Search Results

The HomeSleepTest is a non-invasive prescription device for home use with patients suspected to have sleep disorders including sleep-related breathing disorders. The HomeSleepTest is a diagnostic aid for the detection of sleep-related breathing disorders, sleep staging (REM, N1, N2, N3, Wake), and snoring level. Using three frontal electrodes and one mastoid electrode, the HomeSleepTest records electrical data. In addition, the device records triaxial accelerometer data, ambient light and acoustic data. With help of the ComfortOxyRing, the device records plethysmographic data, as well as SpO2, heart rate and activity data. The HomeSleepTest calculates and reports to clinicians EEG/EOG/EMG, sleep stages, SpO2, plethysmography, pulse rate and snoring level. Based on this, the HomeSleepTest indices derived parameters, such as autonomic arousal (based on plethysmogram of ring), oxygen desaturation index and hypnogram-derived indices, such as time in each sleep stage, as well as other sleep-related parameters, to aid in determining sleep quality and quantity. HomeSleepTest data is not intended to be used as the sole or primary basis for diagnosing any sleep disorders, or sleep-related breathing disorders, prescribing treatment, or determining whether additional diagnostic assessment is warranted. The HomeSleepTest is not intended for use in life-support and monitoring systems. The HomeSleepTest and its accessories are not intended for patients requiring monitoring and intensive care. The HomeSleepTest is a prescription device indicated for adult patients aged 21 years and over.

The HomeSleepTest is used to record vital signs to determine a hypnogram (sleep profile) and sleep parameters that can be helpful in objectively determining sleep quality and quantity. The HomeSleepTest is available in a standard HomeSleepTest (HST) version and a HomeSleepTest REM+ (HST REM+) version. The only difference between the two basic devices is the measuring point of the outer electrodes on the forehead. HomeSleepTest refers to both versions of the device. Furthermore, the HomeSleepTest can be used to detect the patient's activity, head position and snoring. A recording with the HomeSleepTest is initialized in the clinic/practice. For this purpose, the patient is given the HomeSleepTest and a tablet to take home. The recording can thus be carried out independently in the home environment. Immediately after recording, the data is automatically transferred to the HST cloud. The physician has access to this data via the HST cloud where they can analyze the data via the HST cloud in DOMINO and generate a report. A tablet app with video sequences supports the patient in correct application and guides them through the required biocalibration of the system. Once the test is started, all data from the HomeSleepTest is recorded via Bluetooth. The HomeSleepTest records nine signals (3 x frontopolar EEG, 2 x EOG, EMG, snoring, activity and head position). Snoring and snoring rhythm are recorded via the tablet's microphone. Head position, movement and light support information about time in bed (TIB) and other sleep-related parameters. After completion of the measurement the next morning by the patient, the data is automatically uploaded to the HST cloud where it can be analyzed with help of DOMINO software. After the data has been successfully transferred to the cloud, an exchange with the physician is possible via the feed-back function. It is also possible to release a new measurement for this patient, so that recordings can be made over several nights to capture variability. An overview of all measurements is available to the physician in the HST Cloud. A chat area is used for communication between doctor and patient. In the cloud-based evaluation software, both the pre-evaluation and the raw data of the measurement should be analyzed or edited in an AASM compliant manner. A simple report is available immediately after uploading the measurement. However, the recorded data must still be verified by a physician: for the detailed report (standard report), the measurement is opened in the DOMINO software and scored manually. After evaluation, the standard report is also available in the overview and provides additional information on the various sleep parameters.

Here's an analysis of the acceptance criteria and the study proving the device meets them, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

Ask a specific question about this device

ABPMpro Ambulatory Blood Pressure Recorder is a Non-Invasive oscillometric and ECG device intended to acquire Ambulatory non-invasive Blood Pressure signals and 3 Channel ECG signals from the upper body surfaces. Cardiac rhythm is acquired via 3 Channel ECG signals. Additional physiological signals like plethysmogram, body position and activity are also measured. The Recorder is intended for adults and children who are over the age of 12 years. ABPMpro Software allows transfer of Blood Pressure-, ECG- and data from additional signals from the Recorder to a Windows-based PC-based computer program via USB cable for the purpose of creating reports and printouts. The Software does not perform diagnostics. Physicians carry out diagnostics evaluations of this data. The system is only for measurement, recording and display. It makes no diagnosis.

