Tempus ECG-Low EF

K250119

Tempus AI, Inc. · cleared 2025-07-15 · product code QYE · Cardiovascular

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.6)
“Tempus ECG-Low EF is a cardiovascular machine learning software intended for analysis of 12-lead resting ECG recordings using machine-learning techniques to detect signs of cardiovascular conditions for further referral or diagnostic follow-up.”
Algorithmmachine learning techniques
source quote (p.6)
“The software employs machine learning techniques to analyze ECG recordings and detect signs associated with a patient experiencing low left ventricular ejection fraction (LVEF), less than or equal to 40%.”
Adaptive (vs locked)No
source quote (p.6)
“It checks the format and quality of the input data, analyzes the data via a trained and 'locked' machine-learning model to generate an uncalibrated risk score, converts the model results to a binary output (or reports that the input data are unclassifiable), and evaluates the uncalibrated risk score against pre-set operating points (thresholds) to produce a final result.”
PCCPFDA source did not state this
Cybersecurity addressedYes
source quote (p.7)
“Cybersecurity Testing: Cybersecurity activities were completed and associated risks have been appropriately mitigated.”

Validation studies (1)

Retrospective clinical

n=14,924 patients · 4 site(s)

endpoints: prediction of LVEF ≤ 40%; prediction of LVEF > 40%

Reported performance (4 observations)

sensitivity0.86CI 84%
source quote (p.7)
“The point estimate for sensitivity for the prediction of LVEF ≤ 40% was 86% and the lower bound of the 95% CI was 84% which was above the predetermined acceptance criteria of 80%.”
specificity0.83CI 82%
source quote (p.7)
“The point estimate for specificity for the prediction of LVEF > 40% was 83% and the lower bound of the 95% CI was 82% which was above the predetermined acceptance criteria of 80%.”
ppvas written: “positive predictive value (PPV)”0.38
source quote (p.7)
“The overall positive predictive value (PPV) observed in the study was 38% and the negative predictive value (NPV) was 98%.”
npvas written: “negative predictive value (NPV)”0.98
source quote (p.7)
“The overall positive predictive value (PPV) observed in the study was 38% and the negative predictive value (NPV) was 98%.”

Each value carries its own analysis unit and task — never compare or pool across devices. Source: 510(k) summary PDF.

Predicate network

Postmarket — what happened after clearance

0
recalls in product code, 24mo
0
MAUDE reports in code, 12mo
—
vs code's own 3-yr baseline
0
drift signals on this device

Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device); a recall is shown as device-attributed only when the recall record itself lists this clearance number. Signals are descriptive observables with sources — never a judgment that the device is unsafe or drifting. Snapshot 2026-07-08.

Reimbursement — how devices like this got paid

Not yet tracked — no payment pathway indexed for this clearance (the reimbursement corpus is a growing seed set).

Applicable FDA guidance — what the submission is measured against

FDA guidance documents and guiding principles applicable to 510(k) AI/ML devices in the Cardiovascular panel. A curated reference index, not legal or regulatory advice — each item states its own status, and a draft is never binding.

Applicability is derived from the device's FDA advisory panel and pathway — cross-cutting guidances apply to every AI/ML device; panel-specific ones are flagged. Titles, dates, and links verified against fda.gov as of July 2026.

Constat Precedent · public FDA/CMS data · descriptive decision-support, not regulatory or reimbursement advice. Share this page: constat.dev/precedent/device/K250119