JBS-LVO

K241480

JLK, Inc. · cleared 2024-09-27 · product code QAS · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.5)

“JBS-LVO is a radiological computer aided triage and notification (CADt) software package compliant with the DICOM standard.”

Algorithmartificial intelligence (AI) software algorithm utilizing convolutional neural network (CNN)

source quote (p.6)

“The JBS-LVO Image Analysis Algorithm (LVO Detection Algorithm) is a locked, artificial intelligence (AI) software algorithm utilizing convolutional neural network (CNN) that analyzes CTA images of the brain for a suspected LVO.”

Adaptive (vs locked)No

source quote (p.6)

“The JBS-LVO Image Analysis Algorithm (LVO Detection Algorithm) is a locked, artificial intelligence (AI) software algorithm utilizing convolutional neural network (CNN) that analyzes CTA images of the brain for a suspected LVO.”

PCCPFDA source did not state this

Cybersecurity addressedFDA source did not state this

Validation studies (3)

Bench

sample size not stated

Standalone

sample size not stated

Retrospective clinical

sample size not stated

endpoints: sensitivity; specificity; time-to-notification

Reported performance (4 observations)

sensitivity91.8CI 85.8% to 95.8%

source quote (p.7)

“Specifically, the sensitivity was 91.8% with a 95% confidence interval (CI) of 85.8% to 95.8%.”

specificity92.8CI 87.2% to 96.5%

source quote (p.7)

“The specificity was 92.8% with a 95% CI of 87.2% to 96.5%.”

aurocas written: “auc”95.6CI 93.0% to 98.1%

source quote (p.7)

“The area under the curve (AUC) was 95.6% with a 95% CI of 93.0% to 98.1%.”

time_to_resultas written: “CTA-to-notification time (mean)”2.95CI 2.89 - 3.02

source quote (p.7)

“The total CTA-to-notification time for the JBS-LVO system ranged from 2.32 to 3.29 minutes, with a mean time of 2.95 minutes (95% CI: 2.89 - 3.02).”

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).