Search Results
Found 451 results
510(k) Data Aggregation
(28 days)
North Carolina 27513
Re: K260585
Trade/Device Name: Noxturnal Web
Regulation Number: 21 CFR 882.1400
Classification Name: Standard Polysomnograph with Electroencephalograph
Regulation Number: 21 CFR 882.1400
| Somnomedics GmbH |
| 510(k) Number | TBD | K241288 | K201054 |
| Regulation Description | 21 CFR 882.1400
| 21 CFR 882.1400 | 21 CFR 882.1400 |
| Regulation Name | Electroencephalograph | Electroencephalograph
Noxturnal Web is intended to be used for the diagnostic evaluation by a physician to assess sleep quality and as an aid for the diagnosis of sleep and respiratory-related sleep disorders in adults (18 years and above).
Noxturnal Web is a software-only medical device to be used to analyze physiological signals and manually score sleep study results, including the staging of sleep, AHI, and detection of sleep disordered breathing events including obstructive apneas.
It is intended to be used under the supervision of a clinician in a clinical environment.
Noxturnal Web is a web-based software that can be utilized to screen various sleep and respiratory-related sleep disorders. The users of Noxturnal Web are medical professionals who have received training in the areas of hospital/clinical procedures, physiological monitoring of human subjects, or sleep disorder investigation. Users can input a sleep study recording stored on the cloud (electronic medical record repository) using their established credentials. Once the sleep study data has been retrieved, the Noxturnal Web software can be used to display, manually analyze, generate reports and print the pre-recorded physiological signals.
Noxturnal Web is used to read sleep study data for the display, analysis, summarization, and retrieval of physiological parameters recorded during sleep and awake. Noxturnal Web facilitates a user to review or manually score a sleep study either before the initiation of treatment or during the treatment follow-up for various sleep and respiratory-related sleep disorders.
Noxturnal Web presents information from the input sleep study data in an organized layout. Multiple visualization layouts (e.g., Study Overview, Respiratory Signal Sheet, etc.) are available to allow the users to optimize the visualization of key data components. The reports generated by Noxturnal Web allow the inclusion of custom user comments, and these reports can then be viewed on the screen and/or printed.
N/A
Ask a specific question about this device
(30 days)
Texas 78705
Re: K260455
Trade/Device Name: New Wave System
Regulation Number: 21 CFR 882.1400
electroencephalograph |
| Classification Name | Electroencephalograph |
| Regulation Number | 21 CFR 882.1400
Information |
|---------|-------------|
| Product Code | GWQ, GXY |
| Classification Regulation | 21 CFR 882.1400
The New Wave system is intended for prescription use in an outpatient healthcare facility or home use to acquire, transmit, display and store EEG and auxiliary signals for adults and children, not including newborns. The New Wave system acquires, transmits, displays and stores electroencephalogram (EEG), and optionally electrocardiogram (ECG), electrooculogram (EOG), electromyogram (EMG), orientation sensor data, photic sensor data, external trigger signals, and video. The system is only intended to be used for short-term recordings up to 2.5 hours.
The New Wave System is intended to acquire, analyze, transmit, display and store primarily EEG and optionally auxiliary signals. The New Wave is designed to perform EEG using 19 signal electrodes and 1 dedicated active ground/driven-right-leg (DRL) electrode, adjusted and placed to comply with the 10-20 EEG system.
The device consists of the following components:
- Head Unit
- Electrodes
- Charger
- Display Unit
- Extension Unit
- Lead wires
- Software and Zeto Cloud Platform (ZCP)
- Firmware and Display Unit software
- Data center application
- Client application
N/A
Ask a specific question about this device
(107 days)
Re: K253668
Trade/Device Name: Onera SleepMap (SLEEPMAP)
Regulation Number: 21 CFR 882.1400
Trade name:* Onera SleepMap
Common Name: Electroencephalograph
Classification: 21 CFR 882.1400
| EnsoData Inc., USA | -- |
| 510(k) number | K253668 | K162627 | -- |
| Regulation number | 21 CFR 882.1400
| 21 CFR 882.1400 | Identical |
| Product code | OLZ | OLZ | Identical |
| Indications general | SleepMap
SleepMap system is intended for use as an aid for physicians in the diagnosis of sleep and respiratory related disorders in adult patients (aged 18 and up), who have been prescribed a sleep study by their doctor.
SleepMap is a software-only medical device to be used under the supervision of a clinician to analyze physiological signals and automatically score sleep study recordings, including the staging of sleep, detection of arousals, leg movements, desaturations, obstructive apneas and obstructive hypopneas.
Respiratory event subtypes (central and mixed apneas; central hypopneas), RERA, Cheyne Stokes Breathing, Snoring Events, and Arrhythmia Events are not automatically detected and must be manually marked within records.
All automatically scored stages and detected events can be manually marked or edited within records during review.
