Hearing assist is an over-the-counter (OTC), self-fitting software as a medical device (SaMD) hearing aid to be used with compatible wearable electronic products. Hearing assist is intended to compensate for perceived mild to moderate hearing loss for users 18 years of age and older. Hearing assist utilizes a self-fitting strategy and is adjusted by the user to meet their hearing needs without the assistance of a hearing healthcare professional.
Device Story
Hearing assist is an OTC SaMD hearing aid operating on a compatible smart glasses wearable platform and a smartphone iOS application. The device uses the smart glasses' microphones to capture environmental sound and loudspeakers to deliver amplified audio. Users perform an initial onboarding and self-fitting process via the smartphone app to generate a proprietary hearing profile; this profile dictates the amplification parameters. The system employs wide dynamic range compression to process sound. Users can adjust volume, sharpness, and balance bilaterally via the smartphone app. The device is intended for use by the patient without professional assistance. It provides real-world sound amplification to compensate for hearing loss, improving speech-in-noise performance. The device includes a PCCP for future expansion to Android platforms.
Clinical Evidence
Clinical investigation of 142 subjects (18+ years) with mild to moderate hearing impairment. Study compared self-fit (SF) vs. professional-fit (PF) groups over 14 days. Primary endpoint: IOI-HA survey scores (SF mean 25.77 vs. PF mean 26.81; p=0.004 for non-inferiority). Secondary endpoint: QuickSIN speech-in-noise performance (SF mean SNR loss 4.4 dB vs. PF 4.2 dB; p<0.001 for non-inferiority). No unanticipated adverse device effects reported; mild, transient headaches/fatigue observed.
Technological Characteristics
Air-conduction hearing aid software (SaMD) running on smart glasses (microphones/loudspeakers) and iOS smartphone. Uses wide dynamic range compression. Rechargeable Li-ion battery. Connectivity via mobile app for settings and remote firmware updates. Complies with ANSI S3.22, ANSI/CTA-2051, IEC 62304, IEC 60601-1, and 21 CFR 800.30. Locked algorithm architecture.
Indications for Use
Indicated for individuals 18 years of age and older with perceived mild to moderate hearing loss.
Regulatory Classification
Identification
Air-conduction hearing aid software is a device that is intended to be used with a compatible wearable hardware platform to compensate for impaired hearing. The software also allows for customization to the user's hearing needs. The Hearing Aid Feature (HAF) is a software-only mobile medical application intended to amplify sound for individuals 18 years of age or older with perceived mild to moderate hearing impairment, utilizing a self-fitting strategy adjusted by the user without the assistance of a hearing healthcare professional.
Special Controls
In combination with the general controls of the FD&C Act, including 21 CFR 800.30 (over-thecounter hearing aids) and 21 CFR 801.422 (prescription hearing aids) as applicable, airconduction hearing aid software is subject to the following special controls:
{0}
[LOGO]
FDA
U.S. FOOD & DRUG
ADMINISTRATION
July 13, 2026
Meta Platform Technologies, LLC
Lucas Fernandez
Director
Reality Labs Medical Devices, Health Technologies Team
333 Airport Blvd.
Burlingame, California 94010
Re: K254044
Trade/Device Name: Hearing assist
Regulation Number: 21 CFR 874.3335
Regulation Name: Air-Conduction Hearing Aid Software
Regulatory Class: Class II
Product Code: SCR
Dated: June 10, 2026
Received: June 11, 2026
Dear Lucas Fernandez:
We have reviewed your section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (the Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database available at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.
If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.
U.S. Food & Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993
www.fda.gov
{1}
K254044 - Lucas Fernandez
Page 2
FDA's substantial equivalence determination also included the review and clearance of your Predetermined Change Control Plan (PCCP). Under section 515C(b)(1) of the Act, a new premarket notification is not required for a change to a device cleared under section 510(k) of the Act, if such change is consistent with an established PCCP granted pursuant to section 515C(b)(2) of the Act. Under 21 CFR 807.81(a)(3), a new premarket notification is required if there is a major change or modification in the intended use of a device, or if there is a change or modification in a device that could significantly affect the safety or effectiveness of the device, e.g., a significant change or modification in design, material, chemical composition, energy source, or manufacturing process. Accordingly, if deviations from the established PCCP result in a major change or modification in the intended use of the device, or result in a change or modification in the device that could significantly affect the safety or effectiveness of the device, then a new premarket notification would be required consistent with section 515C(b)(1) of the Act and 21 CFR 807.81(a)(3). Failure to submit such a premarket submission would constitute adulteration and misbranding under sections 501(f)(1)(B) and 502(o) of the Act, respectively.
Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled "Deciding When to Submit a 510(k) for a Change to an Existing Device" (https://www.fda.gov/media/99812/download) and "Deciding When to Submit a 510(k) for a Software Change to an Existing Device" (https://www.fda.gov/media/99785/download).
Your device is also subject to, among other requirements, the Quality Management System Regulation (QMSR) (21 CFR Part 820), which includes, but is not limited to, ISO 13485 clause 7.3 (Design controls), ISO 13485 clause 8.3 (Nonconforming product), ISO 13485 clause 8.5.2 (Corrective action), and ISO 13485 clause 8.5.3 (Preventative action). Please note that regardless of whether a change requires premarket review, the QMSR requires device manufacturers to review and approve changes to device design and production (ISO 13485 clause 7.3 and ISO 13485 clause 7.5) and document changes and approvals in the Medical Device File (ISO 13485 clause 4.2.3).
Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting (reporting of medical device-related adverse events) (21 CFR Part 803) for devices or postmarketing safety reporting (21 CFR Part 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reporting-combination-products); good manufacturing practice requirements as set forth in the Quality Management System Regulation (QMSR) (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050.
All medical devices, including Class I and unclassified devices and combination product device constituent parts are required to be in compliance with the final Unique Device Identification System rule ("UDI Rule"). The UDI Rule requires, among other things, that a device bear a unique device identifier (UDI) on its label and package (21 CFR 801.20(a)) unless an exception or alternative applies (21 CFR 801.20(b)) and that the dates on the device label be formatted in accordance with 21 CFR 801.18. The UDI Rule (21 CFR 830.300(a) and 830.320(b)) also requires that certain information be submitted to the Global Unique Device Identification Database (GUDID) (21 CFR Part 830 Subpart E). For additional information on these
{2}
K254044 - Lucas Fernandez
Page 3
requirements, please see the UDI System webpage at https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance/unique-device-identification-system-udi-system.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-devices/medical-device-safety/medical-device-reporting-mdr-how-report-medical-device-problems.
For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely,
SRINIVAS NANDKUMAR -S
Srinivas Nandkumar, Ph.D.
Director
DHT1B: Division of Dental and
ENT Devices
OHT1: Office of Ophthalmic, Anesthesia,
Respiratory, ENT and Dental Devices
Office of Product Evaluation and Quality
Center for Devices and Radiological Health
Enclosure
{3}
| Indications for Use | | |
| --- | --- | --- |
| Please type in the marketing application/submission number, if it is known. This textbox will be left blank for original applications/submissions. | K254044 | ? |
| Please provide the device trade name(s). | | ? |
| Hearing assist | | |
| Please provide your Indications for Use below. | | ? |
| Hearing assist is an over-the-counter (OTC), self-fitting software as a medical device (SaMD) hearing aid to be used with compatible wearable electronic products. Hearing assist is intended to compensate for perceived mild to moderate hearing loss for users 18 years of age and older. Hearing assist utilizes a self-fitting strategy and is adjusted by the user to meet their hearing needs without the assistance of a hearing healthcare professional. | | |
| Please select the types of uses (select one or both, as applicable). | ☐ Prescription Use (21 CFR 801 Subpart D) ☑ Over-The-Counter Use (21 CFR 801 Subpart C) | ? |
{4}
Meta
# 1. Submitter Information
Submitter: Meta Platforms Technologies, LLC
333 Airport Boulevard
Burlingame, California 94010
Email: rl_mdcompliance@meta.com
Primary Correspondent: Lucas Fernandez
Director of Medical Devices | Meta
333 Airport Boulevard
Burlingame, California 94010
Secondary Correspondent: Elizabeth Khalil
Regulatory Affairs Lead | Meta
333 Airport Boulevard
Burlingame, California 94010
Date Prepared: July 13, 2026
# 2. Device information
| Device Name: | Hearing assist |
| --- | --- |
| Common Name: | Air-conduction hearing aid software |
| Regulation Number: | 21 CFR 874.3335 |
| Regulation Name: | Air-conduction hearing aid software |
| Product Code: | SCR |
| Regulatory Class: | Class II |
# 3. Predicate Device Information
| Device Name: | Apple Hearing Aid Feature (HAF) |
| --- | --- |
| 510(k) Number: | DEN230081 |
| Manufacturer: | Apple Inc. |
The predicate device has not been subject to a design related recall.
