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

This Otonova Pro device is indicated for use when there is a requirement to screen for hearing disorders by objective and non-invasive means. ABR, TEOAE and DPOAE screening test results are automatically interpreted and a clear "Pass' or 'Refer' result is presented to the user. Use of the device is indicated when the patient is unable to give reliable voluntary responses to sound, especially with infants.

Use of the device facilitates the early detection of hearing loss and its characterization. Where the individual to be screened is healthy with no medical conditions related to the ear, as in the case of well-baby hearing screening, the user can be a trained screener. In all other cases the user should be an audiologist or medical professional.

The TEOAE and DPOAE analytical functions of the device are indicated when objective non-invasive clinical investigations require the characterization and monitoring of the peripheral auditory function. For this purpose, the device is intended to be used by audiologists or other professionals skilled in audiology.

These TEOAE and DPOAE tests are applicable to populations of any age to obtain objective evidence of peripheral auditory function.

OtoNova is a compact, portable battery-powered electronic device which records physiological responses to sound for the purpose of hearing testing. It Is controlled wirelessly from a local controlling device.

OtoNova has two hardware variants: OtoNova and OtoNova Pro.

Both the OtoNova and OtoNova Pro devices have been directly engineered from Otodynamics' currently marketed Otoport OAE+ABR device, retaining all the testing algorithms of the Otoport OAE+ABR device. The primary aim of the development was to physically separate the control console from the testing device while maintaining the same performance and effectiveness.

Like the predicate Otoport OAE+ABR device, both OtoNova devices can record two different physiological indicators of a functioning auditory system's peripheral response to sound namely a) Otoacoustic emission (OAEs), which are small sounds made by the inner ear in response to acoustic stimulation, and b) Auditory brainstem responses (ABRs) are tiny electrical signals emanating from the auditory brainstem in response to sound. Automatic recognition of an ABR response is referred to as AABR.

During ABR or OAE testing, low-level sounds are delivered to the ear. The responses to multiple presentations of these sounds (either acoustic or electrical responses) are recorded digitally and added together to enhance repeated responses with respect to the random/ noise signals that are always present. The averaged signal is automatically analysed by the device to identify and quantify true physiological response component and to assess the degree of noise contamination. This allows the quality/ accuracy of the recording to be determined for evidence of response validity. The processed data is reported to and displayed on the controlling device.

The provided text describes the regulatory clearance (K234095) for the Otodynamics OtoNova/OtoNova Pro device, comparing it to its predicate device, the Otoport/Otocheck OAE+ABR (K143395). The document focuses on demonstrating substantial equivalence, rather than detailing a specific clinical study with predefined acceptance criteria for AI model performance.

However, based on the information provided, we can infer the acceptance criteria and the study that "proves" the device meets them, primarily through the lens of functional equivalence and clinical agreement with a well-established predicate device. The core argument is that the OtoNova/OtoNova Pro performs audiological tests substantially the same as the predicate device, despite changes in physical design and user interface.

Here's an analysis based on the provided text, structured to answer your questions:

Inferred Acceptance Criteria and Reported Device Performance

The acceptance criteria are not explicitly stated with quantitative metrics for the new device. Instead, the performance is deemed acceptable if it is "substantially the same" or "similar" to the predicate device, which is already legally marketed and presumed efficacious. The "study" is a combination of bench testing and a small clinical validation aimed at demonstrating this equivalence.

Here's a table based on the comparisons made in the document:

Study Details:

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

2. Sample sized used for the test set and the data provenance:

   • Clinical Testing: "data collected from 20 volunteer adult subjects" for functional equivalence comparison between OtoNova Pro and the predicate Otoport. The text does not specify the country of origin, but the company is based in the UK and the prior validation of the predicate included trials in "USA, Brazil, Israel and UK," implying international data.
   • Clinical Testing (Predicate Validation): The predicate's ABR infant screening algorithm was validated on "70 infants performed at Otodynamics Ltd" and independently trialed in "collaborating hospitals in USA, Brazil, Israel and UK." The algorithm was validated from "1078 tests files." This data is retrospective for the predicate's prior clearance, but serves as the basis for asserting current device's equivalence.
   • Human Factors/Usability Testing: "16 participants external to Otodynamics." Provenance not specified but likely conducted in the UK given the company's location.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

   • For the current device's clinical testing, the "ground truth" is highly comparative to the predicate device's output. The subjective assessment of "similar," "no wider than," and "within expected tolerance" implies expert judgment, but the number and qualifications of experts involved in data interpretation for this specific equivalence trial are not provided.
   • For the predicate's ABR template, it was derived from a database of "1000 infant's ABR screening response waveforms independently collected using the Otodynamics ILO88 instrument... as part of a multicenter investigation into the Identification of Neonatal Hearing Impairment." This suggests a consensus-based ground truth from a large research study, likely involving multiple clinical experts (audiologists, researchers specialized in neonatal hearing). Their specific qualifications aren't listed, but the citation to a scientific publication (Norton et al., 2000) implies peer-reviewed clinical expertise.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not explicitly stated. Given the nature of objective audiometric measurements (Pass/Refer based on algorithms comparing to criteria, and quantitative signal levels), adjudication in the typical sense of human reader consensus for subjective interpretations (like radiology reads) is less applicable. The "ground truth" is intrinsically linked to the device algorithms and their comparison to the predicate's algorithms, which are well-established.

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: Not applicable. This device is not an AI interpretation model for human readers. It's a diagnostic/screening device that produces objective measurements and automatically interpreted Pass/Refer results. The "AI" (automated interpretation) is core to the device's function, not an assistance tool for human interpretation.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Yes, in essence, the "bench tests" and the comparison of the algorithms' outputs (Pass/Refer, quantitative levels) can be considered a standalone assessment of the device's core functionality as an automated system. The device automatically analyzes the recorded physiological responses and presents a clear "Pass" or "Refer" result, which is the algorithm's standalone output.