All automatically scored stages, detected events and physiological signals which are retrieved, analyzed, displayed, and summarized are subject to verification by a qualified clinician.
Onera SleepMap is a software-only medical device that analyses previously recorded physiological signals obtained during sleep through a polysomnography sleep test with the Onera STS I device. SleepMap can analyze at-home or in-lab sleep study recordings of adult patients.
Automated algorithms are applied to the raw input signals (read from a measurement file in the EDF file format originating from the Onera STS I device) in order to derive additional signals:
- a heartrate (HR) signal from the raw ECG signal. The heartrate algorithm does not include any automated arrhythmia analysis.
- a quantized position signal from the raw continuous value position signal.
Additionally, multiple algorithms are used to interpret the raw and derived signals by classifying sleep stages, sleep events and artifacts. The software automates recognition of the following sleep events: obstructive apnea and obstructive hypopnea events, arousal events, desaturation events, leg movement and PLM events.
The Onera SleepMap contains the following algorithms:
- Sleep staging algorithm, a deep learning model (AI-model) which classifies sleep stages, based on EEG, EOG and EMG inputs.
- Arousals algorithm, a Convolutional Neural Network (AI-model) which predicts arousals, based on sleep stages, EEG, EOG, EMG, ECG and nasal pressure inputs.
- Desaturation algorithm, a rule-based algorithm which detects events of minimum 3% or 4% oxygenation drop based on sleep stages and SpO2 signal inputs.
- Apnea (obstructive) detection, a rule-based algorithm which detects ≥90% nasal pressure drops, based on sleep stages and nasal pressure signal inputs.
- Hypopneas (obstructive) detection, a rule-based algorithm which detects ≥30% nasal pressure drops based on sleep stages, nasal pressure signal, arousal events, and desaturation event inputs.
- Leg Movement algorithm, a rule-based algorithm which detects (repetitive) EMG amplitude increasements, based on sleep stages, EMG signal and respiratory event inputs.
- Artifact algorithms, rule-based algorithms which detect artifacts, based on SpO2, EEG, EOG, EMG and heart rate inputs.
Additionally, clinical users can manually annotate: respiratory event subtypes (central and mixed apneas and central hypopneas), RERA, Cheyne Stokes Breathing, Snoring Events, and Arrhythmia Events.
The raw signals, derived signals and all automated analysis results (annotations) must be visually inspected and reviewed by sleep analysts and physicians prior to the results being integrated into a sleep study report.
SleepMap calculates aggregated metrics and indexes on the set of annotations resulting from the sleep analyst or physician review and integrates these into a technical sleep report that can be previewed.
The technical sleep study report summarizes the sleep stage annotations in a hypnogram, provides the aggregated metrics and indexes, and the technician notes into a PDF document which is the main output of SleepMap. The technical sleep study report is transferred to the Onera Digital Health Platform for storage and is used by the physician to diagnose the sleep disorder.
Here's a breakdown of the acceptance criteria and study details for the Onera SleepMap, based on the provided FDA 510(k) clearance letter:
Onera SleepMap Acceptance Criteria and Study Summary
The Onera SleepMap is a software-only medical device intended as an aid for physicians in the diagnosis of sleep and respiratory related disorders in adult patients (18 and up) who have been prescribed a sleep study. It analyzes physiological signals and automatically scores sleep study recordings for sleep staging and the detection of arousals, leg movements, desaturations, obstructive apneas, and obstructive hypopneas.
1. Acceptance Criteria and Reported Device Performance
The acceptance criteria for the Onera SleepMap's automated scoring algorithms are implicitly defined by the reported performance metrics (Positive Agreement, Negative Agreement, Overall Agreement, False Discovery Rate) against a 2/3 majority ground truth from expert scorers. The performance metrics are presented with 95% bootstrap confidence intervals. The device is deemed acceptable if these metrics demonstrate sufficient agreement with human expert consensus, indicating it can serve as a reliable aid for physicians.
