JLK-ICH
K243363JLK, Inc. · cleared 2025-01-03 · product code QAS · Radiology
Premarket evidence — what FDA accepted
Device typesamd
source quote (p.4)
“JLK-ICH is a radiological computer-aided triage and notification software indicated for use in the analysis of non-contrast CT images.”
Algorithmartificial intelligence and machine learning (AI/ML) algorithms
source quote (p.7)
“Both the subject and predicate devices utilize artificial intelligence and machine learning (AI/ML) algorithms and mobile notification software to identify and notify specialists, respectively, of patients with the presence of suspected intracranial hemorrhage (ICH) on non-contrast CT imaging of the head.”
Adaptive (vs locked)No
source quote (p.6)
“All cases are carefully separated from the clinical performance datasets.”
PCCPFDA source did not state this
Cybersecurity addressedFDA source did not state this
Validation studies (2)
Bench
sample size not stated
Retrospective clinical
n=376 cases
endpoints: sensitivity; standalone performance; notification functionality
standards: IEC 80002-2080
Reported performance (4 observations)
sensitivity0.973CI 94.8% to 99.5%
source quote (p.9)
“Specifically, the sensitivity was 97.3% with a 95% confidence interval (CI) of 94.8% to 99.5%.”
specificity0.979CI 95% CI of 95.5% to 99.5%
source quote (p.9)
“The specificity was 97.9% with a 95% CI of 95.5% to 99.5%.”
aurocas written: “auc”0.978CI 0.959 to 0.992
source quote (p.9)
“The area under the curve (AUC) was 0.978 with a 95% CI of 0.959 to 0.992.”
time_to_resultas written: “NCCT-to-notification time”0.19CI 0.186 to 0.197
source quote (p.11)
“The JLK-ICH system for ICH-positive cases demonstrated efficient triage with a total NCCT-to-notification time ranging from an average of 0.19±0.04 minutes, which successfully meets the target of 0.49±0.15 minutes established by the predicate device, Viz ICH (K193658).”
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).