encevis (2.1)

K240993

AIT Austrian Institute of Technology GmbH · cleared 2024-09-27 · product code OMB · Neurology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.8)
“encevis combines several modalities for viewing and analyzing EEG data in one integrated software package. The software package can be used both as a standalone desktop application for opening and analyzing stored EEG files (offline mode) and as a module for integration into external EEG systems via the provided API interfaces, enabling the processing of real-time streaming data in online mode.”
AlgorithmAI-model
source quote (p.22)
“the seizure detection algorithm of the subject device (encevis 2.1) combines detections of the algorithm in encevis 1.12 and an additional AI-model to achieve high sensitivity.”
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedFDA source did not state this

Validation studies (6)

Retrospective clinical

n=55 patients

endpoints: positive percentage agreement (detection sensitivity based on the reference standard); negative disagreement rate (false detections per 24 hours based on reference standard)

Retrospective clinical

n=81 patients · 2 site(s)

endpoints: positive percentage agreement (PPA, sensitivity) for seizure detection; negative disagreement rate (NDR, given as false detections in one hour) for seizure detection; positive percentage agreement (PPA, sensitivity) for electrographic status epilepticus detection; negative percentage agreement (NPA, specificity) for electrographic status epilepticus detection; positive percentage agreement (PPA, sensitivity) for short-time seizure burden (STSB); negative percentage agreement (NPA, specificity) for short-time seizure burden (STSB); positive percentage agreement (PPA, sensitivity) for hourly seizure burden (HSB); negative percentage agreement (NPA, specificity) for hourly seizure burden (HSB)

standards: ACNS criteria

Retrospective clinical

n=23 patients

endpoints: positive percentage agreement (PPA); negative percentage agreement (NPA); positive localization percentage agreement (PLPA)

Bench

n=128 cases

endpoints: relative suppression of true EEG in dB; signal-to-noise ratio after artifact removal

Retrospective clinical

n=83 scans · 2 site(s)

endpoints: sensitivity; specificity

standards: ACNS (American Clinical Neurophysiology Society) ICU EEG Terminology (Hirsch et al., 2013)

Retrospective clinical

n=83 scans · 2 site(s)

endpoints: sensitivity (SE); specificity (SP); positive predictive value (PPV); negative predictive value (NPV)

Reported performance (14 observations)

sensitivity0.826CI 60.9%-95.7%
source quote (p.29)
“The PPA for ESE detection with encevis 2.1 is 82.6% [CI 60.9%-95.7%]”
specificity0.914CI 81.0%-96.6%
source quote (p.29)
“whereas the NPA was 91.4% [CI 81.0%-96.6%]”
sensitivityas written: “Sensitivity for ANY pattern detection”0.8186CI 79.9-83.8
source quote (p.38)
“ANY 81.86 (79.9-83.8)”
specificityas written: “Specificity for ANY pattern detection”0.838CI 83.1-84.5
source quote (p.38)
“ANY 83.80 (83.1-84.5)”
sensitivityas written: “Sensitivity for PD pattern detection”0.6973CI 67.2 - 72.3
source quote (p.38)
“PD 69.73 (67.2 - 72.3)”
specificityas written: “Specificity for PD pattern detection”0.9589CI 95.5-96.3
source quote (p.38)
“PD 95.89 (95.5-96.3)”
sensitivityas written: “Sensitivity for ARA pattern detection”0.894CI 84.2-94.6
source quote (p.39)
“ARA (including RTA, RAA, RDA+SW) 89.40 (84.2- 94.6)”
specificityas written: “Specificity for ARA pattern detection”0.9485CI 94.5-95.3
source quote (p.39)
“ARA (including RTA, RAA, RDA+SW) 94.85 (94.5-95.3)”
sensitivityas written: “Sensitivity for RDA pattern detection”0.9173CI 86.4 - 97.1
source quote (p.39)
“RDA 91.73 (86.4 - 97.1)”
specificityas written: “Specificity for RDA pattern detection”0.8605CI 85.4-86.7
source quote (p.39)
“RDA 86.05 (85.4-86.7)”
sensitivityas written: “Sensitivity for Burst Suppression”0.87
source quote (p.41)
“SE (%) 87”
specificityas written: “Specificity for Burst Suppression”0.92
source quote (p.41)
“SP (%) 92”
ppvas written: “Positive Predictive Value for Burst Suppression”0.61
source quote (p.41)
“PPV (%) 61”
npvas written: “Negative Predictive Value for Burst Suppression”0.98
source quote (p.41)
“NPV (%) 98”

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
-100%
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 Neurology 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/K240993