| Category | Metric | Acceptance Criteria (Implicit) | Reported Device Performance |
|---|---|---|---|
| Sleep Staging | Wake | High Overall Agreement (OA), High Negative Agreement (NA), Low False Discovery Rate (FDR) | OA: 95.3% (94.1%, 96.2%), NA: 98.4% (97.6%, 99.1%), FDR: 7.1% (4.3%, 10.2%) |
| N1 | Reasonable Positive Agreement (PA) and Overall Agreement (OA) | PA: 69.6% (65.0%, 74.5%), OA: 90.9% (89.5%, 92.1%), FDR: 90.4% (89.1%, 91.6%) | |
| N2 | High Overall Agreement (OA) and Negative Agreement (NA) | OA: 83.4% (81.5%, 85.2%), NA: 92.1% (91.0%, 93.2%) | |
| N3 | High Overall Agreement (OA) and Positive Agreement (PA), moderate FDR | OA: 93.2% (91.6%, 94.4%), PA: 85.6% (82.9%, 88.4%), FDR: 41.4% (34.1%, 48.4%) | |
| REM | High Overall Agreement (OA), Positive Agreement (PA), and Negative Agreement (NA) | OA: 95.2% (94.5%, 95.8%), PA: 82.7% (79.8%, 85.4%), NA: 97.8% (97.1%, 98.3%) | |
| Total (all stages) | High Overall Agreement (OA) | OA: 91.6% (90.7%, 92.4%) | |
| Sleep Event Detection | Sleep Disordered Breathing | High Overall Agreement (OA) and Positive Agreement (PA) | OA: 88.8% (87.7%, 89.8%), PA: 78.2% (72.8%, 82.7%) |
| Apnea | High Overall Agreement (OA) and Positive Agreement (PA), and Negative Agreement (NA) | OA: 96.3% (95.6%, 96.9%), PA: 85.7% (79.0%, 89.9%), NA: 97.0% (96.4%, 97.6%) | |
| Obstructive Apnea | High Overall Agreement (OA) | OA: 94.9% (93.6%, 96.0%) | |
| Hypopnea | High Overall Agreement (OA) | OA: 88.8% (87.7%, 90.1%) | |
| Obstructive Hypopnea | High Overall Agreement (OA) | OA: 88.8% (87.7%, 90.1%) | |
| Desaturation | High Overall Agreement (OA) and Positive Agreement (PA) | OA: 85.9% (84.1%, 87.5%), PA: 87.5% (85.0%, 89.4%) | |
| Arousal | High Overall Agreement (OA) and Negative Agreement (NA) | OA: 89.9% (89.0%, 90.7%), NA: 95.1% (94.3%, 95.8%) | |
| Leg Movement | Reasonable Overall Agreement (OA) and Positive Agreement (PA) | OA: 86.5% (83.9%, 88.7%), PA: 77.6% (74.2%, 80.6%) | |
| Periodic Leg Movement | Reasonable Overall Agreement (OA) and Positive Agreement (PA) | OA: 91.0% (88.6%, 93.2%), PA: 72.0% (62.2%, 78.5%) | |
| Heart Rate (HR) Algorithm | Absolute Error | Absolute error of less than 3 bpm for over 99% of runs, with only brief transient deviations less than 4s. | Absolute error of less than 3 bpm for over 99% of runs, with only brief transient deviations less than 4s. |
2. Sample size used for the test set and the data provenance
- Automated Scoring Service (Sleep Staging & Events):
- Sample Size: 98 PSG night studies from 98 unique patients.
- Data Provenance:
- N=72 studies from the United States (home environment), acquired August 2023 to August 2025.
- N=26 studies from Germany (clinic environment), acquired September 2022 to April 2024.
- Heartrate (HR) Algorithm:
- Sample Size: 249 PSG night studies from 215 unique patients. The validation used 5-minute time intervals from these studies.
- Data Provenance:
- N=171 studies from the United States (home environment), acquired August 2023 to August 2025.
- N=78 studies from Germany (clinic environment), acquired September 2022 to April 2024.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
- Automated Scoring Service (Sleep Staging & Events):
- Number of Experts: 3
- Qualifications: Independent, US-based certified sleep professionals.
- Heartrate (HR) Algorithm:
- Number of Experts: 2 independent cardiac technologists initially for manual annotation, and an expert board-certified cardiologist for adjudication.
- Qualifications: Independent cardiac technologists and an expert board-certified cardiologist from Florida, USA.
4. Adjudication method for the test set
- Automated Scoring Service (Sleep Staging & Events): A 2 out of 3 (2/3) majority scoring was constructed as the ground truth reference. Epochs where a 2/3 majority agreement was not reached (n=3282 for sleep staging) were excluded from validation.
- Heartrate (HR) Algorithm: Disagreements in annotations between the 2 cardiac technologists were adjudicated by an expert board-certified cardiologist.
5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance
The provided document does not indicate that an MRMC comparative effectiveness study was performed to evaluate human readers' improvement with AI assistance. The study focuses on the standalone performance of the AI algorithms against expert consensus.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Yes, a standalone performance study was done. The reported performance metrics (Positive Agreement, Negative Agreement, Overall Agreement, False Discovery Rate, and absolute error for HR) describe the Onera SleepMap algorithms' performance independently against the established ground truth. The device is designed for use "under the supervision of a clinician," and all automatically scored stages and events "are subject to verification by a qualified clinician," indicating that the reported standalone performance is intended as an aid for, not a replacement of, human review.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
- Automated Scoring Service (Sleep Staging & Events): Expert consensus, specifically a 2/3 majority agreement from 3 independent, US-based certified sleep professionals, in compliance with AASM scoring guidelines.
- Heartrate (HR) Algorithm: Expert consensus derived from manual annotations by 2 independent cardiac technologists, with disagreements adjudicated by an expert board-certified cardiologist.