Page 1 of 12
{5}
## 4. Device Description
The Meta Hearing assist feature is an air-conduction hearing aid software medical device (SaMD) intended to be used with a smart glasses wearable multi-function hardware platform to compensate for impaired hearing. Hearing assist is comprised of a pair of software modules which operate on two separate required products: (1) Hearing assist Smartphone iOS Application on a compatible iOS phone, and (2) Hearing assist Smart Glasses App software (i.e., firmware) on a compatible wearable electronic computing platform. Refer to Figure 1.

Hearing assist Smartphone iOS Application

Hearing assist Smartglasses App software on compatible wearable electronic computing platform
Figure 1: Meta Hearing assist Platform Components
Page 2 of 12
{6}

Figure 2: Meta Hearing assist main screen for iOS
Hearing assist is intended for over-the-counter (OTC) use and is self-fit and customized by the user to meet their hearing needs. It is intended for individuals 18 years of age or older with perceived mild to moderate hearing loss.
Users must complete onboarding and self-fitting via the Smartphone app while wearing the glasses in order to create a hearing profile prior to use of the Hearing assist device. The hearing
Page 3 of 12
{7}
test/profile generator functionality is integrated into the Hearing assist software modules and is not a standalone application. The hearing profile is a proprietary data format that specifies how real-world sounds should be amplified for each ear. Once users complete self-fitting (i.e. have a hearing profile), they can turn on Hearing assist's real-world sound amplification to compensate for their hearing loss. In addition to onboarding and self-fitting, the Hearing assist Smartphone App contains settings and personalization controls for Hearing assist (Figure 2). Volume and sharpness user controls in the Meta Hearing assist Smartphone app applies adjustments bilaterally (i.e., to both ears simultaneously). These user controls cannot be fine-tuned independently for each ear. However, the effective gain realized in each ear is bounded by per-ear gain limits, ensuring safe amplification in both the better and poorer ear.
The Hearing assist Smart Glasses App is installed and runs within the smart glasses platform. The Hearing assist Smart Glasses App uses the smart glasses platform hardware (such as microphones and loudspeakers) and software (such as audio processing pipelines and control interfaces) features provided by the smart glasses platform to perform device functions such as playing tones during self-fitting, processing incoming environmental sound, and delivering amplified sound based on the user's hearing profile. The Hearing assist Smart Glasses App is also responsible for calculating and storing/persisting the user's hearing profile after the self-fitting process is completed.
## 5. Indications for Use
Hearing assist is an over-the-counter (OTC), self-fitting software as a medical device (SaMD) hearing aid to be used with compatible wearable electronic products. Hearing assist is intended to compensate for perceived mild to moderate hearing loss for users 18 years of age and older. Hearing assist utilizes a self-fitting strategy and is adjusted by the user to meet their hearing needs without the assistance of a hearing healthcare professional.
## 6. Comparison of Intended Use and Technological Characteristics with the Predicate Device
The table below compares the intended use and the technological characteristics of the subject device and predicate device.
