Accipiolx
K201310MaxQ Al Ltd. · cleared 2020-08-07 · product code QAS · Radiology
Premarket evidence — what FDA accepted
Device typesamd
source quote (p.4)
“Accipiolx is a software device designed to be installed within healthcare facility radiology networks to identify and prioritize non-contrast head CT (NCCT) scans based on algorithmically-identified findings of acute intracranial hemorrhage (aICH). The device, which utilizes deep learning technologies, facilitates prioritization of CT scans containing findings of aICH.”
Algorithmdeep learning technologies, algorithmic methods involving execution of multiple computational steps, CNN-based segmentation
source quote (p.4)
“Accipiolx is a software device designed to be installed within healthcare facility radiology networks to identify and prioritize non-contrast head CT (NCCT) scans based on algorithmically-identified findings of acute intracranial hemorrhage (aICH). The device, which utilizes deep learning technologies, facilitates prioritization of CT scans containing findings of aICH. Accipiolx receives CT scans identified by the Accipio Agent or other compatible Medical Image Communications Device (MICD), processes them using algorithmic methods involving execution of multiple computational steps to identify suspected presence of aICH, and generates a results file to be transferred by the Accipio Agent or a similar MICD device for output to a PACS system or workstation for worklist prioritization.”
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedFDA source did not state this
Validation studies (1)
Retrospective clinical
n=360 cases · 17 site(s)
endpoints: Sensitivity; Specificity; average per-case processing time
Reported performance (6 observations)
sensitivity0.97CI 95% CI: 92.8% - 98.8%
source quote (p.7)
“Analysis of 360 newly tested cases collected from multiple sites across 17 US states demonstrated device Sensitivity and Specificity of 97% (95% CI: 92.8% - 98.8%) and 93% (95% CI: 88.6% - 96.6%), respectively.”
specificity0.93CI 95% CI: 88.6% - 96.6%
source quote (p.7)
“Analysis of 360 newly tested cases collected from multiple sites across 17 US states demonstrated device Sensitivity and Specificity of 97% (95% CI: 92.8% - 98.8%) and 93% (95% CI: 88.6% - 96.6%), respectively.”
sensitivityas written: “Sensitivity for intra-axial hemorrhages”1CI 95% CI: 96.6% - 100%
source quote (p.7)
“Sensitivity for intra-axial and extra-axial hemorrhages was 100% (95% CI: 96.6% - 100%) and 92% (95% CI: 82.7% - 96.9%), respectively.”
sensitivityas written: “Sensitivity for extra-axial hemorrhages”0.92CI 95% CI: 82.7% - 96.9%
source quote (p.7)
“Sensitivity for intra-axial and extra-axial hemorrhages was 100% (95% CI: 96.6% - 100%) and 92% (95% CI: 82.7% - 96.9%), respectively.”
npvas written: “NPV”0.998CI 95% CI: 99.7% - 100%
source quote (p.8)
“Analysis of additional accuracy parameters, tested as secondary endpoints, demonstrated NPV and PPV of 99.8% (95% CI: 99.7% - 100%) and 43.3% (95% CI: 25.9% - 53%), respectively.”
ppvas written: “PPV”0.433CI 95% CI: 25.9% - 53%
source quote (p.8)
“Analysis of additional accuracy parameters, tested as secondary endpoints, demonstrated NPV and PPV of 99.8% (95% CI: 99.7% - 100%) and 43.3% (95% CI: 25.9% - 53%), respectively.”
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).