(114 days)
The device, Sound Options Timitus Treatment, version SO 2.0, is for the temporary relief of tinnitus symptoms. The device is a software application that embeds sounds and spectral content into music to relieve patients suffering from timitus and can be used as part of a timitus management program for adults 18 years and older. The device is for prescription use by a physician, audiologist or other healthcare professional.
The device is a software application that embeds sounds and spectral content into music to relieve patients suffering from tinnitus and can be used as part of a tinnitus management program.
The Sound Options device software version is 2.0. The device comprises of tinnitus pitch match and audiogram submission software for health care professionals (Web Software) and Sound Options software application for sound therapy generation (manufacturer use only)
Acceptance Criteria and Study for Sound Options Tinnitus Treatment
This document describes the acceptance criteria and the study performed for the Sound Options Tinnitus Treatment device, version SO 2.0.
1. Table of Acceptance Criteria and Reported Device Performance
The provided document does not explicitly state quantitative acceptance criteria in a table format. However, the study aims to demonstrate clinical effectiveness, which implies that the acceptance criteria are met if the device shows a statistically significant and clinically meaningful improvement in tinnitus symptoms compared to a placebo.
Based on the study results, the reported device performance can be summarized as:
| Performance Metric | Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|---|
| THI Total Score | Statistically significant and clinically meaningful reduction from baseline | Significantly lower at 3, 6, and 12-month follow-ups compared to baseline in the treatment group. |
| TFI Total Score | Statistically significant and clinically meaningful reduction from baseline | Significantly lower at 3, 6, and 12-month follow-ups compared to baseline in the treatment group. |
| Anxiety Symptoms (HADS) | Reduction from baseline | Reduced from baseline to follow-ups, with a significant change occurring at 6 months. |
| Depression Symptoms (HADS) | Reduction from baseline | No significant change. |
| Adverse Effects | No serious adverse effects | No adverse effects reported. |
Implicit Acceptance Criteria: The device's performance must demonstrate a positive and statistically significant impact on tinnitus symptoms, as measured by validated questionnaires (THI, TFI), and be safe for use without adverse effects. The significant reduction in THI and TFI scores in the treatment group, compared to no significant changes in the placebo group, indicates that these implied criteria were met.
2. Sample Size Used for the Test Set and Data Provenance
- Test Set Sample Size:
- Baseline: 45 eligible participants were randomized (22 to treatment, 23 to placebo).
- Follow-up (3, 6, 12 months): 15 participants in the treatment group and 19 participants in the placebo group were assessed.
- Data Provenance: Canada (indicated as "Location of Study"). The study was conducted as a prospective, randomized, multi-arm, "blinded" study with concurrent sham (placebo) control.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications
The document does not specify the number of experts or their qualifications used to establish the ground truth for the test set. The primary effectiveness endpoints (THI, TFI, HADS) are self-reported measures filled out by the study participants themselves, rather than evaluations by experts to establish ground truth for each case. The reliability and validity of these measures are cited from scientific literature.
4. Adjudication Method for the Test Set
No adjudication method is described for the test set. Given that the endpoints are self-reported questionnaires, an adjudication process by experts would not typically be applicable in the same way it would be for image interpretation or diagnosis.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No Multi-Reader Multi-Case (MRMC) comparative effectiveness study was done. The study compares the device's effectiveness against a placebo, focusing on patient-reported outcomes rather than human reader performance with or without AI assistance.
6. Standalone Performance Study
Yes, a standalone study of the algorithm's effect was performed. The clinical study evaluated the direct impact of the "Sound Options customized music" (the device's output) on tinnitus symptoms in a controlled setting, effectively studying the algorithm's output without human intervention in the application of the therapy once customized music files are generated. Once the music is generated, patients listen to it on their personal music-playing devices.
7. Type of Ground Truth Used
The ground truth used for evaluating the device's effectiveness was based on patient-reported outcomes data derived from validated clinical questionnaires:
- Tinnitus Handicap Inventory (THI): A 25-item self-report measure for overall tinnitus distress.
- Tinnitus Functional Index (TFI): A 25-item self-reported clinical measure for chronic tinnitus, measuring overall severity and negative impact across eight domains.
- Hospital Anxiety and Depression Scale (HADS): A 14-item self-report measure to assess anxiety and depression levels.
8. Sample Size for the Training Set
The document does not provide information about a "training set" in the context of an AI/machine learning model. The device description states that the software "modifies frequency-specific amplitudes within music tracks to a customized music based sound therapy for tinnitus patients" based on patient audiogram and tinnitus frequency/pitch match provided by healthcare professionals. This suggests a rule-based or algorithmic approach for customization rather than a machine learning model that would require a separate training set.
9. How the Ground Truth for the Training Set Was Established
As there is no mention of a traditional machine learning "training set" or AI model that learns from data, the concept of establishing ground truth for a training set is not applicable here. The device's operation is based on established audiological principles and patient-specific data (audiogram, tinnitus type, pitch match) to generate customized sound therapy.
§ 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.