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

   • Primary Ground Truth: For the current device, the ground truth is established by functional and clinical equivalence to a legally marketed predicate device. The presumption is that the predicate's performance is already validated against a clinical ground truth.
   • Underlying Ground Truth (for predicate's algorithms):
     • OAE Screening: Based on the "Rhode Island Hearing Screening Assessment Project" and its reported algorithm, which was verified against clinical outcomes or established audiometric standards for hearing screening.
     • ABR Screening: Derived from a database of "1000 infant's ABR screening response waveforms Independently collected" as part of a "multicenter investigation into the Identification of Neonatal Hearing Impairment" (Norton et al., 2000). This implies a large-scale clinical dataset with established diagnoses/outcomes as the ultimate ground truth for the ABR algorithm's development.

8. The sample size for the training set:

   • The document explicitly states that the OtoNova/OtoNova Pro uses the "same DSP firmware algorithms" as the predicate device. Therefore, there was no new training set specifically for this device's algorithms.
   • The training data implied for the predicate's ABR algorithm development was a database of "1000 infant's ABR screening response waveforms." This served as the basis for the "newborn ABR template" used by both devices.
   • The OAE algorithm's "training" or validation was performed as part of the "Rhode Island Hearing Screening Assessment Project," though no specific sample size for a "training set" is provided for that.

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

   • For the ABR "training" (template creation): The "newborn ABR template" was derived from "1000 infant's ABR screening response waveforms independently collected." The ground truth for these 1000 waveforms would have been established through a comprehensive clinical protocol, likely involving repeated measures, follow-up diagnostics, and potentially consensus interpretation by expert audiologists from the multicenter investigation. The goal was to characterize "normal" ABR responses in neonates.
   • For the OAE algorithm: While not explicitly detailed as a "training set," the underlying principles and validation came from the "Rhode Island Hearing Screening Assessment Project," suggesting that the "Pass/Refer" criteria were correlated with actual hearing status as determined by more definitive diagnostic tests, forming the ground truth.

Ask a specific question about this device

The Otoport Pro device is indicated for use when there is a requirement to screen for hearing disorders by objective and non-invasive means. ABR, TEOAE and DPOAE screening test results are automatically interpreted and a clear "Pass' or 'Refer' result is presented to the device is indicated when the patient is unable to give reliable voluntary responses to sound, especially with infants. Use of the device facilitates the early detection of hearing loss and its characterization.

Where the individual to be screened is healthy with no medical conditions related to the ear, as in the case of well-baby hearing screening, the user can be a trained screener. In all other cases the user should be an audiologist or medical professional.

The TEOAE and DPOAE analytical functions of the device are indicated when objective non-invasive clinical investigations require the characterization and monitoring of the peripheral auditory function. For this purpose, the device is intended to be used by audiologists or other professionals skilled in audiology. These TEOAE and DPOAE tests are applicable to populations of any age to obtain objective evidence of peripheral auditory function.

The Otodynamics Ltd ("Otodynamics") Otoport Pro device is a compact handheld device capable of high quality OAE measurements for clinical purposes and also automated ABR and OAE testing for fast infant screening.

Responses to sound are recorded via an applied earphone and or adhesive surface electrode pad. Specifically, the device can record Otoacoustic Emissions (type DPOAEs or TEOAEs) and auditory brainstem responses (ABRs) to sound. These responses are especially useful in the hearing of infants for deafness. The more detailed analysis of DPOAE and TEOAE responses is additionally useful as a component of the audiological diagnostic test battery.

The Otoport Pro is simple to use with customizable automation to make testing easy and the results clear. It has user access controls, graphical display panel, and extensive test database features. The Otoport Pro when configured for clinical use has advanced test features including extensive raw data capture for offline review and analysis if required.

Otoport Pro device is a hardware/ software revision of the currently marketed Otoport OAE+ABR, having the same performance and intended uses as the Otoport OAE+ABR device.

Here's a breakdown of the acceptance criteria and study information for the Otoport Pro device, based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

The document describes the performance of the Otoport Pro in comparison to its predicate device (Otoport OAE+ABR, K143395) rather than setting distinct acceptance criteria with specific threshold values. The primary acceptance criterion appears to be demonstrating substantial equivalence in performance to the predicate device.

Ask a specific question about this device

hearOAE is intended to be used by hearing healthcare professionals in the audiologic evaluation and documentation of ear function and ear disorders using Transient Evoked Otoacoustic Emissions (TEOAEs) and Distortion Product Otoacoustic Emissions (DPOAEs). The target population for the hearOAE includes all ages.

Per 21 CFR 874.1050, the hearOAE (otoacoustic emission device) is a portable, handheld, battery-operated device that can detect hearing loss using Otoacoustic Emission technologies. The hearOAE device may be configured to support one or any combination of TEOAE or DPOAE. Otoacoustic Emission devices are class II medical devices.

hearOAE consists of three main components listed below:

• hearOAE Application (available on supported Android devices supplied by i hearX)
• hearOAE Codec
• hearOAE Probe

The hearOAE Application:

• is operated on an Android smart device that uses Bluetooth connectivity to communicate with the hearOAE Codec.
• enables the user to choose and set up testing protocols for both TEOAE and DPOAE.
• enables the checking of the probe functionality, namely "Probe Check".
• controls the start and stop of a TEOAE and DPOAE test including pre-test functions such as Probe Check and in-ear calibration.
• provides feedback during and after the test in the form of tables, figures, and graphs.

The hearOAE Codec:

• consists of hardware and software for generating the test signals and measuring the responses.
• has the ability to generate, measure and process signals.
• contains a rechargeable lithium-ion battery to power the device.
• uses three light indicators to provide a visual display of the status of the hearOAE Codec to the user. A push button (signified by a Power symbol) is located on the case of the hearOAE Codec to allow the user to switch it on or off.
• communicates the test results via Bluetooth to the hearOAE smart device which will be displayed on the Smart device screen to the user within the application.

The hearOAE Probe:

• houses the speakers (drivers), and a microphone that produces the test stimuli and measures the sound pressure level (SPL) present in the ear canal.
• has a removable probe coupler with ear tips which fit onto the probe coupler.