The ABPMpro is a portable device for recording physiological signals. The ABPMpro is used as a long-term blood pressure as well as a long-term ECG device. The ABPMpro is a portable device worn on the upper arm by means of a cuff and used as an oscillometric 24h ambulatory blood pressure recorder. The ABPMpro consists of the following hardware: ABPMpro recorder with integrated accelerometer and position sensor; Brachial blood pressure cuff (3 sizes available); Optional: 3-channel ECG sensor; Optional: Plethysmogram-sensor (LED). Following the completion of the patient recording session, the device, cuff and electrodes are removed from the patient. The ABPMPro is connected to the PC using the USB cable. With the downloaded ABPMpro Analyzer Software open on the PC, the user can download the recorded data. The user can select the patient data and begin analysis. The device is intended for prescription use.

The provided text details the 510(k) premarket notification for the SOMNOmedics GmbH ABPMpro device. It outlines the device's intended use and presents a summary of performance testing and substantial equivalence comparison to predicate devices.

Here's an analysis of the acceptance criteria and the study that proves the device meets them, based on the provided text:

1. A table of acceptance criteria and the reported device performance

The document doesn't explicitly present a table of "acceptance criteria" with quantitative targets alongside the device's performance. Instead, it states that performance testing was conducted to confirm "compliance to device specifications" and that recorded signals "comply with the performance criteria set forth by SOMNOmedics that includes the minimum performance specification recommended by the applicable standards."

The key standards referenced for performance are:

• IEC 80601-2-30: for automated non-invasive sphygmomanometers (blood pressure).
• IEC 60601-2-47: for ambulatory electrocardiographic systems (ECG).

The reported device performance based on the clinical study related to blood pressure measurement against a recognized standard (ISO 81060-2:2018) is the most direct evidence provided for meeting performance criteria:

2. Sample size used for the test set and the data provenance

The clinical testing data provenance is described as an "open, prospective, clinical validation study."

• General validation study (for blood pressure at rest): N = 90
  • Age: 12-76 years (Mean age 39.7 ± 15.1)
  • Gender: 47 male (52%), 43 female (48%)
• Ambulatory validation study (for blood pressure under dynamic exercise): N = 36
  • Age: 22-65 years (Mean age 40.9 ± 11.0)
  • Gender: 20 male (56%), 16 female (44%)

The country of origin for the data is not explicitly stated, but the sponsor is "SOMNOmedics GmbH Am Sonnenstuhl 63 Randersacker, Germany D-97236", which suggests the study may have been conducted in Germany or a location adhering to European standards. The study received "Ethics Committee approval" and was conducted "in accordance with good clinical practice (GCP) as described in 21 CFR 812.28(a)(1)," which are US regulations. This suggests a study potentially designed for US regulatory submission, but the exact location is not provided.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

For the blood pressure measurements, the ground truth was established by:

• Two observers provided simultaneous auscultatory reference BP measurements using a dual-head teaching stethoscope.
• Qualifications of experts: Not explicitly stated beyond "two observers." It's implied they are trained to accurately use the reference sphygmomanometer and stethoscope for auscultatory measurements.

4. Adjudication method for the test set

The method for establishing reference blood pressure was the "same arm sequential method" described in the Universal Standard (ISO 81060-2:2018). The involvement of "two observers" taking "simultaneous auscultatory reference BP measurements" suggests a form of consensus or comparison between them to establish the reference, as per the standard's requirements for validating automated sphygmomanometers. However, a specific adjudication method (e.g., 2+1, 3+1, averaging, arbitration) for discrepancies between the two observers is not explicitly described. The standard itself outlines how such measurements are to be handled.

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

No MRMC comparative effectiveness study was mentioned. The device, ABPMpro, does not appear to be an AI-assisted diagnostic tool; rather, it is a data acquisition and display device. The software "does not perform diagnostics. Physicians carry out diagnostics evaluations of this data. The system is only for measurement, recording and display. It makes no diagnosis." Therefore, a human-in-the-loop or AI assistance study involving human readers would not be applicable or expected for this device's stated function.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

The primary performance evaluation for the blood pressure measurement was the "accuracy" against the reference standard (ISO 81060-2:2018), which is a standalone performance assessment of the device's ability to accurately measure BP. For ECG, the compliance to IEC 60601-2-47 further indicates a standalone performance assessment of its signal acquisition capabilities.

