Brainomix 360 Triage Stroke

K232496

Brainomix Limited · cleared 2023-11-21 · product code QAS · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.6)
“Brainomix 360 Triage Stroke is a radiological computer aided triage and notification software package compliant with the DICOM standard and running on an off-the-shelf physical or virtual server.”
Algorithmartificial intelligence algorithm that uses advanced non adaptive imaging algorithms, artificial intelligence, and large data analytics. ICH analysis uses hyperdense volume identification. NCCT LVO suspicion uses combined analysis of ASPECTS and hyperdense vessel sign (HDVS) algorithms.
source quote (p.6)
“Brainomix 360 Triage Stroke is a stand-alone software device which uses machine learning algorithms that uses advanced non adaptive imaging algorithms, artificial intelligence, and large data analytics to automatically identify suspected LVO and ICH on non-contrast CT (NCCT) imaging acquired from adult patients in the acute setting, within 24 hours of the onset of the acute symptoms, or where this is unclear, since last known well (LKW) time. The output of the module is a priority notification to clinicians indicating the suspicion of LVO or ICH based on positive findings. Specifically, Brainomix 360 Triage Stroke's ICH analysis is optimized to identify findings of hyperdense volume in the parenchyma typically associated with acute intracranial hemorrhage; and the NCCT LVO suspicion uses the combined analysis of the ASPECTS and hyperdense vessel sign (HDVS) algorithms.”
Adaptive (vs locked)No
source quote (p.6)
“uses advanced non adaptive imaging algorithms”
PCCPFDA source did not state this
Cybersecurity addressedFDA source did not state this

Validation studies (2)

Retrospective clinical

n=267 cases

endpoints: identifying NCCT head images containing intracranial hemorrhage (ICH); identifying NCCT head images containing large vessel occlusion (LVO) findings

standards: EN ISO 14971:2019, IEC 62304:2015

Reader study (MRMC)

sample size not stated

endpoints: expert non-inferiority; non-expert superiority

Reported performance (10 observations)

sensitivity68.75CI 59.71-76.90%
source quote (p.10)
“NCCT LVO performance was observed at 68.75% sensitivity (CI: 59.71-76.90%)”
specificity89.57CI 82.92-94.36%
source quote (p.10)
“NCCT LVO performance was observed at 68.75% sensitivity (CI: 59.71-76.90%) and 89.57% specificity (CI: 82.92-94.36%).”
sensitivityas written: “ICH Sensitivity”92.5CI 80.97-98.36%
source quote (p.10)
“ICH performance was observed at 92.5% sensitivity (95% CI: 80.97-98.36%)”
specificityas written: “ICH Specificity”87.22CI 82.39-91.18%
source quote (p.10)
“and 87.22% specificity (CI: 82.39-91.18%).”
sensitivityas written: “Reader Study Sensitivity (all readers)”47.94CI 37.91-57.97%
source quote (p.10)
“with a sensitivity for all readers (experts and non-experts) of 47.94% (CI: 37.91-57.97%).”
sensitivityas written: “Difference between device sensitivity and all readers”20.52CI 8.26-32.78%
source quote (p.10)
“The difference between the device's sensitivity and that of all readers was 20.52% (CI: 8.26-32.78%).”
sensitivityas written: “Reader Study Sensitivity (general radiologists)”47.18CI 33.62-60.75%
source quote (p.10)
“The general radiologists (non-experts) performed with a sensitivity of 47.18% (CI: 33.62-60.75%).”
sensitivityas written: “Difference between device sensitivity and non-expert sensitivity”21.28CI 5.84-36.72%
source quote (p.10)
“The difference between the device and non-expert sensitivity was 21.28% (CI: 5.84-36.72%).”
time_to_resultas written: “Minimum expected time-to-notification”62
source quote (p.10)
“The results were a minimum expected time-to-notification of 62 seconds”
time_to_resultas written: “Maximum expected time-to-notification”134
source quote (p.10)
“and a maximum of 134 seconds.”

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
1
drift signals on this device
  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K251983 (decision 2025-08-26) from Brainomix Limited for a matching device line ("Brainomix 360 Triage Stroke") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K251983

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/K232496