Here's an analysis of the acceptance criteria and study detailed in the provided document:

Acceptance Criteria and Device Performance

• IEC 60645-6:2022 (Electroacoustics - Audiometric equipment – Part 6: Instruments for the measurement of otoacoustic emissions)
• IEC 60601-1:2005+A1:2012 (Basic Safety and Essential Performance)
• IEC 60601-1-2:2014 (Electromagnetic Compatibility)
• ISO 10993-1:2009 (Biocompatibility)
• IEC 62304:2006+A1:2015 (Software Verification and Validation)
• FDA Guidance for Cybersecurity
• IEEE / ANSI C63.27:2017 & AAMI TIR 69:2020 (Bluetooth SIG Compliance) | All tests passed. |
  | Clinical Study (Adults) - Test-retest Reliability (DPOAE & TEOAE) | 95% CI of the test-retest difference of the hearOAE signal, noise, and SNR had to be within a -3.0 to 3.0 dB SPL (lower and upper limit) margin. | For DPOAE, 95% CI for signal, noise, and SNR differences were within a 3 dB SPL margin across frequencies. For TEOAE, 95% CI for test-retest differences fell within a 3 dB SPL margin. |
  | Clinical Study (Adults) - Validity (DPOAE & TEOAE) | For DPOAE: 95% CI lower limit of the signal difference between the hearOAE and predicate device was no less than -3.0 dB SPL across frequencies.
  For TEOAE: (Implicitly, similar to DPOAE criteria for signal difference from predicate) | For DPOAE, differences between hearOAE and the predicate device were non-significant across all frequencies (excluding 3kHz). All but 3 kHz met OAE signal acceptance criteria (lower 95% CI limit ≥ -3.0 dB SPL). Although 3 kHz was slightly outside (-0.5 dB SPL), the device was deemed compliant.
  For TEOAE, all frequencies met the TEOAE signal acceptance criteria (lower 95% CI limit ≥ -3.0 dB SPL). |
  | Clinical Study (Infants) - Screening Outcomes | High device agreement (> 85%) for screening DPOAEs and TEOAEs between the investigational device and the comparator device in terms of Pass/Refer rates, mean signal, noise and SNR. | For DPOAE, within-participant diagnostic concordance between the two devices was 89.7%.
  For TEOAE, within-participant diagnostic concordance of 85% was measured between devices. |

Study Information

• Sample size used for the test set and the data provenance:

  • Adults (Sub-aim A):
    • DPOAEs: 78 adult ears (58 normal hearing; 20 with hearing loss).
    • TEOAEs: 90 adult ears (66 normal hearing; 24 with hearing loss).
  • Infants (Sub-aim B):
    • DPOAE screening: 175 infant ears.
    • TEOAE screening: 174 infant ears.
  • Data Provenance: The study was conducted in South Africa, as indicated by the location of the submitting company (hearX SA (Pty) Ltd) and the recruitment from "three public healthcare hospitals" for newborn hearing screening. The study design (cross-sectional, within-subject repeated measures) suggests prospective data collection for the clinical comparison.

• Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

  • The document implies that "qualified and Health Professions Council of South Africa (HPCSA) registered audiologists with prior knowledge of ears and hearing as well as prior OAE device experience" were used to operate both the investigational and predicate devices and conduct the assessments. It does not specify the number of distinct experts used for ground truth establishment if that ground truth was separate from the device readings themselves. For the adult portion, the comparator device (Otodynamics ILO288 Echoport Plus OAE System) served as a "gold standard" for validity, and the audiologists followed established audiometric procedures (e.g., pure tone audiometry for hearing loss classification) to determine participant groups. For infants, the "Pass/Refer" rates from both devices were compared, with the predicate serving as the benchmark for agreement.

• Adjudication method for the test set:

  • The document describes a "cross-sectional, within-subject repeated measures design" where "the diagnostic OAE test with each device was repeated in each ear in order to determine test-retest reliability." For validity, the hearOAE was compared against the predicate device. For screening infants, "diagnostic agreement of the investigator device and comparator device" was measured. This suggests a direct comparison method rather than an adjudication by a separate panel to establish a distinct "ground truth" that differed from the device readings or the predicate device's output. The comparison itself served as the adjudication.

• 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 was not an MRMC study in the typical sense of evaluating human reader performance with and without AI assistance for interpretation. It's a device comparison study where human healthcare professionals (audiologists) use the devices. The study compares the performance of a new device (hearOAE) to an existing predicate device, focusing on technical performance and diagnostic agreement, not on improving human reader interpretation with AI.

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

  • No, a standalone (algorithm only) performance study was not described. The hearOAE device is operated by "hearing healthcare professionals" and involves a "human-in-the-loop" for setting up tests, performing "Probe Check," and interpreting results displayed on a smart device.

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

  • The ground truth varied:
    • For adult participant classification (normal hearing vs. SNHL): Behavioral pure tone air conduction audiometry thresholds were used as the basis for classifying normal hearing (PTA ≤ 25 dB HL) and SNHL (air conduction PTA > 25 dB HL, bone conduction within 10 dB HL of air conduction). This is an established clinical diagnostic method.
    • For device performance validation: The predicate device (Otodynamics ILO288 Echoport Plus OAE System) served as the comparator or "reference" for evaluating the hearOAE's DPOAE and TEOAE signals, noise, and SNR, and for determining diagnostic agreement in infants.
    • For test-retest reliability: The concept of test-retest reliability inherently uses repeated measures from the same device on the same subject as its own internal ground truth for consistency.

• The sample size for the training set:

  • The document describes a clinical validation study, not a study for training an AI model. Therefore, there is no mention of a "training set" in the context of machine learning.

• How the ground truth for the training set was established:

  • As no AI model training was described, there is no information on how a training set's ground truth would have been established.

