Fetal EchoScan

K242342

BrightHeart · cleared 2024-11-14 · product code POK · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.5)

“Fetal EchoScan is a cloud-based software-only device which uses neural networks to detect suspicious cardiac radiographic findings for further review by trained and qualified physicians.”

Algorithmneural networks

source quote (p.5)

“Fetal EchoScan is a cloud-based software-only device which uses neural networks to detect suspicious cardiac radiographic findings for further review by trained and qualified physicians.”

Adaptive (vs locked)FDA source did not state this

PCCPFDA source did not state this

Cybersecurity addressedYes

source quote (p.8)

“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 (2)

Standalone

n=877 cases · 11 site(s)

endpoints: Sensitivity; Specificity

standards: IEC 62304:2016

Reader study (MRMC)

n=200 cases

endpoints: ROC AUC; Sensitivity; Specificity

Reported performance (13 observations)

sensitivity0.977CI 0.954; 0.989

source quote (p.10)

“0.977 (0.954; 0.989)”

specificity0.977CI 0.961; 0.987

source quote (p.10)

“0.977 (0.961; 0.987)”

aurocas written: “auc”0.974CI 0.957; 0.990

source quote (p.11)

“0.974 (0.957; 0.990)”

sensitivityas written: “Sensitivity (Best-Case) for Any suspicious findings (Inconclusive Exams Counted as Positive)”0.987CI 0.967; 0.995

source quote (p.10)

“0.987 (0.967; 0.995)”

specificityas written: “Specificity (Worst-Case) for Any suspicious findings (Inconclusive Exams Counted as Positive)”0.963CI 0.944; 0.976

source quote (p.10)

“0.963 (0.944; 0.976)”

aurocas written: “Model Estimate AUC (95% CI) for Overriding artery (Aided)”0.953CI 0.916; 0.990

source quote (p.11)

“0.953 (0.916; 0.990)”

aurocas written: “Model Estimate AUC (95% CI) for Cardiac crux septal defect (Aided)”0.971CI 0.943; 0.999

source quote (p.11)

“0.971 (0.943; 0.999)”

aurocas written: “Model Estimate AUC (95% CI) for Abn. OT relationship (Aided)”0.972CI 0.953; 0.992

source quote (p.11)

“0.972 (0.953; 0.992)”

aurocas written: “Model Estimate AUC (95% CI) for Enlarged CTR (Aided)”0.96CI 0.930; 0.989

source quote (p.11)

“0.960 (0.930; 0.989)”

aurocas written: “Model Estimate AUC (95% CI) for Cardiac axis deviation (Aided)”0.967CI 0.932; 1.000

source quote (p.11)

“0.967 (0.932; 1.000)”

aurocas written: “Model Estimate AUC (95% CI) for PV/AV size discrepancy (Aided)”0.979CI 0.962; 0.997

source quote (p.11)

“0.979 (0.962; 0.997)”

aurocas written: “Model Estimate AUC (95% CI) for RV/LV size discrepancy (Aided)”0.991CI 0.983; 0.999

source quote (p.11)

“0.991 (0.983; 0.999)”

aurocas written: “Model Estimate AUC (95% CI) for TV/MV size discrepancy (Aided)”0.964CI 0.938; 0.990

source quote (p.11)

“0.964 (0.938; 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

recalls in product code, 24mo

MAUDE reports in code, 12mo

—

vs code's own 3-yr baseline

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
re_clearance
The FDA AI/ML device list shows a newer 510(k) K251071 (decision 2025-05-02) from BrightHeart for a matching device line ("Fetal EchoScan (v1.1)") — a new clearance for the same line is a change event.
first seen 2026-07-08 · k_number:K251071

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).