HALO

K200873

NICo-Lab B.V. · cleared 2020-11-20 · product code QAS · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.3)
HALO is a notification only cloud-based image processing software application using artificial intelligence algorithms to analyze patient imaging data in parallel to the standard of care imaging interpretation.
Algorithmartificial intelligence algorithms
source quote (p.3)
HALO is a notification only cloud-based image processing software application using artificial intelligence algorithms to analyze patient imaging data in parallel to the standard of care imaging interpretation.
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedYes
source quote (p.7)
Non-Clinical software testing has been performed in accordance with the "Guidance for Industry and FDA Staff – Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices” (issued May 11, 2005, document number 337) and “Content of Premarket Submissions for Management of Cybersecurity in Medical Devices” (issued October 2, 2014, document number 1825).

Validation studies (1)

Retrospective clinical

n=364 patients

endpoints: LVO detection; median notification time

standards: Guidance for Industry and FDA Staff – Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices” (issued May 11, 2005, document number 337), Content of Premarket Submissions for Management of Cybersecurity in Medical Devices” (issued October 2, 2014, document number 1825)

Reported performance (4 observations)

sensitivity91.1CI 95% CI, 86.0%-94.8%
source quote (p.7)
For the primary endpoint: calculation of the performance of the HALO algorithm showed a sensitivity and specificity for LVO detection of respectively 91.1% (95% CI, 86.0%-94.8%) and 87.0% (95% CI, 81.2%-91.5%).
specificity87CI 95% CI, 81.2%-91.5%
source quote (p.7)
For the primary endpoint: calculation of the performance of the HALO algorithm showed a sensitivity and specificity for LVO detection of respectively 91.1% (95% CI, 86.0%-94.8%) and 87.0% (95% CI, 81.2%-91.5%).
aurocas written: “auc0.97
source quote (p.7)
The area under the curve (AUC) is 0.97.
time_to_resultas written: “median notification timestated without valueCI minimum of 3:47 and maximal 7:12
source quote (p.7)
For the secondary endpoints the median notification time for the detected LVO cases was 4 minutes 31 seconds, with a minimum of 3:47 and maximal 7:12.

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).

RIGOR™ Precedent · public FDA/CMS data · descriptive decision-support, not regulatory or reimbursement advice. Share this page: radar.healthai.com/precedent/device/K200873