(19 days)
The Bio-logic Evoked Potential (EP) product family is indicated for use in the recording and analysis of human physiological data necessary for the diagnosis of auditory and hearing-related disorders. An auditory stimulus (click, tone, etc.) is presented to the patient's ear through an earphone or headphones, and the Brainstem Auditory Evoked Response from the patient is recorded using EEG electrodes placed on the scalp. Although this Brainstem Response is very low in amplitude (with respect to surrounding EEG "noise"), the stimulus-response cycle is repeated many times and the resulting responses are averaged from the time of the stimuli. The random noise averages to zero, but if the Brainstem Response signal will be easily determined in the averaged signal.
The Bio-logic EP System can be used for patients of all ages, from children infants and geriatric patients. It is especially indicated for use in testing individuals for whom behavioral are deemed unreliable, such as infants, young children, and cognitively impaired or uncooperative adults. The use of the Bio-logic EP family of products is to be performed under the prescription and supervision of a physician or other trained health care professional.
The feature modifications represented in this Special 510(k) are for the use of a redesigned hardware package and a Windowsbased software program to control the hardware. The functions and electronic design of the hardware are substantially the same as those of the Predicate Device hardware. The software for control of this device is a simplified subset of the DOS-based Predicate Device software. Together, they implement the same infant hearing screening functions and perform the same intended use as the Predicate Device, but with improved ease-of-use. The POVR algorithm described in the Predicate Device is implemented in the new Windows software to generally assist in test data interpretation, and specifically assist in the assessment of signal-to-noise ratio and the quality of the Brainstem Auditory Evoked Response in infants. Based on this automatic assessment, the speed of testing may be reduced and/or the quality of the data recording may be improved, without compromising the quality of recorded data or limiting the control and flexibility of the health care professional administering the test.
The Bio-logic Evoked Potential family of products is intended to be used for the recording and analysis of human physiological data for the purpose of neurological diagnosis and treatment of sensory disorders. The Predicate Device performs Evoked Potential recording and analysis functions, provides two channels of simultaneous data recording, and includes the option of applying the Point Optimized Variance Ratio (POVR) algorithm for optimizing signal quality and speed of test completion. This new device has both hardware and software modifications and improvements over the Predicate and related devices. The changes described in this 510(k) are to incorporate a repackaged variation of the previouslydescribed "E" Series hardware (2-channel), along with a new Windows-based software program for the control of this new hardware. This hardware performs the AEP test only, so, correspondingly, the software contains only AEP control and analysis features. The Navigator Pro hardware is very similar in electronics design to the Navigator E hardware used in the Predicate Device, except that the electronics hardware has been re-packaged into a stand-alone box which derives its power from a separate medical-grade power supply and connects to the host computer through a serial port. The host software for the Predicate Device is DOS-based, whereas the host software for the ABAER - Navigator Pro (subject of this Special 510(k)) is WINDOWS-based. The WINDOWS program has much of the same functionality as that of the predicate device, but with improved user interfaces and overall ease-of-use.
The provided text is a 510(k) summary for a medical device modification, specifically the Bio-logic ABAER / Navigator Pro. It primarily focuses on demonstrating substantial equivalence to a predicate device rather than presenting a study with specific acceptance criteria and performance data in the manner typically seen for novel or significantly modified devices involving AI/ML.
Therefore, much of the requested information regarding "acceptance criteria and reported device performance" from a formal study, sample sizes for test/training sets, expert ground truth establishment, adjudication methods, and MRMC comparatives is not present in this document. The document describes a comparison to a predicate device to establish substantial equivalence.
Here's an attempt to extract and interpret the available information according to your request, with significant caveats for the missing data:
Acceptance Criteria and Device Performance
This 510(k) focuses on demonstrating substantial equivalence to a predicate device (Bio-logic Evoked Potential for ABAER I, reference 510(k) #K992807). The "acceptance criteria" are therefore implicitly that the new device performs similarly to the predicate device in terms of safety and effectiveness, and that any differences do not adversely affect safety or effectiveness.
The document uses a comparative table to show that the new device has "no significant differences" in critical performance parameters.
