Search Results
Found 1 results
510(k) Data Aggregation
(123 days)
Luxottica Group S.P.A.
The Nuance Audio Hearing Aid Software 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 software utilizes a preset 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 Nuance Audio Hearing Aid Software is a software-only device that is comprised of a pair of software modules which operate on two separate required products: (1) Nuance Audio Application on a compatible iOS or Android product, and (2) Nuance Audio Hearing Aid Software Firmware (FW) using the compatible wearable electronic computing platform, the Nuance Audio Glasses (smart glasses). The Nuance Audio Hearing Aid Software amplifies sounds for adult users, 18 years of age and older, who have a perceived mild to moderate hearing loss. The Nuance Audio™ App, iOS or Android mobile application, quides the user through the initial onboarding and set up process providing step-by-step instructions to guide the users can select from four preset options, which are generated from typical mild to moderate hearing loss configurations (Urbanski et al., 2021) with NAL-NL2 gain settings applied. The user may also adjust the overall volume, noise reduction, and microphone directionality. The device incorporates a feedback control algorithm to reduce the likelihood of the user experiencing acoustic feedback. The same amplification settings will be applied to both the left and right ear. This device can be fitted by a user without assistance from a hearing healthcare professional.
Here's a breakdown of the acceptance criteria and study information for the Nuance Audio Hearing Aid Software, based on the provided text:
Nuance Audio Hearing Aid Software: Acceptance Criteria and Study Information
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria Category | Specific Metric/Standard | Acceptance Criteria (Target) | Reported Device Performance (Nuance Audio Hearing Aid Software) |
|---|---|---|---|
| Electro-Acoustics | Latency Clause | Meets 21 CFR 800.30 requirements (implicit: similar to predicate or within acceptable tolerance) | 8.8 ms (Predicate: 3.15 ms – performance testing evaluated differences and supports substantial equivalence) |
| Frequency Response | Meets 21 CFR 800.30 requirements (implicit: similar to predicate or within acceptable tolerance) | 200Hz - 6300 Hz (Predicate: 100 — 10,000 Hz – performance testing evaluated differences and supports substantial equivalence) | |
| Self-Generated Noise | Meets 21 CFR 800.30 requirements (implicit: similar to predicate or within acceptable tolerance) | 29.9 dBA (Predicate: 28 dBA – performance testing evaluated differences and supports substantial equivalence) | |
| Harmonic Distortion | Less than or equal to 1% | Less than or equal to 1% | |
| Maximum Output Value | Meets 21 CFR 800.30 requirements (implicit: similar to predicate or within acceptable tolerance) | 112.7 dB SPL (Predicate: 106 dB SPL – performance testing evaluated differences and supports substantial equivalence) | |
| Insertion Gain | Within 5 dB of predicate device at most frequencies; within 5 dB of NAL-NL2 targets except at one frequency (5 kHz, within 8 dB). | Within 5 dB of predicate device at most frequencies; within 5 dB of NAL-NL2 targets except at one frequency (5 kHz, within 8 dB). | |
| Usability Testing | Critical Errors | Zero critical errors during simulated use scenarios | All tasks completed without critical errors. |
| User Satisfaction | Overall positive satisfaction on usability | Overall positive satisfaction on the usability of the device expressed by users. | |
| Acceptance Criteria | All defined acceptance criteria for EN 62366-1:2015 met | All defined acceptance criteria were met (EN 62366-1:2015). | |
| Clinical Performance | Real-Ear Aided Response (REAR) | Each preset (A, B, C, D) within ±6 dB of NAL-NL2 targets at 250, 500, 1000, 2000, and 4000Hz. | Each Nuance Audio Hearing Aid Software preset (A, B, C, and D) profile was within the pre-specified criterion range of NAL-NL2 targets (±6 dB). |
| Speech-in-Noise (SNR-50) | Improvement in SNR (threshold not explicitly stated, but typically a positive improvement is expected) | Average unaided vs. aided improvement was 3.49 dB. | |
| IOI-HA Total Score | Clinically meaningful outcome score for the intended population (threshold not explicitly stated) | Mean IOI-HA total score was 29.04 (SD = 4.62), considered clinically meaningful for individuals with perceived mild to moderate hearing loss to achieve hearing benefit. | |
| General Compliance | Special Controls | Meets special controls for 874.3335 (including addressing clinical performance for fitting strategy) | Meets special controls for 874.3335, and clinical data provided to address differences in technology (preset vs. self-fitting) to support substantial equivalence. |
| OTC Hearing Aids | Meets specifications associated with over-the-counter hearing aids (21 CFR 800.30) | Nuance Audio Hearing Aid Software was shown to meet the specifications associated with over-the-counter hearing aids (21 CFR 800.30). |
2. Sample Size Used for the Test Set and Data Provenance
- Usability Testing:
- Sample Size: 15 representative adult users.
