(13 days)
The SpeechLink 100 is a hearing aid calibrator and analysis system that is an electronic reference device intended to calibrate and assess the electroacoustic frequency and sound intensity characteristics emanating from a hearing aid.
The SpeechLink is a PC-based system that contains hardware and software for one or more applications. The applications are controlled from self-contained software modules installed on a common software platform. The following applications are available: Audio fitting system and Simulator system.
The fitting system consists of a neckset, a charger unit with mains adapter, two probes connected to the neckset, software for installation on a PC and hardware for connection to a PC. The neckset is connected to the PC via a Bluetooth radio link, i.e. no physical connection to the PC.
The simulator consists of software for installation on a PC and hardware for connection to a PC.
The provided document outlines the acceptance criteria and a study demonstrating the SpeechLink 100 type 1053 device's performance.
1. Table of Acceptance Criteria and Reported Device Performance:
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Agreement with Predicate Device (Audioscan Verifit VF-1) | "high agreement between the measurements from the systems and that any observable differences between the peak curves are smaller than the tolerances regulated by the standard IEC 61669 (2001-01) Electroacoustics - Equipment for the measurement of real-ear acoustical characteristics of hearing aids." |
| Compliance with IEC 61669 (2001-01) tolerances | "any observable differences between the peak curves are smaller than the tolerances regulated by the standard IEC 61669 (2001-01)" |
2. Sample Size Used for the Test Set and Data Provenance:
- Sample Size: The document does not explicitly state a specific numerical sample size for the test set. It refers to "Speech mapping recordings" being measured, implying multiple recordings were taken.
- Data Provenance: Not specified. The document does not mention the country of origin of the data or whether the study was retrospective or prospective.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications:
- Not applicable. The study compares the device's measurements against a predicate device and a technical standard and does not involve human expert interpretation of results to establish ground truth in the traditional sense of medical image analysis or diagnosis.
4. Adjudication Method for the Test Set:
- Not applicable. As noted above, the comparison is against a predicate device's measurements and technical standard tolerances, not against adjudicated expert opinions.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
- No, a multi-reader multi-case (MRMC) comparative effectiveness study was not performed. The study compares the device against another device and a technical standard, not human readers with and without AI assistance.
6. Standalone Performance (Algorithm Only Without Human-in-the-Loop Performance):
- Yes, a standalone performance assessment was conducted. The study directly compares the measurements from the SpeechLink 100 with those from the Audioscan Verifit VF-1, and assesses its compliance with a technical standard. This is an evaluation of the device's (or its underlying algorithm's) performance in generating measurements without human intervention in the measurement process itself.
7. Type of Ground Truth Used:
- The ground truth in this context is established by:
- The measurements obtained from the predicate device (Audioscan Verifit VF-1).
- The tolerances defined by the IEC 61669 (2001-01) Electroacoustics - Equipment for the measurement of real-ear acoustical characteristics of hearing aids standard.
8. Sample Size for the Training Set:
- Not applicable. The provided document details a performance study comparing the device to a predicate and a standard, not a machine learning model's training process.
9. How the Ground Truth for the Training Set Was Established:
- Not applicable. The provided document details a performance study comparing the device to a predicate and a standard, not a machine learning model's training process.
§ 874.3310 Hearing aid calibrator and analysis system.
(a)
Identification. A hearing aid calibrator and analysis system is an electronic reference device intended to calibrate and assess the electroacoustic frequency and sound intensity characteristics emanating from a hearing aid, master hearing aid, group hearing aid or group auditory trainer. The device consists of an acoustic complex of known cavity volume, a sound level meter, a microphone, oscillators, frequency counters, microphone amplifiers, a distoration analyzer, a chart recorder, and a hearing aid test box.(b)
Classification. Class II (special controls). The device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 874.9.