CuraRad-ICH
K192167CuraCloud Corp. · cleared 2020-04-13 · product code QAS · Radiology
Premarket evidence — what FDA accepted
Device typesamd
source quote (p.4)
“CuraRad-ICH is software as a medical device (SaMD) that detects intracranial hemorrhage (ICH) condition by analyzing non-contrast CT images.”
Algorithmdeep learning algorithm utilizing an end-to-end trainable 3D classification framework
source quote (p.5)
“The core technology of this software is a deep learning algorithm trained on non-contrast head CT scans with ICH ground truth provided by experienced radiologists. The algorithm utilizes an end-to-end trainable 3D classification framework for automatic ICH detection.”
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=388 cases · 296 site(s)
endpoints: identifying ICH findings from non-contrast head CT scans; system processing time of the device
Reported performance (8 observations)
sensitivity90.6CI 95% CI: 85.9%–94.2%
source quote (p.6)
“The observed ICH detection sensitivity was 90.6% (95% CI: 85.9%–94.2%)”
specificity93.1CI 95% CI: 88.3%–96.4%
source quote (p.6)
“and specificity was 93.1% (95% CI: 88.3%–96.4%)”
ppvas written: “Positive Predictive Value (1% prevalence)”11.8CI 95% CI: 7.2%-18.8%
source quote (p.6)
“At a prevalence rate of 1%, PPV was 11.8% (95% CI: 7.2%-18.8%)”
npvas written: “Negative Predictive Value (1% prevalence)”99.9CI 95% CI: 99.8%-100%
source quote (p.6)
“and NPV was 99.9% (95% CI: 99.8%-100%).”
ppvas written: “Positive Predictive Value (15% prevalence)”70CI 95% CI: 57.4%-80.1%
source quote (p.6)
“At a prevalence rate of 15%, PPV was 70% (95% CI: 57.4%-80.1%)”
npvas written: “Negative Predictive Value (15% prevalence)”98.3CI 95% CI: 97.4%-98.8%
source quote (p.6)
“and NPV was 98.3% (95% CI: 97.4%-98.8%).”
ppvas written: “Positive Predictive Value (54.9% prevalence)”89.1CI 95% CI: 84.3%-92.5%
source quote (p.6)
“At a prevalence rate of 54.9%, PPV was 89.1% (95% CI: 84.3%-92.5%)”
npvas written: “Negative Predictive Value (54.9% prevalence)”91.8CI 88.6%-94.3%
source quote (p.6)
“and NPV was 91.8% (88.6%-94.3%).”
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).