- Data Provenance: Not explicitly stated, but implies prospective data collection from participants in a usability validation study.
- Real-ear measurements:
- Sample Size: 29 participant ears.
- Data Provenance: Not explicitly stated, but implies prospective data collection from participants.
- Speech in noise clinical performance:
- Sample Size: 19 adults with mild to moderate hearing loss.
- Data Provenance: Not explicitly stated, but implies prospective data collection from participants.
- Patient Reported Outcome Measure (IOI-HA):
- Sample Size: 23 adult subjects identified with self-perceived mild-to-moderate sensorineural hearing loss.
- Data Provenance: Not explicitly stated, but implies prospective data collection after a 14-day trial.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
The document does not explicitly mention the use of experts to establish ground truth for the test set from these clinical studies. Instead, the studies compare the device's performance against:
- Objective measures: NAL-NL2 targets (a commonly used clinical fitting formula).
- Standardized clinical outcomes: SNR-50 (speech-in-noise ratio) and IOI-HA scores (patient-reported outcome).
- Usability standards: IEC 62366-1:2015.
The ground truth for the "typical mild to moderate hearing loss configurations" used to generate the presets (Urbanski et al., 2021) suggests a reliance on established audiological research rather than individual expert consensus for a specific test set.
4. Adjudication Method for the Test Set
No adjudication method (e.g., 2+1, 3+1) is mentioned for any of the test sets. The studies appear to rely on direct measurements, standardized clinical tests, or user feedback.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No MRMC comparative effectiveness study is reported in relation to human readers improving with AI vs. without AI assistance. The device is a "hearing aid software" rather than an interpretative AI for medical imaging, for example, where MRMC studies are common. The clinical performance studies directly evaluate the device's efficacy.
6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study
Yes, the studies described for "Performance Testing" (Electro-Acoustics, Real-ear measurements, Speech in Noise, IOI-HA) represent standalone performance of the algorithm integrated into the compatible hardware (Nuance Audio Glasses) without human-in-the-loop clinical decision-making. The usability testing assesses the user's ability to operate the device effectively, which is human-in-the-loop operation, but the core performance metrics are evaluating the device's output.
7. Type of Ground Truth Used for the Test Set
The ground truth for the test sets consisted of:
- Objective Audiological Targets: NAL-NL2 (National Acoustics Laboratories-Non-Linear 2) fitting formula.
- Standardized Clinical Metrics: SNR-50 (signal-to-noise ratio at 50% word recognition) and International Outcome Inventory for Hearing Aids (IOI-HA) scores.
- Usability Standards: Compliance with IEC 62366:2015 and completion of tasks without critical errors.
- Bench Test Standards: Adherence to ISO, ANSI/ASA, CTA, IEC standards for biocompatibility, electrical safety, EMC, battery safety, and software.
8. Sample Size for the Training Set
The document does not specify a sample size for a training set. The device uses "four preset options, which are generated from typical mild to moderate hearing loss configurations (Urbanski et al., 2021) with NAL-NL2 gain settings applied." This suggests that the "training" or development of these presets was based on established audiological research and fitting formulas, rather than a data-driven machine learning training set in the typical sense.
9. How the Ground Truth for the Training Set Was Established
The ground truth for the "training" (i.e., the generation of the preset fitting strategies) for the Nuance Audio Hearing Aid Software was established based on:
- Published Audiological Research: "Typical mild to moderate hearing loss configurations (Urbanski et al., 2021)."
- Standardized Fitting Formula: Application of the NAL-NL2 (National Acoustics Laboratories-Non-Linear 2) gain settings to these configurations.
This indicates that the presets are derived from established audiological science and validated hearing loss profiles, rather than being "learned" from a distinct training dataset with a separate ground truth determination process.
Ask a specific question about this device
Page 1 of 1