Brainomix 360 Triage Stroke

K251983

Brainomix Limited · cleared 2025-08-26 · product code QAS · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.7)
Brainomix 360 Triage Stroke (also referred to as Triage Stroke in this submission) 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. Triage Stroke is a non-contrast CT processing software-only medical device which operates within the integrated Brainomix 360 Platform to provide triage and notification prioritization of suspected large vessel occlusion (LVO) or intracranial hemorrhage (ICH).
Algorithmmachine learning algorithms such as advanced non adaptive imaging algorithms, artificial intelligence, and large data analytics; updated ICH algorithm using a different deep learning framework, CNN architecture
source quote (p.13)
The proposed device features an updated ICH algorithm using a different deep learning framework, CNN architecture, training data and post-processing capabilities of the algorithm.
Adaptive (vs locked)No
source quote (p.7)
The device uses machine learning algorithms such as advanced non adaptive imaging algorithms, artificial intelligence, and large data analytics.
PCCPFDA source did not state this
Cybersecurity addressedYes
source quote (p.12)
Brainomix 360 Triage Stroke has been designed to follow the FDA Cybersecurity Guidance and IEC 81001-5-1.

Validation studies (3)

Retrospective clinical

n=341 cases

endpoints: assessing the performance of Brainomix 360 Triage Stroke in identifying ICH findings in NCCT head images

standards: ISO 14971:2019, IEC 62304:2015

Retrospective clinical

n=267 cases

endpoints: assessing the performance of Brainomix 360 Triage Stroke in identifying NCCT head images containing large vessel occlusion (LVO) or intracranial hemorrhage (ICH)

standards: ISO 14971:2019, IEC 62304:2015

Reader study (MRMC)

sample size not stated

endpoints: compare NCCT LVO sensitivity of the device to that of radiologists; expert non-inferiority; non-expert superiority

standards: ISO 14971:2019, IEC 62304:2015

Reported performance (14 observations)

sensitivity0.9641CI 95% CI: 92.65-98.65%
source quote (p.10)
sensitivity was 96.41% (95% CI: 92.65-98.65%)
specificity0.9655CI CI: 92.94-98.70%
source quote (p.10)
specificity was 96.55% (CI: 92.94-98.70%).
sensitivityas written: “SAH sensitivity0.8571CI CI: 60.99-97.67%
source quote (p.10)
sensitivity was 85.71% (CI: 60.99-97.67%)
specificityas written: “SAH specificity0.9655CI CI: 80.60-98.87%
source quote (p.10)
specificity was 96.55% (CI: 80.60-98.87%).
sensitivityas written: “LVO sensitivity0.6964CI CI: 60.65-77.70%
source quote (p.11)
NCCT LVO performance was observed at 69.64% sensitivity (CI: 60.65-77.70%)
specificityas written: “LVO specificity0.8957CI CI: 82.92-94.36%
source quote (p.11)
89.57% specificity (CI: 82.92-94.36%).
sensitivityas written: “ICH sensitivity (subset)0.95CI [84.47-99.29%]
source quote (p.11)
sensitivity: 95.00% [84.47-99.29%]
specificityas written: “ICH specificity (subset)0.8811CI [83.39-91.92%]
source quote (p.11)
specificity: 88.11% [83.39-91.92%]).
sensitivityas written: “Reader study sensitivity (all readers)0.4794CI CI: 37.91-57.97%
source quote (p.11)
Triage Stroke passed both conditions, with a sensitivity for all readers (experts and non-experts) of 47.94% (CI: 37.91-57.97%).
sensitivityas written: “Difference in sensitivity (device vs all readers)0.2052CI CI: 8.26-32.78%
source quote (p.11)
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)0.4718CI CI: 33.62-60.75%
source quote (p.11)
The general radiologists (non-experts) performed with a sensitivity of 47.18% (CI: 33.62-60.75%).
sensitivityas written: “Difference in sensitivity (device vs non-expert)0.2128CI CI: 5.84-36.72%
source quote (p.11)
The difference between the device and non-expert sensitivity was 21.28% (CI: 5.84-36.72%).
time_to_resultas written: “Minimum time-to-notification58.3
source quote (p.11)
The minimum time-to-notification was 58.3 seconds
time_to_resultas written: “Maximum time-to-notification150.7
source quote (p.11)
the maximum was 150.7 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
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).

RIGOR™ Precedent · public FDA/CMS data · descriptive decision-support, not regulatory or reimbursement advice. Share this page: radar.healthai.com/precedent/device/K251983