Search Results

The BNA™ Analysis System is to be used by qualified medical professionals for the posthoc statistical analysis of the human electroencephalogram ("EEG"), utilizing evoked response potentials ("ERP"). This device is indicated for use in individuals 14 to 24 years of age. The BNA™ Analysis System is to be used with the auditory oddball task only.

The BNA Analysis System is an accessory to EEG. The BNA Analysis System is a software device that is used to analyze EEG-ERP data with regards to conventional, well established characteristics of amplitude and latency. Statistical analysis is performed to express the differences between the patient (individual) and a task-matched reference group in the indicated age group in the form of Z-scores. The BNA Analysis System report displays the test results in the following format; (1) Test and Patient Information; (2) ERP waveforms; (3) Summarized patient results - Z-Score Tables, Z-Score Maps and BNA Composite Scores. BNA Composite Scores are a calculation of the global comparison of the individual to the normative group (RBNM) for the following well-established EEG-ERP components: amplitude and absolute time. These calculations are a measure of the overall similarity of the single subject EEG-ERP components to the EEG-ERP components of the normative group (RBNM) based on Z-scores. The BNA scores should not be used as stand-alone information: rather, such scores should complement all of the information included in the report, as well as the clinical evaluation.

Here's a breakdown of the acceptance criteria and study details for the ElMindA Ltd.'s BNA™ Analysis System, based on the provided 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance:

The document focuses on the repeatability of BNA scores as a key performance metric. The acceptance criteria aren't explicitly stated as numerical targets in the same way clinical accuracy metrics (like sensitivity/specificity) often are. Instead, the study aims to demonstrate that the device produces consistent results across identical test sessions. The "acceptance criteria" here implicitly refer to demonstrating acceptable agreement between repeated measurements, as evaluated by Bland-Altman analysis.

Note on Interpretation: Bland-Altman limits of agreement quantify the range within which 95% of the differences between two measurements are expected to lie. Smaller limits indicate better agreement (repeatability). The document doesn't provide a specific numerical threshold for "acceptable" limits, relying on the overall demonstration of repeatability.

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

• Test Set Sample Size: Not explicitly stated. The document mentions "clinical performance testing was conducted to assess the repeatability of the BNA scores," but doesn't give the number of subjects.
• Data Provenance: Not specified in terms of country of origin. The study was conducted as part of the regulatory submission for ElMindA Ltd., an Israeli company. The type of study was prospective, as it involved conducting two identical test sessions within a specific timeframe to assess repeatability.

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

This information is not applicable and not provided in the document. The study was a repeatability study comparing the device's own scores across two sessions, not a study evaluating the device's diagnostic accuracy against an expert-established ground truth for a specific condition. The "ground truth" in this context is the subsequent measurement by the same device.

4. Adjudication Method for the Test Set:

This information is not applicable and not provided. As explained above, this was a repeatability study, not one requiring adjudication against a clinical ground truth.

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:

This information is not applicable and not provided. This document pertains to a standalone software device that performs post-hoc statistical analysis of EEG/ERP data. It is not an AI-assisted diagnostic tool designed to be used by human readers for interpretation, nor does it conduct comparative effectiveness studies with human readers. The BNA scores are intended to "complement all of the information included in the report, as well as the clinical evaluation," but the study is not designed to measure human reader improvement with the device.

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

Yes, a standalone performance assessment was done. The entire "Performance Data" section describes the assessment of the BNA Analysis System's repeatability, which is an intrinsic characteristic of the algorithm's output (BNA scores) when analyzing EEG-ERP data. The device itself performs the statistical analysis and generates the scores.

7. The Type of Ground Truth Used:

The "ground truth" in this repeatability study is the device's own measurement from the first test session. The study aims to see how repeatable the device's output (BNA scores) is when the same subject undergoes an identical test shortly after. It's a self-assessment of consistency, not a comparison to an external clinical or pathological ground truth.

8. The Sample Size for the Training Set:

This information is not provided in the document. The BNA Analysis System performs statistical analysis relative to a "task-matched reference group in the indicated age group." While this implies a normative dataset was used, the sample size for this reference group (which could be considered analogous to a training or normative dataset) is not detailed.

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

This information is not provided in the document. It mentions that BNA Composite Scores compare the individual to a "normative group (RBNM)." However, it does not explain how this normative group was established, including the criteria for inclusion, data acquisition methods, or any expert review process for defining the "ground truth" or normal range for these parameters.

Ask a specific question about this device