Search Results

The hearing aid is a disposable, extended-wear air conduction hearing aid, designed to be used and worn by hearing-impaired persons. Hearing assistance is achieved through amplification of sound pressure waves, which are transmitted to the external ear canal via air conduction. The hearing aid is initially placed in the ear canal by an appropriately trained ENT physician, Audiologist or Hearing Aid Dispenser and can remain in the ear canal for up to 4 months or until the battery is depleted. It is then replaced by a new device by the previously mentioned parties, or by an adult patient 22 years and older who have been wearing Lyric for a minimum period of 3 months under the direction and training of the ENT physician, Audiologist or Hearing Aid Dispenser. Upon device removal the hearing aid is discarded.

Device Description

Lyric4 is a non-sterile, extended wear hearing aid that is worn 24 hours a day, 7 days a week for months-at-a-time. Due to the deep placement inside the ear canal, it is 100% invisible. For patients, Lyric4 is very easy to operate with no batteries to change, no ongoing maintenance required and no daily insertion or removal. Lyric4 takes advantage of the deep placement in the ear canal for natural sound quality and the natural directivity of the pinna. Lyric4 is designed for single insertion and is not reused once removed from the ear (single-use only).

Compared to the currently marketed Lyric4, there are no modifications to the technology (hardware and software), materials, or accessories when Lyric4 is used for self-replacement. Only the indications for use statement and labeling have been modified.

AI/ML Overview

Here's a summary of the acceptance criteria and the study that proves the device meets them, based on the provided text:

Device: Lyric4 Hearing Aid (for self-replacement)

Clinical Study Objective: To demonstrate the effectiveness and safety of the HCP-guided Lyric4 self-replacement procedure compared to the commercially available HCP-replacement procedure.

1. Table of Acceptance Criteria and Reported Device Performance

Endpoint	Acceptance Criterion	Reported Device Performance	Result
Primary Effectiveness: Achieved Insertion Depth	Non-inferiority margin of 2mm for the Mean Absolute Difference of self-replacement vs. HCP-replacement. (Lower Mean Absolute Difference indicates better agreement)	Left Ears (N=50): Mean Absolute Difference = 0.6 mm, 95% CI (0.30, 0.82 mm), p-value <.0001 (for non-inferiority).Right Ears (N=49): Mean Absolute Difference = 0.6 mm, 95% CI (0.35, 0.89 mm), p-value <.0001 (for non-inferiority).	Met
Co-Secondary Effectiveness: Aided Audiometric Thresholds	Non-inferiority margin of 10 dB HL for the Estimated Difference of self-replacement vs. HCP-replacement at 500, 1000, 2000, and 4000 Hz.	Left Ears (N=50): Estimated Differences at all frequencies were well below 10 dB HL. (e.g., 500 Hz: -0.5 dB HL, 1000 Hz: 1.5 dB HL, etc.)Right Ears (N=49): Estimated Differences at all frequencies were well below 10 dB HL. (e.g., 500 Hz: -0.69 dB HL, 1000 Hz: 0.31 dB HL, etc.)p-value <.0001 for all frequencies in both ears.	Met
Co-Secondary Effectiveness: Aided Speech-in-Noise Testing SNR Loss	Non-inferiority margin of 5 dB for the Estimated Difference of self-replacement vs. HCP-replacement SNR Loss scores.	Left Ears: Estimated Difference = 0.10 dB, 95% CI (-0.81 dB, 1.01 dB), adjusted p-value <.0001.Right Ears: Estimated Difference = 0.46 dB, 95% CI (-0.54 dB, 1.46 dB), adjusted p-value <.0001.	Met
Primary Safety: Incidence of Ear Health Issues Requiring Medical Referral and Related to Device Placement	Not explicitly stated with a numerical acceptance criterion, but implies a low and manageable incidence.	One instance of cerumen impaction requiring medical referral and cerumen management.	Met (Implicitly)
Secondary Safety: Incidence of Treatment-Emergent Adverse Events	Not explicitly stated with a numerical acceptance criterion, but implies comparability between self-replacement and HCP-replacement conditions.	Overall incidence of AEs: Self-Replacement: 13 (23.21%) subjects; HCP-Replacement: 17 (29.82%) subjects. Overall incidence of Adverse Device Effects: Self-Replacement: 12 (21.43%) subjects; HCP-Replacement: 16 (28.07%) subjects. One subject withdrew from study due to AE under self-replacement. No SAEs or deaths. All TEAEs commonly observed ear health symptoms.	Met (Comparability)
Exploratory: Incidence of Gross Placement Errors During Self-Replacement	Not explicitly stated with a numerical acceptance criterion, but implies zero or very low incidence.	No instances of gross placement errors observed during self-replacement.	Met (Zero)
Human Factors/Usability (Non-clinical): Effectiveness of Training	Assessed through objective (performance-based) and subjective (user-feedback) evaluation of success for critical tasks. No use error leading to unknown hazardous situations with unacceptable risk.	Only a few use difficulties and errors observed. One participant omitted hand washing (considered redundant in test). Understanding of atmospheric pressure symbol was hardest but 10/15 participants used IFU successfully. No use errors leading to unacceptable risk.	Met

