Search Results

The NAS-1000 System is a medical acoustic system intended as an adjunct to standard clinical practice for use in non-invasively monitoring, detecting, recording and displaying acoustic signals in the brain. It is used for any subject undergoing a physical examination and intended only for medical assessment purposes in a clinic or hospital.

The NAS-1000 System is a non-invasive, non-energy emitting device indicated for monitoring and recording of acoustic signals from the brain. The earbud passively receives the acoustic signal from the brain and the result is graphically displayed as an acoustic waveform on the monitor (NAS-1000M).

The NAS-1000 System consists of two components: a non-sterile, disposable, single patient use Headset (NAS-1000H) with four different sized earbuds (XS, S, M, L), and a tablet-based Monitor (NAS-1000M) which contains the software (NAS-1000S).

The provided text describes the Neuro Assessment System (NAS-1000) and its substantial equivalence to a predicate device, the 3M™ Littmann® Electronic Stethoscope, Model 3200 (K083903). While it details non-clinical and clinical testing, it does not explicitly provide an acceptance criterion table with reported device performance or information typically found in a comparative effectiveness study with AI assistance.

Here's a breakdown of the information available and what is missing based on your request:

1. Table of acceptance criteria and the reported device performance

The document does not provide a table of acceptance criteria with corresponding performance metrics. Instead, it describes general findings from phantom bench testing and clinical testing on volunteers. The core comparison is framed around "substantial equivalence" to the predicate device, K083903.

The document states:

• Phantom Bench Testing: "The NAS-1000 System and the 3M Littmann e-Stethoscope performed comparably and were able to graphically display the simulated systolic pulse from the phantom."
• Clinical Testing: "The study demonstrated the ability of the NAS-1000 System to detect and generate waveforms from the brain to provide a tool for monitoring brain acoustic signals / sounds over various time intervals." and "The tablet outputs demonstrate the ability of the NAS-1000 System to display brain acoustic signals / sounds of in the volunteers based on the analysis of waveform data."

2. Sample size used for the test set and the data provenance

• Sample Size for Test Set: 50 volunteers.
• Data Provenance: The document states "A performance testing study of the NAS-1000 System was conducted on volunteers" and "A total of 50 volunteers were measured and monitored." This indicates a prospective clinical study on human subjects, but the country of origin is not specified. It is implied to be a direct collection for the device's validation.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

This information is not provided in the document. The study aimed to demonstrate the device's ability to detect and generate waveforms from the brain, implying the ground truth was the actual detection of acoustic signals rather than a diagnostic interpretation by experts. The device is for "monitoring, detecting, recording and displaying acoustic signals," not for providing a diagnosis based on an expert's assessment.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

This information is not provided and is not applicable given the reported nature of the study as a technical performance validation rather than a diagnostic accuracy study requiring expert adjudication of ground truth labels.

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

An MRMC comparative effectiveness study was not conducted or described. The NAS-1000 System is presented as an acoustic monitoring device that displays waveforms, not an AI-powered diagnostic tool that assists human readers in making diagnoses. Thus, there is no mention of human reader improvement with AI assistance.

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

The device itself is a standalone system for monitoring and displaying acoustic signals. The clinical testing described directly assesses the system's ability to "detect and generate waveforms" and "display brain acoustic signals," which aligns with a standalone performance assessment of the device's core functionality.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

The ground truth for the clinical study was the presence and characteristics of brain acoustic signals/sounds in volunteers. The study demonstrated the device's ability to detect and generate waveforms from these signals. For the phantom bench testing, the ground truth was a "simulated systolic pulse" generated by a peristaltic pump, and the device's output was compared to this known input signal.

8. The sample size for the training set

This information is not provided. The document focuses on regulatory submission and doesn't detail the development and training of potential machine learning models, if any are employed beyond signal processing. Given the device's description as a system for monitoring, detecting, recording, and displaying acoustic signals, it's more likely relying on signal processing algorithms rather than a trained AI model in the typical sense that would require a large training set for diagnostic purposes.

9. How the ground truth for the training set was established

This information is not provided as the concept of a "training set" for an AI model is not discussed in the context of this device's validation.

Ask a specific question about this device