8. The sample size for the training set
The document does not specify the sample size used for the training set for any of the algorithms. It only describes the validation data sets.
9. How the ground truth for the training set was established
The document does not specify how the ground truth for the training set was established. It only details the ground truth establishment for the validation data set.
Ask a specific question about this device
(183 days)
Ghent, 9050
Belgium
Re: K252565
Trade/Device Name: PreOp v3
Regulation Number: 21 CFR 882.1400
Localization Software for Electroencephalography or magnetoencephalographyClassification Number: 882.1400
Localization Software for Electroencephalography or magnetoencephalographyClassification Number: 882.1400
PreOp V3 is intended for use by a trained/qualified EEG technologist or physician on both adult and pediatric subjects at least 3 years of age for the visualization of human brain function by fusing a variety of EEG information with rendered images of an individualized head model and an individualized MRI image.
PreOp is medical device software that combines EEG data and MRI images to visualize recorded EEG activity in 3D in the brain. PreOp can be subdivided in 3 main modules: 3D Electrical Source Imaging (i.e. 3D ESI), Report generation and Viewer generation. The device's input is the MRI and EEG data that are provided by means of Persyst software. The output of the device is a report containing the results of the visualization and the ability to evaluate the results in 3D using the 3D viewer. The user can access the output through Persyst software.
The subject device, PreOp V3, incorporates technological enhancements compared to the predicate device PreOp V1 (K172858) while maintaining the same intended use, patient population, and core functional principles. PreOp V3 includes integration with the Persyst EEG Review and Analysis Software, allowing clinical users to access PreOp functionality directly within the Persyst interface, whereas PreOp V1 required operators to access the system through a separate cloud-based workflow. PreOp V3 also standardizes the anatomical workflow by supporting both an idealized (average) MRI model and individualized, patient-specific MRI data, whereas PreOp V1 supported only individualized MRI. PreOp V3 automates multiple functions that were previously performed manually in the predicate device, including EEG data preprocessing, spike detection, MRI segmentation, and clustering, thereby improving workflow efficiency without altering user control of final review steps. The spike clustering algorithms in PreOp V3 is enhanced to incorporate morphology and topography-based features, supporting improved precision of spike classification.
PreOp V3 also introduces a modernized, modular, containerized software architecture that replaces the monolithic design of PreOp V1. This updated architecture uses cloud-native microservices, enabling improved scalability, maintainability, and system performance, particularly when handling larger datasets. Additionally, PreOp V3 includes 3D visualization capabilities for head models and electrode positioning, improved temporal and spatial accuracy of source estimation, and refined reporting features with automated quality control checks.
N/A
Ask a specific question about this device
(271 days)
. |
| Neurology | §882.1400, II | OLW | Index-Generating Electroencephalograph Software |
| Neurology
| §882.1400, II | OLT | Non-normalizing quantitative electroencephalograph software |
| Neurology |
§882.1400, II | OMC | Reduced- montage standard electroencephalograph |
| Neurology | §882.1400, II |
The N10, N12, N15, N10MPro, N12MPro, NM15Pro Multi-parameter Patient Monitors are intended for monitoring, displaying, reviewing, storing, alarming and transferring of multiple physiological parameters including ECG (3-lead, 5-lead, 12-lead selectable), Arrhythmia Analysis, ST Segment Analysis, QT Analysis, Heart Rate (HR) and Heart-Rate-Variability(HRV)), interpretations of resting 12-lead ECG, Respiration rate(Resp), Temperature(Temp), Pulse Oxygen Saturation (SpO2), Pulse Rate (PR), Non-invasive Blood Pressure (NIBP), Invasive Blood Pressure (IBP), Pulmonary Artery Wedge Pressure (PAWP), Cardiac Output (C.O.), Carbon Dioxide (CO2). The N10MPro, N12MPro, NM15Pro Multi-parameter Patient Monitors are also intended for monitoring, displaying, reviewing, storing, alarming and transferring of physiological parameters including Masimo Rainbow SpO2, Anesthesia gas (AG), oxygen (O2) respiratory gas monitoring, Bispectral Index (BIS), Respiration Mechanics (RM) and Neuromuscular Transmission Monitoring (NMT). All the parameters can be monitored on single adult, pediatric, and neonatal patient except for the following:
- Arrhythmia analysis is intended to use on adult patients only and is not intended and shall not be used on pediatric and neonatal population.
- NIBP measurement continual mode is not applicable to neonates.
- When using COMEN SpO2, the monitor is intended to be used on adult patient only.
- PAWP is intended for adult and pediatric patients only.
- C.O. measurement is intended for adult patients only.
- BIS monitoring is intended for adult patients only.
- RM is intended for adult and pediatric patients only.
- NMT monitoring is intended for adult and pediatric patients only.
