endpoints were the occurrence of a new AF diagnosis within one year or a one‑year period of AF‑free follow‑up.
Results showed that the ECG‑AF risk score exceeded the prespecified performance thresholds at all three sites, demonstrating consistent predictive accuracy across varied clinical environments. This consistency reinforces the device’s reliability as a decision‑support tool and provided the evidence base that supported the FDA’s clearance decision.
Brandon Fornwalt, senior vice president of cardiology at Tempus and co‑author of the study, said the validation marks an important step toward shifting cardiac care from late‑stage intervention to early risk detection. He added that the AI model’s ability to surface hidden risks sooner could enable clinicians to pursue earlier, more targeted diagnosis and care, potentially reducing serious complications such as stroke and heart failure.
The Tempus ECG‑AF device is the first FDA‑cleared ECG‑AI tool in the company’s expanding portfolio of next‑generation devices that identify patients at risk for a range of cardiovascular conditions. While the software analyzes only ECG data, Tempus cautions that results should be interpreted alongside other diagnostic information—including the patient’s original ECG recordings, clinical history, and symptoms.
By publishing in Heart Rhythm, Tempus provides an independent peer‑reviewed validation of the device’s performance and underscores the growing role of AI in cardiology. Automated analysis of routine ECGs can uncover subtle patterns that predict arrhythmia risk before clinical symptoms appear, a capability that may become a standard component of cardiovascular care as the FDA continues to approve AI‑enabled medical devices.
At present, the Tempus ECG‑AF device remains available under its FDA‑cleared status. The company has not announced additional product launches or updates related to this device. Nonetheless, the validation study reinforces the regulatory foundation for broader adoption of the technology in clinical practice.
The publication highlights the importance of rigorous, multi‑site testing for AI‑driven diagnostic tools and suggests that early risk detection may soon become a routine part of managing cardiovascular health.
Tempus, a precision‑medicine company founded in 2015 and listed on Nasdaq as TEM, received 510(k) clearance for ECG‑AF in 2024. The approval allows the device to be marketed as a medical device that uses artificial intelligence to forecast a patient’s one‑year risk of atrial fibrillation (AF) or atrial flutter before any clinical diagnosis.
The validation study, titled “Multi‑Center Validation of an Artificial Intelligence‑Enabled ECG Model to Predict 1‑Year Risk of Atrial Fibrillation or Flutter,” enrolled 4,017 patients aged 65 and older who had no prior history of AF, atrial flutter, pacemaker, or defibrillator implantation. ECG data from each site were aggregated, and patient charts were manually reviewed to confirm eligibility. The primary endpoints were the occurrence of a new AF diagnosis within one year or a one‑year period of AF‑free follow‑up.
Results showed that the ECG‑AF risk score exceeded the prespecified performance thresholds at all three sites, demonstrating consistent predictive accuracy across varied clinical environments. This consistency reinforces the device’s reliability as a decision‑support tool and provided the evidence base that supported the FDA’s clearance decision.
Brandon Fornwalt, senior vice president of cardiology at Tempus and co‑author of the study, said the validation marks an important step toward shifting cardiac care from late‑stage intervention to early risk detection. He added that the AI model’s ability to surface hidden risks sooner could enable clinicians to pursue earlier, more targeted diagnosis and care, potentially reducing serious complications such as stroke and heart failure.
The Tempus ECG‑AF device is the first FDA‑cleared ECG‑AI tool in the company’s expanding portfolio of next‑generation devices that identify patients at risk for a range of cardiovascular conditions. While the software analyzes only ECG data, Tempus cautions that results should be interpreted alongside other diagnostic information—including the patient’s original ECG recordings, clinical history, and symptoms.
By publishing in Heart Rhythm, Tempus provides an independent peer‑reviewed validation of the device’s performance and underscores the growing role of AI in cardiology. Automated analysis of routine ECGs can uncover subtle patterns that predict arrhythmia risk before clinical symptoms appear, a capability that may become a standard component of cardiovascular care as the FDA continues to approve AI‑enabled medical devices.
At present, the Tempus ECG‑AF device remains available under its FDA‑cleared status. The company has not announced additional product launches or updates related to this device. Nonetheless, the validation study reinforces the regulatory foundation for broader adoption of the technology in clinical practice.
The publication highlights the importance of rigorous, multi‑site testing for AI‑driven diagnostic tools and suggests that early risk detection may soon become a routine part of managing cardiovascular health.
