Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K011834
    Device Name
    BIS ENGINE
    Date Cleared
    2001-07-10

    (28 days)

    Product Code
    Regulation Number
    882.1400
    Reference & Predicate Devices
    Predicate For
    N/A
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    Intended to monitor the state of the brain by data acquisition of EEG signals in the intensive care unit, operating room and for clinical research.
    The BIS, a processed EEG variable, may be used as an aid in monitoring the effects of certain anesthetic agents.

    Device Description

    The Aspect Medical Systems, Inc. BIS Engine - 4 channel support provides the means for incorporating Aspect's proprietary BIS technology into OEM (original equipment manufacturer's, i.e. our business partner's) finished devices. It is a small printed circuit board (PCB) that can either reside inside the OEM finished device or is re-designed for smaller size and packaged in a housing that will connect to the OEM finished device.
    The fundamental scientific technology has not changed. The BIS technology remains the same. The BIS Engine - 4 channel support (subject of this 510(k)) has the same basic function, and same operating principal as the Predicate Device.
    Only the software is changing. More specifically, the only difference is that the BIS Engine (subject of this 510(k)) can process up to 4 channels of EEG, compared to the Predicate Device, which can process up to 2 channels of EEG. The BIS processed parameter will only be calculated when in 2 channel maximum mode.

    AI/ML Overview

    The provided text is a 510(k) summary for the BIS Engine, a component of an EEG Monitor. The submission focuses on a software change allowing the device to process up to 4 channels of EEG, compared to the predicate device's 2 channels. The core BIS technology and algorithm remain unchanged.

    Here's an analysis of the acceptance criteria and study information, based on the provided text:

    1. Table of Acceptance Criteria and Reported Device Performance

    The document does not explicitly present a table of acceptance criteria with specific performance metrics (e.g., sensitivity, specificity, accuracy, or quantitative thresholds). Instead, it states that the device's substantial equivalence is based on:

    Acceptance Criteria CategoryReported Device Performance (Summary)
    Risk Analysis"There are no additional hazards introduced by the BIS Engine - 4 channel that are severe enough to warrant tracking on the risk management record."
    Software Validation"The applicable testing was completed... Results show all tests are acceptable."
    Substantial Equivalence"The BIS Engine - 4 channel support is substantially equivalent to the Predicate Device." This is based on the fundamental technology, indications for use, BIS technology/algorithm, parameters, operating principle, signal processing design, hardware design, and electrical/mechanical designs remaining the same. The only difference is the capability to process up to 4 channels (vs. 2) of EEG, with the BIS parameter still calculated in 2-channel mode.

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

    The document does not specify a "test set" in the context of a clinical performance study using patient data. The validation described is focused on software and risk analysis for the change from 2-channel to 4-channel EEG processing. It doesn't mention a dataset of patient EEGs used to evaluate the performance of the 4-channel processing itself in terms of diagnostic or clinical accuracy.

    • Sample Size: Not specified for a clinical performance test set.
    • Data Provenance: Not specified for a clinical performance test set.

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

    This information is not provided. The submission focuses on software validation and risk analysis, not on establishing ground truth for a clinical dataset.

    4. Adjudication Method for the Test Set

    This information is not provided, as there is no mention of a clinical "test set" requiring ground truth adjudication.

    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 MRMC study was performed or discussed. The device is an EEG monitor component, not an AI-assisted diagnostic tool for human readers in the context of a "multi-reader, multi-case" study. The 510(k) summary clearly states: "The BIS, a processed EBG variable, may be used as an aid in monitoring the effects of certain anesthetic agents." This implies it provides data, not an interpretation that human readers would "improve with."

    6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) Was Done

    The device itself, the BIS Engine, is an algorithm-only component that processes EEG signals. The submission describes its validation as part of a larger device. While the BIS algorithm itself processes data without human intervention, the "standalone performance" in the context of typical AI algorithm evaluations (e.g., sensitivity, specificity for a specific diagnostic task) is not presented. The document is about the change in channel capacity, not a de novo evaluation of the BIS algorithm's core performance.

    7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)

    Ground truth, in the context of a clinical performance study, is not described as part of this 510(k) submission. The validation focused on the software's ability to process the increased number of channels and on risk analysis for the hardware/software change.

    8. The Sample Size for the Training Set

    Not applicable. This submission is for a modification to an existing device's software (increasing channel capacity) where the core algorithm remains the same. There's no mention of retraining an AI model or a new training set.

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

    Not applicable, as there is no mention of a training set for an AI model in this submission.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1