Search Results

Hardware

· Guides

The Materialise PKA Guides are intended to be used as a surgical instrument to assist in the intra-operative positioning of Partial Knee Replacement components and in guiding the marking of bone before cutting of the bone.

The Materialise PKA Guides must be used in conjunction with the compatible prostheses families only: ZUK UNI. JOURNEY™ UNI, JOURNEY II UNI, JZ (Hybrid) UNI knee systems, Vanguard™ M Unicompartmental Knee System, Oxford® Partial Knee System and Persona® Partial Knee System.

The Zimmer Biomet Patient Specific Instruments are compatible for use with the Oxford® Partial Knee System as approved in P010014.

The Materialise PKA Guides are intended for single use only.

• Models

The Materialise PKA Models are intended to be used as a surgical instrument to assist in the intra-operative positioning of Partial Knee Replacement components.

The Materialise PKA Models must be used in conjunction with the compatible prostheses families only: ZUK UNI, JOURNEY™ UNI, JOURNEY II UNI, JZ (Hybrid) UNI knee systems, Vanguard™ M Unicompartmental Knee System, Oxford® Partial Knee System and Persona® Partial Knee System.

The Zimmer Biomet Patient Specific Instruments are compatible for use with the Oxford® Partial Knee System as approved in P010014.

The Materialise PKA Models are intended for single use only.

Software

The SurgiCase Knee Planner is intended to be used as a pre-surgical planner for knee orthopedic surgery. The software is used to pre-operatively plan the positioning of knee components. The SurgiCase Knee Planner allows the surgeon to visualize, measure, reconstruct, annotate and edit pre-surgical plan data. The generation of a surgery report along with a pre-surgical plan data file which is used as input data to design the Materialise Knee Guides and Models.

The Materialise PKA guide system is a medical device designed to implant a partial knee prosthesis during partial knee arthroplasty surgical procedures.

The device is a system that consists of the following two functional components:

• . A software component, branded as SurgiCase Knee Planner. This software is a planning tool used to generate a pre-surgical PKA plan for a specific patient.
• . A hardware component, branded as Materialise PKA Guides and Models, which are patientspecific guides and models that are based on a pre-surgical plan. This pre-surgical plan is generated using the software component. Materialise PKA Guides and Models is an instrument set containing a femur and/or tibia guide (s) and bone models (optional). Both femoral and tibial guides are designed and manufactured to fit the anatomy of a specific patient. If the surgeon requests it, a bone model of the femur and tibia is delivered with the Materialise PKA Guides. The Materialise PKA Guides and Models assist in the intra-operative positioning of partial knee replacement components. The guides assist in guiding the marking of bone before cutting and cutting of the bone. The models serve as a visual reference for the surgeon in the operating room.

The Materialise PKA Guides and Models must only be used within the intended use of the compatible components (510(k) cleared, legally marketed prosthesis).

The provided text is a 510(k) Premarket Notification summary for the Materialise PKA Guide System. It focuses on demonstrating substantial equivalence to a predicate device rather than presenting a detailed study proving the device meets specific acceptance criteria in the manner requested (e.g., in terms of sensitivity, specificity, or human improvement with AI assistance).

The document states that the new device is an update to an existing one (K173970) and primarily incorporates compatibility with additional knee implant systems (Persona® Partial Knee). It emphasizes that the device shares the same fundamental scientific technology, intended use, and software codebase as the predicate.

Therefore, many of the requested details, such as specific acceptance criteria for performance metrics like sensitivity/specificity, sample sizes for test sets, data provenance, expert ground truth establishment, or human-in-the-loop study results, are not present in this document. The document relies on the prior clearance of the predicate device and the claim that the changes do not raise new issues of safety or effectiveness.

However, based on the information provided, here's what can be extracted and inferred:

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

The document does not provide a quantitative table of acceptance criteria and reported device performance in terms of typical AI/medical device evaluation metrics (e.g., accuracy, sensitivity, specificity). Instead, the performance evaluation is framed as demonstrating substantial equivalence to the predicate device.

The performance aspects highlighted are:

• Hardware:
  • Applicability of previous testing for cleaning, debris, dimensional stability, and packaging.
  • Verification that "accuracy and performance of the system is adequate to perform as intended." (No specific metrics or thresholds provided).
  • Stability of device placement, surgical technique, intended use, and functional elements are similar to the predicate.
  • Biocompatibility re-evaluation: Shown to be non-cytotoxic, non-sensitizing, non-irritant, non-systematically toxic (acute), and non-pyrogenic according to ISO 10993-1:2008. (This is a qualitative acceptance of safety).
  • Sterilization re-evaluation: All samples passed the sterilization parameters in accordance with ISO 17665-1:2006. (This is a qualitative acceptance of safety).
• Software:
  • "New software validation/verification testing of the SurgiCase Knee Planner was done in support of this premarket notification in the form of end-user evaluations." (No specific metrics or quantitative performance results for these evaluations are provided).
  • The software technology is stated to have the same codebase and use the "exact same methods for design and verification and validation as the predicate device."
  • The "subject software technology differences have been demonstrated to not affectiveness or raise new issues of safety or effectiveness compared to the predicate device."

2. Sample sizes used for the test set and the data provenance:

• Test Set Sample Size: Not specified. The document mentions "end-user evaluations" for software and "simulated surgeries using rapid prototyped bone models" and "cadaver testing" (from the predicate device) for hardware, but no specific sample sizes for these test cases are given.
• Data Provenance: Not specified. It's implied some internal "end-user evaluations" were done. The document does not indicate the country of origin of the data or whether it was retrospective or prospective.

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

This information is not provided. The document states that "end-user evaluations" were performed but does not elaborate on the nature of these evaluations, who performed them, or how ground truth was established, particularly for performance metrics beyond basic functionality.

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

This information is not provided.

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 comparative effectiveness study is mentioned or implied. The device is a surgical guide system and planning software, not a diagnostic AI tool where human reader improvement is typically measured. The focus is on the hardware's ability to assist in positioning and guiding, and the software's ability to plan.

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

The software component (SurgiCase Knee Planner) is described as a "pre-surgical planner" that allows the surgeon to "visualize, measure, reconstruct, annotate and edit pre-surgical plan data." It explicitly states that the surgeon inspects, fine-tunes, and approves the pre-surgical plan. Therefore, it is inherently a human-in-the-loop system, and a standalone algorithm-only performance assessment (in the sense of a fully automated diagnosis or measurement) is not the primary mode of evaluation described. The "new software validation/verification testing... in the form of end-user evaluations" would likely involve human interaction with the software.

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

This is not explicitly stated in the provided text. For hardware performance, the "accuracy and performance" would likely be judged against technical specifications for guide fit and alignment, possibly through physical measurements on bone models or cadavers. For software, "end-user evaluations" might involve assessing the accuracy of measurements, reconstruction, or the usability of the planning interface against known anatomical landmarks or surgical objectives, likely established by expert surgeons. However, the exact method for establishing this "ground truth" is not detailed.

8. The sample size for the training set:

The document describes a 510(k) submission for a medical device (surgical guides and planning software), not an AI model that undergoes a distinct "training" phase with a large dataset. The software is built based on established algorithms and presumably validated against engineering specifications and clinical use cases, but there's no mention of a "training set" in the context of machine learning.

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/provided. The software is described as having the "same code base as the predicate device and uses exactly the same methods for design and verification and validation."

Ask a specific question about this device