(90 days)
The Grason-Stadler Inc. model GSI 70 AudioPath™ Hearing Screener is similar to and predicated upon the Grason-Stadler Inc. model GSI 60 Otoacoustic Emissions/Screening Audiometer, the GSI 37 Auto Tymp Middle Ear Analyzer, and the GSI 17 Pure Tone Screening Audiometer. The purpose of this device is to detect as well as track hearing loss and abnormal middle ear conditions in all ages of patients (from premature infants through adults). The instrument has combined a battery of testing capabilities such as Otoacoustic Emission Screening, Tympanometry, and Pure Tone Audiometry within one hand held instrument. The device is intended to be used by trained personnel within a medical or school environment. This device is not intended for use in prescribing or fitting assistive listening devices such as hearing aids, cochlear implants or wireless microphones, or to diagnose the causes of detected hearing losses.
The Grason-Stadler Inc. model GSI 70 AudioPath™ Screener is similar to and predicated upon the Grason-Stadler Inc. model GSI 60 Otoacoustic Emissions/Screening Audiometer, the GSI 37 Auto Tymp Middle Ear Analyzer, and the GSI 17 Pure Tone Screening Audiometer. The purpose of this device is to detect as well as track hearing loss and abnormal middle ear conditions in all ages of patients (From premature infants through adults age). The instrument has a battery of testing capabilities such as Otoacoustic Emission Screening, Tympanometry, and Pure Tone Audiometry. The device is intended to be used by trained personnel in a medical or school environment. This device is not intended for use in prescribing or fitting assisstive listening devices such as hearing aids, cochlea implants or wireless microphones.
This 510(k) summary does not contain a typical "study" that would demonstrate the device meets specific performance acceptance criteria in a quantitative sense as might be expected for an AI/ML device. Instead, it argues for substantial equivalence primarily based on technological characteristics and safety.
The document does not provide a dedicated study with quantitative acceptance criteria and results for the GSI 70 AudioPath™ Screener's effectiveness in detecting and tracking hearing loss. Instead, it asserts its effectiveness by stating it is "equivalent or better in effectiveness" than its predicate devices, which are individual audiometric products.
Here's a breakdown of the requested information based on the provided text, highlighting the absence of some details for this particular submission:
1. A table of acceptance criteria and the reported device performance
Since this is a 510(k) for a medical device that combines existing technologies rather than introducing a new diagnostic AI/ML algorithm, the acceptance criteria are focused on safety and functional equivalence to predicate devices, rather than performance metrics like sensitivity or specificity for hearing loss detection.
| Acceptance Criteria Category | Reported Device Performance |
|---|---|
| Safety Compliance | Meets IEC 601-1, UL2601, and CSA 601-1-M90. |
| Watchdog timers monitor the system and disable tone generation when disparity is detected to prevent excessive tone levels. | |
| Speakers are incapable of producing enough decibels to permanently damage the ear. | |
| Tympanometry pump volume is incapable of producing pressure exceeding ANSI S3.39 safe levels. | |
| Electromagnetic Compatibility (EMC) | Certified to: |
- EMI EN55011 (Group 1 Class B requirements for medical equipment, conducted and radiated emissions).
- IEC801-2 (ESD Susceptibility).
- IEC801-3 (Radiated Electromagnetic Field Susceptibility).
- IEC801-4 (Conducted Susceptibility to Line Transients). |
| CE Mark Compliance | Conforms with provisions of European Council Directive 93/42/EEC concerning medical devices. |
| Functional Equivalence (Audiometry) | "Tones are presented by a miniature speaker within the probe which if perceived is indicated by the patient using a response switch. Tone quality and frequency specified per ANSI S3.6." (Functionally equivalent to GSI 17 which uses a speaker headset). |
| Functional Equivalence (Tympanometry) | "Same as GSI 37" (Tones presented during pressurization of the ear by a miniature pump; response recorded by a microphone; tone quality and frequency controlled by ANSI S3.39). |
| Functional Equivalence (OAE Probe Design & DSP Software) | "Same as GSI 60" (Two speakers and a microphone present and record response from cochlea; uses GSI 60 DSP Software). |
| Overall Effectiveness | "Equivalent or better in effectiveness for the detection and tracking of hearing loss and abnormal middle ear conditions in all ages of patients (from premature infants through adults)" compared to the combined individual predicate devices (GSI 60, GSI 37, GSI 17). This is an assertion of equivalence rather than a quantitative performance metric from a study. |
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Not Applicable / Not Provided: The document does not describe a clinical study with a "test set" in the context of diagnostic performance (e.g., for sensitivity/specificity) for the GSI 70 AudioPath™ Screener itself. The submission relies on the established performance and safety of its predicate devices and the technical comparison to demonstrate substantial equivalence.
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)
- Not Applicable / Not Provided: No such ground truth establishment by experts for a specific test set is mentioned for the GSI 70 AudioPath™ Screener in this summary.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Not Applicable / Not Provided: No adjudication method is described as there's no clinical performance study presented that would require it.
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: No MRMC study was conducted or reported. This device is not an AI-assisted diagnostic tool for interpretation by human readers. It's a screening instrument.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Yes, implicitly, but not as an AI/ML algorithm: The device itself performs the audiometry, tympanometry, and OAE screenings standalone. Its "performance" is based on its ability to generate tones, measure responses, and process signals according to established audiological standards (ANSI S3.6, ANSI S3.39 for the respective functions) which are derived from the predicate devices. There isn't an "algorithm" in the modern AI/ML sense being evaluated independently, but rather the integrated functionality of the hardware and embedded software. The provided text doesn't offer quantitative standalone performance metrics like sensitivity/specificity for hearing loss detection from a new study for the combined device.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
- Not Applicable / Not Provided for this specific device: For the predicate devices, the "ground truth" would implicitly be the established audiological standards for detecting hearing loss and middle ear conditions. The current submission for the GSI 70 relies on the equivalence to these predicate devices rather than generating new ground truth data to validate new performance claims.
8. The sample size for the training set
- Not Applicable / Not Provided: There is no mention of a "training set" as this device does not utilize a machine learning model that would require one.
9. How the ground truth for the training set was established
- Not Applicable / Not Provided: As there is no training set mentioned, this information is not relevant.
§ 874.1050 Audiometer.
(a)
Identification. An audiometer or automated audiometer is an electroacoustic device that produces controlled levels of test tones and signals intended for use in conducting diagnostic hearing evaluations and assisting in the diagnosis of possible otologic disorders.(b)
Classification. Class II. Except for the otoacoustic emission device, the device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter, if it is in compliance with American National Standard Institute S3.6-1996, “Specification for Audiometers,” and subject to the limitations in § 874.9.