JLK-NCCT

K252421

JLK, Inc. · cleared 2026-03-24 · product code QAS · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.4)

“JLK-NCCT is a radiological computer-aided triage and notification software designed for analyzing non-contrast head CT (NCCT) images.”

Algorithmartificial intelligence (AI) algorithm

source quote (p.4)

“JLK-NCCT employs an artificial intelligence (AI) algorithm to analyze images and highlight cases with detected (1) ICH or (2) LVO on an on-premises or cloud-based JLK server.”

Adaptive (vs locked)FDA source did not state this

PCCPNo

Cybersecurity addressedNo

Validation studies (2)

Standalone

n=288 cases

endpoints: sensitivity; specificity; area under the curve (AUC); time-to-notification performance

standards: ISO 13485, ISO 13484

Reader study (MRMC)

sample size not stated

endpoints: Neuroradiologist non-inferiority; General Radiologist superiority; sensitivity; specificity

Reported performance (6 observations)

sensitivity78.5CI 71.9%–84.7%

source quote (p.8)

“the observed sensitivity was 78.5% (95% Confidence Interval [CI]: 71.9%–84.7%)”

specificity90.3CI 85.1%–94.7%

source quote (p.8)

“the specificity was 90.3% (95% CI: 85.1%–94.7%)”

aurocas written: “auc”0.88CI 0.837–0.920

source quote (p.8)

“The area under the curve (AUC) was 0.880 with a 95% CI of 0.837–0.920.”

time_to_resultas written: “average NCCT-to-notification time”1.67

source quote (p.8)

“For suspected LVO cases, the system demonstrated triage with an average NCCT-to-notification time of 1.67 ± 0.10 minutes.”

sensitivityas written: “reader study sensitivity (JLK-NCCT)”0.792

source quote (p.9)

“JLK-NCCT demonstrated a sensitivity of 0.792 and passed the conditions compared to all readers (Neuroradiologist and General Radiologist) whose average sensitivity was 0.568”

specificityas written: “reader study specificity (JLK-NCCT)”0.933

source quote (p.9)

“Also, JLK-NCCT demonstrated a specificity of 0.933 and passed the conditions compared to all readers (Neuroradiologist and General Radiologist) whose average specificity was 0.840”

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).