Search Filters

Search Results

Found 4 results

510(k) Data Aggregation

    Why did this record match?
    Reference Devices :

    K051380, K141056, K172326

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

    General Total Knee Arthroplasty (TKR) Indications:

    • Painful, disabling joint disease of the knee resulting from: noninflammatory degenerative joint disease (including osteoarthritis, traumatic arthritis, or avascular necrosis), rheumatoid arthritis or post-traumatic arthritis.
    • Post-traumatic loss of knee joint configuration and function.
    • Moderate varus, valgus, or flexion deformity in which the ligamentous structures can be returned to adequate function and stability.
    • Revision of previous unsuccessful knee replacement or other procedure.
    • Fracture of the distal femur and/or proximal tibia that cannot be stabilized by standard fracture-management techniques.

    The Triathlon Tritanium Tibial Baseplate and Tritanium Metal-Backed Patella components are indicated for both uncemented and cemented use.

    The Triathlon Total Knee System beaded and beaded with Peri-Apatite components are intended for uncemented use only.

    The Triathlon All Polyethylene tibial components are indicated for cemented use only.

    Additional Indications for Posterior Stabilized (PS) and Total Stabilizer (TS) Components:

    • Ligamentous instability requiring implant bearing surface geometries with increased constraint.
    • Absent or non-functioning posterior cruciate ligament.
    • Severe anteroposterior instability of the knee joint.

    Additional Indications for Total Stabilizer (TS) Components:

    • Severe instability of the knee secondary to compromised collateral ligament integrity or function.

    Indications for Bone Augments:

    • Painful, disabling joint disease of the knee secondary to: degenerative arthritis, rheumatoid arthritis, or post-traumatic arthritis, complicated by the presence of bone loss.
    • Salvage of previous unsuccessful total knee replacement or other surgical procedure, accompanied bone loss.

    Additional Indications for Cone Augments

    • Severe degeneration or trauma requiring extensive resection and replacement
    • Femoral and tibial bone voids
    • Metaphyseal reconstruction

    The Triathlon Tritanium® Cone Augments are intended for cemented or cemented or cementless use.

    Device Description

    The Triathlon® Posterior Stabilized (PS) Femoral Component - beaded with Peri-Apatite (PA) and Triathlon® Cruciate Retaining (CR) Femoral Component - beaded with Peri-Apatite (PA) are components of the Triathlon® Total Knee System previously cleared via 510(k)s K051380, K141056 and K172326. The subject Triathlon® Femoral Components are components of the Triathlon® Total Knee System and are used in total knee arthroplasty procedures. The subject Triathlon® Femoral Components are available in 8 different sizes and in left and right configurations that are anatomically suited to the left or right knee. The subject Triathlon® Femoral Components are manufactured from cast cobalt-chrome-molybdenum alloy (ASTM F75) with a cobalt-chrome-molybdenum alloy (ASTM F75) double layer porous coating (beading) on the femoral fixation surface. Additionally, the subject Triathlon® Femoral Components are coated with Peri-Apatite (ASTM F1185).

    The design and materials of the subject Triathlon® Femoral Components are identical to the predicate Triathlon® Femoral Components cleared via 510(k)s K051380, K141056 and K172326. The proposed modification is to introduce automated equipment for the first and second porous coating (beading) application process steps for the subject Triathlon® Femoral Components. There are no modifications proposed to the other components of the Triathlon® Total Knee System previously cleared via 510(k)s K051380, K141056 and K172326. The subject Triathlon® Femoral Components will have the same performance specifications as the predicate Triathlon® Femoral Components cleared via 510(k)s K051380, K141056 and K172326.

    AI/ML Overview

    This document describes the Stryker Corporation's 510(k) submission for the Triathlon Posterior Stabilized Femoral Component - beaded with Peri-Apatite and Triathlon Cruciate Retaining Femoral Component - beaded with Peri-Apatite. The submission, K200782, aims to demonstrate substantial equivalence to previously cleared devices.

    Here's a breakdown of the requested information based on the provided text:

    1. Table of Acceptance Criteria and Reported Device Performance

    The acceptance criteria are implied by the comparison to predicate devices and the performance of non-clinical testing. The device is considered to meet these criteria if it demonstrates "substantial equivalence" and the proposed modification does not affect safety or effectiveness.