Ask a specific question about this device

Devices of the Sentiero device families offer different test methods which can be configured to fit the professional's needs for hearing screening or diagnostics and vestibular diagnostics (Sentiero Advanced only),

Available psycho-acoustical methods on Sentiero devices are especially indicated for use with cooperative patients starting at the age of two years or adequate development age, which enables them to do play/interactive audiometry. Physiological modules which require active paticipation (e.g. VEMP) are indicated for use with cooperative patients who are mentally and physically able to perform the required task. All other physiological modules are suitable to be used for all ages elder than infants from 34 weeks (gestational age) that are ready for discharge from the hospital.

Sentiero is an audiometric examination platform which consists of the Sentiero device with a touch screen display together with different accessories such as mains adapter, OAE probes, headphones, bone conductor, electrode cable, ear coupler cable, patient response switch. These accessories can be connected to Sentiero based on a special plug, which holds the information about the connected transducer / cable. Therefore, the firmware can make use of this information and adapt the measurement procedures accordingly or provide information to the user via its display.

Furthermore, each model can be configured to allow different test methods and features (modules) by a license key in the device. Sentiero is based on configurable modules. Sentiero can have one single module or a combination of multiple.

The measurement application is controlled from a self-contained firmware. The measurement flow is menu guided on a touch screen. Evaluation of test results is based on signal statistics (if available for the test method). Besides that, wave forms and result information are displayed for the user's evaluation.

The patient/test data can be transferred from the device to a PC via a USB connection and the accompanied data management and archiving software MRA. Patient/test data on the PC software can be password- protected so that unauthorized access is prohibited.

Compared to the original 510(k) submission of the Sentiero in its predicate state, the Sentiero now offers a VEMP test module. Vestibular evoked myogenic potential (VEMP) is a short latency muscle reflex driven by otolithic organs that play a major role for detecting the orientation, static balance and linear acceleration of the head. Vestibular dysfunctions arise from various different regions along the vestibular pathway. Vestibular neuritis, vestibular schwannoma, multiple sclerosis or Meniere's disease will be indicated by the decrease or absence of VEMP responses.

The provided text describes a 510(k) premarket notification for a medical device called Sentiero, specifically addressing the addition of a Vestibular Evoked Myogenic Potential (VEMP) module. The document focuses on demonstrating substantial equivalence to a predicate device and a reference device, rather than presenting a performance study with detailed acceptance criteria of an AI/ML powered device.

Therefore, many of the requested criteria for acceptance and proof of performance relating to AI/ML devices (e.g., sample size for test set with provenance, number of experts for ground truth, MRMC studies, standalone AI performance, etc.) are not applicable to this submission, as the Sentiero device and its VEMP module are described as audiometric examination platforms with physiological test procedures, and do not appear to incorporate AI/ML algorithms that would require such performance evaluations.

However, I can extract information related to the device's functional performance and its verification and validation.

Here's a breakdown of the available information based on your request, highlighting what is present and what is not applicable:

1. A table of Acceptance Criteria and the Reported Device Performance

The document does not explicitly state "acceptance criteria" in the typical sense of a target metric for an AI/ML algorithm's performance (e.g., "AUC must be > 0.90"). Instead, it demonstrates the device's appropriate functionality and reliability through testing.

The primary performance data provided is related to the repeatability and reliability of the VEMP measurements.

2. Sample size used for the test set and the data provenance

• Test Set Sample Size: 16 normal hearing adults.
• Data Provenance: Not explicitly stated, but the submission is from a German company (Path Medical GmbH, Germering, Bavaria, Germany), implying that the clinical evaluation data likely originated from Europe, potentially Germany. The study is prospective as it describes "conducted tests" with "test subjects."

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

This is not applicable in the context of AI/ML algorithm evaluation for this device. The device itself is an audiometric instrument that records physiological signals (VEMPs). The "ground truth" for VEMP measurements is the actual physiological response (P1, N1 latencies, interpeak amplitude). The device's role is to accurately capture and display this response. Interpretation of these results for diagnosis is explicitly stated to be performed by an "ENT specialist."

4. Adjudication method for the test set

Not applicable. Since the device measures physiological signals, there's no diagnostic "ground truth" adjudicated by multiple experts for the device's output itself. The measurements (latencies, amplitudes) are derived from the recorded waveforms.

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

Not applicable. This device does not incorporate AI to assist human readers/clinicians in interpretation or diagnosis. It is a measurement tool.

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

Not applicable. The device is an instrument operated by a healthcare professional. There is no AI algorithm that performs a standalone diagnosis or interpretation. The performance tested is the accuracy and consistency of its measurements as a medical device.

7. The type of ground truth used

The "ground truth" is the physiological VEMP response itself, measured by the device. The study design ("Repeatability [Coefficient of variation]" and "Reliability [Coefficient of variation]") indicates that the device's ability to consistently and accurately measure these expected physiological parameters (P1 latency, N1 latency, Interpeak latency, Interpeak Amplitude) from repeated tests was evaluated. The comparison is against established academic literature for typical VEMP findings.

8. The sample size for the training set

Not applicable. This is a medical device that measures physiological signals, not an AI/ML model that requires a "training set" in the computational sense. The core technology is signal acquisition and processing based on established audiometry principles.

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

Not applicable. (See point 8).

Ask a specific question about this device

The Audera Pro is intended to be used for the stimulation, recording and measurement of auditory evoked potentials, vestibular evoked myogenic potentials, auditory steady state responses and otoacoustic emissions. The device is indicated for use in the evaluation, identification, documentation and diagnosis of auditory and vestibular disorders. The device is intended to be used on patients of any age.

The Audera Pro is intended to be used by qualified medical personnel such as an audiologist, physician, hearing healthcare professional, or trained technician. The Audera Pro is intended to be used in a hospital, clinic, or other healthcare facility with a suitable quiet testing environment.