The monitors are to be used in healthcare facilities by healthcare professionals or under their guidance.
The Multi-parameter Patient monitors are not intended for emergency and transport use, aircraft environment or home use.
The monitors are not intend for use as apnea monitors.
The monitors are not intended for use in MRI or CT environments.
The monitors are not used on patients who have a demonstrated need for cardiac monitoring known arrhythmias of VT, Accelerated Idioventricular rhythm and Torsades de Pointes.
There are six (6) models under evaluation, namely N10, N12, N15, N10MPro, N12MPro, N15MPro. All models share the same intended condition of use, the same intended patient population and operator profile, biological safety characteristic and principle of operation. All these models are the same on electric and electrical circuit and components, mechanical construction, software and alarm system. The only difference lies on the screen and configuration of with/without plug-in module slot and the number of battery packs.
N/A
Ask a specific question about this device
(268 days)
99336
Re: K250851
Trade/Device Name: Hypnos (369054-200)
Regulation Number: 21 CFR 882.1400
Common Name:** Standard Polysomnograph with Electroencephalograph
Classification Name: 21 CFR 882.1400
Trade Name: Sleepware G3
Submitter Name: Respironics
Classification Name: 21 CFR 882.1400
Classification Name: 21 CFR 882.1400, Electroencephalograph
Product Code: OLZ
Device Description
Cadwell Hypnos is a software application used for Polysomnography (PSG) and other clinical sleep studies. It is intended for use by research and clinical sleep professionals. It measures, records, displays, organizes, analyzes, summarizes, and retrieves physiological signals during sleep and wake used to assist in the assessment of sleep and the diagnosis of various sleep disorders including sleep related breathing disorders. The software can be used for analysis (computer-assisted as well as manual scoring of events), display, retrieval, summarization, reporting and networking of data received from devices used to monitor sleep related parameters.
Hypnos is indicated for use in all sleep disorders patient populations from neonate to adult, including infants, pediatrics and geriatric populations. Computer-assisted analysis features of the application are only intended for use on adults.
Hypnos is only indicated for use by trained medical professionals for the purpose of assessing sleep disorders.
Intended environments include hospitals, institutions, sleep centers, sleep clinics, and other sleep disorders testing environments.
Hypnos is NOT intended to be used to perform automatic diagnosis.
Hypnos software is used to acquire, record, transmit, analyze, store, manage, report, and display physiological and environmental data collected by PSG and/or HSAT hardware. Hypnos software allows users to analyze signals both manually and using detectors to facilitate interpretation of a sleep study by a qualified user.
N/A
Ask a specific question about this device
(168 days)
Texas 75083
Re: K251881
Trade/Device Name: HippoMind (v1.0)
Regulation Number: 21 CFR 882.1400
| Classification Name | Amplitude-Integrated Electroencephalograph |
| Regulation Number | 882.1400
| 882.1400 | n/a |
| Product Code | OLT; OMA | OLT; OMA | n/a |
| **Intended Use/Indications for
Both devices share a similar intended use under 21 CFR 882.1400, enabling qualified medical practitioners
| 882.1400 | n/a |
| Product Code | OLT; OMA; OLY | OLY | n/a |
| **Intended Use/Indications for
HippoMind is a software application that displays neuroimaging and neurosignaling data for review by a health care provider. It provides simple tools for analysis of both medical images and EEG/MEG data. It also allows for storage and transfer of data, and association of data with electronic health records. It is intended for use by qualified health care professionals.
HippoMind is a cloud-based software platform designed for neurologists and neurodiagnostic technologists to review neurophysiological and neuroimaging data. It provides secure, remote access to patient data, through an intuitive interface, to support clinical decision-making.
The platform includes two main modules:
Neurophysiological signal platform: This module enables the review of EEG and MEG data with customizable settings such as amplitude, filtering, and channel templates. It features a labeling system to annotate events, and advanced signal visualization with topological energy graphs. The platform supports Natus EEG, EDF, and CTF MEG formats.
Neuroimaging Review Platform: This module displays 3D MRI, CT, PET, and SPECT images in DICOM or NiFTI format. It offers flexible viewing options, including 3D rendering, customizable color schemes, annotation tools, and an overlay system to superimpose imaging modalities (e.g., T1 and T2 images) using affine transformation.
N/A
Ask a specific question about this device
(188 days)
Paris, 75006
France
Re: K251550
Trade/Device Name: NX01 (nx01)
Regulation Number: 21 CFR 882.1400
Reduced-Montage Standard Electroencephalograph (Class II) |
| Product Code | OMC |
| Regulation Number | 21 CFR 882.1400
| Device** | |
|---|---|
| Tradename | Byteflies Kit |
| 510(k) | K192549 |
| Regulation number | 21 CFR 882.1400 |
| Primary Predicate Device) | Discussion |
| --- | --- |
| Regulatory | Product Code OMC 21 CFR 882.1400 |
| Product Code OMC 21 CFR 882.1400 | EQUIVALENT Both devices share the same primary OMC product |
NX01 is intended for use in healthcare or home settings to acquire, record, and transmit electrical activity of the brain by placing non-invasive electrodes in the ears of patients. It acquires, records and transmits one channel of electroencephalogram (EEG) data. The medical use of data acquired by NX01 is to be performed under the direction and interpretation of a licensed medical professional. NX01 does not provide any diagnostic conclusions about the patient's condition.
