Aurora

K231355

EnsoData · cleared 2024-02-09 · product code MNR · Anesthesiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.4)
“Aurora is a Software as a Medical Device (SaMD) that establishes sleep quality.”
Algorithmmachine learning algorithms including multiple deep neural network machine learning models, statistical signal processing analyses including time-domain and time-frequency domain analyses over multiple time and resolution scales, and other analyses
source quote (p.6)
“Following upload of a compatible PPG study to the cloud software, the algorithm functions by verifying minimum signal quality, study length, and technical adequacy requirements, preprocessing the data including normalization, digital filtration, and artifact detection/rejection procedures, applying machine learning algorithms including multiple deep neural network machine learning models, statistical signal processing analyses including time-domain and time-frequency domain analyses over multiple time and resolution scales, and other analyses.”
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedYes
source quote (p.9)
“Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions - FDA guidance issued September 27, 2023”

Validation studies (1)

Retrospective clinical

n=158 patients

endpoints: Aurora Apnea Hypopnea Index (eAHI); Wake; Light non-rapid eye movement (NREM); Deep NREM; REM Sleep; Total Sleep Time (TST); Sleep Efficiency (SE); Sleep Latency (SL); Wake After Sleep Onset (WASO); Oxygen Desaturation Events Index (ODI)

standards: EN ISO 13485 Third Edition 2016/A11 Medical devices – Quality management systems – Requirements for regulatory purposes, EN ISO 14971 Third Edition 2019-12 Medical devices - Application of risk management to medical devices, IEC 62304 Edition 1.1 2015-06 Medical device software - Software life cycle processes, Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions - FDA guidance issued September 27, 2023, Content of Premarket Submissions for Device Software Functions – FDA guidance issued June 14, 2023

Reported performance (17 observations)

sensitivity92.6CI (87.2%, 97.2%)
source quote (p.10)
“92.6% (87.2%, 97.2%)”
specificity71.6CI (59.2%, 83.7%)
source quote (p.10)
“71.6% (59.2%, 83.7%)”
sensitivityas written: “Sensitivity (4% Desaturation)”89.4CI (81.6%, 96.1%)
source quote (p.10)
“89.4% (81.6%, 96.1%)”
specificityas written: “Specificity (4% Desaturation)”76.8CI (67.1%, 85.4%)
source quote (p.10)
“76.8% (67.1%, 85.4%)”
sensitivityas written: “Sensitivity (Wake)”86.7CI (86.5%, 87.0%)
source quote (p.10)
“86.7% (86.5%, 87.0%)”
specificityas written: “Specificity (Wake)”93.5CI (93.4%, 93.7%)
source quote (p.10)
“93.5% (93.4%, 93.7%)”
sensitivityas written: “Sensitivity (Light Non-REM)”80.9CI (80.6%, 81.2%)
source quote (p.10)
“80.9% (80.6%, 81.2%)”
specificityas written: “Specificity (Light Non-REM)”85.5CI (85.2%, 85.7%)
source quote (p.10)
“85.5% (85.2%, 85.7%)”
sensitivityas written: “Sensitivity (Deep Non-REM)”63.4CI (62.4%, 64.3%)
source quote (p.10)
“63.4% (62.4%, 64.3%)”
specificityas written: “Specificity (Deep Non-REM)”95.9CI (95.7%, 96.0%)
source quote (p.10)
“95.9% (95.7%, 96.0%)”
sensitivityas written: “Sensitivity (REM)”83.6CI (83.0%, 84.2%)
source quote (p.10)
“83.6% (83.0%, 84.2%)”
specificityas written: “Specificity (REM)”97.5CI (97.4%, 97.5%)
source quote (p.10)
“97.5% (97.4%, 97.5%)”
time_to_resultas written: “Sleep Latency Slope β1”1.114CI (0.997, 1.290)
source quote (p.11)
“1.114 (0.997, 1.290)”
time_to_resultas written: “Sleep Latency Intercept B0”-0.023CI (-0.185, 0.090)
source quote (p.11)
“-0.023 (-0.185, 0.090)”
time_to_resultas written: “Sleep Latency Mean Difference (MD)”-0.129CI (-0.154, -0.089)
source quote (p.11)
“-0.129 (-0.154, -0.089)”
time_to_resultas written: “Sleep Latency Upper Limit (ULOA)”0.884CI (0.831, 0.970)
source quote (p.11)
“0.884 (0.831, 0.970)”
time_to_resultas written: “Sleep Latency Lower Limit (LLOA)”-1.143CI (-1.196, -1.057)
source quote (p.11)
“-1.143 (-1.196, -1.057)”

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
37
MAUDE reports in code, 12mo
+171%
vs code's own 3-yr baseline
1
drift signals on this device
  • adverse_event_inflection

    MAUDE adverse-event reports for product code MNR: 37 in the 12 months ending 2026-06, vs a 13.7/12mo average over the prior 3 windows (+171%). Code-level count — reports are not attributed to this specific device.

    first seen 2026-07-08 · openFDA /device/event.json count=date_received product_code=MNR

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 Anesthesiology 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/K231355