Search Results

SomniCheck is a prescription-use physiological data recorder intended to amplify, digitize, and record data from multiple physiological channels for subsequent transfer to polysomnography systems. The device measures the following signals:

• · EEG (4-channel),
• · PPG (by Maxim),
• · Temperature,
• · 3-axis accelerometer,
• · Gyroscope (position), and
• · Audio/ sound for snoring.

It is intended for use on adult patients (18 and older) and can be used in a hospital, clinic, or home.

SomniCheck is an integrated single-use disposable physiological data recorder intended to amplify, digitize, and record data from multiple physiological channels for subsequent transfer to polysomnography systems for neurophysiology or sleep disorder studies. It is intended for adult use and can be used in a hospital, clinic, or patient home. The associated software There is proprietary software that is currently under development, but the subject device's signal recording capabilities have been validated using the Natus Sleepworks K090277 via bench testing. The proprietary sleep software will be submitted in a future 510(k) Submission.

The device is affixed to the forehead of the patient and designed for continuous wear (e.g. during sleep) for up to approximately 10 hours. Once activated, the device records data for the duration of the wear period. After the wear period, the device is removed and may be thrown away. The device measures the following signals:

• · EEG (4-channel),
• PPG (by Maxim®),
• · Temperature,
• · 3-axis accelerometer,
• · Gyroscope (position), and
• Audio/ sound for snoring.

The provided text describes the predicate device information, applicable standards, and a comparison of the proposed device (SomniCheck) with predicate devices. However, it does not contain details about specific acceptance criteria for performance metrics, nor does it present the results of a study proving the device meets those criteria.

The document states:

• "(b)(1) Non-clinical bench performance tests included System Requirements Verification, Electromagnetic Compatibility (EMC) Verification, and Device Firmware Verification, including applicable clauses from the following standards: [lists various IEC and ISO standards]."
• "(b)(2) Clinical performance testing is not applicable to the device type."
• "(b)(3) The performance testing demonstrates that the device is as safe, as effective, and performs as well as the legally marketed predicate devices identified in paragraph (a)(3) of this section and therefore substantially equivalent."
• "The associated software There is proprietary software that is currently under development, but the subject device's signal recording capabilities have been validated using the Natus Sleepworks K090277 via bench testing. The proprietary sleep software will be submitted in a future 510(k) Submission."

Based on this, the device's clearance is based on bench testing against established standards and substantial equivalence to predicate devices, rather than a clinical performance study with specific acceptance criteria that would typically involve a test set, ground truth experts, and MRMC studies.

Therefore, most of the requested information cannot be extracted from the provided text.

Here's what can be inferred or stated based on the given document:

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

• Acceptance Criteria: Not explicitly stated as specific performance metrics (e.g., sensitivity, specificity) for signal detection or interpretation. The acceptance criteria are implicit in compliance with the listed IEC and ISO standards for electrical safety, EMC, usability, and risk management, and the demonstration of "as safe, as effective, and performs as well as the legally marketed predicate devices."
• Reported Device Performance: The document only states that "performance testing demonstrates that the device is as safe, as effective, and performs as well as the legally marketed predicate devices," and that "signal recording capabilities have been validated using the Natus Sleepworks K090277 via bench testing." No quantitative performance data (e.g., EEG signal fidelity, PPG accuracy) from these bench tests are provided.

2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

• Not applicable as "Clinical performance testing is not applicable to the device type." The validation was done via bench testing.
• Data provenance: Bench testing.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

• Not applicable. The ground truth for bench testing involves adherence to engineering standards and comparison with predicate device specifications, not expert interpretation of data.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

• Not applicable.

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. This device is a physiological data recorder, not an AI-powered diagnostic aide for human readers. It records signals for subsequent transfer to polysomnography systems.

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

• The device's signal recording capabilities were validated via bench testing with Natus Sleepworks K090277. This is fundamentally a standalone hardware performance validation. There is no mention of a standalone algorithm performance in the context of interpretation, as the proprietary sleep software is still "under development" and will be "submitted in a future 510(k) Submission."

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

• The ground truth for this device's validation (signal recording) would be based on engineering specifications, known signal characteristics, and comparison to the performance of the predicate device/system (Natus Sleepworks K090277) under controlled bench conditions. It is not based on clinical "ground truth" such as expert consensus or pathology, as these are related to the interpretation of the collected physiological signals, which is outside the scope of this device's current submission.

8. The sample size for the training set

• Not applicable. This is a hardware/firmware device for signal acquisition, not a machine learning model for which a "training set" would be used in the context of this 510(k). The proprietary software is still under development.

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

• Not applicable. (See #8)

Ask a specific question about this device