(83 days)
The Tinnitus Sound Generator Module is a tool to generate sounds to be used in a Tinnitus Management Program to temporarily relieve patients suffering from Tinnitus. The target population is primarily the adult population over 18 years of age. This product may also be used with children 5 years of age or older.
The Tinnitus Sound Generator Module is targeted for healthcare professionals, which are treating patients suffering from Tinnitus, as well as conventional hearing disorders. The Tinnitus Sound Generator Module must be done during an in-office visit by a hearing professional participating in a Tinnitus Management Program. If deemed feasible by the hearing professional, subsequent fittings of the Tinnitus Sound Generator Module may be performed remotely and in real time while having live communication via live audio, video and chat on the user's dedicated app.
The Tinnitus Sound Generator (TSG) Module is software that provides a means for healthcare professionals to create a hearing instrument solution that provides temporary relief for Tinnitus patients. This software solution is embedded into a digital hearing instrument platform, so that the end-user (EU) can wear this device in all environments. The fitting of the digital device, which contains the TSG Module, is performed by a healthcare professional, in order to meet the exact needs of the Tinnitus patient.
A mobile medical application (app) is available as an optional device to use with the TSG. The mobile medical app allows the user to adjust the hearing aid within the limits set by the healthcare professional during fitting of the hearing aid. The app is known as the TSG Tinnitus Manager app and is part of the Smart3D app. The Smart3D app also enables a Health Care Professional (HCP) to remotely adjust the TSG settings using a Remote Fine Tuning Feature (RFT). The Support for the RFT feature for the TSG Module can be enabled by the doctor, audiologist or other hearing healthcare professional, at the time of first fitting. Afterwards, the doctor, audiologist or other hearing healthcare professional is able to remotely make adjustments to TSG Module settings. RFT is only enabled when the doctor, audiologist or other hearing healthcare professional finds it feasible, based on an initial in-office assessment of the user and communication with the user, and the parent or legal guardian in cases where the user is a minor. Subsequent to the in-office assessment, the user, or the parent or legal guardian in cases where the user is a minor, is required to accept to receive the adjustments via the TSG portion of the Smart3D app, called the Tinnitus Manager.
Compared to the Remote Fine Tuning, available in the predicate device, the subject TSG Module additionally supports Remote Fitting, being used for real time, online adjustments, with live communication with the end user. Support for Remote Fitting is a process where the end user (EU) has a scheduled appointment with the hearing Health Care Professional (HCP) while the EU is at a remote location, like at home. HCP and EU meet via an HCP initiated live audio, live video and chat on the user's Smart3D app, and adjustments can be made to the Hearing Aids per agreement and prescription of the HCP. During this process, the HCP can make multiple adjustments in real time to the Hearing Aids, including TSG, while having live communication with the EU as if they were in the same room. The session is similar to an adjustment session done at the HCP office, but with the EU at a remote location. When the final settings are decided, a fitting data package is generated by the HCP, and the Hearing Aids are updated remotely while having the live session with the EU. Subsequent to the in-office assessment, the user, or the parent or legal guardian in cases where the user is a minor, is required to accept the adjustments. The Remote Fitting is only made available and technically working for follow-up sessions when found feasible by the HCP, and not available for the initial first-time fitting of the Hearing Aids, that has to take place at the HCP office.
The provided text describes a 510(k) premarket notification for a Tinnitus Sound Generator Module. However, it does not include information about acceptance criteria or a study that proves the device meets those criteria in the context of typical AI/ML medical device submissions.
The document states that the Tinnitus Sound Generator Module is software embedded into a digital hearing instrument. The 510(k) is specifically for a Special 510(k), indicating a modification to an already cleared device (the predicate device K180495).