1. Table of acceptance criteria and the reported device performance:
| Parameter for Comparison | Implicit Acceptance Criteria | Reported Device Performance (Bio-logic ABAER / Navigator Pro) |
|---|---|---|
| Intended Use | No differences from predicate device. | No differences. |
| Population | No differences from predicate device. | No differences. |
| Test Performance - Time to Complete | No significant differences from predicate device. | No significant differences. |
| Test Performance - Data Quality | No significant differences from predicate device. | No significant differences. |
| Safety Characteristics | No differences from predicate device (e.g., patient connection, isolation circuits). | No differences. (Uses same patient isolation methods and medical-grade power supply) |
| Hardware Configuration | Similar functionality, patient connection, and patient isolation circuits to predicate device. | Redesigned package, but similar functionality, patient connection, and patient isolation circuits. |
| Computer Control Software | Implements same functionality and intended use as predicate device, with improved ease-of-use. | Windows-based, simplified subset of DOS-based predicate software. Implements same functionality and intended use. |
| Patient Information and Tracking | Improved performance over predecessor. | Incorporates EXCEL-compatible database for patient and test info, improving performance over DOS filename-based method. |
| Product Labeling | Labels reflect physical characteristics, comply with standards. | Different due to physical characteristics; uses standard international symbols. |
| Anatomical Sites | No differences from predicate device. | No differences. |
| Physical Characteristics | Physically different but functionally equivalent; provides more flexibility. | Housed in separate module, separate power supply, serial port connection. Offers more flexibility. |
| POVR Algorithm Functionality | Maintains signal-to-noise ratio assessment and quality of Brainstem Auditory Evoked Response in infants. | Implemented in new Windows software for same purpose, assisting in test data interpretation and signal-to-noise ratio assessment. |
2. Sample size used for the test set and the data provenance:
- Not explicitly stated. The document describes a design and development process for the modification and a comparison to the predicate device, but it does not provide details on a specific test set, its size, or its provenance for evaluating the quantitative performance metrics of the POVR algorithm or other features. The evaluation appears to be based on the functional equivalence and safety assessment during the design process, rather than a separate clinical performance study with a defined test set.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Not applicable/Not stated. The document does not describe the establishment of ground truth by experts for a specific test set. The assessment relies on the judgment that the modified device's functionality is "substantially the same" as the predicate device.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set:
- Not applicable/Not stated. No formal adjudication method for a test set is described.
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. This device is an Evoked Potential system, not an AI/ML diagnostic tool used by human readers for interpretation in the sense of an MRMC study. The POVR algorithm is described as optimizing signal quality and speed of test completion and assisting in test data interpretation, but not in a way that suggests a human reader's performance is being measured with and without its "assistance" in a clinical diagnostic decision-making context that typically warrants an MRMC study.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
- Not applicable in the typical AI/ML sense. The device performs a signal acquisition and averaging task, and the POVR algorithm optimizes signal quality. The device is not making a "diagnosis" autonomously. It provides data for "review by the EP Technologist or Physician," who can "modify, override or delete" program "recommendations." The document states: "The ABAER / Navigator Pro software does not make any final decisions that result in any automatic forms of diagnosis or treatment."
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- Not explicitly stated in the context of a performance study. The basis for "ground truth" (or more accurately, validation) appears to be alignment with the known performance and expected physiological responses obtained from the predicate device, and the established principles of Evoked Potential recording and analysis. For instance, the premise of the POVR algorithm is that it "monitors the signal-to-noise ratio," and the "random noise averages to zero, but if the Brainstem Response signal is present, it's signal will be easily determined." This reflects established biophysical principles rather than a specific expert-labeled dataset.
8. The sample size for the training set:
- Not applicable/Not stated. The document describes a device modification, not the development of a de novo AI/ML algorithm that undergoes a training phase with a specific dataset. The POVR algorithm itself was already part of the predicate device.
9. How the ground truth for the training set was established:
- Not applicable/Not stated. See point 8.
§ 882.1900 Evoked response auditory stimulator.
(a)
Identification. An evoked response auditory stimulator is a device that produces a sound stimulus for use in evoked response measurements or electroencephalogram activation.(b)
Classification. Class II (performance standards).