JLK-SDH

K243611

JLK, Inc. · cleared 2025-03-03 · product code QAS · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.5)
“JLK-SDH is a radiological computer-assisted triage and notification (CADt) software package compliant with the DICOM standard. Utilizing an artificial intelligence algorithm, the system automatically receives and analyzes NCCT studies for image features indicating the presence of SDH and sends a notification to alert a radiologist of the case.”
Algorithmartificial intelligence algorithm, convolutional neural network (CNN), AI/ML algorithms
source quote (p.5)
“Utilizing an artificial intelligence algorithm, the system automatically receives and analyzes NCCT studies for image features indicating the presence of SDH and sends a notification to alert a radiologist of the case. The training dataset utilized to develop the convolutional neural network (CNN) included 29,524 non-contrast CT (NCCT) scans that had been obtained in patients with and without intracranial hemorrhage.”
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=560 scans

endpoints: sensitivity; specificity

standards: §892.2080 special controls

Reported performance (4 observations)

sensitivity0.971CI 95% confidence interval (CI) of 94.4% to 99.4%
source quote (p.9)
“Specifically, the sensitivity was 97.1%, with a 95% confidence interval (CI) of 94.4% to 99.4%.”
specificity0.974CI 95% CI of 95.8% to 99.0%
source quote (p.9)
“The specificity was 97.4%, with a 95% CI of 95.8% to 99.0%.”
aurocas written: “auc”0.974CI 95% CI of 0.958 to 0.989
source quote (p.9)
“The area under the curve (AUC) was 0.974 with a 95% CI of 0.958 to 0.989.”
time_to_resultas written: “time-to-notification”0.19CI ±0.05 minutes
source quote (p.12)
“A secondary endpoint of time-to-notification from non-contrast CT scans to notification for SDH-positive cases was also evaluated. The JLK-SDH system for SDH-positive cases demonstrated efficient triage with a total NCCT-to-notification time ranging from an average of 11.49±3.04 seconds (0.19± 0.05 minutes), which successfully meets the target of 69.1±34.3 seconds (1.15±0.57 minutes) established by the predicate device, Viz SDH (K220439).”

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); a recall is shown as device-attributed only when the recall record itself lists this clearance number. 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).

Applicable FDA guidance — what the submission is measured against

FDA guidance documents and guiding principles applicable to 510(k) AI/ML devices in the Radiology panel. A curated reference index, not legal or regulatory advice — each item states its own status, and a draft is never binding.

Applicability is derived from the device's FDA advisory panel and pathway — cross-cutting guidances apply to every AI/ML device; panel-specific ones are flagged. Titles, dates, and links verified against fda.gov as of July 2026.

Constat Precedent · public FDA/CMS data · descriptive decision-support, not regulatory or reimbursement advice. Share this page: constat.dev/precedent/device/K243611