7. The type of ground truth used

The ground truth for blood pressure measurements was established using:

• Expert Consensus/Reference Measurement: Simultaneous auscultatory reference BP measurements taken by two trained observers (using a calibrated standard aneroid sphygmomanometer and a dual-head teaching stethoscope). This aligns with the "expert consensus" category for reference standard measurements in clinical studies of measurement devices.
• Standardized Method: The "same arm sequential method" described in the ISO 81060-2:2018 Universal Standard.

8. The sample size for the training set

The document does not specify a training set or its sample size. This is typical for medical devices that are not "machine learning/AI" devices requiring a distinct training and test split for an algorithm. The "ABPMpro" is presented as a measurement and recording device, not one with a diagnostic AI algorithm that learns from data.

9. How the ground truth for the training set was established

As no training set is mentioned (see point 8), this information is not applicable.

Ask a specific question about this device

EEG adhesive conductive paste (hereafter EEG-acp) is intended for use in clinical and research EEG recordings from humans under professional guidance. EEG-acp is an electroconductive paste which should be used in combination with EEG cup electrodes on the scalp.

EEG adhesive conductive paste (hereafter EEG-acp) is intended for use in clinical and research EEG recordings from humans (from the age of 2) under professional guidance. EEG-acp is an electroconductive paste which should be used in combination with EEG cup electrodes on the scalp. It acts as a conductor between the scalp and the cup electrodes to reduce impedance between the electrode surface and the skin. The reduction in impedance facilitates better recording of the signal. It is intended to be used for up to 10 hours after application to healthy, intact skin. After drying, it is self-adhesive and can be washed off with water. The cream is provided non-sterile and in a 100g aluminum tube. It is white and has no adverse smell. Its texture is smooth and creamy directly after withdrawal from the tube, and solid after drying. EEG-acp is intended to be used as an electroconductive medium between the electrode and the patient's skin, i.e., it amplifies the electrical signal and thereby improves the electrophysiological recording. The high salt content of the cream is responsible for its conductive properties. Its impedance is -1.9 kOhm and its conductivity is 20 mS/cm.

The provided text describes the 510(k) summary for the EEG-acp device. This document is a premarket notification to the FDA to demonstrate that the device is at least as safe and effective as a legally marketed predicate device. The information details the device, its intended use, and comparative data against a predicate device.

Here's an analysis of the acceptance criteria and study proving device performance based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are not explicitly stated as typical performance metrics (e.g., sensitivity, specificity, AUC) for an AI/ML diagnostic device, because EEG-acp is an "Electroconductive Media" (a physical cream), not a diagnostic algorithm. Instead, the "acceptance criteria" for this device are established by demonstrating substantial equivalence to a legally marketed predicate device (SAC2 Electrode Cream, K192606) in terms of its physical and performance characteristics.

The table below summarizes the key comparisons made for "acceptance" of EEG-acp:

2. Sample Size Used for the Test Set and the Data Provenance

The document does not describe a clinical study in humans with a "test set" in the traditional sense of an AI/ML algorithm evaluation (i.e., a dataset of patient data used to evaluate algorithm performance). Instead, the studies performed are bench testing and biocompatibility testing of the physical cream itself.

• Bench Testing:
  • Impedance and Conductivity: Measured to confirm equivalence with the predicate device. The sample size for these measurements is not specified (e.g., number of cream samples, number of measurements).
  • Qualitative characteristics (Color, odor, adhesiveness, time to dry): Verified to be as specified and equivalent to the predicate device. Sample size not specified.
  • Shelf-life: Validated by accelerated aging testing in accordance with ASTM F1980-16. Sample size not specified (e.g., number of batches, number of samples tested over time).
• Biocompatibility Testing:
  • The tests performed were:
    • ISO 10993-5: Cytotoxicity in vitro Skin Irritation (Human Skin Model Test)
    • ISO 10993-10: Acute Dermal Irritation/Corrosion, Irritation/Skin Sensitization, Guinea Pig Maximization Test.
  • These are laboratory tests on cells/animal models, not human patient data. The sample sizes for these specific biological assays are not detailed in the summary.
• Data Provenance: The document does not explicitly state the country of origin for the data or whether the tests were retrospective or prospective, though it implicitly describes prospective laboratory/bench testing.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts

This information is not applicable to the evaluation of this device. As EEG-acp is an electroconductive paste, its performance is assessed through physical and chemical property measurements and biocompatibility testing, not through expert interpretation of diagnostic images or clinical outcomes. Therefore, there is no "ground truth" expert adjudication process in the context of diagnostic accuracy.

4. Adjudication Method for the Test Set

Not applicable, as there is no expert adjudication of a diagnostic performance test set.

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

Not applicable. This device is not an AI/ML algorithm designed to assist human readers (e.g., radiologists) in diagnostic interpretation. It is a physical medical device (conductive paste).

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done

Not applicable. This is not an algorithm. Bench tests (e.g., impedance, conductivity, shelf-life) could be considered "standalone" in the sense that they evaluate the properties of the cream itself, independent of human application for diagnosis, but this term (standalone) is typically used for AI/ML algorithms.

7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)

The "ground truth" for this device's acceptance is based on:

• Physical and Chemical Properties: Measured values (e.g., impedance, conductivity, pH, time to dry, color, odor, adhesiveness, consistency) are compared against scientifically established standards or performance of the predicate device.
• Biocompatibility Standards: Results from tests defined by ISO 10993-1, -5, and -10 are used as "ground truth" for safety regarding biological compatibility (cytotoxicity, irritation, sensitization).
• Shelf-life Standards: Accelerated aging tests following ASTM F1980-16 provide the "ground truth" for shelf-life performance.

8. The Sample Size for the Training Set

Not applicable. This is not an AI/ML algorithm that requires a training set.

9. How the Ground Truth for the Training Set Was Established

Not applicable, as there is no training set for this type of device.

Ask a specific question about this device

The SOMNOscreen® plus is a non-life-supporting portable physiological signal recording device intended to be used for testing adults and children (age 2 to 12 years)/adolescents (age 12 and above) suspected of having sheep related breathing disorders.

The SOMNOscreen® plus is a modular system with the following components available .: Thermistor, Nasal Canula, Effort belts with respective sensor, SpO2-Sensor, Microphone, Headbox (EXG Channels), external body position sensor, shoulder belts, activity sensor, EMG-PLM sensor, pressure sensor, gold cup electrodes and LoFlo CO2-module (optional). The SOMNOscreen® plus device provides 13 AC channels (10 Referential and 3 Differential), 11 Respiratory and AUX Channels, and 8 Internal Channels.

The SOMNOscreen plus is available in 4 different configurations.

• . Cardio-RESP
• Home Sleep
• PSG .
• . EEG 32

The purpose of this 510(k) submission is to expand the patient population to include children and adolescents. For the use in pediatric patients the DOMINO software only allows manual (visual) scoring by qualified RPSG. There is no automated analysis or highlighting available for pediatric patients.

The provided text describes a medical device, SOMNOscreen plus, and its FDA 510(k) clearance. The submission focuses on expanding the patient population to include children and adolescents, emphasizing that for this new population, only manual scoring by qualified personnel is allowed, with no automated analysis.

Here's an analysis of the acceptance criteria and study information, based only on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of "acceptance criteria" against "reported device performance" in a quantitative manner for specific diagnostic metrics (e.g., accuracy, sensitivity, specificity for detecting sleep-related breathing disorders). Instead, it discusses compliance with general safety and performance standards for electroencephalographs and polysomnographs.

