Brainomix 360 Triage Stroke
K251983Brainomix Limited · cleared 2025-08-26 · product code QAS · Radiology
Premarket evidence — what FDA accepted
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).”
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.”
source quote (p.7)
“The device uses machine learning algorithms such as advanced non adaptive imaging algorithms, artificial intelligence, and large data analytics.”
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)
source quote (p.10)
“sensitivity was 96.41% (95% CI: 92.65-98.65%)”
source quote (p.10)
“specificity was 96.55% (CI: 92.94-98.70%).”
source quote (p.10)
“sensitivity was 85.71% (CI: 60.99-97.67%)”
source quote (p.10)
“specificity was 96.55% (CI: 80.60-98.87%).”
source quote (p.11)
“NCCT LVO performance was observed at 69.64% sensitivity (CI: 60.65-77.70%)”
source quote (p.11)
“89.57% specificity (CI: 82.92-94.36%).”
source quote (p.11)
“sensitivity: 95.00% [84.47-99.29%]”
source quote (p.11)
“specificity: 88.11% [83.39-91.92%]).”
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%).”
source quote (p.11)
“The difference between the device's sensitivity and that of all readers was 20.52% (CI: 8.26-32.78%).”
source quote (p.11)
“The general radiologists (non-experts) performed with a sensitivity of 47.18% (CI: 33.62-60.75%).”
source quote (p.11)
“The difference between the device and non-expert sensitivity was 21.28% (CI: 5.84-36.72%).”
source quote (p.11)
“The minimum time-to-notification was 58.3 seconds”
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
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).