Brainomix 360 e-ASPECTS

K243294

Brainomix Limited · cleared 2025-02-14 · product code POK · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.7)

“Brainomix 360 e-ASPECTS is a stand-alone software device which uses machine learning algorithms to automatically process NCCT brain image data to provide an output ASPECTS score based on the Alberta Stroke Program Early CT Score (ASPECTS) guidelines.”

AlgorithmML/AI/Random Forest

source quote (p.17)

“ML/AI/Random Forest”

Adaptive (vs locked)FDA source did not state this

PCCPFDA source did not state this

Cybersecurity addressedYes

source quote (p.13)

“Brainomix 360 e-ASPECTS has been designed to follow the FDA Cybersecurity Guidance and IEC 81001-5-1.”

Validation studies (3)

Bench

n=110 cases

endpoints: absolute bias of the difference between volumes computed and ground truth (< 12 mL); the standard deviation (SD) of the difference between volumes computed and the ground truth (< 19 mL); Pearson's correlation between volume contributing to e-ASPECTS and known phantom volumes (> 0.86)

Retrospective clinical

n=137 patients · 3 site(s)

endpoints: Region-level sensitivity; Region-level specificity; Region-level AUC; Case-level agreement; Positive percentage agreement; Negative percentage agreement

Reader study (MRMC)

n=140 scans

endpoints: AUC; Sensitivity; Specificity; Cohen's Kappa; Weighted Kappa

Reported performance (8 observations)

sensitivity0.69CI 56-75%

source quote (p.11)

“with a sensitivity of 69% (95% CI: 56-75%)”

specificity0.97CI 80-97%

source quote (p.11)

“and a specificity of 97% (95% CI: 80-97%).”

aurocas written: “auc”0.83CI 80-86%

source quote (p.11)

“Overall performance in 137 showed an area under the curve (AUC) of 83% (95% CI: 80-86%)”

aurocas written: “AUC (reader study with e-ASPECTS support)”0.85

source quote (p.12)

“Comparison of the area under the curve (AUC) for readers with and without e-ASPECTS support showed a statistically significant improvement of 6.4%, from 78% without e-ASPECTS to 85% with e-ASPECTS (p=.03), which was the primary outcome measure of the study.”

sensitivityas written: “Sensitivity (reader study with e-ASPECTS support)”0.72

source quote (p.12)

“This was driven by an improvement in sensitivity (from 61% to 72%)”

specificityas written: “Specificity (reader study with e-ASPECTS support)”0.98

source quote (p.12)

“and a small improvement in specificity (from 96% to 98%).”

agreement_kappaas written: “Cohen's Kappa”stated without value

source quote (p.12)

“Cohen's Kappa and weighted Kappa also improved significantly with versus without e-ASPECTS.”

agreement_kappaas written: “Weighted Kappa”stated without value

source quote (p.12)

“Cohen's Kappa and weighted Kappa also improved significantly with versus without e-ASPECTS.”

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

recalls in product code, 24mo

MAUDE reports in code, 12mo

—

vs code's own 3-yr baseline

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).