**Table 1:** Summary of substantial equivalence
| | Subject Device | Predicate Device | Comparison |
| --- | --- | --- | --- |
| Trade name | Meta Hearing assist | Apple Hearing Aid Feature (HAF) | |
| FDA Number | K254044 | DEN 230081 | N/A |
| Product Code | SCR | SCR | Same as predicate |
| Regulation Number | 21 CFR 874.3335 | 21 CFR 874.3335 | Same as predicate |
| Regulatory Class | II | II | Same as predicate |
Page 4 of 12
{8}
| | Subject Device | Predicate Device | Comparison |
| --- | --- | --- | --- |
| Trade name | Meta Hearing assist | Apple Hearing Aid Feature (HAF) | |
| Patient Population | Individuals 18 years of age or older with perceived mild to moderate hearing impairment. | Individuals 18 years of age or older with perceived mild to moderate hearing impairment. | Same as predicate |
| Indications for Use | Hearing assist is an over-the-counter (OTC), self-fitting software as a medical device (SaMD) hearing aid to be used with compatible wearable electronic products. Hearing assist is intended to compensate for perceived mild to moderate hearing loss for users 18 years of age and older. Hearing assist 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 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 indications for the subject and predicate devices are the same; both devices are intended for similar patient populations. The compatible wearable electronic devices are different for the subject and predicate devices, i.e. smart glasses vs ear buds platforms. |
Page 5 of 12
{9}
| | Subject Device | Predicate Device | Comparison |
| --- | --- | --- | --- |
| Trade name | Meta Hearing assist | Apple Hearing Aid Feature (HAF) | |
| Wearable Platform | Hearing assist is housed in the compatible Smart Glasses which is a combination of a class 1 medical device for vision correction and general computing platform for features such as cameras for picture taking and mics/speakers for audio. Hearing assist uses the general purpose platform hardware and software features to perform medical device functions during the user's self-fit journey and for delivering amplified sound based on the user's hearing profile. | The HAF software is housed in the Apple AirPods Pro 2, a consumer electronic earbud. The amplified sound is delivered via an ear-tip situated inside the ear canal. | Different Both the subject and predicate device use general computing platforms for their device functions. The Smart Glasses deliver the air conducted signal without the device obstructing the ear canal, whereas the predicate device uses a compatible hardware that resides within the concha and ear canal. Any technology differences do not raise any new safety or effectiveness questions. Performance testing, including bench and clinical, evaluated these differences in technology and the results support substantial equivalence. A glasses form factor with external speaker and mic placement has been previously cleared by FDA under K243150 (Nuance) under the SCR product code. |
Page 6 of 12
{10}
| | Subject Device | Predicate Device | Comparison |
| --- | --- | --- | --- |
| Trade name | Meta Hearing assist | Apple Hearing Aid Feature (HAF) | |
| Fitting Method | The Hearing assist Smart Phone application guides the user through the initial onboarding and self-fitting process, providing step-by-step instructions to guide the users. There are three types of adjustments (volume, sharpness, balance) that the user can make to optimize their hearing preferences. The user is able to adjust the fine-tuning settings anytime in the Smart Phone application. | The Apple HAF requires the user to select a hearing test result from the Health app on the iOS device. Once the HAF onboarding is completed, then fine-tuning becomes available to the user. There are three types of adjustments (Amplification, Tone and Balance) that the user can optimize for their hearing preferences. The user is able to adjust the fine-tuning settings anytime on a compatible iPhone, iPad, MacBook or Apple Watch. | Similar to predicate. Both subject and predicate devices use a self-fitting strategy. Both devices are intended for OTC use and do not require the assistance of a professional. The subject device was tested and verified to meet the amplification needs for the intended users in both clinical and non-clinical testing. |
| Input signal compression | Wide dynamic range compression | Wide dynamic range compression | Same as predicate |
| Microphones | Multiple Microphone System in the glasses can be configured by the user in standard (all-around) or focus (frontal) mode. | Microphones in AirPods can be configured by User in omni-directional and directional mode. | Similar to predicate |
| Battery technology | Rechargeable Li-ion battery | Rechargeable Li-ion battery | Same technology |
| Battery lifetime | Hearing assist is designed to last at least 3 hours of continuous use on fully charged Smart Glasses. The companion charging case provides up to 32 hours of charging for glasses. | ~4-6 hours on single charge and a companion charging case | Similar to predicate. Performance testing on subject device support substantial equivalence including 800.30(e) |
Page 7 of 12
{11}
| | Subject Device | Predicate Device | Comparison |
| --- | --- | --- | --- |
| Trade name | Meta Hearing assist | Apple Hearing Aid Feature (HAF) | |
| Active noise reduction | Included | Included | Similar to predicate |
| Mobile App | Mobile application on a compatible iOS operating platform. | Mobile application on a compatible iOS operating platform. | Similar to predicate |
| Remote firmware updates | Remote firmware updates via mobile application. | Remote firmware updates via mobile application. | Similar to predicate |
| Latency clause | Device Latency: 9.25 msec | Median Latency: 3.15 msec | Subject device meets 21 CFR 800.30 requirements. Performance testing evaluated these differences in technology and the results support substantial equivalence. |
| Frequency response | 232 Hz to 7809 Hz | 100 - 10,000 Hz | Similar to predicate Both the subject and predicate device meet the requirements of 21 CFR 800.30 (e) for Frequency Response Bandwidth. |
| Self generated noise value | Max Self-Generated Noise: 25.2dBA | Max Self-Generated Noise: 28.2 dBA | The subject device meets 21 CFR 800.30 requirements. Performance testing evaluated these differences in technology and the results support substantial equivalence. |
| Harmonic distortion | Less than or equal to 2% | Less than or equal to 1% | The subject device meets 21 CFR 800.30 requirements. Performance testing evaluated these differences in technology and the results support substantial equivalence. |
| Maximum output value (Output Sound Pressure Level 90) (OSPL90) | Max OSPL90: 108.6 dB SPL | Max OSPL90: 105.93 dB SPL | The subject device meets 21 CFR 800.30 requirements. Performance testing evaluated these differences in technology and the results support substantial equivalence. |
Page 8 of 12
{12}
# 7. Summary of Non-Clinical Performance Testing
Hearing assist was tested for conformity to the following FDA recognized consensus standards applicable to the OTC air conduction hearing aids for the device's intended use.
