Tempus ECG-AF
Tempus AI, Inc.Tempus ECG-AF is an AI-powered software that analyzes standard 12-lead ECG recordings from patients aged 65 and older to detect signs indicating an increased risk of atrial fibrillation or atrial flutter within the next 12 months. It assists clinicians by providing risk notifications based on ECG data, improving early identification of patients who may require further diagnostic follow-up.
Intended Use
Tempus ECG-AF is intended for use to analyze recordings of 12-lead ECG devices and detect signs associated with a patient experiencing atrial fibrillation and/or atrial flutter within the next 12 months in patients 65 years or older without prior history of AF.
Technology
Tempus ECG-AF uses a locked machine-learning model to analyze standard 12-lead resting ECG recordings collected by FDA-authorized ECG machines from GE and Philips with a sampling rate of 500 Hz. It processes input ECG data, patient age, and sex to generate an uncalibrated risk score, which is thresholded to a binary risk classification, and outputs the result via standard communication protocols to other medical systems for clinical decision support.
Performance
Clinical performance was validated in a retrospective study with 4017 patients aged 65 and older, showing sensitivity of 31%, specificity of 92%, positive predictive value (PPV) of 19%, and negative predictive value (NPV) of 95% for predicting atrial fibrillation within 12 months. The model was trained on over 1.5 million ECGs and validated on multi-site data including various ECG machines.
Predicate Devices
No predicate devices specified
Ready to Sharpen Your Edge?
Subscribe to join 7,600+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.
We respect your privacy. Unsubscribe at any time.