Nelli (Version 7.11)

K251506

Neuro Event Labs OY · cleared 2025-11-21 · product code POS · Neurology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.5)
“Nelli is a seizure detection and monitoring system based upon the analysis of audio/video recording which does not require the patient to be fitted with any body-worn accessory which may interfere with sleep and/or rest. Nelli uses machine learning algorithms to detect and categorize into review priority classes events indicative of seizure activity with a positive motor component.”
Algorithmmachine learning algorithms
source quote (p.5)
“Nelli uses machine learning algorithms to detect and categorize into review priority classes events indicative of seizure activity with a positive motor component.”
Adaptive (vs locked)FDA source did not state this
PCCPNo
Cybersecurity addressedYes
source quote (p.8)
“Cybersecurity (documentation per guidance on cybersecurity⁴)”

Validation studies (2)

Bench

sample size not stated

standards: ISO 14971, ISO 15223-1, ISO 7010, IEC 62304, IEC 62366-1, IEC 81001-5-1, AAMI TIR57

Prospective clinical

n=172 patients · 3 site(s)

endpoints: event-level Sensitivity (“Se”, expressed as Positive Percent Agreement) in convulsive seizures (tonic-clonic and bilateral clonic); False Detection Rate (“FDR”, i.e. False Positives per hour) in convulsive seizures (tonic-clonic and bilateral clonic); event-level Sensitivity ("Se", expressed as Positive Percent Agreement) in other major motor seizures (tonic, unilateral clonic, or hyperkinetic seizures with a motor duration over 10s and other motor seizure types with a motor duration over 30s); False Detection Rate (“FDR”, i.e. False Positives per hour) in other major motor seizures (tonic, unilateral clonic, or hyperkinetic seizures with a motor duration over 10s and other motor seizure types with a motor duration over 30s)

standards: 21 CFR §812.2(b)(1), ISO 14155

Reported performance (5 observations)

sensitivity84.5CI [74.6%, 94.2%]
source quote (p.9)
“I: High Priority (Convulsive) ... Sensitivity (%) 84.5% ... Sensitivity* [95% CI] [74.6%, 94.2%]”
detection_rateas written: “False Detection Rate (FDR) (FP/hour) for High Priority (Convulsive)”0.05CI [0.0376, 0.0636]
source quote (p.9)
“I: High Priority (Convulsive) ... FDR d (FP/hour) 0.050 ... FDR d [95% CI] [0.0376, 0.0636]”
detection_rateas written: “False Detection Rate (FDR) (FP/24 hours) for High Priority (Convulsive)”1.2CI [0.902, 1.53]
source quote (p.9)
“I: High Priority (Convulsive) ... FDR (FP/24 hours) [95% CI] 1.20 [0.902, 1.53]”
detection_rateas written: “False Detection Rate (FDR) (FP/hour) for Medium Priority (Other Major Motor)”6.08CI [5.63, 6.54]
source quote (p.9)
“II: Medium Priority (Other Major Motor) ... FDR d (FP/hour) 6.08 ... FDR d [95% CI] [5.63, 6.54]”
detection_rateas written: “False Detection Rate (FDR) (FP/24 hours) for Medium Priority (Other Major Motor)”146CI [135, 157]
source quote (p.9)
“II: Medium Priority (Other Major Motor) ... FDR (FP/24 hours) [95% CI] 146 [135, 157]”

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
2
MAUDE reports in code, 12mo
+500%
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/K251506