However, we can infer some performance aspects based on the technical specifications and comparisons:

2. Sample Size Used for the Test Set and Data Provenance

The document explicitly states: "Clinical data were not relied upon for a determination of substantial equivalence." This means no specific clinical test set was used to evaluate the device's diagnostic performance for sleep-related breathing disorders in humans for this submission. The evaluation focused on technical and safety equivalence to predicate devices and adherence to standards.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts

As no clinical data was relied upon, there was no test set requiring expert-established ground truth. The "ground truth" implicitly referred to here is compliance with technical standards and AASM recommendations for polysomnography signal acquisition. For pediatric applications, the text mentions "manual (visual) scoring by qualified RPSG" (Registered Polysomnographic Technologist), implying that human experts are crucial for interpreting the device's output, especially in the expanded pediatric population. However, this is about the use of the device, not the validation of its performance in a clinical study for this submission.

4. Adjudication Method for the Test Set

Not applicable, as no clinical test set was used or described.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done

No, an MRMC comparative effectiveness study was not done, as stated by "Clinical data were not relied upon for a determination of substantial equivalence." The document indicates that for pediatric populations, the software "only allows manual (visual) scoring by qualified RPSG. There is no automated analysis or highlighting available for pediatric patients." This suggests that any comparative effectiveness of human readers with AI assistance versus without AI assistance is not relevant to this specific clearance for the pediatric population, as AI assistance for scoring is explicitly not provided for them.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was Done

No standalone algorithm performance study was described. In fact, for the new pediatric population, the device explicitly does not offer automated analysis or highlighting, emphasizing human interpretation.

7. The Type of Ground Truth Used

For the purposes of this 510(k) submission, the "ground truth" used was primarily compliance with recognized standards (IEC 60601-1, IEC 60601-1-2, ISO 14971, ISO 10993, IEC 62366-1) and technical specifications, as well as adherence to minimum performance specifications recommended by the American Academy of Sleep Medicine (AASM) for signal types. No clinical ground truth (like pathology, expert consensus on diagnostic outcomes, or long-term outcomes data) was used in a specific clinical study for this submission.

8. The Sample Size for the Training Set

No training set information is provided, as the submission did not rely on clinical data or automated algorithms that would require a training set for this clearance. The "training" here refers to the design and verification process of the device itself against engineering and safety requirements.

9. How the Ground Truth for the Training Set Was Established

Not applicable, as no training set for an AI algorithm was described. The device's "training" in an engineering sense involved verification and validation against pre-specified requirement specifications and relevant performance standards, ensuring basic safety and essential performance.

Ask a specific question about this device

The SOMNOtouch RESP is a portable physiological signal recorder. It is indicated for use in the recording, displaying, monitoring, printing, and storage of biophysical parameters for the purpose of assisting in the diagnosis of sleep disorders and sleep related respiratory disorders of adult patients. The device is intended to be prescribed for use by a physician in the office, sleep laboratory or patient's home.

This device is NOT designed to be used in life support situations.

The SOMNOtouch™ RESP is a small, portable physiological signal recording system intended to be used to record, display, monitor, print and store biophysical parameters to aid in the diagnosis of sleep disorders. The device is intended to be prescribed for use by a physician in the office, sleep laboratory or patient's home.

The SOMNOtouch™ RESP consists of the following:

1. The recording device (worn on the thorax),
2. the finger probe, which is used to detect SpO2,
3. the external effort sensor,
4. two effort belts to measure thoracic and abdominal expansion,
5. the nasal cannula.
6. the Software DOMINOlight for visualization of the recorded data.

The SOMNOtouch™ RESP typically will be worn at the thorax, attached by a thorax belt. It contains a sensor to measure the respiratory effort signal of the thorax. The device has an internal accelerometer, measuring body position and motion activity. It provides a connector to attach a nasal cannula, which allows the recording of respiratory flow and snore signals with the internal pressure sensor. Arterial oxygen saturation (SpO2) and pulse rate can be determined via a pulse oximetric finger sensor. Abdominal respiratory effort is measured with an external sensor, attached with a belt to the abdomen. This information is stored in the internal memory of the device.

The system provides up to 10 internal channels for data acquisition, Pressure/Flow, Thoracic Effort, SpO2, Pulserate, Snoring, Finger Plethysmogram, Body Position, Movement, Patient Marker, CPAP, and 1 external Abdominal Effort Sensor. The data from all channels can be recorded separately or in any combination with the other channels.

