Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K232385
    Device Name
    OxiplexTS200
    Manufacturer
    Date Cleared
    2024-03-01

    (205 days)

    Product Code
    Regulation Number
    870.2700
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    ISS Medical, Inc.

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The OxiplexTS200 tissue oximeter is intended to non-invasively estimate the percent oxygen saturation (StO2) in a volume of tissue. It is indicated for monitoring patients during circulatory or perfusion examinations of skeletal muscle or when there is a suspicion of compromised circulation. The device can be used for monitoring in Medical Clinics, laboratories and outpatient facilities.

    The OxiplexTS200 should not be used as the sole basis for diagnosis or therapy. The value of these measurements in disease states has not been demonstrated.

    Device Description

    The ISS Medical non-invasive tissue oximeter. OxiplexTS200. is intended for use as an adjunct monitor of regional oxy- and deoxy-hemoglobin concentration, and of hemoglobin oxygen saturation of blood in tissues during circulatory or perfusion examinations of skeletal muscle or when there is a suspicion of compromised circulation.

    The OxiplexTS200 is a device for use in spot-checking as well as continuous monitoring of patients in healthcare facilities. It is not intended for home use or to be used for "out of hospital" transport.

    The OxiplexTS200 is an instrument system and includes the following components:

    • OxiplexTS200 Unit with two sensors and phantom block ●
    • Power cable ●
    • Accessories (straps for sensors; strap for phantom block; dark cloth) ●
    • ISS flash memory
    • Operation Manual
    • Analoq Input module with USB cable (optional)
    • . Analog Output module with USB cable (optional)

    The OxiplexTS200 uses near-Infrared Spectroscopy (NIRS), a noninvasive diagnostic tool, to offer features for the assessment and monitoring of oxygenation in tissues such as brain and muscle. Near-infrared light (in the wavelength range 700-900 nm) can penetrate several centimeters into numerous body tissues. NIRS enables continuous real time measurements of changes in the hemoglobin oxygenation state, thus providing information on tissue oxygenation and hemodynamics.

    AI/ML Overview

    The ISS Medical OxiplexTS200 is a tissue oximeter that non-invasively estimates percent oxygen saturation (StO2) in tissue. Its performance testing compared it to the ViOptix ODISsey Tissue Oximeter model OXY-2.

    1. Acceptance Criteria and Reported Device Performance

    ParameterAcceptance Criteria (Predicate Device ViOptix ODISsey)Reported Device Performance (OxiplexTS200)
    Accuracy (StO2)80-100%: 2.7%
    60-80%: 2.3%
    40-60%: 5.2%
    10-40%: 13.3%50-100%: 2%
    26-49%: 3%
    0-25%: 10%
    Range (StO2)0-100%0-100%

    Note about accuracy: The provided tables show the stated accuracy of the predicate device (ViOptix ODISsey) and the OxiplexTS200, which are presented as similar. The study's finding of "essentially identical sensitive, reliable and accurate measurements of StO2" suggests that the OxiplexTS200 meets or performs comparably to the predicate's accuracy levels over a relevant range.

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

    • Sample Size (Clinical Test Set): 25 human subjects
    • Data Provenance (Clinical Test Set): Data was collected through comparison measurements acquired in the Biomedical Optics Research Laboratory at the Department of Neonatology at University Hospital Zürich in Zürich, Switzerland. This indicates prospective data collection from human subjects.
    • Sample Size (Bench Test Set): Not explicitly stated as a number of "samples", but the test involved a phantom containing human blood diluted in an optically scattering medium "at three levels; from physiological levels to increasingly higher concentrations."

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

    There is no mention of experts being used to establish a ground truth for the test set. The comparison was made between the OxiplexTS200 and a legally marketed predicate device (ViOptix ODISsey Tissue Oximeter model OXY-2). The predicate device's measurements serve as the reference for comparison. The study was conducted in a research laboratory directed by a Professor in Neonatology, indicating scientific oversight.

    4. Adjudication Method for the Test Set

    No adjudication method is described. The study compared the StO2 readings of the OxiplexTS200 directly against those of the predicate device.

    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

    A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not conducted. This device is an oximeter, not an AI-powered diagnostic tool requiring human interpretation.

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

    Yes, a standalone performance assessment was conducted for the OxiplexTS200 by comparing its readings to a predicate device. The device's output (StO2 measurements) was directly compared, as it functions as an automated measurement device.

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

    The ground truth for the clinical study was established by comparing the OxiplexTS200's StO2 readings against those obtained simultaneously from the legally marketed predicate device, the ViOptix ODISsey Tissue Oximeter model OXY-2. For the bench testing, a phantom with simulated physiological properties and known (controlled) StO2 levels was used, where the predicate device's readings served as the reference.

    8. The sample size for the training set

    The document does not provide information about a "training set" characteristic of machine learning models. The OxiplexTS200 is a hardware device utilizing Near-Infrared Spectroscopy (NIRS) principles, not a software algorithm that undergoes a training phase with a dataset in the conventional sense.

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

    As there is no mention of a "training set" in the context of machine learning, this information is not applicable. The device's operation is based on established NIRS principles and optical parameters, which are inherent to its design and calibration, rather than on a trained dataset.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1