syngo.CT LVO Detection
K243145Siemens Medical Solutions USA, Inc. · cleared 2025-04-10 · product code QAS · Radiology
Premarket evidence — what FDA accepted
Device typesamd
source quote (p.6)
“The subject device syngo.CT LVO Detection is an image processing software that utilizes artificial intelligence learning algorithms to support qualified clinicians (Radiologists, Neuroradiologists, Neurologists) in prioritization of CT-angiography images by algorithmically identifying findings suspicious of a large vessel occlusion and providing notification to the user.”
Algorithmartificial intelligence learning algorithms
source quote (p.6)
“The subject device syngo.CT LVO Detection is an image processing software that utilizes artificial intelligence learning algorithms to support qualified clinicians (Radiologists, Neuroradiologists, Neurologists) in prioritization of CT-angiography images by algorithmically identifying findings suspicious of a large vessel occlusion and providing notification to the user.”
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedFDA source did not state this
Validation studies (1)
Retrospective clinical
n=602 patients · 4 site(s)
endpoints: sensitivity; specificity
standards: IEC 62304, NEMA PS 3.1 - 3.20, ISO 14971, IEC 62366-1, ISO 15223-1, ISO 20417:2021
Reported performance (2 observations)
sensitivity90.6CI [86.8% - 93.3%]
source quote (p.8)
“The observed sensitivity and specificity with 95%-confidence intervals were 90.6% [86.8% - 93.3%] and 88.8% [84.7% – 91.9%], respectively, exceeding the predefined acceptance threshold of >80% sensitivity and specificity.”
specificity88.8CI [84.7% – 91.9%]
source quote (p.8)
“The observed sensitivity and specificity with 95%-confidence intervals were 90.6% [86.8% - 93.3%] and 88.8% [84.7% – 91.9%], respectively, exceeding the predefined acceptance threshold of >80% sensitivity and specificity.”
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
0
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).