syngo.CT Brain Hemorrhage

K232431

Siemens Medical Solutions USA, Inc. · cleared 2024-03-22 · product code QAS · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.5)

“The subject device syngo.CT Brain Hemorrhage is an image-processing software that uses an artificial intelligence algorithm to support qualified clinicians in the analysis and prioritization of non-contrast head CT images.”

Algorithmartificial intelligence algorithm

source quote (p.5)

“The subject device syngo.CT Brain Hemorrhage is an image-processing software that uses an artificial intelligence algorithm to support qualified clinicians in the analysis and prioritization of non-contrast head CT images.”

Adaptive (vs locked)No

PCCPNo

Cybersecurity addressedNo

Validation studies (1)

Retrospective clinical

n=900 cases · 5 site(s)

endpoints: triage of intracranial hemorrhage (sensitivity and specificity); triage of subarachnoid hemorrhage (sensitivity and specificity); average per-case processing time

standards: ANSI AAMI IEC 62304, NEMA PS 3.1 - 3.20 2022d, ISO 14971, IEC 62366-1, ISO 15223-1, ISO 20417:2021

Reported performance (4 observations)

sensitivity95CI 92.5%-96.7%

source quote (p.7)

“For the triage of intracranial hemorrhage, the sensitivity was 95.0% (95% CI: 92.5%-96.7%) and the specificity was 93.1% (95% CI: 90.5%-95.1%).”

specificity93.1CI 90.5%-95.1%

source quote (p.7)

“For the triage of intracranial hemorrhage, the sensitivity was 95.0% (95% CI: 92.5%-96.7%) and the specificity was 93.1% (95% CI: 90.5%-95.1%).”

sensitivityas written: “Sensitivity for triage of subarachnoid hemorrhage”86.1CI 81.1%-90.0%

source quote (p.7)

“For the triage of subarachnoid hemorrhage, the sensitivity was 86.1% (95% CI: 81.1%-90.0%) and the specificity was 85.2% (95% CI: 82.3%-87.7%).”

specificityas written: “Specificity for triage of subarachnoid hemorrhage”85.2CI 82.3%-87.7%

source quote (p.7)

“For the triage of subarachnoid hemorrhage, the sensitivity was 86.1% (95% CI: 81.1%-90.0%) and the specificity was 85.2% (95% CI: 82.3%-87.7%).”

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

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).