Information is stored on an internal 512 MB flash memory and can be transferred to a PC via a USB docking station. The DOMINOlight software retrieves the data from the SOMNOtouch™ RESP, displays and analyzes the data, and can store data for future reference and comparison. The SOMNOtouch RESP does not provide automatic diagnosis and is not designed to be used in Life Support situations.

The SOMNOtouch™ RESP device is a portable physiological signal recorder used to assist in diagnosing sleep disorders and sleep-related respiratory disorders in adult patients. The acceptance criteria and supporting study details are as follows:

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size and Data Provenance (for test set, which is the clinical study)

• Sample Size: "Subjects were recruited out of the regular patient collective of the sleep lab where the study was conducted." The exact number of subjects is not specified in the provided text.
• Data Provenance: The study was performed in a "professional sleep lab" in Germany (based on the applicant's country). This indicates prospective data collection for the purpose of the study.

3. Number of Experts and Qualifications for Ground Truth (Test Set)

• Number of Experts: "different qualified professionals"
• Qualifications of Experts: Not explicitly stated beyond "qualified professionals". It is implied that they are qualified to manually score sleep study data.

4. Adjudication Method (Test Set)

• The text states: "Data sets were scored manually by different qualified professionals." This implies independent scoring of the data by multiple experts, but it does not specify an adjudication method like 2+1 or 3+1 for resolving discrepancies.

5. Multi Reader Multi Case (MRMC) Comparative Effectiveness Study

• No MRMC comparative effectiveness study was done regarding human readers' improvement with or without AI assistance. The study described compares the device's performance to a predicate device, not the impact on human reader performance.

6. Standalone Performance Study

• Yes, a standalone study was performed. The clinical study evaluated the SOMNOtouch™ RESP's ability to detect breathing events and provide AHI measurements, which is the algorithm's direct output. The comparison was to the predicate device's output, indicating a standalone assessment of the new device.

7. Type of Ground Truth Used

• Expert Consensus: The ground truth for the clinical study was established by "manual scoring by different qualified professionals" of the sleep study data.

8. Sample Size for the Training Set

• The document does not provide information on a training set or its sample size. This submission is for a medical device that records physiological signals for diagnosis, and the "clinical study" described is a validation study rather than directly evaluating an AI/ML algorithm that would typically require a training set. The device itself performs measurements and records data, which are then manually interpreted by experts.

9. How the Ground Truth for the Training Set Was Established

• As no training set is mentioned or implied for an AI/ML algorithm, this information is not applicable.

Ask a specific question about this device

The SOMNOwatch is a non-life-supporting portable physiological signal recording device intended to be used for testing adult patients suspected of having movement-correlated sleep disturbances.

The SOMNOwatch is a small, portable physiological signal recording system intended to be used to record, display, monitor, print and store biophysical events to aid in the diagnosis of sleep disorders. The device is intended to be prescribed for use by a physician in the office, sleep laboratory or patient's home.

The SOMNOwatch is a small, typically wrist-worn activity monitor. The device is intended to be used to analyze circadian rhythms, automatically collect and score data for sleep parameters. These parameters, representing the number and intensity of limb movements, are directly associated to movement-correlated sleep disturbances. The unit can also be used to assess activity in any instance where quantifiable analysis of physical motion is desired. For PLM-detection two identical SOMNOwatches may be affixed to the patients legs, one to each leg.

The SOMNOwatch 510(k) Premarket Application (K081485) describes the device, its intended use, and a summary of nonclinical and clinical testing. However, it does not explicitly define acceptance criteria in terms of specific performance metrics (e.g., sensitivity, specificity, accuracy) or provide a detailed study that proves the device meets such criteria. Instead, the submission focuses on establishing substantial equivalence to predicate devices primarily through nonclinical performance testing and a "clinical comparison" study, without providing quantitative results against predefined thresholds.

Based on the provided text, here's a breakdown of the requested information:

1. A table of acceptance criteria and the reported device performance

The provided document does not contain explicit numerical acceptance criteria or quantifiable performance metrics (like sensitivity, specificity, or accuracy for diagnosing sleep disturbances) for the SOMNOwatch itself. The "reported device performance" is broadly stated as:

2. Sample sized used for the test set and the data provenance

• Test Set Sample Size: Not specified. The document only mentions "clinical comparison studies" without detailing the number of participants or the data size.
• Data Provenance: Not specified. It's unclear if the data was retrospective or prospective, or the country of origin.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

Not specified. The document does not describe how ground truth was established for any clinical comparison.