The anatomical sites of contact for auditory evoked potential (AEP) testing are the patient's ear canal (with the contact object being a sound delivery eartip or headphone, or an ear probe and eartip) and the patient's scalp and possibly other body sites (with the contact object being a bone transducer or electrodes that are capable of measuring bio-potentials). The anatomical sites of contact for vestibular evoked myogenic potential (VEMP) testing are the patient's ear canal (with the contact object being a sound delivery eartip or headphone, or an ear probe and eartip) and the patient's head and neck and possibly other body sites (with the contact object being a bone transducer or electrodes that are capable of measuring bio-potentials). The anatomical sites of contact for otoacoustic emission (DPOAE, TEOAE) testing are the patient's ear canal (with the contact object being an ear probe and eartip).

The device is a configurable platform used to aid in the screening and diagnosis of sensory-neural and hearing conditions. It is capable of performing the following procedures: Auditory Evoked Potentials (EP), Auditory Steady-State Response (ASSR), Distortion Products Otoacoustic Emissions (DPOAE), Transient Evoked Otoacoustic Emissions (TEOAE), and vestibular evoked myogenic potentials (VEMP). The device system consists of a laptop PC with Windows 10 Pro, placed on top of or beside a specialized hardware implementation interface (i.e. platform) for the procedures. Software in the laptop controls the specialized hardware and collects and analyzes the resulting signals. Transducers and various accessories connect to the specialized hardware via connectors on the back of the hardware package.

The provided FDA 510(k) summary for the GSI Audera Pro describes acceptance criteria and studies primarily through comparison to predicate devices and adherence to international standards.

Here's the information broken down as requested:

1. Table of Acceptance Criteria and Reported Device Performance

The device's acceptance criteria are framed in terms of meeting the requirements of various international standards and demonstrating comparability to predicate devices. The "Reported Device Performance" column reflects the conclusions drawn from the testing against these standards or the comparison to the predicates.

2. Sample size used for the test set and the data provenance

The document does not specify a "sample size" in terms of patient data or clinical cases for a test set. The studies described are primarily non-clinical bench testing and comparative technical assessments against predicate devices and international standards. Therefore, there's no mention of data provenance (e.g., country of origin) as clinical data was not used.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

Not applicable. As clinical testing was not performed and the studies were non-clinical bench tests and comparisons to predicate devices, there was no need for experts to establish ground truth in the context of patient diagnoses or outcomes. The "ground truth" for these tests would be the established specifications and performance characteristics defined by the relevant international standards and the predicate devices.

4. Adjudication method for the test set

Not applicable. Given that the studies were non-clinical bench tests and comparisons to predicate devices, there was no independent adjudication of results in the way it would be done for a clinical study with multiple human readers. The evaluation methods included "Bland-Altman analyses and correlation coefficient comparison" for the module comparison, which are statistical methods rather than adjudication by experts.

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 MRMC study was performed. The device is not an AI-assisted diagnostic tool that would typically involve human readers interpreting results. It is an "Evoked Response Auditory Stimulator" used for physiological measurements.

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

This concept doesn't directly apply because the device is hardware and software for stimulation, recording, and measurement of biological responses, not an algorithm providing a diagnosis or interpretation in a standalone capacity that would typically interface with human practitioners in an AI context. The performance evaluations described are of the device's ability to accurately generate and measure these physiological signals.

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

For the non-clinical studies described:

• International Standards: The primary "ground truth" for electrical safety, EMC, EMG, calibration, OAE, and ABR measurements are the specifications and performance requirements detailed within the referenced IEC and ISO standards (e.g., IEC 60601-1, IEC 60645 series).
• Predicate Device Performance: For the module comparison, the performance characteristics of the legally marketed predicate devices (K163326 and K061443) served as the benchmark for demonstrating comparability.
• Product Design Requirements: For software, cybersecurity, and mechanical evaluations, the established design requirements and FDA guidance documents served as the "ground truth" or criteria for successful performance.

8. The sample size for the training set

Not applicable. This device is not an AI/ML model that undergoes a training phase with a dataset. It is a medical device system built on established principles of electronics, signal processing, and audiometry.

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

Not applicable, as there is no training set for this type of device.

Ask a specific question about this device

The Lyra with DPOAE is intended for use in the audiologic evaluation and documentation of ear disorders using Distortion Product Otoacoustic Emissions. The target population for Lyra with DPOAE includes all ages.

The Lyra with TEOAE is intended for use in the audiologic evaluation of ear disorders using Transient Evoked Otoacoustic Emissions. The target population for Lyra with TEOAE includes all ages.

The Lyra System is to be used by trained personnel only, such as audiologists, ENT surgeons, doctors, hearing healthcare professionals or personnel with a similar level of education. The device should not be used without the necessary knowledge and training to understand its use and how results should be interpreted.

The device is audiometric equipment used for assisting of inner ear abnormalities. Lyra features a hardware unit connecting to a PC installed with IA OAE suite software designated for use with Lyra. The PC software provides a user interface designed to integrate in the standard Microsoft Windows environment. Lyra can be purchased with various licenses allowing you to perform different hearing screening tests.

Distortion product otoacoustic emissions (DPOAE) technology uses pairs of pure tones presented in sequence to screen patients for cochlear hearing loss. Responses to the stimulus are predictable and therefore can be measured via a sensitive microphone placed in the patient's ear canal.

Transient otoacoustic emissions (TEOAE) technology uses a short duration stimulus to screen patients for cochlear hearing loss. Responses to the stimulus are predictable and therefore can be measured via a sensitive microphone placed in the patient's ear canal. The response can be divided into frequency bands for assessment.

The provided text describes a 510(k) premarket notification for an audiometric device named Lyra. The submission asserts the substantial equivalence of the Lyra device to legally marketed predicate devices (Titan™ TEOAE and Titan™ DPOAE).

However, the documentation does not contain information related to acceptance criteria, a specific study proving the device meets acceptance criteria, sample sizes for test or training sets, data provenance, the number or qualifications of experts, adjudication methods, MRMC studies, standalone algorithm performance, or how ground truth was established beyond general statements about design verification and validation against standards.

