(178 days)
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:
| Acceptance Criteria (Inferred from Predicate Equivalence) | Reported Device Performance (OtoNova/OtoNova Pro) |
|---|---|
| Electrical Driving Signals Equivalence: Stimulator probe transducer electrical driving signals must be substantially the same as the predicate (within 1dB) across the functional frequency range for TEOAE, DPOAE, and ABR. | "Found to be substantially the same (to within 1dB) across the functional frequency range." |
| Acoustic Stimulation Equivalence: Acoustic stimulation delivered by the probe into a calibrated ear simulator must be substantially the same as the predicate (within 1dB) across the functional frequency range for TEOAE, DPOAE, and ABR (including ABR with ear-cup). | "Found to be substantially the same (to within 1dB) across the functional frequency range." |
| Sensitivity to Simulated Responses Equivalence: OAE and ABR responses recorded from a factory-reference 'response simulator' must be substantially the same levels/waveforms as the predicate (within 1dB). | "Responses recorded by the OtoNova Pro were substantially the same levels (within 1dB) across the functional frequency for OAEs, and the ABR recorded had substantially the same size and waveform for ABR (within 1dB)." |
| Clinical Screening Test Result Agreement: OtoNova's Nova-Link should yield the same "Pass," "Refer," or "Invalid test result" as the predicate device under the same screening criteria. | "OtoNova’s Nova-Link gives same screening test result under the same screening criteria (i.e. clear response, no clear response, invalid result) as the predicate device." |
| Clinical Physical Characteristics of Recorded Responses Agreement: Physical characteristics of recorded responses (OAE, ABR waveforms) should be similar to the predicate, with marginal variability no wider than the predicate. | "The physical characteristics of the recorded responses were similar on each device. In the case of marginal response levels, where variability is to be expected, the range of marginality was no wider than for the Otoport OAE+ABR." |
| Clinical Reported Response Levels (OAE) Agreement: Reported OAE response levels should be the same across frequency as the predicate, within expected tolerance due to subject movement. | "In the recording of OAE response for clinical purposes the OtoNova and OtoNova Pro the reported response levels were the same across frequency as with the Otoport OAE +ABR device within the tolerance expected due to subject movement." |
| Clinical Reported Noise Levels Agreement: Reported noise levels should be similar to those reported by the predicate, within the expected intrinsic variability of noise. | "The reported noise levels reported by Novalink were similar to those reported by the Otoport C. within the expected intrinsic variability of noise." |
| Usability (Human Factors) Acceptance: Users should be able to sufficiently understand the product/IFU to successfully record tests and use the device per its intended use with no substantial issues. | "All the 16 users were able to sufficiently understand the OtoNova product/ IFU, to successfully record tests and use the medical device per its intended use... There were no substantial issues found during this OtoNova summative evaluation." |
Study Details:
-
A table of acceptance criteria and the reported device performance: See table above.
-
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.
-
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.
-
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.
-
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.
-
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.
-
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.
-
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.
-
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.
§ 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.