Search Results

The Hearing Aid Feature is a software-only mobile medical application that is intended to be used with compatible wearable electronic products. The feature is intended to amplify sound for individuals 18 years of age or older with perceived mild to moderate hearing impairment. The Hearing Aid Feature utilizes a self-fitting strategy and is adjusted by the user to meet their hearing needs without the assistance of a hearing healthcare professional. The device is intended for Over-the-Counter use.

The Hearing Aid Feature (HAF) is a software-only device that is comprised of a pair of software modules which operate on two separate required products: (1) HAF iOS Application on a compatible iOS product, and (2) HAF software (i.e., firmware) on the Apple AirPods Pro 2. Refer to Figure I, middle and right, respectively, The AirPods Pro 2, formerly named AirPods Pro (2nd generation), supported this granting and are hereafter simply referred to as "AirPods Pro" in this document.

The HAF iOS Application guides users through the onboarding and setup process for the HAF. The process is self-guided by the user and includes step-by-step instructions and informational content (e.g. warnings, instructions for use). To initiate HAF setup, the user must select a saved audiogram from the iOS HealthKit.

Once the audiogram has been imported by the HAF, the feature will configure the amplification for the user's audiogram based upon Apple's proprietary fitting formula. Once the initial set-up is complete, users can listen with the HAF using the AirPods Pro and refine their settings. Fine tuning is facilitated by user controls on the iOS device that can adjust amplification, tone, and balance. A user can access the fine tuning settings at any time after setting up the HAF.

The HAF settings are transferred to the HAF Firmware Module on the AirPods Pro. The HAF Firmware Module utilizes the general purpose computing platform features of the AirPods Pro, including the microphone, speakers, amplifiers, and audio processing software, to process incoming sound and provide amplification at a specific frequency and gain based on the user's custom settings. The user's custom settings are stored on the HAF Firmware Module and will be available even when the AirPods Pro are not connected to the iOS device.

Acceptance Criteria and Device Performance for Apple's Hearing Aid Feature (HAF)

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Sizes Used for the Test Set and Data Provenance

Bench/Non-Clinical Tests:

• Performance Testing (21 CFR 800.30(d) & (e)): No specific sample size (n) is provided, but the tests refer to "all test frequencies" and compliance with ANSI/ASA S3.22 or ANSI/CTA 2051:2017 clauses. This implies comprehensive testing across the specified parameters, rather than a limited sample.
• Human Factors Formative Testing: 39 subjects.
• Audiogram Input Risk and Mitigation Study: No specific sample size (n) for the study itself, but refers to the Hearing Test Feature (HTF) validation study dataset.

Clinical Study:

• Overall Clinical Study (HAF Self-Fit vs. Professionally-Fit): 118 total participants (59 in Self-Fit group, 59 in Professionally-Fit group for FAS/CCAS; 59 in Self-Fit, 58 in Professionally-Fit for PP analysis).
• Data Provenance: Prospective, non-significant risk study from three sites across the United States.

Supplemental Clinical Data (Apple Hearing Test Feature Validation):

• Comparison of HTF outputs to professionally derived audiograms: n = 202.
• Gain analysis for HAF with HTF vs. professionally-derived audiograms: n = 173 (subset with mild to moderate hearing loss from the n=202 dataset).

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications

Bench/Non-Clinical Tests:

• Performance Testing: Ground truth is established by well-defined regulatory standards (21 CFR 800.30) and industry standards (ANSI/ASA S3.22, ANSI/CTA 2051:2017). Expertise is inherent in the test methodologies themselves.
• Human Factors Formative Testing: No explicitly stated "experts" establishing ground truth in the context of diagnostic accuracy. The testing assessed use-related risks, and findings led to software design modifications.
• Audiogram Input Risk and Mitigation Study: No explicitly stated "experts" for ground truth on this specific study, but the study for the Hearing Test Feature Validation (see below) involved professional audiograms which would have been established by qualified audiologists.

Clinical Study (HAF Self-Fit vs. Professionally-Fit):

• Ground Truth for Professional-Fit (PF) Group: The "Professionally-Fit" group had their hearing aids fitted by an audiologist and underwent an optional audiologist fine-tuning session. This implies a number of audiologists (not specified but plural) provided this professional fit, thus establishing a "ground truth" reference for professional care. The study design intrinsically compares the self-fit approach to professional audiologist care, using the latter as the benchmark for a successful fit in terms of patient-perceived benefit.

