DeepRESP

K241960

Nox Medical ehf · cleared 2025-03-14 · product code OLZ · Neurology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.5)
“DeepRESP is a cloud-based software as a medical device (SaMD), designed to perform analysis of sleep study recordings, with and without EEG signals, providing data for the assessment and diagnosis of sleep-related disorders.”
Algorithmcloud-based artificial intelligence-enabled software application using an algorithmic framework with artificial intelligence and rule-based models to categorize sleep-related events, derive sleep staging, score respiratory events, and calculate parameters.
source quote (p.5)
“DeepRESP is a cloud-based artificial intelligence-enabled software application used for analysis (automatic scoring), retrieval, and summarization of data recorded with sleep monitoring devices. The device uses an algorithm to categorize sleep-related events that help aid in the diagnosis of sleep-related disorders. Its algorithmic framework provides the derivation of sleep staging including arousals, scoring of respiratory events and key parameters such as the Apnea-Hypopnea Index (AHI). Predefined sequences called Protocols that run data analyses, including artificial intelligence and rule-based models for the scoring of sleep studies, and a parameter calculation service.”
Adaptive (vs locked)FDA source did not state this
PCCPNo
Cybersecurity addressedYes
source quote (p.12)
“Software verification and validation testing were performed per IEC 62304:2006/A1:2015 Medical device software – Software life cycle processes, IEC 82304-1:2017 Health Software general requirements for product safety and the FDA guidance General Principles of Software Validation to demonstrate safety and performance based on current industry standards and that we met the intended use and user needs.”

Validation studies (2)

Retrospective clinical

n=2,224 cases

endpoints: severity classification of sleep recordings (AHI ≥5, AHI ≥15, AHI ≥30); overall respiratory event scoring; sleep state estimation (Wake, NREM, N1, N2, N3, REM); arousal event scoring

standards: IEC 62304:2006/A1:2015, IEC 82304-1:2017, ISO 14971:2019, ANSI/AAMI SW96:2023

Retrospective clinical

n=3,488 cases

endpoints: severity classification of sleep recordings (AHI ≥5, AHI ≥15, AHI ≥30); overall respiratory event scoring; sleep state estimation (Wake, NREM, REM); arousal event scoring

standards: IEC 62304:2006/A1:2015, IEC 82304-1:2017, ISO 14971:2019, ANSI/AAMI SW96:2023

Reported performance (4 observations)

sensitivity0.875CI [86.2, 89.0]
source quote (p.13)
“AHI ≥5 PPA% [95% CI]: 87.5 [86.2, 89.0]”
specificity0.919CI [87.4, 95.8]
source quote (p.13)
“AHI ≥5 NPA % [95% CI]: 91.9 [87.4, 95% CI]: 95.8”
agreement_kappaas written: “ArI ICC (Arousal events, Type I/II)”0.63CI [95% CI]: 0.63
source quote (p.10)
“Arousal events ArI ICC [95% CI]: 0.63”
agreement_kappaas written: “ArI ICC (Arousal events, Type III)”0.73CI [95% CI]: 0.73
source quote (p.11)
“Arousal events ArI ICC [95% CI]: 0.73”

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
+20%
vs code's own 3-yr baseline
1
drift signals on this device
  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K252330 (decision 2025-11-17) from Nox Medical Ehf for a matching device line ("DeepRESP") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K252330

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/K241960