    Acceptance Criteria (Implied)Reported Device Performance
    Substantial equivalence in intended useThe subject Triathlon Femoral Components have the same intended use as the predicate Triathlon Femoral Components.
    Substantial equivalence in indications for useThe subject Triathlon Femoral Components have the same Indications for Use as the predicate Triathlon Femoral Components.
    Substantial equivalence in designThe design of the subject Triathlon Femoral Components is identical to the predicate Triathlon Femoral Components. The proposed modification is to introduce automated equipment for the porous coating application, not a design change of the component itself.
    Substantial equivalence in materialsThe materials of the subject Triathlon Femoral Components are identical to the predicate Triathlon Femoral Components (cast cobalt-chrome-molybdenum alloy (ASTM F75) with a cobalt-chrome-molybdenum alloy (ASTM F75) double layer porous coating, coated with Peri-Apatite).
    Substantial equivalence in performance characteristicsThe subject Triathlon Femoral Components will have the same performance specifications as the predicate Triathlon Femoral Components. Non-clinical testing for porous coating type (beaded, sintered cobalt-chrome coatings) showed substantial equivalence.
    Substantial equivalence in operational principlesNot explicitly detailed, but implied by the overall statement of substantial equivalence.
    Proposed modification does not affect safety or effectivenessNon-clinical testing for porous coating type (beaded, sintered cobalt-chrome coatings) demonstrated that the proposed modification does not affect safety or effectiveness.

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

    The document does not explicitly state a sample size in the context of a test set for clinical performance. The evaluation conducted here is primarily non-clinical, focusing on the comparison of an updated manufacturing process against existing devices.

    • Test Set: Not applicable in the traditional sense of a clinical test set with patient data. The "test set" consists of the subject Triathlon Femoral Components undergoing non-clinical testing.
    • Data Provenance: The testing was non-clinical laboratory testing. No geographical or temporal (retrospective/prospective) information is provided as it's not human subject data.

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

    Not applicable. This submission relies on non-clinical testing for performance characteristics, specifically for the porous coating process. The "ground truth" is established through physical and material science testing standards, not expert consensus on medical images or diagnoses.

    4. Adjudication Method for the Test Set

    Not applicable. As described above, the evaluation is based on non-clinical laboratory testing, not a human reader assessment requiring 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

    Not applicable. This is a submission for an orthopedic implant (knee femoral component), not an AI-powered diagnostic or assistive device that would involve human readers.

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

    Not applicable. This is not an algorithm or AI device. The "performance" being evaluated is the physical and material characteristics of a medical implant after a manufacturing process change.

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

    The ground truth used for proving the device meets acceptance criteria is based on non-clinical laboratory testing standards and direct comparison of material properties and design to legally marketed predicate devices. Specifically, it mentions "Testing for porous coating type a. beaded, sintered cobalt-chrome coatings on a cobalt-chrome substrate as per FDA guidance document, 'Guidance Document for Testing Orthopedic Implants with Modified Metallic Surfaces Apposing Bone or Bone Cement,' dated April 28, 1994."

    8. The Sample Size for the Training Set

    Not applicable. Since there's no clinical study or AI algorithm involved, there is no "training set" in the context of this submission. The device is a physical implant.

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

    Not applicable as there is no training set.

    Ask a Question

    Ask a specific question about this device

    K Number
    K132624
    Date Cleared
    2013-11-26

    (96 days)

    Product Code
    Regulation Number
    888.3565
    Why did this record match?
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    General Total Knee Arthroplasty (TKR) Indications:

    • Painful, disabling joint disease of the knee resulting from: noninflammatory degenerative joint disease (including osteoarthritis, traumatic arthritis, or avascular necrosis), rheumatoid arthritis or post-traumatic arthritis.
    • Post-traumatic loss of knee joint configuration and function.
    • Moderate varus, valgus, or flexion deformity in which the ligamentous structures can be returned to adequate function and stability.
    • Revision of previous unsuccessful knee replacement or other procedure.
    • Fracture of the distal femur and/or proximal tibia that cannot be stabilized by standard fracture -management techniques.

    The Triathlon® Tritanium® Tibial Baseplate and Tritaium® Metal-Backed Patella components are indicated for both uncemented and cemented use.