The NX01 is intended for use with adult and pediatric patients (6+).
NX01 is a wearable device for continuous recording of non-invasive EEG signals in healthcare and home settings. NX01 is intended to be prescribed by a trained healthcare professional. It consists of a pair of earbuds (one per ear) integrating a pair of active, dry electrodes, connected by a cable to a command panel. This command panel houses the battery, the internal memory to store the data, the main acquisition unit with function buttons and LEDs which display the device's status.
The NX01 solution is composed of:
- Two earbuds (1) connected by 45 cm cables, to a command panel (5). This command panel houses the battery, the internal memory to store the data, the main acquisition unit with function buttons (2 - Left button and 3 - Right button) and LEDs (4) which display the device's status.
- A set of eartips, to be placed on the earbuds for the recording. Eartips are single use consumable that should be discarded and replaced for every recording that takes place.
- A medical grade PSU with the following specifications: Input AC 100-240V, 50/60Hz; Output USB-C DC 5.0V, min 1.0A; Compliance IEC 60601-1, IEC 62368-1 or IEC 60950-1.
N/A
Ask a specific question about this device
(143 days)
K252070**
Trade/Device Name: Ceribell Infant Seizure Detection Software
Regulation Number: 21 CFR 882.1400
Software for Full-Montage Electroencephalograph
Classification: Electroencephalograph (21 CFR 882.1400
The Ceribell Infant Seizure Detection Software is intended to mark previously acquired sections of EEG recordings in newborns (defined as preterm or term neonates of 25-44 weeks postmenstrual age) and infants less than 1 year of age that may correspond to electrographic seizures in order to assist qualified clinical practitioners in the assessment of EEG traces. The Seizure Detection Software also provides notifications to the user when detected seizure prevalence is "Frequent", "Abundant", or "Continuous", per the definitions of the American Clinical Neurophysiology Society Guideline 14. Delays of up to several minutes can occur between the beginning of a seizure and when the Seizure Detection notifications will be shown to a user.
The Ceribell Infant Seizure Detection Software does not provide any diagnostic conclusion about the subject's condition and Seizure Detection notifications cannot be used as a substitute for real time monitoring of the underlying EEG by a trained expert.
The Ceribell Infant Seizure Detection Software is a software-only device that is intended to mark previously acquired sections of EEG recordings that may correspond to electrographic seizures in order to assist qualified clinical practitioners in the assessment of EEG traces.
Ceribell Infant Seizure Detection Software: Acceptance Criteria and Supporting Study
1. Table of Acceptance Criteria and Reported Device Performance
| Activity Category | Metric | Acceptance Criteria | Device Performance (Overall) | 95% Confidence Interval | Meets Criteria? |
|---|---|---|---|---|---|
| Seizure Episodes with Seizure Burden ≥10% (Frequent) | PPA | Lower bound of 95% CI ≥ 70% | 91.36% | [85.71, 94.91] | Yes |
| FP/hr | Upper bound of 95% CI ≤ 0.446 FP/hr | 0.204 | [0.180, 0.230] | Yes | |
| Seizure Episodes with Seizure Burden ≥50% (Abundant) | PPA | Lower bound of 95% CI ≥ 70% | 91.23% | [82.67, 96.57] | Yes |
| FP/hr | Upper bound of 95% CI ≤ 0.446 FP/hr | 0.083 | [0.069, 0.100] | Yes | |
| Seizure Episodes with Seizure Burden ≥90% (Continuous) | PPA | Lower bound of 95% CI ≥ 70% | 91.18% | [75.00, 100.00] | Yes |
| FP/hr | Upper bound of 95% CI ≤ 0.446 FP/hr | 0.057 | [0.045, 0.072] | Yes |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size: 713 patients.
- 25-36 weeks PMA: 155 patients
- 37-44 weeks PMA: 321 patients
-
44 weeks PMA: 237 patients
- Data Provenance: The EEG recordings were obtained from patients less than 1 year of age who received continuous EEG monitoring within the hospital environment. The study was retrospective. The country of origin is not explicitly stated in the provided text.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
- Number of Experts: 3
- Qualifications of Experts: Expert pediatric neurologists who were fellowship-trained in epilepsy or clinical neurophysiology.
