NinesAI

K193351

Nines, Inc. · cleared 2020-04-21 · product code QAS · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.4)

“NinesAI is a software device and does not come into contact with patients.”

AlgorithmArtificial Intelligence (AI) technology to analyze non contrast CT Head scans for the presence of Intracranial Hemorrhage and/or Mass Effect. More specifically, the device utilizes two machine learning (ML) algorithms to detect each finding respectively.

source quote (p.4)

“The image analysis uses Artificial Intelligence (AI) technology to analyze non contrast CT Head scans for the presence of Intracranial Hemorrhage and/or Mass Effect. More specifically, the device utilizes two machine learning (ML) algorithms to detect each finding respectively.”

Adaptive (vs locked)FDA source did not state this

PCCPNo

Cybersecurity addressedNo

Validation studies (1)

Retrospective clinical

sample size not stated · 20 site(s)

endpoints: sensitivity; specificity; Positive Predictive Value; Negative Predictive Value; ROC AUC; time savings relative to standard of care; agreement rate between labelers

Reported performance (8 observations)

sensitivity0.899CI [0.837, 0.940]

source quote (p.7)

“Intracranial Hemorrhage Sensitivity [95% confidence intervals] 0.899 [0.837, 0.940]”

specificity0.974CI [0.994, 0.992]

source quote (p.7)

“Intracranial Hemorrhage Specificity [95% confidence intervals] 0.974 [0.994, 0.992]”

sensitivityas written: “Mass Effect Sensitivity”0.964CI [0.916, 0.987]

source quote (p.7)

“Mass Effect Sensitivity [95% confidence intervals] 0.964 [0.916, 0.987]”

specificityas written: “Mass Effect Specificity”0.911CI [0.856, 0.948]

source quote (p.7)

“Mass Effect Specificity [95% confidence intervals] 0.911 [0.856, 0.948]”

time_to_resultas written: “Time-to-open-dictation standard of care (Intracranial Hemorrhage) Mean”159.4CI [67.07, 251.7]

source quote (p.7)

“Time-to-open-dictation standard of care Mean (min) 159.4 [67.07, 251.7]”

time_to_resultas written: “Time-to-open-dictation standard of care (Intracranial Hemorrhage) Median”6

source quote (p.7)

“Time-to-open-dictation standard of care Median (min) 6.0”

time_to_resultas written: “Time-to-open-dictation standard of care (Mass Effect) Mean”28.5CI [14.1, 42.8]

source quote (p.8)

“Time-to-open-dictation standard of care Mean (min) 28.5 [14.1, 42.8]”

time_to_resultas written: “Time-to-open-dictation standard of care (Mass Effect) Median”7.5

source quote (p.8)

“Time-to-open-dictation standard of care Median (min) 7.5”

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).