Supplemental Clinical Data (Apple Hearing Test Feature Validation):

• Comparison to Professionally Derived Audiograms: These would have been established by qualified hearing healthcare professionals, such as audiologists. The exact number of such professionals establishing these audiograms for the 202 subjects is not specified but the term "professionally derived" implies expertise.

4. Adjudication Method for the Test Set

Bench/Non-Clinical Tests:

• Performance Testing: Not applicable; compliance is determined by direct measurement against pre-defined numerical thresholds in regulatory and industry standards.
• Human Factors Formative Testing: Not applicable; the output is identification of use-related risks and subsequent design modifications.
• Audiogram Input Risk and Mitigation Study: Not applicable.

Clinical Study (HAF Self-Fit vs. Professionally-Fit):

• Primary Endpoint (IOI-HA score): Not applicable in the sense of expert adjudication of a diagnostic finding. The primary outcome was a patient-reported outcome measure (IOI-HA score), a subjective assessment collected directly from participants. The comparison was statistical (non-inferiority margin) between the two groups.
• Objective Measures (QuickSIN, REM): These are objective measurements and do not require adjudication.

Supplemental Clinical Data (Apple Hearing Test Feature Validation):

• Audiogram Comparison & Gain Analysis: Not applicable. The comparison was quantitative (pure-tone average, gain differences) between HTF-derived and professionally-derived audiograms.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• No, a traditional MRMC comparative effectiveness study, as typically seen in diagnostic imaging where multiple readers interpret cases with and without AI assistance, was not performed for the core Hearing Aid Feature.
• Instead, a clinical study compared two groups:
  • Self-Fit (SF): Users applying the HAF's self-fitting algorithm.
  • Professionally-Fit (PF): Users whose devices were fitted by an audiologist using the NAL-NL2 formula.
• This study evaluated the effectiveness of the HAF's self-fitting approach directly against professional care by assessing patient-reported outcomes (IOI-HA) and objective measures (QuickSIN, REM).
• Effect Size of Human Readers Improve with AI vs without AI assistance: This metric is not applicable as the study design was a comparison of a self-fitting AI system against professional human fitting, not a study of human readers improving with AI assistance. The study concluded that the HAF Self-Fit group achieved non-inferior perceived benefit (IOI-HA scores) compared to the Professionally-Fit group, indicating equivalent patient outcomes without the direct involvement of a hearing healthcare professional in the fitting process.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study

• Yes, a standalone study was inherently performed to assess the performance of the HAF's self-fitting algorithm.
• The "Self-Fit (SF)" group in the clinical study directly represents the standalone performance of the algorithm. These users utilized the HAF's automatic fitting algorithm and then could adjust amplification, tone, and balance themselves. The device's performance, as measured by IOI-HA scores, QuickSIN, and REM, was attributed to this self-fitting strategy.
• The comparison to the "Professionally-Fit (PF)" group served as a benchmark for what a human expert (audiologist) would achieve.
• Therefore, the clinical study's SF arm is a direct measure of the algorithm's standalone performance in a real-world setting.

7. Type of Ground Truth Used

Bench/Non-Clinical Tests:

• Regulatory and Industry Standards: Ground truth is defined by explicit numerical thresholds and methodologies prescribed by 21 CFR 800.30 and ANSI/ASA/CTA standards.
• Human Factors: "Ground truth" is the identification of potential use errors and associated risks, which is derived from observing user interactions and conducting risk analysis.

Clinical Study (HAF Self-Fit vs. Professionally-Fit):

• Expert Consensus / Professional Practice: The "Professionally-Fit" group, whose devices were fitted by audiologists using a standard clinical fitting formula (NAL-NL2), served as the gold standard or ground truth for best clinical practice in hearing aid fitting. The HAF's performance was evaluated against this professional benchmark.
• Patient-Reported Outcomes (IOI-HA): The primary ground truth for effectiveness was the subjective perception of benefit, satisfaction, and quality of life as reported by the patients themselves via the IOI-HA questionnaire.
• Objective Outcomes Data (QuickSIN, REM): These objective functional measures also served as ground truth regarding speech intelligibility and actual gain.

Supplemental Clinical Data (Apple Hearing Test Feature Validation):

• Expert Consensus / Professional Practice: The comparison was made against "professionally derived audiograms," implying that these audiograms, established by trained hearing healthcare professionals, served as the ground truth.

8. Sample Size for the Training Set

The document does not explicitly state the sample size for the training set used to develop Apple's proprietary fitting formula within the HAF. The description only refers to the clinical study as establishing safety and effectiveness, and the HAF's fitting formula is described as "Apple's proprietary fitting formula." This formula would have been developed using a separate dataset prior to the validation study.

