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.”
AlgorithmMachine Learning Model
source quote (p.7)
“Machine Learning Model”
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)

Retrospective clinical

n=877 cases · 11 site(s)

endpoints: detection of any suspicious radiographic finding; detection of each suspicious radiographic finding

Reader study (MRMC)

n=200 cases

endpoints: identification of any suspicious radiographic finding; identification of each suspicious radiographic finding

Reported performance (11 observations)

sensitivity0.935CI 0.892-0.978
source quote (p.11)
“The mean sensitivity for identification of any claimed suspicious finding was 0.935 (0.892-0.978) in the aided reading condition vs 0.782 (0.686-0.878) in the unaided reading condition: +15.3% increase in sensitivity.”
specificity0.97CI 0.949-0.991
source quote (p.11)
“The mean specificity for identification of any claimed suspicious finding was 0.970 (0.949-0.991) in the aided reading condition vs 0.759 (0.630-0.887) in the unaided reading condition: +21.1% increase in specificity.”
aurocas written: “auc”0.974CI 0.957; 0.990
source quote (p.11)
“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) vs 0.825 (0.741-0.908), p=0.002 (using the Dorfman-Berbaum-Metz and Obuchowski-Rockette method): +14.9% increase in AUC.”
aurocas written: “Overriding artery AUC (aided)”0.953CI 0.916; 0.990
source quote (p.11)
“0.953 (0.916; 0.990)”
aurocas written: “Cardiac crux septal defect AUC (aided)”0.971CI 0.943; 0.999
source quote (p.11)
“0.971 (0.943; 0.999)”
aurocas written: “Abn. OT relationship AUC (aided)”0.972CI 0.953; 0.992
source quote (p.11)
“0.972 (0.953; 0.992)”
aurocas written: “Enlarged CTR AUC (aided)”0.96CI 0.930; 0.989
source quote (p.11)
“0.960 (0.930; 0.989)”
aurocas written: “Cardiac axis deviation AUC (aided)”0.967CI 0.932; 1.000
source quote (p.11)
“0.967 (0.932; 1.000)”
aurocas written: “PV/AV size discrepancy AUC (aided)”0.979CI 0.962; 0.997
source quote (p.11)
“0.979 (0.962; 0.997)”
aurocas written: “RV/LV size discrepancy AUC (aided)”0.991CI 0.983; 0.999
source quote (p.11)
“0.991 (0.983; 0.999)”
aurocas written: “TV/MV size discrepancy AUC (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

0
recalls in product code, 24mo
0
MAUDE reports in code, 12mo
—
vs code's own 3-yr baseline
2
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); 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 Radiology 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/K242342