(28 days)
The Multiflex Tinnitus Technology is a tool to generate sounds to be used in a Tinnitus Management Program to relieve patients suffering from tinnitus. The target population is primarily the adult population over 18 years of age.
The Multiflex Tinnitus Technology is targeted for healthcare professionals, which are treating patients suffering from tinnitus, as well as conventional hearing disorders. The fitting of the Multiflex Tinnitus Technology must be done by a hearing professional participating in a Tinnitus Management Program.
Multiflex Tinnitus TechnologyTM (Tinnitus Multiflex) is designed to generate noise that can optionally periodically fluctuate in amplitude and frequency to provide relief for patients suffering from tinnitus.
Tinnitus Multiflex is a firmware program code (algorithm) that is embedded as part of the integrated circuit (IC) in the Digital Signal Processing (DSP) stage of a hearing-aid. More specifically, Tinnitus Multiflex is an added branch of code that is separate from the normal existing hearing-aid firmware. As such, hearing-aid operating characteristics (besides tinnitus-stimulus functionalities) are not impacted by the Tinnitus Multiflex branch of code. Tinnitus Multiflex may be deployed across all Starkey hearing-aid models.
Tinnitus Multiflex functionalities and parameters are enabled and adjusted by a hearing-care professional utilizing the Starkey proprietary hearing-aid programming software, Inspire. The Tinnitus Multiflex can be manually adjusted to a patient's stimulus needs or automatically adjusted via the new audiogram shaping functionality.
The provided text describes a 510(k) premarket notification for a Tinnitus Masker device (Multiflex Tinnitus Technology) and does not contain detailed information about a clinical study involving experts, test sets, or ground truth establishment in the context of typical AI/ML device evaluations. The submission primarily focuses on demonstrating substantial equivalence to a predicate device (K122876) based on technological characteristics and performance specifications for non-clinical testing.
Therefore, many of the requested items (2, 3, 4, 5, 6, 7, 8, 9) cannot be answered directly from the provided text as they pertain to clinical evaluations that were explicitly stated as not being performed for this submission.
Here is the information that can be extracted from the document:
1. A table of acceptance criteria and the reported device performance
| Acceptance Criteria (Predicate Device) | Reported Device Performance (Subject Device) |
|---|---|
| Max overall output level - 87 dB SPL | Same (Acoustic measurements of output levels, utilizing previously defined limits, were used during verification to ensure that the maximum allowable stimulus level for the subject device was the same as the predicate device. All results passed.) |
| Max A-weighted overall output - 87 dB SPL | Same (Acoustic measurements of output levels... All results passed.) |
| Max 1/3 octave output level – 87 dB SPL | Same (Acoustic measurements of output levels... All results passed.) |
| Maximum output in a 2cc coupler limited to 87 dB SPL | Same (Acoustic measurements of output levels... All results passed.) |
| Tinnitus output levels are set to specified limits by the hearing-care professional. Patient volume/level controls can be enabled to provide adjustments that can decrease or increase output levels within set limits. | Same |
| Power Source: May use any 1.4V hearing-aid battery (size 13, 312 or 10) or be rechargeable. | Same |
| Risk analysis and verification testing to ensure safety and effectiveness. | Risk analyses and verification testing were performed for the addition of the audiogram-shaping functionality. Results demonstrated that Tinnitus Multiflex meets the device testing acceptance criteria described in the predicate submission (K122876) and is substantially equivalent. |
| Addition of audiogram-shaping functionality does not impact safety and effectiveness. | The addition of the audiogram-shaping functionality was assessed by appropriate risk management methodology and addressed with verification and validation testing. The results of the verification and validation testing support that the addition of the audiogram-shaping functionality does not impact safety and effectiveness. |
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. No clinical test set data was reported. The device is a "firmware program code (algorithm)" embedded in a hearing aid, and the testing described is non-clinical (risk analysis, verification, and validation testing for the audiogram-shaping functionality).
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. No clinical expert review for ground truth was reported.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
Not applicable. No clinical adjudication method was reported.
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. No MRMC study was reported. The device is a "Tinnitus Masker" technology, not an AI assistance tool for human readers.
6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done
Not applicable in the context of typical AI/ML algorithm-only performance studies. The Multiflex Tinnitus Technology is described as an algorithm embedded in a hearing aid, but its "performance" is primarily related to its ability to generate specific sound characteristics and adjust based on audiograms, rather than an AI-driven diagnostic or interpretative function. The evaluation focuses on meeting predefined acoustic output limits and maintaining safety and effectiveness.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
Not applicable. For the non-clinical testing performed, the "ground truth" consisted of predetermined acoustic specifications and safety/effectiveness criteria for the device's functionality.
8. The sample size for the training set
Not applicable. This document is a 510(k) submission for a non-AI/ML device (firmware for a tinnitus masker) and does not describe a machine learning training process or training set.
9. How the ground truth for the training set was established
Not applicable, as there was no reported machine learning training set.
§ 874.3400 Tinnitus masker.
(a)
Identification. A tinnitus masker is an electronic device intended to generate noise of sufficient intensity and bandwidth to mask ringing in the ears or internal head noises. Because the device is able to mask internal noises, it is also used as an aid in hearing external noises and speech.(b)
Classification. Class II. The special control for this device is patient labeling regarding:(1) Hearing health care professional diagnosis, fitting of the device, and followup care,
(2) Risks,
(3) Benefits,
(4) Warnings for safe use, and
(5) Specifications.