4. Adjudication method for the test set

Not specified. There is no mention of an adjudication method.

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

No MRMC study was described. The SOMNOwatch is an activity recording device that provides raw data and analysis software (DOMINOlight) but the document does not discuss human reader performance improvement with or without AI assistance. The focus is on the device's ability to record and score data for sleep parameters related to movement-correlated sleep disturbances.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

The device is intended to "automatically collect and score data for sleep parameters," implying a standalone algorithmic analysis. The "DOMINOlight software retrieves the data from the SOMNOwatch, displays the data, and can store data for future reference and comparison. DOMINOlight also allows automatic analysis of all signals including the body position." However, no specific standalone performance metrics (e.g., for automated PLM detection accuracy) are provided in this summary. The evaluation focuses on equivalence to predicate devices rather than direct algorithmic performance.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

Not specified. The document does not describe the specific type of ground truth used in its "clinical comparison studies." Given the device's function to "automatically collect and score data for sleep parameters" related to movement, it's possible that the comparison was against similar data from predicate devices or established polysomnography (PSG) techniques, but this is not explicitly stated.

8. The sample size for the training set

Not applicable/Not specified. The document does not mention a training set, as it does not describe the development or validation of a new AI/ML algorithm through traditional training/testing splits with a separate training set. The clinical evaluation mentioned is a "comparison study" to predicate devices for substantial equivalence.

9. How the ground truth for the training set was established

Not applicable/Not specified as no training set was described.

Ask a specific question about this device

The SOMNOscreen EEG10-20 is a non-life-supporting portable physiological signal recording device intended to be used for testing adult patients suspected of having sleep-related breathing disorders.

The SOMNOscreen EEG10-20 is a portable physiological signal recording system intended to be used to record, display, monitor, print and store biophysical events to aid in the diagnosis of neurologic and sleep disorders. The device is intended to be prescribed for use by a physician in the office, sleep laboratory or patient's home.

The SOMNOscreen EEG10-20, a portable physiological signal recording system, did not undergo a study with acceptance criteria in the provided documentation. Instead, its substantial equivalence to a predicate device, the Somnomedics SOMNOscreen (K060708), was established through performance testing and a comparison of technological characteristics.

Here's an analysis based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size Used for the Test Set and Data Provenance

• Sample Size: Not applicable. The submission describes performance testing for device specifications and compliance with standards, not a clinical study with a patient test set.
• Data Provenance: Not applicable. The testing was described as "performance testing" and "testing to the international standards," which implies internal device validation rather than clinical data.

3. Number of Experts Used to Establish Ground Truth and Qualifications

• Not applicable. This information is not provided because no clinical (human subject) test set requiring expert adjudication was conducted for this 510(k) submission.

4. Adjudication Method

• Not applicable. No clinical test set requiring ground truth establishment through expert adjudication was mentioned.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• No. An MRMC study was not described in the provided text. The device is a physiological signal recording system, and the submission focuses on its technical performance and equivalence to a predicate, not on human reader interpretation or AI assistance.

6. Standalone Performance Study

• Yes, effectively. The performance testing described ("Performance testing was conducted to confirm compliance to device specifications; all functions were verified to operate as designed. Measured parameters met required ranges and accuracies.") can be considered a standalone assessment of the device's functional performance, albeit at a technical level rather than a clinical performance (e.g., diagnostic accuracy) level. The submission is for a recording device, not an analytical algorithm.

7. Type of Ground Truth Used

• Technical specifications/Compliance Standards. The "ground truth" for the performance testing was derived from the device's technical specifications and the requirements of international standards for electrical safety and electromagnetic compatibility. This is not clinical ground truth like pathology or expert consensus.

8. Sample Size for the Training Set

• Not applicable. This device is a physiological signal recording system, not an AI/ML algorithm that requires a training set of data for development.

9. How the Ground Truth for the Training Set Was Established

• Not applicable. As the device is not an AI/ML algorithm, it does not have a training set.