| Electro-Acoustics | - ANSI S3.22: Specification of Hearing Aid Characteristics - ANSI/CTA-2051: Electroacoustics-Hearing aids-Measurement of electroacoustic characteristics |
| --- | --- |
| Software and labeling | - IEC 62304 Ed 1.1 (2015) Software life cycle - 21 CFR 800.30 (2022 Final Rule) |
| Electrical Safety and EMC | - IEC 60601-1:2005 + A1:2012 + A2:2020 - IEC 60601-2-66:2019 - IEC 60601-1-11:2015 + A1:2020 + A2:2022 - IEC 60601-1-2, AMDI:2020; Part 1-2 |
Testing was also performed to show conformance to the Special Controls for air-conduction hearing aid software, as specified in the De Novo classification order for software-only hearing aid features (DEN230081). Hearing assist passed all the relevant non-clinical performance tests with representative, compatible computing platform hardware (Smart Glasses) and was verified that the amplified acoustic signal output by the hardware platform is calibrated. Software verification and validation, testing against established standards for electrical safety, EMC, and battery safety were conducted using representative, compatible hardware (Smart Glasses) platforms to verify the amplified acoustic signal output. Supplementary electrical safety and EMC testing was completed to demonstrate compliance to the medical device standards listed above.
A bench performance comparison of gain between the subject and predicate devices was performed to further support substantial equivalence. Frequency-specific real-ear insertion gain (REIG) was characterized on a head and torso simulator (HATS) using a speech stimulus at a conversational input level, evaluated across four audiometric profiles representing mild through moderate hearing loss. The subject device achieved gains closely aligned with NAL-NL2 prescriptive targets and provided comparable amplification to the predicate.
## Human Factors and Usability Testing
Per Special Control 3 for an OTC medical device intended to be used without the support of a hearing healthcare professional, human factors and usability validation studies were conducted, in compliance with IEC 62366-1:2015. Test results demonstrated that end-users can correctly and safely perform all critical tasks for using the Hearing assist software medical device (SaMD) within a simulated use environment. This testing assessed the effectiveness of the user interface and supporting instructional materials, ensuring usability, minimizing the risk of user error, and confirming that users are able to navigate the system, understand instructions, and achieve successful device setup and routine operation. Representative users were able to complete all tasks without critical errors, and all defined acceptance criteria were met.
Page 9 of 12
{13}
## Clinical Data
Hearing assist was validated in a clinical investigation involving 142 subjects aged 18 years or older with mild to moderate hearing impairment, or perceived hearing difficulties with normal hearing thresholds. Subjects reflected the intended OTC user population and were enrolled based upon an audiological assessment of hearing thresholds defined by the four-frequency pure tone average (4PTA). The enrolled subjects were distributed across each of the following categories: No Impairment/Perceived Hearing Loss (4PTA: 15-25 dB HL), Mild Hearing Loss (4PTA: 26-40 dB HL), and Moderate Hearing Loss (4PTA: 41-60 dB HL). Subjects were also enrolled based on specific age and sex targets, representative of the intended patient population.