9. How the Ground Truth for the Training Set Was Established

Since the training set size and characteristics are not provided, the method for establishing its ground truth is also not explicitly stated in this document.

However, based on the nature of hearing aid fitting algorithms and the validation study design, it is highly probable that the proprietary fitting formula was developed and refined using:

• Large datasets of audiogram data: Likely anonymized audiograms from various sources, potentially including those collected by Apple's own Hearing Test Feature over time or from research collaborations.
• Patient-reported outcomes data: To correlate objective audiometric data with subjective patient benefit and preference.
• Expert knowledge/models: Incorporating established audiological principles, validated fitting targets (e.g., NAL-NL2, DSL v5), and clinical experience synthesized into an algorithmic form.
• Iterative development and testing: The "proprietary fitting formula" would have undergone extensive internal testing, likely including simulations and pilot studies with real users, where the "ground truth" would be established by comparing algorithm outputs to professional recommendations or patient preferences.

Ask a specific question about this device

The Vibe SF seff-fitting hearing aid is intended to amplify sound for individuals 18 years of age or older with perceived mild to moderate hearing impairment. It is adjusted by the user's hearing needs through software tools. The device is intended for direct-to-consumer sale and use without the assistance of a hearing care professional.

The EasyFit self-fitting web application is intended to support self-fitting and fine-tuning of the Vibe SF hearing aid.

The Vibe SF Self-Fitting Hearing Aid ("Vibe SF") is a self-fitting air conduction hearing aid that is intended to compensate for impaired hearing and incorporates technology, including software, that allows users to program their hearing aids. This technology integrates user input with a self-fitting strategy and enables users to independently derive and customize their hearing aid fitting and settings.

The Vibe SF hearing aid is based on WSAUD's wireless hearing aid series Signia Silk 1X (regulated under 21 C.F.R. § 874.3305). However, unlike standard wireless air-conduction hearing aids, the Vibe SF is intended to be sold directly to the end-user without involvement of a hearing care professional. Briefly, the self-fitting hearing aid system consists of two components:

• a) A wireless hearing aid with a self-fitting feature (Vibe SF); and
• b) A mobile web application (EasyFit) to support the self-fitting and fine-tuning of the hearing aid.

The Vibe SF wireless hearing aid hardware includes: Ear pieces (click sleeves), housing, circuit board, battery, chip, and electroacoustic components. The subject device is fitted for bilateral use with a left and right device. Left and right hearing aids are able to communicate with each other over a magnetic inductive wireless link. The instant fit in-the-ear (ITE) style of the Vibe SF hearing aid uses Click Sleeves in 4 different sizes to couple with the ear canal. The hearing aids are marked with 'R' for right and 'L' for left, and are powered by standard (non-rechargeable) Zinc-Air batteries (size 10A). The Vibe SF hearing aid includes software that communicates with the EasyFit app to provide self-fitting functionality.

The Vibe SF is fitted by the user through the EasyFit self-fitting web application, which is run on an Internet browser on the user's mobile device (smartphone or tablet with iOS or Android operating system). The EasyFit self-fitting web application guides the user through the selffitting procedure and also allows the user to set audiological gain parameters and preferred settings on the Vibe SF Hearing Aid. In addition, a software application (app for iOS and Android) called Vibe app is available as remote control for adjusting volume during daily use.

Here's a breakdown of the acceptance criteria and study details for the Vibe SF Self-Fitting Hearing Aid, based on the provided text:

Acceptance Criteria and Reported Device Performance

The primary objective of the clinical study was to demonstrate non-inferiority of the Vibe SF self-fitting strategy compared to an audiologist-fit (HCP fit) strategy regarding perceived hearing aid benefit. This was measured using the Abbreviated Profile of Hearing Aid Benefit (APHAB) subscales for ease of communication (EC), background noise (BN), and reverberant room (RV).

The acceptance criterion for effectiveness was simultaneous non-inferiority on all three APHAB subscales.

Ask a specific question about this device

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 by a hearing professional participating in a Tinnitus Management Program.