4. Adjudication Method for the Test Set
- Adjudication Method: A two-thirds majority agreement among the 3 expert pediatric neurologists was required to form a determination of seizures, establishing the reference standard for the test set.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done
- No, a multi-reader multi-case (MRMC) comparative effectiveness study was not explicitly described. The study focused on the standalone performance of the algorithm against an expert-adjudicated ground truth.
6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done
- Yes, a standalone performance study was done. The performance metrics (PPA and FP/hr) were evaluated for the Ceribell Infant Seizure Detection Software algorithm without human intervention in the detection process. The reviewing neurologists for ground truth establishment were explicitly blinded to the software's output.
7. The Type of Ground Truth Used
- Type of Ground Truth: Expert consensus (adjudication by a panel of 3 expert pediatric neurologists).
8. The Sample Size for the Training Set
- The sample size for the training set is not provided in the document. The document states, "Importantly, none of the data in the validation dataset were used for training of the Seizure Detection algorithm; the validation dataset is completely independent."
9. How the Ground Truth for the Training Set Was Established
- The document does not explicitly state how the ground truth for the training set was established. It only mentions that the validation dataset was independent and not used for training.
Ask a specific question about this device
(115 days)
Monroeville, Pennsylvania 15146
Re: K252330
Trade/Device Name: DeepRESP
Regulation Number: 21 CFR 882.1400
Automatic Event Detection Software for Polysomnograph with Electroencephalograph
Regulation Number: 882.1400
Medical | Nox Medical |
| 510(k) Number | K252330 | K241960 | K192469 |
| Regulation Number | 21 CFR 882.1400
| 21 CFR 882.1400 | 21 CFR 882.1400 |
| Regulation Name | Electroencephalograph | Electroencephalograph
DeepRESP is an aid in the diagnosis of various sleep disorders where subjects are often evaluated during the initiation or follow-up of treatment of various sleep disorders. The recordings to be analyzed by DeepRESP can be performed in a hospital, a patient's home, or an ambulatory setting. It is indicated for use with adults (18 years and above) in a clinical environment by or on the order of a medical professional.
DeepRESP is intended to mark sleep study signals to aid in the identification of events and annotations of traces; automatically calculate measures obtained from recorded signals (e.g., magnitude, time, frequency, and statistical measures of marked events); and infer sleep staging with arousals with EEG and in the absence of EEG. All output is subject to verification by a medical professional.
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. 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) and Central Apnea-Hypopnea Index (CAHI).
DeepRESP (K252330) is hosted on a serverless stack. It consists of:
- A web Application Programming Interface (API) intended to interface with a third-party client application, allowing medical professionals to access DeepRESP's analytical capabilities.
- 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.
- A Result storage using an object storage service to temporarily store outputs from the DeepRESP Protocols.
Here's a breakdown of the acceptance criteria and study details for DeepRESP, based on the provided FDA 510(k) clearance letter:
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly state pre-defined acceptance criteria (e.g., "DeepRESP must achieve AHI ≥ 5 PPA% of at least X%"). Instead, it reports the performance of the device and compares it to predicate devices to demonstrate substantial equivalence and non-inferiority. The "Observed paired differences" columns, particularly those where the confidence interval does not cross zero, imply a comparison to show that the new DeepRESP v2.0 performs at least as well as the previous version or the additional predicate.
For the purpose of this analysis, I will present the reported performance of the Subject Device (DeepRESP v2.0) as the "reported device performance." Since no explicit acceptance criteria thresholds are given, the comparison to predicates and the demonstration of non-inferiority served as the implicit acceptance path for the FDA clearance.