The primary focus of this 510(k) is the addition of "Support for Remote Fitting" to the existing TSG Module. The document explicitly states:
- "The TSG software is unchanged, but now claims support for the added Remote Fitting feature." (Page 6)
- "The acceptance criteria were not altered, and no additional types of evaluation was needed." (Page 6)
Therefore, the study design elements you've requested (e.g., sample size for test/training sets, expert ground truth establishment, MRMC studies, standalone performance) are typically associated with performance studies for novel devices or significant algorithmic changes in AI/ML products. This submission is for a feature addition to existing software that, according to the manufacturer, uses "already implemented services" and does not change the "basic operating principle of the TSG module" or raise "new or different questions of safety or effectiveness."
Instead of a clinical performance study with acceptance criteria around diagnostic accuracy or efficacy, the document describes verification and validation activities focused on the software and system functionality related to the new remote fitting feature.
Here's a breakdown of what is reported, in the context of your questions, and what is not:
1. A table of acceptance criteria and the reported device performance
- Acceptance Criteria: The document states: "The acceptance criteria were not altered, and no additional types of evaluation was needed." This implies that the original acceptance criteria for the TSG Module itself still apply, but these are not detailed in the document. For the new remote fitting feature, the acceptance criteria appear to be an implicit set of functional and usability requirements focused on the safe and effective operation of the remote fitting process.
- Reported Device Performance:
- "The result of the system verification show that tests has passed with no defects critical for function, form, intended use, or pose any user risks." (Page 7)
- "The successful validation activities related to the Support for Remote Fitting feature were conducted to show that human factors and usability are safe and effective as the predicate device." (Page 7)
2. Sample size used for the test set and the data provenance
- Test Set Sample Size: Does not apply in the context of a typical clinical performance study for an AI/ML diagnostic. The "testing" described is system verification and validation. There's no mention of a "test set" of patient data in the sense of clinical images or physiological signals.
- Data Provenance: Not applicable. The "software design model" and "verification and validation method" used are "well-established" and the "same as used in the previously cleared 510(k)." (Page 6)
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
- Not applicable. There is no "ground truth" establishment described in the sense of expert annotation of patient data, as this is a software update for a sound generator, not a diagnostic AI.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Not applicable. No expert adjudication process 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
- No. An MRMC study was not done. The device is a "Tinnitus Sound Generator Module" creating sounds for temporary relief, not a diagnostic aid that would assist human readers in interpreting medical images or data. The human interaction described is with healthcare professionals for fitting adjustments, not "readers" of medical cases.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- No. This is software within a hearing aid system, designed to be used by healthcare professionals and patients. Standalone performance as an algorithm without human interaction or device integration is not relevant for this type of device.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
- Not applicable. The ground truth for a Tinnitus Sound Generator is its ability to generate specific sounds and for the new feature, to allow remote fitting of those sounds safely and effectively. This is assessed through system functional tests, rather than clinical ground truth from patient data.
8. The sample size for the training set
- Not applicable. This is not a machine learning device that requires a "training set" of data in the typical sense. It is software that generates sounds and facilitates remote adjustments.
9. How the ground truth for the training set was established
- Not applicable.
Summary of Device Performance and Evidence Provided:
The evidence provided for this 510(k) consists primarily of engineering verification and validation efforts designed to demonstrate that the new remote fitting feature works as intended and does not negatively impact the safety and effectiveness of the existing Tinnitus Sound Generator Module.
- Risk Analysis: Performed to demonstrate that all risks are mitigated to an acceptable level.
- Verification & Validation: "Necessary verification and validation activities" performed to show that "design outputs... meet the design input requirements" for the remote fitting feature.
- System Verification: Included "end-to-end testing and interoperability performance testing" of the integrated system (Hearing Instrument hardware, TSG Module, App, Fitting Software).
- Validation for Remote Fitting: Focused on "human factors and usability" to show they are "safe and effective as the predicate device."
In essence, for this specific 510(k) submission, the "study" proving the device met "acceptance criteria" was a comprehensive software and system verification and validation process demonstrating that the updated software behaves functionally as expected and does not introduce new safety concerns for the remote fitting functionality, relying on the already cleared predicate for the core TSG module's performance.
§ 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.