The Tinnitus Sound Generator (TSG) Module 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 subject TSG Module has a new feature. i.e., Remote Fine-tuning (RFT) communication software (PC Interface software) that communicates with a healthcare professional's Fitting Software (FSW) via the user's Smart3D app and is part of the general software on the digital signal processor in GN's legally marketed, class II, 510(k) exempt Hearing Aids (Reference Device). The RFT communication software in the Reference device enables the healthcare professional to remotely adjust the Hearing Aid settings for these legally marketed, class II, 510(k) exempt Hearing Aids, including Hearing Aids that are compatible with the predicate TSG Module and the new TSG Module. Similarly, the new TSG Module has a PC Interface Software modification that supports fine tuning of TSG Module settings from a remote location. The new TSG Module's PC Interface Software modification opens a bridge between the general RFT function on the Hearing Aid's digital signal processor and the TSG feature settings, that are also available for adjustments via the user's Smart3D app. Therefore, the RFT communication software part of the general software on the Hearing Aids containing the new TSG Module is also part of new TSG Module device. The Health Care Professional (HCP) can make all of the same changes (Volume/loudness, Pitch/frequency. Nature sounds, and Amplitude modulation) that the user can make. Additionally, the HCP can turn the TSG/tinnitus masker on or off and can set and adjust the Volume Control range and environmental steering sounds. The TSG Volume Control range feature is available only to the HCP. This feature allows the HCP to set a limit on the TSG volume range an EU can adjust. This feature is specifically designed for the safety of the EU, ensuring that an EU cannot increase the TSG volume above a level determined appropriate by the HCP. The system can in no case exceed 100dB SPL for TSG. The TSG Volume Control range has a range of +12dB to -6dB from the TSG fitting by the HCP and can be found in the FSW under the Fitting / Manual Controls / Volume Control Range. For example, if the HCP sets the TSG Volume Control range to +6dB to -6dB, this means an EU cannot set the TSG volume more than 6dB above or below the initial fitting.

The provided text is a 510(k) summary for the Tinnitus Sound Generator Module (K180495). It details the device, its intended use, comparison with a predicate device, and performance data. However, it does not include specific quantitative acceptance criteria or a detailed study proving the device directly meets those criteria with statistical data.

Instead, the document focuses on demonstrating substantial equivalence to an existing predicate device (Tinnitus Sound Generator Module, K181586) and a reference device (LiNX3D hearing aid) by showing that the minor modifications do not raise new questions of safety or effectiveness.

Therefore, the following information is extracted and where specific details are not present, it is noted.

1. A table of acceptance criteria and the reported device performance

The document does not explicitly present quantitative acceptance criteria or performance metrics for the Tinnitus Sound Generator Module itself (e.g., how effectively it reduces tinnitus symptoms in a specific percentage of patients). Instead, it relies on demonstrating that its design, performance, and technological characteristics are safe and effective, and do not differ significantly from a legally marketed predicate device.

The performance data described focuses on verification and validation of the system and its RFT feature, rather than direct clinical efficacy trials with acceptance criteria.

2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

The document does not specify a separate "test set" with a given sample size in the context of clinical data or patient studies. The performance data refers to verification and validation activities of the device's design and software, and electromagnetic compatibility (EMC) testing. These are primarily engineering and technical tests.

• Sample Size: Not applicable in a clinical sense. The hardware and software components of the system (Hearing Instruments, App, Fitting Software) were tested.
• Data Provenance: The EMC testing was performed by DEKRA Testing and Certification, S.A.U. in Spain. The nature of the other verification and validation activities (e.g., system end-to-end testing) suggests they were conducted internally by GN Hearing. The document does not specify if any user data was collected for these tests, nor its country of origin or whether it was retrospective or prospective.

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)

This is not applicable as the document describes technical verification and validation, and EMC testing, rather than a study requiring expert consensus for a ground truth derived from clinical data. The "ground truth" for these tests would be compliance with engineering standards and design requirements, as determined by qualified engineers and testers.

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

This is not applicable. The verification and validation activities described are technical and engineering-focused, not clinical studies requiring adjudication of results based on expert review.

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

This is not applicable. The Tinnitus Sound Generator Module is a therapeutic device that generates sounds for tinnitus relief, not an diagnostic AI tool for human readers. No MRMC study was mentioned.

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

The device is a "Tinnitus Sound Generator Module" embedded within a digital hearing instrument platform. It is designed to be used in conjunction with a "Tinnitus Management Program" and involves a healthcare professional for fitting and potentially remote fine-tuning.

While the module generates sounds (an algorithmic function), it is not described as a "standalone algorithm" in the typical sense of AI performing an independent diagnostic or predictive task. It functions as part of a system with human intervention (HCP fitting, patient use, remote adjustments).

