Search Results

The BalanceBack VNG device is intended for recording, viewing, and analyzing eye movements in support of identifying balance disorders in human subjects. The VNG is intended for use only by trained physicians or clinicians in an appropriate doctor's office or health care facility. This device provides no diagnoses nor does it provide diagnostic recommendations.

Eve movements have long been known to provide important clues to the identification and location of balance disorders. Physicians and other clinicians employ the VNG system to conduct a set of established, well-known and well-documented eye movement tests. The results of the VNG eye movement tests are combined with other clinical information so that the attending clinicians may render findings on the health of the patient's primary balance sensors and related balance processing system.

Using the VNG, clinicians guide patients through a series of eye movement tests. A testing battery (i.e., an examination) typically consists of all eight tests supported by the VNG: caloric, positional, Hallpike, gaze, saccades, smooth pursuit, optokinetic, and high-frequency head shake. The attending physician may select one, several, or all tests, and has full flexibility in determining the sequence of the tests to be performed.

The patient under examination wears the VNG goggles. The goggles contain one IR light source and one IR camera for each eye. The IR video cameras sense the infrared signal reflected from the eyes and create a continuous monochromatic (grayscale) video motion picture stream of the eyes. The infrared signal is used because the human eye cannot detect the presence of the infrared signal and therefore this illumination does not create perturbations in measurements of eye movement. Measurements may therefore be made both in the presence and in the absence of visible light, thus providing clinicians with maximum flexibility for making measurements in a wide variety of situations.

The video stream from the IR cameras is digitized and transferred into the memory of the digital computer where signal processing software tracks, records, analyzes and displays eye movements for the attending clinician. The VNG system makes appropriate calculations and presents reports of well-known and well-documented parameters associated with each eye movement test.

Some eye tests require the patient to follow a visual stimulus. A projector, controlled by the VNG software, displays stimuli on any light-colored surface, such as a wall or projection screen. The goggles and VNG software record the patient's eye movements while he/she follows the stimulus.

The provided text describes the BalanceBack VNG System, a device for recording, viewing, and analyzing eye movements to assist in identifying balance disorders. However, the document primarily focuses on establishing substantial equivalence to predicate devices and adherence to recognized electrical safety and performance standards. It does not present a study with specific acceptance criteria that the device's performance was measured against in terms of clinical outcomes or diagnostic accuracy.

Here's an analysis based on the provided text, highlighting the absence of the requested information:

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

The document mentions "Verification procedures with pass/fail criteria were developed to ensure that the product met all the specified requirements." However, it does not explicitly state what these acceptance criteria were in terms of device performance for identifying balance disorders, nor does it report the device's performance against such criteria. The criteria mentioned are related to electrical safety and product standards.

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

Not provided. The document does not describe a clinical test set or data. The "Testing" section refers to hardware and software verification, not clinical performance studies on human subjects to assess diagnostic aid capabilities.

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/Not provided. Since no clinical test set for diagnostic accuracy is described, there's no mention of experts establishing ground truth for such a test. The device "provides no diagnoses nor does it provide diagnostic recommendations."

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

Not applicable/Not provided. No clinical test set warranting adjudication is described.

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/Not provided. This device is presented as a tool to aid clinicians by recording, viewing, and analyzing eye movements, not as an AI-assisted diagnostic tool that would typically be evaluated in an MRMC study for improved human reader performance. The device "provides no diagnoses nor does it provide diagnostic recommendations."

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

Not applicable/Not provided. The device is described as "intended for use only by trained physicians or clinicians" and it "provides no diagnoses nor does it provide diagnostic recommendations." Therefore, a standalone diagnostic performance evaluation would not be relevant given its stated function.

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

Not applicable/Not provided. No clinical performance study requiring ground truth is described.

8. The sample size for the training set

Not applicable/Not provided. The document describes a medical device for VNG, and there is no indication of machine learning or AI components that would require a "training set" in the context of diagnostic algorithms.

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

Not applicable/Not provided. As there's no mention of a training set for an AI/ML algorithm, this information is not relevant or present in the document.

In summary: The provided 510(k) summary focuses on demonstrating substantial equivalence to predicate devices based on similar technology and intended use, and indicates compliance with recognized electrical safety and performance standards (though the actual certification is pending marketing). It does not include a study demonstrating the clinical performance or diagnostic accuracy of the BalanceBack VNG System against specific acceptance criteria for identifying balance disorders. The device is explicitly stated not to provide diagnoses or diagnostic recommendations, which simplifies the regulatory pathway by avoiding requirements for extensive clinical performance studies to prove diagnostic accuracy.

Ask a specific question about this device