    The Triathion® Total Knee System beaded and beaded with Peri-Apatite components are intended for uncemented use only.

    The Triathlon® All Polyethylene tibial components are indicated for cemented use only.

    Additional Indications for Posterior Stabilized (PS) and Total Stabilizer (TS) Components:

    • Ligamentous instability requiring implant bearing surface geometries with increased constraint.
    • Absent or non-functioning posterior cruciate ligament.
    • Severe anteroposterior instability of the knee joint.

    Additional Indications for Total Stabilizer (TS) Components:

    • Severe instability of the knee secondary to compromised collateral ligament integrity or function.

    Indications for Bone Augments:

    • Painful, disabling joint disease of the knee secondary to: degenerative arthritis, rheumatoid arthritis, or post-traumatic arthritis, complicated by the presence of bone loss.
    • Salvage of previous unsuccessful total knee replacement or other surgical procedure, accompanied by bone loss.
    Device Description

    The Triathlon® Tritanium® Metal-Backed Patella is an extension of the Triathlon® Total Knee System product line for use in primary and revision Total Knee Arthroplasty. It is a sterile, single-use, non-modular metal-backed patella that is manufactured from UHMWPE (ASTM F648) and commercially pure titanium (ASTM F1580). The device is offered in symmetric and asymmetric designs that are available in multiple sizes. The metalbacking features a porous-coated posterior surface and three porous-coated pegs to provide cemented or cementless fixation to bone.

    AI/ML Overview

    This document, a 510(k) Summary for the Triathlon® Tritanium® Metal-Backed Patella, focuses on demonstrating substantial equivalence to previously cleared devices rather than presenting a study of a device meeting specific acceptance criteria through performance data. Therefore, many of the requested elements for describing an acceptance criteria study are not present in this submission.

    Here's a breakdown based on the provided text:

    1. Table of Acceptance Criteria and Reported Device Performance

    This document does not contain a table of acceptance criteria with corresponding device performance metrics in the typical sense of a clinical or analytical performance study. Instead, it lists non-clinical laboratory tests performed to demonstrate substantial equivalence to predicate devices. The "reported device performance" in this context is the successful completion of these tests, implying that the new device performs comparably to the predicates.

    Acceptance Criteria (Implied by Test Type)Reported Device Performance
    Material Properties:
    Elemental Composition (ASTM E1941, E1447, E1409)Tested and found comparable to predicates
    Metallurgical & Morphological Properties (ASTM E112, F1854)Tested and found comparable to predicates
    Mechanical Properties (ASTM F1147, F1044, F1160, E8)Tested and found comparable to predicates
    Plastic Deformation of Porosity (ASTM F1854)Tested and found comparable to predicates
    Mechanical Performance:
    Static Tensile Bond Strength of UHMWPE/Metal InterfaceTested and found comparable to predicates
    Static Peg Shear StrengthTested and found comparable to predicates
    Patello-Femoral Contact Stress/Contact AreaTested and found comparable to predicates
    Malaligned Endurance TestingTested and found comparable to predicates
    Patellar Subluxation TestingTested and found comparable to predicates

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

    • Sample Size: Not explicitly stated for each test. For non-clinical laboratory testing, the sample size typically refers to the number of test articles (patellar components) subjected to each specific test. This tends to be much smaller than clinical study sample sizes and is dependent on the specific ASTM standard or internal protocol used.
    • Data Provenance: The tests are non-clinical laboratory tests, likely conducted by the manufacturer (Stryker Orthopaedics) or a contract laboratory. The "country of origin of the data" would typically be the location of the testing facility, which is not specified but presumed to be a regulated environment. The data is retrospective in the sense that these are engineering and material characterization tests performed on manufactured devices.

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

    This information is not applicable as this submission is for a medical device and relies on engineering and material testing standards (ASTM) to demonstrate substantial equivalence, not on expert ground truth for an AI or diagnostic device.

    4. Adjudication Method for the Test Set

    This is not applicable. The "test set" here refers to physical components undergoing laboratory testing, not, for example, medical images requiring expert adjudication.

    5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

    No, an MRMC comparative effectiveness study was not done. This type of study is used for diagnostic or AI-assisted devices to assess human reader performance. This submission is for a physical orthopedic implant.

