Search Results

The CLEAR440 - PASSION (or C4-PA) hearing aid is a digital wireless air conduction hearing aid that amplifies sounds for individuals with a hearing impairment. The device is indicated for individuals with a full range of hearing loss severity (from slight (16 to 25 dB HL) to profound (90+ dB HL)) and all hearing loss configurations. The device is to be programmed by hearing healthcare professionals (audiologists, hearing aid specialists, otolaryngologists) who are trained in hearing (re)habilitation.

The C4-PA is a digital air-conduction hearing aid that uses WidexLink, a wireless radio technology to enable communication between a pair of hearing aids and/or between the hearing aid(s) and certain device system accessories. Accessories for WidexLink include the optional remote control (RC-DEX) and the Widex-specific programming module (TM-DEX).

Acceptance Criteria and Device Performance

The device, the C4-PA Wireless Air-Conduction Hearing Aid, meets the acceptance criteria for EMC and Wireless Safety, Software, Biocompatibility, and Clinical Performance of its Inter-ear Compression feature. The clinical study for Inter-ear Compression demonstrates that it does not negatively impact speech perception in noise, and for users with symmetrical hearing loss, it shows a significant improvement in noise tolerance. The manufacturer is not making any claims of improved speech intelligibility based on this preliminary data.

Study Details

1. Sample Size used for the test set and the data provenance:

   • Test Set (Clinical Study for Inter-ear Compression): 12 adult participants.
     • 6 participants with asymmetrical hearing loss.
     • 6 participants with symmetrical hearing loss.
   • Data Provenance: The data appears to be prospective as it was collected specifically for this study due to FDA's request for clinical performance data. The country of origin is not explicitly stated, but the study was conducted by the petitioner (Widex).

2. 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):

   • For the clinical study, the "ground truth" was established by the participants themselves reporting their ability to understand speech in noise, measured using Acceptable Noise Level (ANL). This is a subjective measure based on the listener's perception. There were no external experts used to establish "ground truth" in the sense of an objective diagnosis or label. The study design involved objective measurements of speech and noise levels and subjective participant responses.

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

   • None. The ANL procedure relies on direct participant feedback (adaptive 1-up 1-down method with a 2-dB step) and the final BNL calculated as the average of the last four reversals. It does not involve multiple expert adjudicators for subjective interpretation.

4. 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. This evaluation is for a hearing aid, not an AI diagnostic tool involving "human readers" or "AI assistance" in a diagnostic context. The clinical study evaluates the device's inherent performance with and without a specific feature (Inter-ear compression).
   • Effect Size: For the symmetrical hearing loss group, a 3dB improvement in SNR was observed for the "IE on" condition compared to "IE off". This represents the effect size of the Inter-ear Compression feature for this subgroup. For the asymmetrical group, no significant effect was observed.

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

   • The primary clinical test, as described, is a human-in-the-loop performance study. Participants wearing the hearing aids engaged in speech perception tasks and provided subjective feedback. The device's acoustic processing (including the Inter-ear compression algorithm) is integral to this human-in-the-loop performance. There is no "standalone" algorithm-only performance assessment described in the context of human hearing perception.

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

   • The "ground truth" in the clinical study was based on subjective patient reports of speech understanding in noise, quantified by the Acceptable Noise Level (ANL). This is an established audiological measure of noise tolerance.

7. The sample size for the training set:

   • Not applicable for the clinical study context described. The clinical study was a performance evaluation of the device as a product, not a machine learning model requiring a training set. The device itself (C4-PA hearing aid) likely underwent extensive internal development and testing (implicitly through software development, hardware design, and simulations), but no explicit "training set" for a machine learning algorithm used in diagnosis or prediction is mentioned.

8. How the ground truth for the training set was established:

   • Not applicable, as there was no explicit "training set" for a machine learning algorithm as part of this device's evaluation.

Ask a specific question about this device