Fetal EchoScan (v1.1)

K251071

BrightHeart · cleared 2025-05-02 · product code POK · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.6)
SaMD
AlgorithmMachine Learning Model
source quote (p.6)
Machine Learning Model
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedYes
source quote (p.7)
Cybersecurity documentation was provided as recommended by FDA's Guidance for Industry and FDA Staff, “Content of Premarket Submissions for Management of Cybersecurity in Medical Devices".

Validation studies (3)

Bench

sample size not stated

standards: IEC 62304:2016, Medical device software - Software life cycle processes

Retrospective clinical

n=877 cases · 11 site(s)

endpoints: overriding artery; septal defect at the cardiac crux; abnormal relationship of the outflow tracts; enlarged cardiothoracic ratio; right ventricular to left ventricular size discrepancy; tricuspid valve to mitral valve annular size discrepancy; pulmonary valve to aortic valve annular size discrepancy; cardiac axis deviation

Reader study (MRMC)

n=200 cases

endpoints: any suspicious radiographic finding; overriding artery; cardiac crux septal defect; abnormal relationship of the outflow tracts; enlarged cardiothoracic ratio; cardiac axis deviation; PV/AV size discrepancy; RV/LV size discrepancy; TV/MV size discrepancy

Reported performance (3 observations)

sensitivity0.935CI 0.892-0.978
source quote (p.10)
The mean sensitivity for identification of any claimed suspicious finding was 0.935 (0.892-0.978) in the aided reading condition
specificity0.97CI 0.949-0.991
source quote (p.10)
The mean specificity for identification of any claimed suspicious finding was 0.970 (0.949-0.991) in the aided reading condition
aurocas written: “auc0.974CI 0.957-0.990
source quote (p.10)
The ROC AUC for detection of any suspicious radiographic finding was significantly higher in the aided compared to the unaided reading condition (see Figure 1): 0.974 (95% CI 0.957-0.990)

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
1
drift signals on this device
  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K252294 (decision 2025-12-08) from Brightheart for a matching device line ("Fetal EchoScan (v1.2)") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K252294

Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device). 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).

RIGOR™ Precedent · public FDA/CMS data · descriptive decision-support, not regulatory or reimbursement advice. Share this page: radar.healthai.com/precedent/device/K251071