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

    No, a standalone algorithm performance study was not done. This concept applies to AI/software as a medical device, which this orthopedic implant is not.

    7. The Type of Ground Truth Used

    The "ground truth" for this submission are the established engineering and material specifications, as well as the performance characteristics of the predicate devices. The new device is tested against these benchmarks (often defined by ASTM standards) to show that its properties are within acceptable ranges and comparable to the predicates.

    8. The Sample Size for the Training Set

    This is not applicable. There is no "training set" in the context of an orthopedic implant submission based on substantial equivalence through non-clinical testing. This term is relevant for machine learning algorithms.

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

    This is not applicable for the same reasons as point 8.

    Ask a Question

    Ask a specific question about this device

    K Number
    K122053
    Manufacturer
    Date Cleared
    2012-10-24

    (103 days)

    Product Code
    Regulation Number
    888.3565
    Why did this record match?
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The ShapeMatch Cutting Guides are intended to be used as patient-specific surgical instrumentation to assist in the positioning of total knee arthroplasty components intraoperatively and in guiding the marking of bone before cutting provided that anatomic landmarks necessary for alignment and positioning of the implant are identifiable on patient imaging scans.

    The ShapeMatch Cutting Guides are intended for use with the CR, PS and CS components of the Triathlon® Knee System. The indications for use of the Triathlon Knee System when used with the ShapeMatch Cutting Guides are:

    General Total Knee Arthroplasty (TKR) Indications:

    • Painful, disabling joint disease of the knee resulting from: degenerative arthritis, . rheumatoid arthritis or post-traumatic arthritis.
    • Post-traumatic loss of knee joint configuration and function. ●
    • Moderate varus, valgus, or flexion deformity in which the ligamentous structures . can be returned to adequate function and stability.
    • Failed reconstruction procedures which did not involve the implantation of hardware on . the condylar surfaces

    Additional Indications for Posterior Stabilized (PS):

    • Ligamentous instability requiring implant bearing surface geometries with . increased constraint.
    • Absent or non-functioning posterior cruciate ligament. .
    • Severe anteroposterior instability of the knee joint. .

    The ShapeMatch Cutting Guides are intended for single use only.

    Device Description

    The ShapeMatch Cutting Guides are single-use, disposable, cutting guides designed and manufactured from patient imaging data (MRI/CT). The cutting guides are used to aid the surgeon intra-operatively in making the initial distal femoral and the initial proximal tibial bone cuts during a total knee arthroplasty surgery. The cutting guides also establish the references for component orientations. The cutting guides are manufactured from polyoxymethylene per ASTM F1855.

    The ShapeMatch Cutting Guides are intended for use with the Triathlon® Knee System (Cruciate Retaining (CR), Posterior Stabilized (PS) and Condylar Stabilizing (CS)) determined substantially equivalent via the following 510(k)s K031729, K040267, K042993, K051146, K051380, K053514, K062037, K061251, K063423, and K072575.

    The accessory Triathlon® Extra-medullary (EM) Universal Goniometer is available for the surgeon to use intra-operatively to check the position of the femoral and tibial components. The goniometer mates with the saw slots on both the femoral and tibial guides for use in referencing the cuts with anatomic landmarks prior to resection of the bone. The accessory Triathlon® EM Universal Goniometer is made from Stainless Steel per ASTM A564.

    AI/ML Overview

    The provided 510(k) summary for the ShapeMatch® Cutting Guides ([K122053](https://510k.innolitics.com/search/K122053)) does not include information about specific acceptance criteria or a clinical study designed to prove the device meets such criteria.

    Instead, it relies on non-clinical testing and substantiates equivalence to a predicate device. Here's a breakdown based on the categories requested:

    1. A table of acceptance criteria and the reported device performance:

    • Acceptance Criteria: Not explicitly stated in terms of measurable performance thresholds.
    • Reported Device Performance: The document states "Detailed software verification and validation were performed per FDA Guidance, "General Principles of Software Validation: Final Guidance for Industry and FDA Staff." This indicates that the software aspects of the device (likely related to generating the custom guides from imaging data) were tested for correctness and functionality, but specific performance metrics (e.g., accuracy of cuts, fit of components) are not quantified in this summary.

