Search Results

The Stryker OrthoMap Precision Knee system, which is comprised of the OrthoMap Precision Knee 5.0 Software and a platform of the NAV3i platform family, is intended as a planning and intraoperative guidance system to enable open or percutaneous image guided surgery.

The system can be used for intraoperative guidance where a rigid anatomical structure can be identified. The system is indicated for conditions of the knee joint in which the use of computer assisted surgery may be appropriate.

The Stryker OrthoMap Precision Knee system is intended to be used as a planning and intraoperative guidance system to enable open or percutaneous image guided knee surgery. The system uses wireless optical tracking technology to display to the surgeon the intraoperative location of navigated surgical instruments relative to a computed anatomical model of the patient's leg (femur and tibia). The computed model is based on an intra-operative anatomy survey of the leg. The system consists of a Stryker surgical software application (software), which runs on a platform, consisting of a Stryker computer, a navigation camera, an IO-Tablet and a monitor. The Stryker surgical software application interfaces with smart instruments (e.g. patient trackers, instrument trackers or pointers) and several accessories enabling the tracking of surgical instruments.

The Stryker OrthoMap Precision Knee 5.0 software is compatible with the NAV31 Platform Family. The NAV3i platform family is a family of platforms that, when used with a surgical software application, displays patient specific images and/or patient specific anatomical landmark information and tracks the position and movement of surgical instruments in relation to a target anatomical site on a patient. The NAV3i platform family consists of the following three platforms that have been previously cleared independently or with other Stryker surgical software applications:

• Stryker NAV3 Platform
• Stryker NAV3i Platform ●
• Stryker NAVSuite3 Kit

The platforms consist of the following components:

• Stryker computer
• Navigation camera ●
• IO-Tablet ●
• Monitor
• Mobile cart (if applicable) ●

This document is a 510(k) summary for the Stryker OrthoMap Precision Knee system. It does not describe a study that validates AI performance, but rather outlines the performance criteria and testing for a computer-assisted surgical guidance system. Therefore, some of the requested information regarding AI-specific studies (e.g., MRMC studies, training set details) will not be available.

Here's an analysis of the provided text for the requested information:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Test Set Sample Size: The document does not specify a distinct "test set" in the context of an AI-driven system. Instead, performance testing (bench testing) was conducted.
  • Accuracy Testing: Involved tests according to ASTM Standard F2554-10. The sample size for this specific test is not provided.
  • System Accuracy Testing: Used a "mechanical leg mimicking the patient's anatomy." The number of mechanical legs or repetitions is not specified.
  • Clinical Workflow Testing: Involved "simulated complete total knee arthroplasty procedures using Sawbones." The number of Sawbones or simulated procedures is not specified.
• Data Provenance: The data is from bench testing and simulated procedures, not human patient data. Therefore, country of origin or retrospective/prospective status is not applicable in the traditional sense. It is all laboratory-generated data.

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

• This information is not applicable. The device is a surgical guidance system relying on physical measurements and mechanical models, not interpretation of medical images or data by human experts for ground truth in this context. The "ground truth" for accuracy testing would be the known, precise measurements and angles of the mechanical testing setups.

4. Adjudication Method for the Test Set

• Not applicable as there is no human interpretation or subjective assessment of a test set that would require 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

• No, an MRMC comparative effectiveness study was not done. This document pertains to a computer-assisted surgical navigation system, not an AI-driven image interpretation or diagnostic tool that would typically involve human readers. The focus is on the accuracy and functionality of the guidance system itself.

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

• Yes, in essence, standalone performance was evaluated. The "Performance Testing - Bench" section describes tests aimed at verifying the accuracy and functionality of the system (localization, tracking, software algorithms) in a controlled environment, mimicking patient anatomy. This is an evaluation of the algorithm's performance independent of real-time human surgical input, demonstrating its intrinsic accuracy and function.

7. The Type of Ground Truth Used

• The ground truth used for the bench testing was based on:
  • Standardized Test Procedures: For ASTM accuracy testing, the ground truth would be defined by the standardized procedure itself and the known parameters of the test setup.
  • Mechanical Models and Known Parameters: For system accuracy testing and clinical workflow testing, the ground truth was derived from the precise, known measurements and configurations of the "mechanical leg mimicking the patient's anatomy" and "Sawbones." Essentially, these represent controlled and measurable physical realities within the bench test environment.

8. The Sample Size for the Training Set

• This information is not provided because the document describes a computer-assisted surgical guidance system, not a device developed using machine learning that requires a "training set" in the conventional sense. The "software" here likely refers to deterministic algorithms and established mathematical models for navigation and guidance, rather than a learned AI model.

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

• Not applicable, as there is no mention of a "training set" in the context of machine learning. The software's development would likely be based on engineering principles, anatomical models, and mathematical algorithms, not an iterative training process with labeled data.

Ask a specific question about this device