(104 days)
The HyperSound Group Auditory Trainer is indicated for use as a group auditory trainer or group hearing aid used to communicate simultaneously with one or more listeners with or without hearing loss and with or without the use of hearing aids in order to improve clarity and comprehension of sounds generated from sources such as a microphone, CD/DVD player, TV, Stereo System or other sound generation systems.
The HyperSound Audio System (HSS) utilizes a specially designed emitter (speaker) that delivers beamlike sound that is clear to the listener. The beamed audio content begins to demodulate in the air within six inches of the emitter and results in a cone-like transmission of sound waves that can be directed towards the listener. This device is intended for sale as an over-the-counter product and can be used with any sound source and at any distance from 3 feet to 50 feet or more from the emitters (speakers). Ultrasonic technology has been used for many years in industry and is also utilized in medical devices, such as ultrasonic nebulizers. The ultrasonic sound waves this product is based upon have also used in commercial and localized communications, and they are below the ultrasonic sound safety limits established by OSHA as required by OSHA Noise Standard, 29 CFR 1910.95. The device consists of an amplifier, software, and an emitter (speaker). No ear plugs or head phones are required to use this device. The device is distant from and does not touch the intended patient/user.
Here's a summary of the acceptance criteria and the study proving the device meets them, based on the provided text:
Acceptance Criteria and Device Performance
| Acceptance Criteria (Benchmarking / Equivalence Standard) | Reported Device Performance (HyperSound Audio System) |
|---|---|
| ANSI S3.2-2009 Modified Rhyme Test (MRT) score | Mean score of 91% |
| Speech understanding improvement for hearing-impaired subjects (compared to conventional speakers at 70 dB) | Median AZBio scores increased from 0.0% to 34.9% (quiet), and from 1.8% to 51.6% (noise). Median CNC whole word test scores increased from 0.0% to 54.0%. Median phoneme test scores from 4.0% to 63.4%. (All with p=0.008 or p=0.004) |
Note: The document focuses on demonstrating substantial equivalence rather than defining explicit acceptance criteria in a quantitative pass/fail manner. The reported performance metrics are used to support this claim of equivalence and clinical effectiveness.
Study Details
-
Sample size used for the test set and the data provenance:
- Sample Size: 10 adult patients with mild to severe hearing loss.
- Data Provenance: Clinical study conducted at the California Hearing and Balance Center in La Jolla, CA (USA). Prospective data from a controlled audiology laboratory.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- The document does not explicitly state the number or qualifications of experts establishing ground truth for the test set. However, a "controlled audiology laboratory" suggests that audiologists or similarly qualified professionals would have conducted and interpreted the speech tests.
-
Adjudication method (e.g., 2+1, 3+1, none) for the test set:
- Not specified. The study was a "single-blinded, randomized cross over clinical study," but no details on expert adjudication of results are provided beyond standard audiology testing procedures.
-
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 not an AI-assisted diagnostic tool, but rather an auditory trainer. Therefore, an MRMC study comparing human reader performance with and without AI assistance is not applicable. The clinical study does compare the HSS system to conventional speakers, showing a significant improvement in speech understanding with the HSS.
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Yes, for the non-clinical testing, "Equivalency testing to a predicate device was performed by an independent laboratory pursuant to ANSI S3.2-2009," which would be a standalone assessment of the device's audio output characteristics.
- The clinical study assessed the device's performance directly with human users, but it's not an "algorithm only" test as the device itself is a physical auditory system.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- The ground truth for the clinical study was established by standardized audiological speech tests: Modified Rhyme Test (MRT), Consonant-Nucleus-Consonant (CNC) in quiet, and AzBio in noise. These are objective measures of speech understanding, which serve as the "ground truth" for evaluating the hearing device's effectiveness.
-
The sample size for the training set:
- This device is not an AI/ML model that requires a "training set." It is an auditory trainer employing ultrasonic technology. The design and performance are based on engineering principles and verified through bench testing and clinical studies, not machine learning training.
-
How the ground truth for the training set was established:
- Not applicable, as there is no training set for this type of device.
§ 874.3320 Group hearing aid or group auditory trainer.
(a)
Identification. A group hearing aid or group auditory trainer is a hearing aid that is intended for use in communicating simultaneously with one or more listeners having hearing impairment. The device is used with an associated transmitter microphone. It may be either monaural or binaural, and it provides coupling to the ear through either earphones or earmolds. The generic type of device includes three types of applications: hardwire systems, inductance loop systems, and wireless systems.(b)
Classification. Class II (special controls). The device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 874.9.