The study was performed at three clinical sites across the United States and conducted over two phases. Phase one was conducted in a clinical lab-based setting where hearing aids were fit and clinical assessments performed. The second phase was conducted in the participants' home and community over a 14-day period, where they could freely use their hearing aid device in their own natural listening environments. The study compared two groups: a self-fit (SF) group where subjects independently set up the hearing aid device, and a pro-fit (PF) group where the hearing aid device was set up and fitted by a licensed hearing care professional. Study success was determined by pre-specified primary and secondary endpoints. The primary endpoint was a measure of clinical effectiveness, assessed by the mean group-total score of the International Outcome Inventory for Hearing Aids (IOI-HA) survey. This was evaluated after 14 days of field use. The secondary endpoint was a measure of objective clinical benefit, determined by the average Speech-in-Noise performance using the Quick Speech-in-Noise (QuickSIN) test. All tests were designed to determine non-inferiority of clinical benefit between the SF and PF fitting methods.
The clinical investigation met all predefined objectives. For the primary endpoint, subjects in the SF group were able to achieve the same clinical benefit, compared with subjects who had their settings tuned by a licensed hearing care professional. The mean IOI-HA total scores for the SF and PF cohorts were 25.77 (SD = 4.28) and 26.81 (SD = 3.56), respectively. The mean difference (defined as SF – PF) between the two cohorts was -1.04 (SD = 3.93), with the 95% confidence interval of the mean difference being (-2.28, 0.24) and the p-value for the non-inferiority test being 0.004. Thus, the null hypothesis was rejected, and the SF group was found to be non-inferior to the PF group. Subgroup analyses indicated that the IOI-HA scores were consistent for both the SF and PF groups across hearing classification, age, sex, and race.
The secondary endpoint was also met. The mean SNR Loss scores for the SF and PF cohorts were 4.4 dB (SD = 5.7) and 4.2 dB (SD = 5.9), respectively. The mean difference (defined as PF – SF) between the two cohorts was -0.2 dB (SD = 2.4), with the 95% confidence interval of the mean difference being (-0.5, 0.3) and the p-value for the non-inferiority test being less than 0.001. Thus, the null hypothesis was rejected, and the SF group was found to be non-inferior to the PF group. Subgroup analyses indicated that the mean SNR Loss scores were consistent for both the SF and PF groups across hearing classification, age, sex, and race.
Additional objective measures were also made related to Speech-in-Noise and Real Ear Insertion Gain. A within-participant assessment of speech-in-noise performance showed an average signal-to-noise (SNR) benefit of 4.8 dB (SD = 5.3) with SF. This implies participants could understand speech more easily in noisy environments when using Hearing assist compared to without, reflecting an improvement in their ability to hear when background sounds
Page 10 of 12
{14}
are present. Real Ear Measures (REM) were also collected to assess objective differences in amplification between the SF and PF groups. REM results confirmed equivalent insertion gains across all speech input levels (50, 65, 75 dB SPL), consistent with non-inferior IOI-HA and SNR Loss outcomes.
During the course of the clinical investigation, all adverse events (AEs) were systematically recorded and analyzed. There were no unanticipated adverse device effects (UADE) or serious adverse device effects (SADE) reported. There were 6 adverse device effects (ADEs) reported by 5 out of 142 participants. Headache was the most commonly reported issue with 5 reports (2.5 events per 1000 observed days). There was 1 report of tiredness and fatigue (0.5 events per 1000 observed days). The reported issues are consistent with the expected safety profile of a Non-Significant Risk (NSR) device, as they do not pose a significant risk to the health, safety, or welfare of study subjects. Headache and fatigue are anticipated side effects for individuals using hearing aids, especially during the initial periods of use while they acclimate to a new device. Importantly, these side effects were reported to be mild and transient in nature, with all subjects fully recovering without any intervention. No subjects withdrew from the study as a result of these effects.
The study had a total of four serious adverse events (SAEs) experienced by 2 out of 142 participants, unrelated to the study device or procedures. One subject experienced a fall with injury and the other had a cardiac event. Both required hospitalization.
There was 1 out of 142 participants who withdrew from the study prior to study completion. Also, there were 5 important protocol deviations reported (4 participants with assessments outside the visit window and 1 participant who was not compliant with the device usage requirement). Robust sensitivity analyses demonstrate that these issues did not impact the study's findings. Overall, the clinical investigation provides reasonable assurance of the safety and effectiveness of Hearing assist. The findings generated from this clinical investigation provide substantial scientific evidence and reasonable assurance that the Hearing assist hearing aid is at least as safe and effective as the legally marketed predicate device (Apple HAF, DEN230081).