Reported Device Performance (DeepRESP v2.0)
| Metric | Type I/II Studies (EEG) Reported Performance PPA% (NPA%, OPA%) | Type III HSAT-Flow Studies Reported Performance PPA% (NPA%, OPA%) | Type III HSAT-RIP Studies Reported Performance PPA% (NPA%, OPA%) |
|---|---|---|---|
| Severity Classification | |||
| AHI ≥ 5 | 87.7 (76.5, 87.3) | 91.0 (78.0, 90.6) | 93.7 (63.5, 92.8) |
| AHI ≥ 15 | 71.9 (94.8, 78.2) | 78.1 (93.9, 81.7) | 81.0 (91.1, 83.4) |
| CAHI ≥ 5 | 80.0 (98.0, 97.2) | 80.7 (98.0, 97.2) | 79.5 (97.6, 96.9) |
| Sleep Stages | |||
| Wake | 92.8 (95.8, 95.1) | 79.7 (96.6, 92.9) | 79.7 (96.6, 92.9) |
| REM | 82.5 (98.8, 96.5) | 77.0 (98.1, 95.2) | 77.0 (98.1, 95.2) |
| NREM1 | 43.1 (94.5, 91.7) | N/A (Only NREM total reported for Type III studies) | N/A (Only NREM total reported for Type III studies) |
| NREM2 | 78.1 (91.5, 85.3) | N/A (Only NREM total reported for Type III studies) | N/A (Only NREM total reported for Type III studies) |
| NREM3 | 87.5 (94.6, 93.7) | N/A (Only NREM total reported for Type III studies) | N/A (Only NREM total reported for Type III studies) |
| NREM (Total for Type III) | N/A | 94.2 (80.1, 89.1) | 94.2 (80.1, 89.1) |
| Respiratory Events | |||
| Respiratory events (overall) | 71.2 (93.2, 85.0) | 74.4 (92.0, 85.5) | 75.0 (90.7, 84.8) |
| All apnea | 83.7 (98.2, 97.1) | 84.5 (98.2, 97.0) | 81.1 (95.7, 94.5) |
| Central apnea | 79.3 (99.2, 99.0) | 77.5 (99.2, 99.0) | 78.8 (99.2, 99.0) |
| Obstructive apnea | 76.2 (98.4, 97.0) | 78.4 (98.4, 97.0) | 74.3 (96.0, 94.4) |
| Hypopnea | 60.1 (92.9, 83.5) | 63.9 (91.7, 83.3) | 58.9 (90.7, 81.0) |
| Desaturation | 98.5 (95.5, 96.1) | 98.8 (96.3, 96.9) | 98.8 (96.3, 96.9) |
| Arousal events | 62.1 (89.1, 81.5) | 64.0 (90.5, 83.1) | 64.0 (90.5, 83.0) |
PPA%: Positive Percent Agreement, NPA%: Negative Percent Agreement, OPA%: Overall Percent Agreement.
2. Sample Sizes and Data Provenance
The clinical validation was conducted using retrospective data.
-
Test Set Sample Size:
- Type I/II Scoring Validation: 4,030 PSG recordings
- Type III Scoring Validation: 5,771 sleep recordings
- This comprised 4,037 Type I recordings and 1,734 Type II recordings, processed as Type III by using only the relevant subset of signals.
-
Data Provenance:
- Country of Origin: United States.
- Data Type: Manually scored sleep recordings from sleep clinics, collected as part of routine clinical work for patients suspected of suffering from sleep disorders.
- Settings: Urban, suburban, and rural areas.
- Demographics: Included individuals in all age groups (18-21, 22-35, 36-45, 46-55, 56-65, >65) and all BMI groups (<25, 25-30, <30). The recording collection for Type I/II scoring consisted of 44% Females, and for Type III scoring, 35% Females. High level of race/ethnicity diversity (Caucasian or White, Black or African American, Other).
3. Number of Experts and Qualifications for Ground Truth
- Number of Experts: Not explicitly stated. The document refers to "manually scored sleep recordings" and "medical professional" for verification. It also mentions "board-certified sleep physicians" in the context of the training set. However, the specific number of experts used to establish the ground truth for the test set is not detailed.
- Qualifications of Experts: For the test set, it's implied that "medical professionals" performed the manual scoring, as the data originated from "routine clinical work." For the training set, "board-certified sleep physicians" were involved in establishing the ground truth.
4. Adjudication Method for the Test Set
The document does not explicitly describe an adjudication method (e.g., 2+1, 3+1) for establishing the ground truth on the test set. It mentions "manually scored sleep recordings" but does not detail how potential disagreements between multiple scorers (if any were used) were resolved.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done.
The study design was a retrospective data study comparing the automatic scoring of DeepRESP to manual scoring (ground truth) and also comparing DeepRESP's performance to two predicate devices (DeepRESP K241960 and Nox Sleep System K192469). This is a standalone performance evaluation against expert-derived ground truth, with a direct comparison to existing automated systems, not an MRMC study assessing human reader improvement with AI assistance.
6. Standalone Performance Study
Yes, a standalone performance study was done. The reported PPA, NPA, and OPA values for DeepRESP v2.0 (Subject Device) represent its performance as a standalone algorithm without human-in-the-loop assistance. The subsequent comparison to the predicate devices also evaluated their standalone performance. The document explicitly states: "All output is subject to verification by a medical professional," indicating that while the device is intended to aid in diagnosis, its performance evaluation was conducted on its automated output before any human review.
7. Type of Ground Truth Used
The ground truth used was expert consensus (manual scoring). The study used "manually scored sleep recordings" from "routine clinical work" as the reference standard against which DeepRESP's automatic scoring was compared.
8. Sample Size for the Training Set
The document does not report the sample size used for the training set. It only states the sample sizes for the validation (test) sets: 4,030 PSG recordings for Type I/II validation and 5,771 sleep recordings for Type III validation.
9. How the Ground Truth for the Training Set was Established
The document states that the ground truth for the training set "was established through a rigorous process involving multiple board-certified sleep physicians." This implies an expert-driven process, likely involving consensus or reconciliation among several highly qualified professionals. However, the exact methodology (e.g., number of physicians, adjudication rules) is not detailed beyond "rigorous process."
Ask a specific question about this device
Page 1 of 46