Search Results

The HyperSound Timitus Module is indicated for patient home use in the temporary relief of tinnitus symptoms. The device is available in HyperSound Clear 500P audio systems to generate and deliver personalized sound output to timitus patients with or without hearing loss and with or without hearing aids. Any fitting of the device must be done by a hearing care professional. The target population is primarily adults (18 years or older).

The HyperSound Tinnitus Module is a tool to a cleared device that provides the means to create personalized sound output to provide temporary relief to patients suffering from tinnitus. It is available as a firmware option embedded in the commercially available over the counter HyperSound Clear 500P system ("500P"), a Class II, 510(k)- cleared group hearing aid (K133352). The 500P consists of an amplifier and one or two emitters (directed audio speakers) and accompanying mains power supply.

Like the 500P, the HyperSound Tinnitus Module may be used by individuals with or without hearing loss and with or without hearing aids. As part of the prescription activation of the HyperSound Tinnitus Module option, a hearing care professional ("HCP") programs a Tinnitus EQ setting for the patient which may be a standard flat EQ or a custom EQ to fit to a patient's hearing loss and/or to shape frequency output to the user's tinnitus therapy preferences.

The activation and programming by the HCP is accomplished using the HyperFit fitting software tool only available to HCPs for use with the 500P. The user may select amongst relief sounds, fine-tune up to nine EQ bans to their liking and adjust common audio settings on the 500P device such as volume and balance (left and right speaker).

The document provided describes the HyperSound Tinnitus Module, a device designed for the temporary relief of tinnitus symptoms.

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

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

The document does not explicitly state "acceptance criteria" in a tabulated format with specific pass/fail thresholds. Instead, it presents the results of a clinical study which effectively serves as the performance data to support the device's efficacy in achieving its intended use (temporary relief of tinnitus symptoms).

Note: The "acceptance criteria" are inferred from the study's objective to "assess whether high-frequency directed audio... reduces the perception of tinnitus." The significant p-values indicate a statistically significant reduction.

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

• Sample Size (Test Set): 11 adult patients
• Data Provenance:
  • Country of Origin: The study was conducted at the California Hearing and Balance Center in La Jolla, California, USA.
  • Retrospective or Prospective: Prospective. It was a "pre and post-intervention clinical outcomes study" where subjects were exposed to the device after baseline measurements were established.

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)

The "ground truth" in this context is the patient's subjective perception of tinnitus loudness and annoyance, measured by a validated Visual Analog Scale (VAS).

• Number of Experts: The document mentions that subjects, in consultation with the Investigator (a HCP - Hearing Care Professional), selected and fine-tuned acoustic stimuli. The Investigator, a HCP, also tuned/shaped the device to the patient's audiogram. The study was conducted in a "controlled audiology clinical office."
• Qualifications of Experts: The "Investigator" is identified as a "HCP" (Hearing Care Professional). No specific years of experience or further credentials (e.g., audiologist) are detailed, but the context implies a qualified professional in audiology.

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

The ground truth was established by direct patient self-report using a validated Visual Analog Scale (VAS) for loudness and annoyance. There was no independent expert adjudication of the patient's reported tinnitus perception. The Investigator's role was in fitting and customizing the device, not adjudicating the patient's subjective responses on the VAS. Therefore, the adjudication method was essentially none, relying on the patient's self-assessment.

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, an MRMC comparative effectiveness study was not done. The device in question is a Tinnitus Module that generates sound for temporary relief, not an AI-powered diagnostic tool that assists human readers (e.g., radiologists) in interpreting medical images.
• The study design was a pre- and post-intervention clinical outcomes study assessing the device's direct effect on patients' tinnitus perception.

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

• Yes, in essence, the "algorithm" performance was evaluated. The HyperSound Tinnitus Module itself, with its firmware and sound generation capabilities, is the core "algorithm." The study measured the direct effect of this module (when customized by a HCP and used by the patient) on tinnitus symptoms.
• However, it's important to note the "human-in-the-loop" aspect during the initial setup and customization: "Any fitting of the device must be done by a hearing care professional." and "a hearing care professional ('HCP') programs a Tinnitus EQ setting for the patient." and "Subjects, in consultation with the Investigator (a HCP), selected from a choice of customized acoustic stimuli... The HyperSound 500P device was tuned or shaped by the Investigator... Subjects, with consultation from the Investigator, then fine-tuned (EQ) settings..." So, while the final delivery of sound is by the device, a HCP is essential for initial personalization.

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

• The ground truth used was patient-reported outcomes data, specifically subjective perception of tinnitus loudness and annoyance, measured by a validated 100-point Visual Analog Scale (VAS-L and VAS-A).

8. The sample size for the training set

• The document does not mention a separate training set for the HyperSound Tinnitus Module. The clinical study described is the primary performance evaluation, serving as the test set.
• The device is a firmware option for an already cleared device (HyperSound Clear 500P). The "software verification and validation" section states that the firmware was verified and validated according to relevant standards, but no specific training data/set for an AI/machine learning model is described. The customization process by the HCP is done in real-time for each patient, not by a pre-trained model.

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

• As no training set is described for an AI/machine learning model, this question is not applicable based on the provided text. The device's operation relies on a HCP to personalize settings based on a patient's self-reported audiogram and tinnitus preferences.

Ask a specific question about this device