Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K060976
    Date Cleared
    2007-03-27

    (351 days)

    Product Code
    Regulation Number
    870.2120
    Reference & Predicate Devices
    Why did this record match?
    Device Name :

    MOORLD12-B1 LASER DOPPLER BURNS IMAGER

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

    The moorLDI2-BI laser Doppler burns imager assesses the blood flow in debrided burn wounds of the skin. It is intended to be used as an aid to burn wound management for patients with Total Body Surface Area burn of up to 30%.

    Device Description

    The moorLDI2-BI laser Doppler imager is a measurement device to aid the clinician judge the healing potential of burns and the need for surgery. It uses the laser Doppler technique to quantify the blood flow in an area of skin damaged by a burn. The device has the means to scan a low power visible red laser beam or low power near infrared laser beam combined with a visible red target beam, across the skin surface enabling a colour coded image of the blood flow in the burn area and the surrounding normal skin to be recorded, together with a monochrome photo image. In addition, a colour video image of the scanned area is recorded using a CCD camera which is an integral part of the device. Regions of interest (e.g. a burn area) can be selected and the statistics of the blood flow values, within the region, calculated and displayed.

    AI/ML Overview

    Here's an analysis of the provided text regarding the acceptance criteria and study for the moorLDI2-BI Laser Doppler Burns Imager:

    1. Table of Acceptance Criteria and Reported Device Performance

    Acceptance Criteria (Prediction Accuracy for Healing Potential)Reported Device Performance
    Better than 90% accuracyBetter than 90% accuracy

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

    • Test Set Sample Size: Not explicitly stated as a number of cases or patients. The study was conducted "over a 3 year period, from 2001 to 2004."
    • Data Provenance: The study was conducted by a group of experienced burns surgeons working in 5 hospital burns centers. The country of origin is not explicitly stated, but the company is based in the UK and the initial predicate device was cleared by the FDA, suggesting international relevance. The study appears to be prospective in nature, as it investigated the use of the devices over a 3-year period to identify and quantify blood flow ranges for prediction.

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

    • Number of Experts: A "group of experienced burns surgeons" from 5 hospital burns centers. The exact number is not specified, but it implies multiple experts.
    • Qualifications of Experts: "Experienced burns surgeons." No further details on years of experience are provided.

    4. Adjudication Method for the Test Set

    The text mentions that the experts "identified and quantified three laser Doppler blood flow ranges (high, medium and low) which allow an experienced burns surgeon to predict the healing potential." This suggests a consensus-based approach among the group of surgeons, but a specific adjudication method (e.g., 2+1, 3+1) is not explicitly stated.

    5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

    A MRMC comparative effectiveness study was not explicitly mentioned. The study described focused on the device's ability to aid surgeons in prediction, not on comparing surgeon performance with and without AI assistance or the device.

    6. Standalone (Algorithm Only) Performance Study

    A standalone performance study was not explicitly mentioned. The device is described as an "aid to burn wound management" and for use "by a trained operator (a burns surgeon or under the direction of a burns surgeon)," indicating a human-in-the-loop system rather than a fully autonomous algorithm. The "PC software uses a colour palette for blood flow images based on the results of this clinical investigate which can be used by a trained operator... as an aid to predicting healing potential."

    7. Type of Ground Truth Used

    The ground truth was based on the healing potential of the burn, categorized as "healing in 21 days." This is a form of outcomes data or clinical endpoint as assessed by experienced burns surgeons.

    8. Sample Size for the Training Set

    The document does not explicitly mention a separate training set or its sample size. The description of the performance study sounds more like a validation of pre-established "laser Doppler blood flow ranges (high, medium and low)" rather than a development or training study for a new algorithm within the moorLDI2-BI. The "PC software for the moorLDI2-BI is designed specifically for the recording and measurement of blood flow in skin burns... uses a colour palette for blood flow images based on the results of this clinical investigate." This implies the "clinical investigate" informed the color palette and predictive ranges used in the software, rather than explicitly training a machine learning model.

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

    As no separate training set is explicitly described in the context of a machine learning algorithm, the establishment of ground truth for a training set is not applicable in the conventional sense of AI/ML development. Instead, the "laser Doppler blood flow ranges (high, medium and low)" (which could be considered analogous to predictive categories) were "identified and quantified" by the "group of experienced burns surgeons" over the 3-year study period based on observed healing outcomes.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1