## 8. Predetermined Change Control Plan
Hearing assist contains a Predetermined Change Control Plan (PCCP) in accordance with 515(c) of the Federal Food, Drug and Cosmetic Act. The PCCP does not include provisions for implementation of adaptive algorithms that will continuously learn in the field. All algorithm modifications will be locked and validated prior to release of the software to the field.
The PCCP is for the addition of an Android mobile platform for the Hearing assist Smartphone App in addition to the iOS platform. The PCCP specifies verification and validation activities in place to implement the Android mobile platform in a controlled manner such that the device remains as safe and effective as the predicate device. The table below outlines the planned testing for implementing the Android mobile platform.
Page 11 of 12
{15}
| Planned Change | Requirements | Test Method |
| --- | --- | --- |
| Launch of Android mobile platform for the Hearing assist smartphone application | - No change to input type - No change to output type - No changes to any other modules of the Hearing assist feature - No change to the intended use - Can be fully verified through requirements specified in the protocol - Cybersecurity requirements for Android mobile platform | Meet the functional and performance requirements as outlined in product requirements. Relevant/applicable cybersecurity testing will be conducted to support the launch of the Android mobile platform. |
## 9. Conclusion
The results of the performance testing described above demonstrate that the Hearing assist is as safe and effective as the predicate device (Apple HAF, DEN230081) and supports a determination of substantial equivalence.
Page 12 of 12
Predicate graph will load when search results are available.
Embedding visualization will load when search results are available.
PDF viewer will load when search results are available.
Loading panels...
Select an item from Submissions
Click any panel, subpart, regulation, product code, or device to see details here.
Section Matches
Results will appear here.
Product Code Matches
Results will appear here.
Special Control Matches
Results will appear here.
Loading collections...
Loading
My Alerts
You will receive email notifications based on the filters and frequency you set for each alert.
Sort by:
Create Alert
Search Filters
Agent Token
Create a read-only bearer token for Claude, ChatGPT, or other agents that can call HTTP APIs.
Copy this now. It will not be shown again.
Connected apps
Apps you authorized through browser sign-in. Disconnecting revokes their access immediately.
Learn the FDA Browser
Two short videos show you everything — or skip straight to the written tutorial if you'd rather read. You can reopen this any time from the Tutorial button in the top bar.
Part 1 — Search, results, and everyday workflows 16 min
Part 2 — Embeddings: the galaxy map 3 min
1. Search: exact and fuzzy
Type a phrase like "coronary artery calcification" into the search box. You get two kinds of results. Exact results match the literal phrase — prefix searches work ("coronary artery calcificati") but suffix searches do not. Fuzzy results match on the meaning and intent of your phrase rather than the exact words, and are sorted by relevance score. Hover over the Exact or Fuzzy badge on any row to see exactly why it matched.
Use the checkboxes above the results to narrow: SaMD keeps only software-only devices, AI / ML keeps only devices with AI.
Exact vs. fuzzy search: what's the difference?
Exact matches on the literal phrase (prefix search works, suffix does not). Fuzzy matches on the meaning and intent of the phrase rather than the exact words. Hover over the badge on any row to see why it matched.
You search "coronary artery calcification" and want only software devices with AI. What two filters do you apply?
Narrow by SaMD (software-only devices), then narrow by AI/ML (devices with AI).
2. The results table
Scroll right in the results table. The intended use is extracted for you — no need to open the PDF. The device story gives a high-level snapshot of what the device does and how it's used. The AI Performance sub-table shows each output name, acceptance criteria, observed values, and development/test dataset descriptions — the same format Innolitics uses for regulatory strategy outputs, and the fastest high-level fingerprint of an AI device. It is AI-generated but has been very reliable in practice.
Where do you find a device's intended use without opening the PDF?
Scroll right in the search results table. The intended use column is extracted for you; no need to dig into the 510(k) summary PDF.
What does the AI Performance sub-table show, and why is it useful?
Output name, acceptance criteria, observed values, development dataset description, and test dataset description. It's the same format we use for regulatory strategy output and Fast 510(k) input, and the fastest high-level fingerprint of an AI device. AI-generated but reliable in practice.
