# K254297: Tempus ECG-MR

- Pathway: 510(k) (Traditional)
- Applicant: Tempus AI, Inc.
- Decided: Sep 25, 2026 after 268 days
- Product code: SBQ (Atrial Fibrillation Risk Prediction Machine Learning-Based Notification Software)
- Device class: 2
- Regulation: 21 CFR 870.2380
- Recalls of this device: none
- Data: FDA decisions to Oct 25, 2026; recalls to Oct 12, 2026

## Lineage
Longest line of descent: 4 generations back to DEN230003 (2023). 4 ancestors in all.
No later device cites it as a predicate yet.
0 of 5 devices in its family (counting itself) have a Class I recall.

## Predicates on the family tree (from the FDA summary)
- K252360: ECG-AI Pulmonary Hypertension (PH) 12-Lead algorithm (1020), Anumana, Inc. (2026). Cleared while this submission was under review Summary page 5.

## Indications for use
Tempus ECG-MR is software intended to analyze resting, non-ambulatory 12-lead ECG recordings and detect signs associated with having moderate or severe mitral regurgitation (MR). It is for use on clinical diagnostic ECG recordings collected at a healthcare facility from patients: • 65 years of age or older • At risk of cardiovascular disease. Such cardiovascular risk factors include, but are not limited to, history of coronary artery disease, hypertension, obesity, or diabetes; or other signs or symptoms of heart disease, such as dyspnea, chest pain, or lower extremity edema. • Without prior mitral valve intervention • Without prior diagnosis of moderate or severe mitral regurgitation Tempus ECG-MR only analyzes ECG data and provides a binary output for interpretation. Tempus ECG-MR is not intended to be a stand-alone diagnostic tool for cardiac conditions, should not be used for serial patient monitoring, and should not be used on ECGs with paced rhythms. Results should be interpreted in conjunction with other diagnostic information, including the patient’s original ECG recordings and other tests, as well as the patient’s symptoms and clinical history.

Source page: https://510kreport.com/device/K254297
Methodology: https://510kreport.com/methodology