The document primarily focuses on establishing substantial equivalence based on:

• Identical Indications for Use: Both Lyra and the predicate devices are intended for audiologic evaluation and documentation of ear disorders using Distortion Product Otoacoustic Emissions (DPOAE) and Transient Evoked Otoacoustic Emissions (TEOAE) for all ages, to be used by trained personnel.
• Similar Technological Characteristics: The document provides detailed comparison tables highlighting that Lyra shares virtually all key technological characteristics (e.g., type, regulation number, product code, target population, intended user, anatomical sites, safety and performance standards, device type, system configuration, stimulus types, frequency ranges, levels, level steps, transducer, probe detection, recording, A/D resolution, artifact reject system, automatic test with display of PASS-REFER) with the predicate devices.
• Non-Clinical Testing Summary: It states that design verification and validation were performed according to current standards (IEC 60601-1 series, IEC 60645 series) to assure the device meets performance specifications, and software verification and validation were conducted.
• Clinical Testing Summary: Crucially, it states "Not applicable. Not required to establish substantial equivalence."

Therefore, based on the provided text, I cannot complete the requested tables and information. The submission for the Lyra device explicitly states that clinical testing was "Not applicable" and "Not required to establish substantial equivalence," meaning the detailed study design elements you requested (like acceptance criteria for performance, sample sizes, ground truth establishment, expert involvement, and comparative effectiveness studies) were not part of this 510(k) submission.

The acceptance criteria for this submission appear to be demonstrating equivalence to established predicate devices through non-clinical performance and technological characteristics, rather than demonstrating a specific level of clinical performance against a clinical ground truth.

In summary, the provided document does not support the specific type of performance study you are asking about, as it relies on substantial equivalence to predicates rather than novel clinical performance demonstration.

Ask a specific question about this device

The GSI Corti series is indicated for testing of cochlear function in infants, children and adults by measuring otoacoustic emissions (OAEs). The OAEs are generated by a series of clicks that are directed into the ear canal. Otoacoustic emissions are low level audio-frequency sounds that are produced by the cochlea as part of the normal-hearing process. Available evidence suggests that otoacoustic emissions are generated by the cochlea's outer hair cells and that the presence of OAEs. is an indication that the outer hair cells are vidence indicates that these emissions normally occur with normal hearing, or at most, mild hearing loss (usually 30-40 dB HL). The majority of hearing-impaired individuals will be identified by a simple OAE test.

Corti test system provides rapid measurement and documentation of Distortion Product Otoacoustic Emissions (DPOAEs) or Transient Evoked Otoacoustic Emissions (TEOAEs) at several frequencies.

The system consists of the instrument, probe, printer, single-use eartips replaceable probe tubes and other accessories. The Corti instrument contains the hardware and software for generating the test stimuli, measuring and displaying the OAEs, and storing the results until they are printed. The plastic housing contains circuit boards that provide the signal processing and display the test results. The instrument also contains a rechargeable lithium-ion battery to power the device. The instrument uses a liquid-crystal display (LCD) and three light-emitting diodes (LEDs) to provide a visual display of test status to the operator. Four push buttons located on the keypad of the device allow the user to control testing and printing, and to reset test protocols.

The Probe houses the speaker and microphone which produce test stimuli and measure the sound pressure level (SPL) present in the sealed ear canal. Interface of the instrument to the ear canal is accomplished through disposable eartips, which fit onto the probe tube. The disposable eartips are color coded to facilitate easy selection by size.

Distortion Product Otoacoustic Emissions (DPOAEs) are acoustic signals that can be detected in the ear canal of a person with normal outer hair cell function, subsequent to stimulation of the auditory system with a pair of pure tones at frequencies f1 and f2. The resulting emission of interest is the distortion product tone at the frequency 2f1-f2.

The Corti instrument generates a series of test tones, directs them into the ear canal, and then measures the level of the DPOAE tone generated by the cochlea. By using different test frequencies, the Corti device provides an estimate of outer hair cell function over a wide range of frequencies.

Transient Evoked Otoacoustic Emissions (TEOAEs) are acoustic signals that can be detected in the ear canal of a person with normal outer hair cell function, subsequent to stimulation of the auditory system with a series of wideband clicks.

The Corti instrument generates a series of clicks, directs them into the ear canal, and then analyzes the spectrum of the returning signal, separating the noise and emission. By using band pass filters, the Corti device provides an estimate of outer hair cell function over a wide range of frequencies

Here's a breakdown of the acceptance criteria and the study details for the GSI Corti device, based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state numerical acceptance criteria in a table format, nor does it provide specific numerical performance values for the GSI Corti that are directly compared against such criteria. Instead, it states that the device was validated to ensure it provides equivalent diagnostic results to an "equivalent device" (the ERO-SCAN predicate device).

The "criteria" are implied by adherence to international standards and the demonstration of "substantial equivalence."

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

• Sample Size: "A selection of test subjects" with a targeted population of approximately 80% normal hearing and 20% having a range of impairment (from complete impairment to mild hearing impairment). The exact number of subjects is not specified but is referred to as "the subject ears."
• Data Provenance: Not explicitly stated, but it's a clinical validation study, implying prospective data collection in a controlled environment. The country of origin for the data is not mentioned.

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

This information is not provided in the document. The study compares the GSI Corti against a predicate device (ERO-SCAN), suggesting that the "ground truth" might be established by the results of the predicate device or by standard audiological assessments. However, the details of how the truth was established (e.g., specific expert audiologists or independent clinical diagnoses) are missing.

4. Adjudication Method for the Test Set

This information is not provided in the document.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size of How Much Human Readers Improve with AI vs. Without AI Assistance

This is not an MRMC study or an AI-assisted interpretation device. The GSI Corti is an audiological device that measures otoacoustic emissions. The study compares the performance of the new device to a predicate device, not the performance of human readers with or without AI assistance.

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

Yes, in a way. The "performance" being evaluated is of the device itself (GSI Corti) in measuring OAEs and providing diagnostic results, in comparison to another device (ERO-SCAN). There isn't a human interpreting the device's output and that output then being compared to a human baseline. The device's output is directly compared to the predicate device's output.