    2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective):

    • Not applicable for clinical efficacy. The document explicitly states "Clinical Testing: Not Applicable to validate changes." The software verification and validation would have involved various test cases, but details on sample size or data provenance for those tests are not provided.

    3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience):

    • Not applicable for clinical efficacy. Since clinical testing was deemed "not applicable," there's no mention of experts establishing a ground truth for a clinical test set.

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

    • Not applicable for clinical efficacy. No information on adjudication methods for a clinical test set.

    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:

    • Not applicable. This device is a cutting guide, not an AI-assisted diagnostic tool for "human readers." No MRMC study was conducted or referenced.

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

    • The device's function is to generate physical cutting guides from imaging data. The "algorithm" here would be the software that processes the MRI/CT data and designs the guide. The "Detailed software verification and validation" would assess the standalone performance of this software in accurately translating image data into guide designs. However, no specific metrics or studies demonstrating this standalone performance (e.g., how precisely the software determines bone geometry or cut planes compared to a 'gold standard') are provided in this summary.

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

    • For the "software verification and validation," the ground truth would likely be established through engineering specifications, validated anatomical models, or potentially comparisons to manual measurements/designs. Specific details are not provided.

    8. The sample size for the training set:

    • This information is not provided, as the summary focuses on software verification and validation rather than a deep learning machine learning model that would require a distinct training set. The device appears to be based on algorithmic design from patient imaging.

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

    • Not applicable as no specific training set for a machine learning model is described. The ground truth for the software development (if one considers the development data as a "training set" in a broader sense) would be based on established anatomical knowledge, engineering principles, and potentially measurements from cadaveric or synthetic models.

    In summary: The 510(k) for the ShapeMatch® Cutting Guides relies on non-clinical software verification and validation for regulatory submission, asserting substantial equivalence to a predicate device. It explicitly states that clinical testing was "Not Applicable to validate changes." Therefore, many of the requested details regarding clinical study design, acceptance criteria, and ground truth establishment for clinical performance are not present in this document.

    Ask a Question

    Ask a specific question about this device

    K Number
    K110533
    Manufacturer
    Date Cleared
    2011-05-19

    (84 days)

    Product Code
    Regulation Number
    888.3565
    Why did this record match?
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The Stryker® Patient Specific Cutting Guides are intended to be used as patient-specific surgical instrumentation to assist in the positioning of total knee arthroplasty components intraoperatively and in guiding the marking of bone before cutting.

    The Stryker Patient Specific Cutting Guides are intended for use with the CR, PS and CS components of the Triathlon® Knee System. The indications for use of the Triathlon Knee System when used with the Stryker Patient Specific Cutting Guides are:

    General Total Knee Arthroplasty (TKR) Indications:

    • Painful, disabling joint disease of the knee resulting from: degenerative arthritis, rheumatoid arthritis or post-traumatic arthritis.
    • Post-traumatic loss of knee joint configuration and function.
    • Moderate varus, valgus, or flexion deformity in which the ligamentous structures can be returned to adequate function and stability.
    • Failed reconstruction procedures which did not involve the implantation of hardware on the condylar surfaces

    Additional Indications for Posterior Stabilized (PS):

    • Ligamentous instability requiring implant bearing surface geometries with increased constraint.
    • Absent or non-functioning posterior cruciate ligament.
    • Severe anteroposterior instability of the knee joint.

    The Stryker Patient Specific Cutting Guides are intended for single use only.

    Device Description

    The Stryker® Patient Specific Cutting Guides are single-use, disposable, cutting guides designed and manufactured from patient imaging data (MRI/CT). The cutting guides are used to aid the surgeon intra-operatively in making the initial distal femoral and the initial proximal tibial bone cuts during a total knee arthroplasty surgery. The cutting guides also establish the references for component orientations. The cutting guides are manufactured from polyoxymethylene per ASTM F1855.

    The Stryker Patient Specific Cutting Guides are intended for use with the Triathlon® Knee System (Cruciate Retaining (CR), Posterior Stabilized (PS) and Condylar Stabilizing (CS)) determined substantially equivalent via the following 510(k)s K031729, K040267, K042993, K051146, K051380, K053514, K062037, K061251, K063423, and K072575.