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

For the technical performance data, the "ground truth" refers to compliance with established engineering and safety standards (e.g., IEC standards for EMC) and the device's design input requirements. There is no mention of clinical outcomes data, pathology, or expert consensus being used as ground truth for a clinical study within this 510(k) summary. The summary focuses on demonstrating substantial equivalence through technical comparisons and verification activities.

8. The sample size for the training set

This is not applicable. The document describes a medical device, not a machine learning or AI model that typically requires a "training set" of data.

9. How the ground truth for the training set was established

This is not applicable, as there is no mention of a training set for a machine learning or AI algorithm.

Ask a specific question about this device

Tinnitus SoundSupport is a tool intended to generate sounds to provide temporary relief to patients suffering from tinnitus as part of a tinnitus management program.

The target population is the adult population (>18yrs).

Tinnitus SoundSupport is targeted for licensed hearing care professionals (audiologists, hearing aid specialists, or otolaryngologists) who are familiar with the evaluation and treatment of tinnitus and hearing losses. The fitting of Tinnitus SoundSupport must be done by a hearing care professional participating in a tinnitus management program.

Oticon's Tinnitus SoundSupport consists of a software module added to the company's class II, 510(k)-exempt wireless air conduction hearing instruments legally marketed under 21 C.F.R. 874.3305. Tinnitus SoundSupport is fitted to the patient by the Hearing Care Professional using Oticon fitting software.

Tinnitus SoundSupport provides the option of relief sounds based on white, pink or red noise. The relief sounds can be limited in frequency by high pass or low pass filters. Tinnitus SoundSupport also provides the option of amplitude modulation, a volume control and automatic level steering.

The design of Tinnitus SoundSupport is based on the controls of the Occupational Safety and Health Administration (OSHA). Compliance with OSHA controls is achieved through (1) output limitation and (2) professional labeling and (3) patient labeling.

Tinnitus SoundSupport must be used as part of a tinnitus management program.

The provided text describes the Tinnitus SoundSupport device and its substantial equivalence to predicate devices, rather than a study with specific acceptance criteria and detailed performance data. The device's performance is primarily assessed through compliance with relevant standards and comparison to existing legally marketed devices.

Here's an analysis of the requested information based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state "acceptance criteria" in a quantitative, measurable sense for clinical performance. Instead, performance is evaluated through compliance with various standards and by demonstrating substantial equivalence to predicate devices. The "reported device performance" is largely qualitative, indicating that the device "functioned as intended and the performance observed was as expected" in relation to these standards.

2. Sample Size Used for the Test Set and Data Provenance

The document does not describe a clinical performance study with a "test set" in the sense of patient data. The performance evaluations mentioned are related to software verification and validation, as well as electrical, EMC, and biocompatibility standards for the device's components. There is no mention of a sample size of patient data, nor its provenance (country of origin, retrospective/prospective).

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications

Since there is no "test set" of patient data with a ground truth established by experts, this information is not applicable and not provided in the document.

4. Adjudication Method for the Test Set

As there is no clinical "test set" of patient data, an adjudication method is not described.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

The document does not mention a MRMC comparative effectiveness study, nor does it discuss human reader improvement with or without AI assistance. The device is a "Tinnitus Masker" and a software module integrated into hearing aids, not an AI-assisted diagnostic or interpretative tool for human readers.

6. Standalone (Algorithm Only) Performance Study

The document describes the performance of the embedded software module and the underlying hearing instruments as meeting relevant standards and functioning as intended. This can be considered a standalone performance evaluation in the sense that the software/device's technical performance was verified. However, it's not a clinical standalone study to assess its effectiveness in relieving tinnitus in patients independent of a human provider's intervention (which is explicitly required as part of a tinnitus management program).

7. Type of Ground Truth Used

For the software and hardware evaluations, the "ground truth" would be the specifications and requirements defined by the relevant standards (IEC 62304, ANSI C63.19-2007, IEC 60118-13, IEC 60601-1-2, IEC 60601-1, ETSI standards, FCC regulations, ISO 10993-1). The device's functionality was compared against these technical specifications.

For the substantial equivalence claim, the "ground truth" is established by comparing the device's indications for use, technological characteristics, and principles of operation to those of the legally marketed predicate devices, with the conclusion that "minor technological differences do not present any new issues of safety or effectiveness."

8. Sample Size for the Training Set

The document does not describe a machine learning algorithm that requires a "training set" of data. The device is a sound generator designed for tinnitus relief, and its functionality is based on established acoustic principles and software engineering, not on learning from a dataset.

9. How the Ground Truth for the Training Set Was Established

As there is no training set for a machine learning algorithm, this question is not applicable.

Ask a specific question about this device

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