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

Clinical Study Test Set (Effectiveness & Safety): 57 experienced Lyric users initially enrolled across 8 sites.
- Effectiveness (Achieved Insertion Depth): N=50 Left Ears, N=49 Right Ears (Intent-to-Test Population reported for primary effectiveness).
- Effectiveness (Aided Audiometric Thresholds): N=50 Left Ears, N=49 Right Ears (Intent-to-Test).
- Effectiveness (Aided Speech-in-Noise Testing SNR Loss): Left and Right Ear groups (exact N for ITT not specified here but implied to be similar to other effectiveness endpoints).
- Safety (TEAEs): N=56 for Self-Replacement condition, N=57 for HCP-Replacement condition.
Human Factors/Usability Test Set: 15 hearing-impaired adults who were current Lyric4 users (at least 3 months).
Data Provenance: The study was a "prospective, non-randomized multi-center, longitudinal clinical investigation." The country of origin is not explicitly stated in the provided text.

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

For Clinical Effectiveness Endpoints (Achieved Insertion Depth, Audiometric Thresholds, SNR Loss): The "ground truth" seems to be derived from objective measurements taken during the study, comparing the self-replacement procedure to the HCP-replacement procedure. The measurements were likely taken by the healthcare professionals (HCPs) at the 8 study sites. Specific qualifications of the individuals taking these measurements (e.g., audiologists, ENT physicians) are not detailed beyond "appropriately trained ENT physician, Audiologist or Hearing Aid Dispenser" for initial placement and training.
For Safety Endpoints (Ear Health Issues, AE's): Adverse events and ear health issues were "judged by the HCP." This implies that the HCPs at the study sites (likely ENT physicians, audiologists, or hearing aid dispensers) were responsible for evaluating and reporting these events.
For Human Factors/Usability: Study staff captured use-error counts and responses elicited during follow-up questioning to determine the root cause, implying observation and assessment by trained personnel in the usability study.

4. Adjudication Method for the Test Set

The document does not explicitly describe a formal adjudication method (like 2+1 or 3+1 consensus) for the clinical study data or the human factors study. Measurements and observations were collected and analyzed, with statistical comparisons for effectiveness endpoints. Adverse events were "judged by the HCP."

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 an AI-driven device. The study is a comparative effectiveness study comparing a self-replacement procedure (patient performing) versus an HCP-replacement procedure (healthcare professional performing) for a hearing aid. Therefore, this section is not applicable.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

This is not an AI-driven device. There is no algorithm or AI component in the Lyric4 Hearing Aid for self-replacement being assessed for standalone performance. The study evaluated human performance (patients vs. HCPs) in replacing the device.

7. The Type of Ground Truth Used

The "ground truth" for this study is based on objective clinical measurements and observations taken by healthcare professionals (HCPs) during the study, comparing the outcomes of the self-replacement procedure to the HCP-replacement procedure. These include:

Achieved Insertion Depth (quantitative measurement)
Aided Audiometric Thresholds (quantitative measurement)
Aided Speech-in-Noise Testing SNR Loss (quantitative measurement)
Incidence of Ear Health Issues and Adverse Events (clinical observation and judgment by HCPs)
Observations of use errors in the human factors study.