7. The Type of Ground Truth Used

The "ground truth" for the clinical validation was effectively the diagnostic results obtained from the predicate device (ERO-SCAN) and the known hearing status of the subjects (approximately 80% normal hearing, 20% impaired). The study aimed to determine if the GSI Corti provided "equivalent diagnostic results" to the ERO-SCAN, suggesting the ERO-SCAN's output served as the reference for equivalence.

8. The Sample Size for the Training Set

This information is not applicable or not provided. This is a device validation study, not a machine learning model training study. The device's algorithms are built into the hardware/software and are not "trained" on a dataset in the typical sense of AI/ML.

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

This information is not applicable or not provided as it's not a machine learning model training study.

Ask a specific question about this device

The Sera™ with DPOAE is intended for use in the audiologic evaluation and documentation of ear disorders using Distortion Product Otoacoustic Emissions. The target population for Sera with DPOAE includes all ages.

The Sera™ with TEOAE is intended for use in the audiologic evaluation and documentation of ear disorders using Transient Evoked Otoacoustic Emissions. The target population for Sera with TEOAE includes all ages.

The Sera™ with ABRIS is intended for use in the audiologic evaluation and documentation of ear and nerve disorders using auditory evoked potentials from the inner ear, the auditory nerve and the brainstem. The target population for Sera with ABRIS is newborns.

The Sera™ System is to be used by trained personnel only, such as audiologists, ENT surgeons, doctors, hearing healthcare professionals or personnel with a similar level of education. The device should not be used without the necessary knowledge and training to understand its use and how results should be interpreted.

The device is audiometric equipment used for assisting of inner ear and auditory brainstem abnormalities.

Sera™ features a touch-screen display and user-friendly software in a compact hardware design. Sera™ can be purchased with various licenses allowing you to perform different hearing screening tests.

Sera™ uses auditory brainstem response (ABRIS) technology to screen patients for hearing loss. A modified click stimulus, the CE-Chirp", of 35 dB nHL is delivered into the patient's ear while electrodes placed on the patient's head measure EEG activity.

Auditory brainstem response (ABRIS) test produces a short acoustic stimulus and measures via transcutaneous electrodes the auditory evoked potentials from the inner ear, the auditory nerve and the brainstem.

The provided document is a 510(k) summary for the Sera™ audiometric equipment. It indicates that no clinical tests were performed to establish acceptance criteria or demonstrate device performance. The device's safety and effectiveness were affirmed based on its fulfillment of international standards for Otoacoustic Emissions (OAE) and Auditory Brainstem Response (ABR) measurements.

Therefore, the following information cannot be extracted from the document:

• A table of acceptance criteria and reported device performance.
• Sample size used for the test set and data provenance.
• Number of experts used to establish ground truth and their qualifications.
• Adjudication method for the test set.
• Effect size of human readers improvement with AI vs without AI (Multi-reader multi-case comparative effectiveness study was not performed as no clinical testing was done).
• Standalone performance (algorithm only without human-in-the-loop) was not explicitly detailed via clinical study.
• Type of ground truth used.
• Sample size for the training set.
• How ground truth for the training set was established.

Summary of Non-Clinical Testing and Device Performance (as described in the document):

The document states:
"Design verification and validation were performed according to current standards for OAE and ABR to assure the device meets its performance specifications. EMC and Safety was performed in compliance with recognized standards IEC 60601-1 series, Medical Equipment – General requirements for basic safety and essential performance. The product meets the requirements from the international standard for OAE measurements IEC 60645 series. Software verification and validation testing were conducted and documentation was provided as recommended by FDA's Guidance for Industry and FDA Staff, "Guidance for the Content of Premarket Submissions for Software Contained in medical Devices." The software for this device was considered as a 'moderate' level of concern since a malfunction of, or a latent design flaw in, the Software Device could lead to an erroneous diagnosis or a delay in delivery of appropriate medical care that would likely lead to Minor Injury. The OAE and ABRIS measurements were divided into 3 phases. Phase 1 included when optimization occurred and involved feedback to the operator so that they could adjust such as probe fit, electrode impedance, ambient electrical and acoustic noise etc. Once the pre-test conditions were optimized, phase 2 of data collection proceeded as rapid as possible to allow the maximum quantity of good quality data to be collected in the shortest possible time. Phase 3 proceeded into the data assessment and decision stage and this ran concurrently with Phase 2 once the predetermined minimum amount of data had been collected. Phase 3 then went into the algorithm descriptions for each TEOAE, DPOAE and ABRIS measurements modes and is provided in detail in Annex 16D of this submission. No clinical tests were performed, but based on the fulfillment of the international standards for OAE and ABR we believe the device is safe and effective. The auditory impedance testing characteristics and safety systems were compared and found to be comparable."

Conclusion regarding acceptance criteria and study in the absence of clinical data:

The acceptance criteria for the Sera™ device and its performance are not directly demonstrated through clinical studies with a defined test set, ground truth established by experts, or statistical performance metrics. Instead, the device's acceptability is based on:

1. Compliance with recognized international standards:
   • IEC 60601-1 series (Medical Equipment – General requirements for basic safety and essential performance) for EMC and Safety.
   • IEC 60645 series (international standard for OAE measurements).
2. Software verification and validation: Per FDA's Guidance for Industry and FDA Staff, "Guidance for the Content of Premarket Submissions for Software Contained in medical Devices." The software was deemed "moderate" level of concern.
3. Bench testing and design verification/validation: To ensure the device meets its performance specifications according to current standards for OAE and ABR.
4. Comparison to a predicate device (easyScreen, K171506): The document asserts substantial equivalence in technological characteristics and indications for use.

The document implies that by meeting these standards and demonstrating comparability to the predicate device through non-clinical means (bench testing, software validation), the device is considered safe and effective, and thus acceptable. The specific 'acceptance criteria' in terms of clinical performance (e.g., sensitivity, specificity for detecting hearing loss) and a study proving it meets these are not presented because clinical testing was not performed.