3. Judging fuzzy relevance
Fuzzy results trail off in relevance as you scroll. Use three signals to decide how far down to go: the fuzzy badge explanations, the intended use column, and whether your target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, you're past the relevant zone. A top hit with a low score (~0.4) and a stretched explanation is a hint the closest predicates are far away — the project may be headed for De Novo. Note the fuzzy search is a pattern match: it doesn't handle negation ("not") well, and hardware devices can appear — filter by SaMD/AI ML to cut them.
How do you judge how far down fuzzy search results to go?
Use the relevancy signals: the fuzzy badge explanations, the intended use column, and whether the target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, results are trailing off in relevancy.
4. Device detail page: chat and citations
Click a device name to open its detail page: device facts on the left, a chat window on the right. Ask something like "Describe the training data". The answer carries little citation bubbles — click one to jump to the highlighted passage in the source PDF, so you can verify every AI answer against the document. There's also a Download PDF button for sharing.
How do you verify an AI chat answer on the device detail page?
Click the citation bubbles to jump to the relevant highlight in the source document.
Reading rule for every project: how many summaries do you read in full?
At least the three most relevant 510(k) or De Novo summaries, in full. After that, use targeted chat questions to confirm your memory quickly. The tool supports this professional habit — it doesn't replace it.
5. Side-by-side comparison
Select multiple rows in the results table (aim for under ~10), then open the PDF Viewer tab. Ask one question — it goes to all selected devices in parallel, each with citations. This is the fastest way to compare and contrast devices: training data, PCCP scope, how they handled adding new scanners, and so on.
What does the side-by-side PDF viewer mode do?
Select multiple devices, open the PDF viewer tab, and ask one question (e.g., "Describe the training data"). It queries all selected devices simultaneously with citations, so you can compare and contrast quickly.
6. Collections
With rows selected, go to the Collections tab and create a labeled collection (e.g., "Cobb Angle Project"). Reload that selection any time — before a client call, pull up the collection and ask questions across all of its devices at once.
How do you save a set of selected devices for later use?
Select the rows, go to the Collections tab, and create a labeled collection (e.g., "Cobb Angle Project"). You can reload the selection anytime and carry it into the PDF viewer and other tabs that support selections.
7. Product codes and the regulations tree
Click a product code in the results to jump to it in the regulations tree — identification text, sibling product codes, and devices you can open in a PDF viewer on the right. Click a regulation number to see its identification, special controls, and related product codes. You can also search by product code or regulation number at the top of the tree. Always read the special controls if any exist for your device — it broadens your search and sharpens pre-kickoff research.
What can you do from the regulations tree view?
Browse product codes and regulation numbers, read the identification text and special controls, browse sibling product codes, open device PDFs on the right, and search by product code or regulation number at the top of the tree.
8. Chart view
Click Show Chart and segment by regulation number (or product code) to see which regulations dominate your result set. Clicking a regulation takes you into the regulations tree. Great for spotting that most matches are, say, hardware laparoscopic devices — a cue to go back and filter.
How do you see which regulations dominate a search result set?
Click "Show Chart" and segment by Regulation Number. Clicking a regulation takes you to the regulations tree.
9. The predicate graph
Open the Predicates tab for a family-tree view of predicate relationships. Click a node to trace its parents and children; selections from search carry over pre-selected. Commonly predicated devices are worth reading — a lot of people predicated them for a reason. The visual lineage is also handy on client calls, e.g. to show how a predicate family evolved and justify why your predicate still holds.
In the predicate graph, why are commonly predicated devices worth reading?
A lot of people predicated them for a reason. Clicking a node traces parents and children, and selections from search carry over pre-selected.
10. Embeddings: the galaxy map
The Embeddings tab plots every matching document in a 2-D "galaxy map" where semantically similar devices cluster together. Hover or click clusters to explore, and let AI label the clusters for you. Embeddings beat product codes for grouping: two devices can carry different product codes (LLZ vs. QIH) yet do the same thing — the embedding captures the meaning of the intended use and device story. This is also exactly how retrieval-augmented generation (RAG) works under the hood, and it makes a great visual on client calls.
Try it yourself
Head to the search page and work through a few of these AI/ML fuzzy searches to build intuition: perivascular fat on CT · aortic valve calcification opportunistic screening on noncontrast CT · breast cancer prediction on digital pathology slides · autism detection · gestational age prediction · a hearing aid that can also detect a pulse · foundation model based analysis of ECG · large language models · penetration test. Watch how the relevance scores, intended use, and AI Performance tables tell you when results stop being meaningful.