Brainomix 360 Triage ICH

K231195

Brainomix Limited · cleared 2023-07-27 · product code QAS · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.6)
“Brainomix 360 Triage ICH 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; machine learning algorithms that uses advanced non adaptive imaging algorithms, artificial intelligence, and large data analytics
source quote (p.5)
“Brainomix 360 Triage ICH uses an artificial intelligence algorithm to analyze images for findings suggestive of a prespecified clinical condition and to notify an appropriate medical specialist of these findings in parallel to standard of care image interpretation. Brainomix 360 Triage ICH 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 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.”
Adaptive (vs locked)No
source quote (p.6)
“advanced non adaptive imaging algorithms”
PCCPNo
Cybersecurity addressedYes
source quote (p.7)
“Both proposed and predicate devices run on standard physical and/or virtual servers which are installed within a hospital network and within the protection of hospital firewalls.”

Validation studies (1)

Retrospective clinical

n=341 scans · 30 site(s)

endpoints: sensitivity; specificity

Reported performance (32 observations)

sensitivity89.22
source quote (p.10)
“The overall performance can also be summarized with the following metrics: sensitivity (or positive percentage agreement, defined as TP/[TP+FN]) was 89.22%”
specificity91.37
source quote (p.10)
“specificity (or negative percentage agreement, defined as TN/[TN+FP]) was 91.37%.”
sensitivityas written: “Sensitivity (Intraparenchymal Hemorrhage (IPH))”96.61CI 88.29-99.59
source quote (p.10)
“Intraparenchymal Hemorrhage (IPH) 96.61% (88.29-99.59)”
sensitivityas written: “Sensitivity (Intraventricular Hemorrhage (IVH))”100CI 59.04-100.00
source quote (p.10)
“Intraventricular Hemorrhage (IVH) 100.00% (59.04-100.00)”
sensitivityas written: “Sensitivity (Subarachnoid Hemorrhage (SAH))”35.71CI 12.76-64.86
source quote (p.10)
“Subarachnoid Hemorrhage (SAH) 35.71% (12.76-64.86)”
sensitivityas written: “Sensitivity (Subdural Hemorrhage (SDH))”66.67CI 40.99-86.66
source quote (p.11)
“Subdural Hemorrhage (SDH) 66.67% (40.99-86.66)”
sensitivityas written: “Sensitivity (Multiple ICH Types)”98.55CI 92.19-99.96
source quote (p.11)
“Multiple Types 98.55% (92.19-99.96)”
sensitivityas written: “Sensitivity (Male)”93.18CI 85.75-97.46
source quote (p.11)
“Male 93.18% (85.75-97.46)”
specificityas written: “Specificity (Male)”91.3CI 83.58-96.17
source quote (p.11)
“Male 91.30% (83.58-96.17)”
sensitivityas written: “Sensitivity (Female)”84.81CI 74.97-91.90
source quote (p.11)
“Female 84.81% (74.97-91.90)”
specificityas written: “Specificity (Female)”91.46CI 83.20-96.50
source quote (p.11)
“Female 91.46% (83.20-96.50)”
sensitivityas written: “Sensitivity (Age 21-50)”83.33CI 67.19-93.63
source quote (p.11)
“21 < Age < 50 83.33% (67.19-93.63)”
specificityas written: “Specificity (Age 21-50)”88.73CI 79.00-95.01
source quote (p.11)
“21 < Age < 50 88.73% (79.00-95.01)”
sensitivityas written: “Sensitivity (Age 50-70)”92.75CI 83.89-97.61
source quote (p.11)
“50 ≤ Age < 70 92.75% (83.89-97.61)”
specificityas written: “Specificity (Age 50-70)”91.25CI 82.80-96.41
source quote (p.11)
“50 ≤ Age < 70 91.25% (82.80-96.41)”
sensitivityas written: “Sensitivity (Age >= 70)”88.71CI 78.11-95.34
source quote (p.11)
“Age ≥ 70 88.71% (78.11-95.34)”
specificityas written: “Specificity (Age >= 70)”100CI 85.18-100.00
source quote (p.11)
“Age ≥ 70 100.00% (85.18-100.00)”
sensitivityas written: “Sensitivity (Slice Thickness < 1.5 mm)”87.5CI 79.92-92.99
source quote (p.11)
“Slice Thickness < 1.5 mm 87.50% (79.92-92.99)”
specificityas written: “Specificity (Slice Thickness < 1.5 mm)”94.21CI 88.44-97.64
source quote (p.11)
“Slice Thickness < 1.5 mm 94.21% (88.44-97.64)”
sensitivityas written: “Sensitivity (Slice Thickness 1.5-3 mm)”95.65CI 78.05-99.89
source quote (p.11)
“1.5mm ≤ Slice Thickness < 3 mm 95.65% (78.05-99.89)”
specificityas written: “Specificity (Slice Thickness 1.5-3 mm)”100CI 82.35-100.00
source quote (p.11)
“1.5mm ≤ Slice Thickness < 3 mm 100.00% (82.35-100.00)”
sensitivityas written: “Sensitivity (Slice Thickness >= 3 mm)”90.62CI 74.98-98.02
source quote (p.11)
“Slice Thickness ≥ 3 mm 90.62% (74.98-98.02)”
specificityas written: “Specificity (Slice Thickness >= 3 mm)”76.47CI 58.83-89.25
source quote (p.11)
“Slice Thickness ≥ 3 mm 76.47% (58.83-89.25)”
sensitivityas written: “Sensitivity (Boston Medical Centre)”89.38CI 82.18-94.39
source quote (p.11)
“Boston Medical Centre 89.38% (82.18-94.39)”
specificityas written: “Specificity (Boston Medical Centre)”94.35CI 88.71-97.70
source quote (p.11)
“Boston Medical Centre 94.35% (88.71-97.70)”
sensitivityas written: “Sensitivity (Other Clinical Sites)”88.89CI 77.37-95.81
source quote (p.11)
“Other 88.89% (77.37-95.81)”
specificityas written: “Specificity (Other Clinical Sites)”84CI 70.89-92.83
source quote (p.11)
“Other 84.00% (70.89-92.83)”
sensitivityas written: “Sensitivity (ICH Volume >= 0 ml)”89.22CI 83.50-93.49
source quote (p.11)
“vol ≥ 0 ml 89.22% (83.50-93.49)”
sensitivityas written: “Sensitivity (ICH Volume >= 0.4ml)”94.59CI 89.63-97.64
source quote (p.11)
“vol ≥ 0.4ml 94.59% (89.63-97.64)”
sensitivityas written: “Sensitivity (ICH Volume >= 1ml)”97.04CI 92.59-99.19
source quote (p.11)
“vol ≥ 1ml 97.04% (92.59-99.19)”
sensitivityas written: “Sensitivity (ICH Volume >= 5ml)”99.04CI 94.76-99.98
source quote (p.11)
“vol ≥ 5ml 99.04% (94.76-99.98)”
time_to_resultas written: “Time to notification (device)”stated without valueCI 50 seconds to 126 seconds
source quote (p.11)
“This ranged from 50 seconds to 126 seconds, and is substantially lower than the average time to notification seen in the Standard of Care reported by the predicate device (38.2 minutes).”

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); 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/K231195