Ask a specific question about this device

The SOMNOscreen is a non-life-supporting portable physiological signal recording device intended to be used for testing adult patients suspected of having sleep-related breathing disorders.

The SOMNOscreen is indicated for use in the recording, displaying, monitoring, and storage of biophysical parameters for the purpose of assisting in the diagnosis of Neurological and Sleep Disorders.

The SOMNOscreen is a portable physiological signal recording system intended to be used to record, display, monitor, print and store biophysical events to aid in the diagnosis of neurologic and sleep disorders. The device is intended to be prescribed for use by a physician in the office, sleep laboratory or patient's home.

This device is NOT designed to be used in a Life Support situation. This device is not designed for use on patients with cardiac pacemakers.

The system provides up to 28 channels for data acquisition; 10 AC Channels, 8 Referential and 2 Differential, 11 Respiratory and AUX Channels, 7 Internal Channels (SPO2, Pulse Rate, Plethysmogram, Body Position, Light, Patient Marker, Thorax/Abdominal Respiratory Effort)

The SOMNOscreen is available in 6 different configurations. All configurations include a Compact Flash Card and Reader, Li ION Batteries, (2000mAh) with 1 x Battery Charger, a Carry Bag for housing the SOMNOscreen and Sensors, Instruction Manuals and the DOMINO software for Initialization, Data Transfer and Analysis.

Here's a summary of the acceptance criteria and study details for the Somnomedics SOMNOscreen based on the provided 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance

The provided document does not explicitly state quantitative "acceptance criteria" for the SOMNOscreen's clinical performance. Instead, it states that the device's clinical performance was found to be "equivalent to the predicate Sleepscreen and the manual scored Polysomnography." Therefore, the reported device performance is its equivalence to these established methods.

2. Sample Size Used for the Test Set and Data Provenance

• Sample Size: 25 patients
• Data Provenance: Not explicitly stated, but the applicant (Somnomedics GmbH & Co.KG) is based in Kist, Germany. It is common for clinical studies associated with German manufacturers to originate from Germany or other European countries; however, this is not confirmed in the document. The study evaluates the device "when used as intended in the targeted patient population," implying prospective data collection for this validation.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications

The document states that the comparison was made against "manual scored Polysomnography." This heavily implies that sleep experts (e.g., polysomnography technologists, sleep physicians) were involved in scoring the PSG data, which would serve as the ground truth. However:

• Number of experts: Not specified.
• Qualifications of experts: Not specified, but generally, manual PSG scoring is performed by registered polysomnographic technologists (RPSGTs) and interpreted by board-certified sleep physicians.

4. Adjudication Method for the Test Set

The document does not describe an explicit adjudication method (e.g., 2+1, 3+1). The "manual scored Polysomnography" itself is considered the reference standard, and deviations from this standard for the SOMNOscreen's output would be assessed.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

No. The study described compares the SOMNOscreen to a predicate device and manual PSG. It does not appear to be an MRMC study designed to evaluate the improvement in human reader performance with or without AI assistance. The SOMNOscreen, as described, is a physiological signal recording system, not an AI-assisted diagnostic tool in the sense of providing automated interpretations that would then be reviewed by human readers.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

Yes, in essence. The study evaluates the "clinical performance of the SOMNOscreen" itself against predicate devices and manual PSG. While a human would still interpret the output from the SOMNOscreen, the study aims to validate the device's ability to record, display, monitor, print, and store biophysical events reliably, standalone from a human "AI assistance" workflow. The device does not appear to have an AI component for automated interpretation that would undergo a separate standalone performance evaluation.

7. The Type of Ground Truth Used

The ground truth used was manual scored Polysomnography (PSG), which is typically considered the gold standard for sleep disorder diagnosis.

8. The Sample Size for the Training Set

The document does not mention a training set or any details about an algorithm that would require one. The SOMNOscreen is described as a physiological signal recording system, implying it captures raw physiological data rather than employing a machine learning algorithm that would need training.

9. How the Ground Truth for the Training Set Was Established

Since no training set is mentioned and the device appears to be a data acquisition system rather than an AI/ML-based interpretive algorithm, this information is not applicable and not provided in the document.

Ask a specific question about this device