    The accessory Triathlon® Extra-medullary (EM) Universal Goniometer is available for the surgeon to use intra-operatively to check the position of the femoral and tibial components. The goniometer mates with the saw slots on both the femoral and tibial guides for use in referencing the cuts with anatomic landmarks prior to resection of the bone. The accessory Triathlon® EM Universal Goniometer is made from Stainless Steel per ASTM A564.

    AI/ML Overview

    Here's a breakdown of the acceptance criteria and the study information for the Stryker Patient Specific Cutting Guides, based on the provided 510(k) summary:

    1. Table of Acceptance Criteria and Reported Device Performance

    The provided document does not explicitly state numerical acceptance criteria. Instead, the non-clinical testing aimed to demonstrate comparable accuracy to conventional jig-based instrumentation, and the clinical testing aimed to show a strong co-relationship between MRI and long-standing radiograph measurements.

    Acceptance Criteria (Implied)Reported Device Performance
    Non-Clinical (Accuracy of Cutting Guides):
    Accuracy relative to pre-operative plan.
    Placement accuracy comparable to conventional jig-based instrumentation.Accuracy quantified in a cadaveric model.
    Placement accuracy achieved with the Stryker Patient Specific Knee Cutting Guides is comparable to conventional jig-based instrumentation.
    Clinical (Accuracy of MRI Protocol):
    Accuracy and repeatability of measurements from a new MRI protocol.
    Strong co-relationship between MRI and long-leg radiograph for mechanical alignment.Accuracy and repeatability of MRI measurements were quantified.
    A strong co-relationship between the long leg x-ray and augmented MRI scanning was demonstrated.

    2. Sample Size and Data Provenance

    • Non-Clinical (Cadaveric Assessment):

      • Sample Size (Test Set): Not explicitly stated, described as "a cadaveric model."
      • Data Provenance: Cadaveric data; implicitly from a controlled laboratory setting (likely within the US, but not specified). It is a prospective study as it involved active experimentation.
    • Clinical Research Study:

      • Sample Size (Test Set): Not explicitly stated.
      • Data Provenance: Not specified (e.g., country of origin). Described as a "clinical research study," implying prospective data collection on human subjects.

    3. Number and Qualifications of Experts for Ground Truth

    The document does not provide information on the number or qualifications of experts used to establish ground truth for either the non-clinical or clinical studies.

    4. Adjudication Method for the Test Set

    The document does not provide any information regarding an adjudication method for the test set.

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

    No multi-reader multi-case (MRMC) comparative effectiveness study is reported that details the effect size of human readers improving with AI vs. without AI assistance. The non-clinical study compared the device's accuracy to conventional jig-based instrumentation, which is a different type of comparison.

    6. Standalone Performance Study

    The studies conducted describe the performance of the "Stryker Patient Specific Cutting Guides" which are patient-specific surgical instruments generated from patient imaging data (MRI/CT). The studies assess the accuracy of these guides and the MRI protocol used to generate the data for the guides. This can be considered a standalone performance assessment of the device's ability to facilitate accurate cuts and the accuracy of the imaging protocol that informs the device. However, it's not "algorithm-only" in the sense of a diagnostic AI, as the device itself is a physical cutting guide. The software component mentioned (detailed software verification and validation) relates to the generation of these guides.

    7. Type of Ground Truth Used

    • Non-Clinical (Cadaveric Assessment): The ground truth was based on the "pre-operative plan" for bone cuts, which would have been established by a surgeon or planning software. The success was measured by comparing the actual cuts made using the guides to this plan.
    • Clinical Research Study: The ground truth for knee alignment was established by "long standing radiograph images," which are a standard clinical method for assessing mechanical alignment.

    8. Sample Size for the Training Set

    The document makes no mention of a training set sample size. The device is generated from individual patient MRI/CT data, so it's a patient-specific design rather than an AI model trained on a large dataset in the conventional sense. The "software verification and validation" would be a separate process from a training set for a machine learning model.

    9. How Ground Truth for Training Set was Established

    As no training set is described for an AI model, there is no information on how its ground truth would have been established. The core of the device relies on patient-specific imaging data translated into a physical guide, not on a machine learning model trained on a general dataset.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1