8. The Sample Size for the Training Set

This product is a medical device (hearing aid) and the current submission is for a change in the indications for use (allowing self-replacement). The device's technology (hardware and software) is unchanged. Therefore, there is no "training set" in the context of an AI/algorithm-driven device.
The human factors study focused on the effectiveness of training provided to HCPs to train end-users. The participants in the clinical study (57 experienced Lyric users) received this training as part of the study design.

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

As this is not an AI/algorithm-driven device with a traditional "training set" for model development, this question is not applicable in that context. The "training" referred to in the human factors study is the instructions and guidance provided to HCPs (who then train patients) for the self-replacement procedure. The effectiveness of this training was assessed by observing the patients' performance (as described in point 7).

Ask a Question

Ask a specific question about this device

K Number

K230538

Device Name

All-Day Clear Slim ADCS1 Hearing Aid. All-Day Clear ADC1 Hearing Aid

Manufacturer

Sonova AG

Date Cleared

2023-06-16

(109 days)

Product Code

Regulation Number

Type

Panel

Reference & Predicate Devices

K211008

Predicate For

N/A

Intended Use

The All-Day Clear Slim hearing aids are intended for individuals 18 years or older with perceived mild to moderate hearing loss. The intended use of the All-Day Clear Slim hearing aids is to amplify and transmit sound to the ears and hereby compensate for hearing loss. The hearing aids must only be used by the intended person. They should not be used by any other person as they could damage hearing. The charging case is intended to charge the battery of the rechargeable hearing aids. The All-Day Clear App is intended for individuals 18 years or older, to set-up and/or adjust All-Day Clear Slim hearing aids through Android and Apple iOS smartphones.

The All-Day Clear hearing aids are intended for individuals 18 years or older with perceived mild to moderate hearing loss. The intended use of the All-Day Clear hearing aids is to amplify and transmit sound to the ears and hereby compensate for hearing loss. The hearing aids must only be used by the intended person. They should not be used by any other person as they could damage hearing. The charging case is intended to charge the battery of the rechargeable hearing aids. The All-Day Clear App is intended for individuals 18 years or older, to set-up and/or adjust All-Day Clear hearing aids through Android and Apple iOS smartphones.

Device Description

The All-Day Clear Slim ADCS1 hearing aid and All-Day Clear ADC1 hearing aid are self-fitting air-conduction hearing aids. The ADCS1 and ADC1 hearing aids are nearly identical except for minor design differences. The hearing aid system consists of hearing aids for left and right ears, charging case, charging cable with USB-A and USB-C connector, wall plug, a set of eartips (small, medium, and large sizes), cleaning brush, carrying case (for ADCS1 hearing aids alone), and wax guards. The ADCS1 and ADC1 hearing aids are indicated for over-the-counter use.

The end user can self-fit the hearing aid by downloading the All-Day Clear App to their Android or Apple iOS device, pairing the hearing aids to the App, and following a series of guided onboarding steps:

Instructions on how to wear the hearing aids
Creation of a sound profile by listening to sample audio in which the user selects parameters for volume and sound clarity
Selection of sound balance

Once the hearing aids have been set up with a sound profile, the App can continue to be used as a remote control of the hearing aids. For example, the end users can use the App to change the volume or mute the hearing aid microphones (together or independently), switch between different hearing aid sound modes, adjust the volume of a streamed signal, adjust equalizer and wind noise control, and read out the status of the hearing aid charge level.

The ADCS1 and ADC1 hearing aid system provides an alternative optional method of fitting the device by letting the end users purchase "In-Clinic Care Package", where they can have a licensed hearing care professional fit their hearing aids using professional fitting software called "All-Day Clear Fitting Software." All-Day Clear Fitting Software is a component of Sonova's TrueFit 5.3 or higher fitting software which can only be used by a licensed hearing care professional. In both scenarios, the end users can use the App as a remote control of the hearing aid.

