Search Filters

Search Results

Found 1 results

510(k) Data Aggregation

    K Number
    K230540
    Date Cleared
    2023-07-25

    (148 days)

    Product Code
    Regulation Number
    892.2050
    Reference & Predicate Devices
    Predicate For
    N/A
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The PSPS bone model is indicated, based on patient-specific radiological images (CT scans), to assist in pre-operative orthopedic planning for patients able to undergo orthopedic procedures and able to be radiologically scanned.

    The PSPS bone model is a diagnostic tool to visually aid in orthopedic pre-operative surgical planning for skeletally mature individuals.

    Be advised, the quality of medical images determines the accuracy of the 3D bone models. Zimmer Biomet recommends using CT Protocol PMI® Patient-Matched Implants CT Protocol. Only images obtained less than six (6) months prior should be used for simulating and/or evaluating orthopedic treatment options.

    Device Description

    The Patient Specific Planning Solution™ 3D Bone Model is a 3-dimensional representation of the requested anatomical bone site. The Bone Models are diagnostic tools to allow the Surgeon to physically and visually aid in pre-operative orthopedic planning to facilitate the implantation of medical devices.

    The Patient Specific Planning Solutions™ are designed of polyamide (nylon) using additive manufacturing (selective laser sintering), based on the approved/finalized orthopedic pre-surgical plan and shipped prior to surgery. The Bone Models are provided non-sterile and are used pre-operatively for education, planning to aid in component selection, sizing, and placement based on patient specific radiological images (CT scan). Physical bone models' critical bony areas are printed at <1mm mean deviation.

    The full-scale 3D printed Patient Specific Bone Model is shipped to the patient's surgery to facilitate pre-operative planning.

    AI/ML Overview

    This document does not contain the detailed information necessary to fully answer all aspects of your request, specifically regarding a multi-reader multi-case (MRMC) comparative effectiveness study, the number of experts for human-in-the-loop studies, the adjudication method, or specific effect sizes. The submission focuses on substantial equivalence to a predicate device, Mimics Medical (K183105), rather than a detailed performance study against specific acceptance criteria for a new AI algorithm.

    However, based on the provided text, here's what can be extracted and inferred regarding the device's acceptance criteria and proven performance:

    Device: Patient Specific Planning Solution™ Bone Models

    Device Function Summary: These are 3D printed physical bone models derived from patient-specific CT scans. They are intended as diagnostic tools to visually aid in orthopedic pre-operative surgical planning and to facilitate the implantation of medical devices.

    1. Table of Acceptance Criteria and Reported Device Performance

    The acceptance criteria provided are primarily related to the geometric accuracy of the 3D-printed bone models compared to the digital input. The performance summary refers to the device utilizing the same geometric accuracy testing as its predicate.

    Acceptance Criteria CategorySpecific Criteria / RequirementReported Device Performance
    Geometric AccuracyPhysical bone models' critical bony areas are printed at <1mm mean deviation."The subject and predicate device utilize the same geometric accuracy of models testing." "Physical bone models' critical bony areas are printed at <1mm mean deviation." (This statement is listed as a description of the device's design, implying it's an inherent performance characteristic that the device is designed to meet and has been validated.) "Additional design and test method validation were performed on the subject device to further ensure geometric and design accuracy..." "Test method validation testing included assessment of the workflow from input digital replica."
    Material PropertiesN/A (implied by "design and test method validation" for "material")"Additional design and test method validation were performed on the subject device to further ensure geometric and design accuracy, including material..."
    Physical CharacteristicsAbsence of burrs and sharp edges (implied by "design and test method validation" for "burrs and sharp edges")"Additional design and test method validation were performed on the subject device to further ensure geometric and design accuracy, including... burrs and sharp edges..."
    CT Scan RequirementsUse of "CT Protocol PMI® Patient-Matched Implants CT Protocol" for optimal accuracy. Images obtained less than six (6) months prior.This is a recommendation for use to ensure accuracy; it's not a direct performance metric of the device itself but a prerequisite for optimal performance. The device is designed to work with images meeting these criteria.
    Workflow ValidationAssessment of the workflow from digital input to physical replica."Test method validation testing included assessment of the workflow from input digital replica."

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

    • Sample Size: Not explicitly stated. The document mentions "Summary of Performance Data" and speaks generally about "geometric accuracy of models testing" and "Additional design and test method validation" but does not provide specific numbers of models or datasets used for these tests.
    • Data Provenance: Not explicitly stated. The bone models are based on "patient-specific radiological images (CT scans)." No information on the country of origin or whether the data was retrospective or prospective is provided. Given the nature of a 510(k) submission for manufacturing medical devices, the data would typically be derived from existing clinical CT scans.

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

    Not applicable/Not stated. The "ground truth" for geometric accuracy testing would typically be the digital 3D model from which the physical model is printed (the "input digital replica"), not expert consensus on medical images for diagnostic purposes. The document doesn't describe any studies involving expert readers for image interpretation or diagnosis. The device's role is to provide a physical model for pre-surgical planning.

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

    Not applicable/Not stated. No adjudication method is mentioned as this is not a study assessing diagnostic accuracy of an AI algorithm on images, but rather the manufacturing accuracy of a physical model.

    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. An MRMC comparative effectiveness study was not performed or mentioned. The submission is for a physical bone model, not an AI software intended to assist human readers in image interpretation or diagnosis. The predicate device, Mimics Medical, is software for creating 3D models from medical images.

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

    Yes, in a sense, the geometric accuracy testing of the physical models against the digital models can be considered a standalone performance evaluation of the manufacturing process and the resulting physical product. It asserts that the physical models meet the specified dimensional tolerances (<1mm mean deviation in critical bony areas).

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

    The ground truth used for assessing the geometric accuracy of the physical bone models is the digital 3D model (the "input digital replica") generated from the patient's CT scans. The deviation of the physical model from this digital blueprint is measured.

    8. The sample size for the training set

    Not applicable/Not stated. This is a 510(k) submission for a physical device manufactured based on given digital data, not an AI algorithm that undergoes training. The "Mimics Medical" software mentioned is the predicate, which is used for segmentation and 3D model creation, but details about its training are not part of this submission.

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

    Not applicable, as no training set for an AI algorithm is described in this document for the device itself.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1