Ask a specific question about this device

The GSI Novus is intended to be used for the measurement and automated analysis of auditory evoked responses (auditory brainstem responses, ABR) and/or otoacoustic emissions (distortion product, DPOAE and transient evoked, TEOAE). These measures are useful in the screening evaluation, documentation and diagnosis of auditory and hearing related disorders. The auditory evoked response (ABR) measurement is intended for newborns and infants up to 6 months of age. The otoacoustic emissions (DPOAE and/or TEOAE) measurement is intended for use in patients of all ages.

The GSI Novus is intended to be used by a healthcare professional such as an ENT doctor, nurse or audiologist or by a trained technician under the supervision of a professional. The device is intended to be used in a hospital, clinic, or other facility with a suitable quiet testing environment.

The device is audiometric equipment used for testing of inner ear and auditory brainstem abnormalities.

Novus features a touch-screen display and user-friendly software in a compact hardware design. Novus can be purchased with various licenses allowing you to perform different hearing screening tests.

Novus uses auditory brainstem response (ABR) technology to screen patients for hearing loss. A modified click stimulus, the CE-Chirp", of 35 dB nHL is delivered into the patient's ear while electrodes placed on the patient's head measure EEG activity.

The EEG is processed and analyzed automatically using the Novus's response detection algorithm. When a response is detected, the screening is stopped automatically and a Pass result is assigned to the test ear. When no response is detected after 3 minutes of EEG activity has been processed, a Refer result is assigned.

Auditory brainstem response (ABR) test produces a short acoustic stimulus and measures via transcutaneous electrodes the auditory evoked potentials from the inner ear, the auditory nerve and the brainstem.

Distortion product otoacoustic emissions (DPOAE) technology uses pairs of pure tones presented in sequence to screen patients for cochlear hearing loss. Responses to the stimulus are predictable and therefore can be measured via a sensitive microphone placed in the patient's ear canal.

Transient otoacoustic emissions (TEOAE) technology uses a click stimulus to screen patients for cochlear hearing loss. Responses to the stimulus are predictable and therefore can be measured via a sensitive microphone placed in the patient's ear canal. The response can be divided into frequency bands for assessment.

The Novus consists of a handheld unit that utilizes a touchscreen display and a rechargeable battery. A simple cradle is included to support charging of the device's battery. The device supports Bluetooth® communication with a label printer for the purpose of printing screening results.

This document does not contain an acceptance criteria table or a study proving the device meets specific acceptance criteria in the format requested. The document is a 510(k) premarket notification letter from the FDA to Grason-Stadler Inc. for their GSI Novus device. It primarily focuses on demonstrating substantial equivalence to predicate devices rather than presenting detailed clinical trial results or specific performance metrics against pre-defined acceptance criteria.

However, based on the provided text, I can extract information related to the device's intended use, general performance claims, and the type of non-clinical testing performed to support its safety and effectiveness.

Here's an attempt to answer your questions based only on the provided text, noting where information is explicitly not present:

Acceptance Criteria and Device Performance Study for GSI Novus (K172403)

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

The document does not provide a table of explicit acceptance criteria with corresponding device performance metrics. Instead, it asserts that the GSI Novus meets performance specifications by complying with international standards and through non-clinical design verification and validation. The "reported device performance" is primarily qualitative, stating that the device is "safe and effective" and that its performance characteristics are comparable to predicate devices.

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 explicitly states: "No clinical tests were performed" and "Summary of Clinical Testing: Not applicable. Not required to establish substantial equivalence." Therefore, there is no test set sample size, data provenance, or information on retrospective/prospective studies from clinical testing. The "data collection" mentioned in Phase 2 refers to data collected during non-clinical verification and validation activities.

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)

Since no clinical tests were performed and no "test set" in the context of human data was used to establish ground truth for clinical performance, this information is not applicable and not provided.

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

Not applicable, as no clinical test set was used for ground truth establishment.

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

Not applicable. The document states "No clinical tests were performed." Furthermore, the GSI Novus is described as an auditory testing device with an automatic response detection algorithm ("Novus's response detection algorithm"), implying it functions as a standalone diagnostic aid rather than an AI assistance tool for human "readers" (in the typical sense of image interpretation).

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

Yes, the device relies on an automated analysis algorithm. The description mentions:

• "The EEG is processed and analyzed automatically using the Novus's response detection algorithm."
• "When a response is detected, the screening is stopped automatically and a Pass result is assigned to the test ear. When no response is detected after 3 minutes of EEG activity has been processed, a Refer result is assigned."
• "The detailed information about the validation and verification of PASS/REFER algorithms for the OAE and ABR modules is provided in the GSI Novus Manual, e.g., PASS/REFER Criteria, Sensitivity and Specificity etc."

This indicates that a standalone algorithm performance was assessed for the automated PASS/REFER results during the non-clinical design verification and validation activities, although specific performance metrics (like sensitivity, specificity) are referenced as being in the manual but not provided in this document.

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

For the non-clinical verification and validation of the "PASS/REFER algorithms," the "ground truth" would have been established by comparing the algorithm's output to expected or reference values derived from recognized audiological principles and potentially a "gold standard" reference measurement or simulation. The document mentions "Phase 3 then went into the algorithm descriptions for each TEOAE, DPOAE and ABRIS measurements modes," implying that the ground truth for validating the algorithms themselves would be based on established audiological standards and the device's ability to accurately detect "responses" or "no responses" against these standards. Specifics of how this "ground truth" was established (e.g., against a known simulated signal, against a predicate device's output, or against expert analysis of raw data) are not detailed here.

8. The sample size for the training set

The document does not mention a "training set" or "training data" in the context of machine learning, nor does it specify any sample size for such a set. Given the context of a 510(k) for an audiometer with an automated algorithm, it's possible the algorithm logic was developed based on established audiological principles and signal processing, rather than a large-scale data training approach commonly associated with AI/ML.

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

Not applicable, as no training set is described or referenced in the document.

Ask a specific question about this device