Fetal EchoScan (v1.1)
K251071BrightHeart · cleared 2025-05-02 · product code POK · Radiology
Premarket evidence — what FDA accepted
source quote (p.6)
“SaMD”
source quote (p.6)
“Machine Learning Model”
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)
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”
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”
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
- 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).