AI/ML Overview

Here's a breakdown of the acceptance criteria and study details based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

Acceptance Criteria (Endpoint)	Non-inferiority Margin	Reported Device Performance (Self-Fit vs. Pro-Fit)	Conclusion on Acceptance Criteria Met?
Primary Effectiveness Endpoint:
APHAB Global Benefit Score (Self-Fit)	Not more than 12.5% below Pro-Fit	Adjusted mean treatment difference: 0.6% (95% CI: -2.919% to 4.742%) (after outlier exclusion)	Met (Lower bound > -12.5%)
Secondary Effectiveness Endpoint:
QuickSiN Benefit Score (Self-Fit)	-1.8 dB or higher	Adjusted mean treatment difference: 0.103 dB SNR (95% CI: -0.867 to 1.074 dB SNR) (Period 1 data)	Met (Lower bound > -1.8 dB)
Safety Endpoint:	(Implicit: No serious adverse events or unacceptable adverse events)	One non-serious treatment-emergent adverse event (ear canal occlusion, not device-related). No serious adverse events.	Met

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

Sample Size for Test Set:
- Clinical Study: 44 participants (enrolled). Due to early discontinuations and outlier exclusion, analysis for effectiveness endpoints was based on varying numbers:
  - APHAB: 40 participants (after excluding 2 outliers from the original 42 for Period 1 analysis).
  - QuickSiN: 40 participants (Period 1 data analysis).
- Human Factors/Usability Study: 30 participants (15 patients, 15 caregivers).
Data Provenance: Retrospective from clinical study performed with "HelloGO" hearing aid, which is stated to have identical hardware and almost identical firmware to the subject devices (ADCS1, ADC1). The human factors study was prospective, conducted specifically for the ADCS1/ADC1. The country of origin for the clinical study is not explicitly stated in the provided text.

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

The clinical study did not involve AI assistance, therefore "ground truth" was established through direct measurement of human hearing abilities and perceptions using standardized audiological tests (APHAB and QuickSiN) with both self-fitted and professionally fitted devices.
Professionally Fit Devices: Implies fitting by audiologists or hearing care professionals, but the specific number or qualifications of these professionals for establishing the "ground truth" (the professional fit as a comparator) are not detailed beyond "professional fitting method."

4. Adjudication Method for the Test Set

Clinical Study (Effectiveness Endpoints): Not applicable in the sense of expert adjudication of a device's output. The study design involved direct comparison of patient-reported outcomes (APHAB) and objective speech-in-noise testing (QuickSiN) under two different fitting conditions (self-fit vs. professional fit). The "ground truth" for the benefit scores was derived directly from participant responses and test results.
Human Factors/Usability Study: "Study staff systematically assessed device usage to identify problems that were encountered by participants, including use errors and close calls during participant performance." This suggests observation and recording of events, rather than a formal expert adjudication of discrete findings.

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 comparative effectiveness study was not done. This study focuses on the effectiveness of a self-fitting hearing aid compared to a professionally fitted one, not on AI assistance for human readers/clinicians.

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

Yes, in a sense, the "self-fitting" method can be considered a standalone performance of the algorithm (as implemented in the app) plus the user's interaction, without a hearing care professional in the loop for the fitting process itself. The study compared this "self-fitted" performance to a "professionally fitted" performance.

7. The Type of Ground Truth Used

Clinical Study (Effectiveness):
- Patient-Reported Outcomes: Abbreviated Profile of Hearing Aid Benefit (APHAB) global benefit score.
- Objective Audiological Measure: Quick Speech-in-Noise (QuickSiN) test benefit score.
- The "ground truth" for comparison was the outcome achieved with a professionally derived fitting.
Safety: Tabulation of adverse events and serious adverse events.
Human Factors/Usability: Observed use errors and close calls in a simulated environment, and participant feedback.

8. The Sample Size for the Training Set

The document does not explicitly mention a "training set" for the clinical study parameters. The study design is a comparative effectiveness study between two fitting methods (self-fit and professional fit) for the hearing aid itself. The "self-fitting algorithm" embedded in the app would have had its own development and possible internal training process, but details of this are not provided in the context of this FDA summary.
The human factors study did not involve a training set; it was a usability validation.

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

As a training set for the specific self-fitting algorithm is not detailed, the method for establishing its "ground truth" (e.g., what data it was trained on to achieve optimal fitting) is not provided in this document. The clinical study established ground truth for effectiveness comparison by using a professionally fitted condition as a benchmark.

Ask a Question

Ask a specific question about this device

Page 1 of 1