(191 days)
The Intellijoint HIP Generation 2A System is a computer-controlled, optical localizer intended to provide intra-operative measurements to a surgeon to aid in selection and positioning of orthopaedic implant system components, where a reference to a rigid anatomical structure can be identified. The system is only compatible with straight acetabular cup impactors.
The Intellijoint HIP Generation 2A System is indicated for patients undergoing orthopaedic surgery, and where the use of stereotactic surgery is considered safe and effective. The system aids the surgeon in performing intra-operative measurements including measurements of limb position, and implant component positioning.
Example orthopaedic surgical procedures include, but are not limited to:
- Total Hip Arthroplasty
- Minimally Invasive Hip Arthroplasty
The intellijoint HIP® Generation 2A System is an imageless optical navigation system intended for use in orthopaedic surgery. The device provides intra-operative assessment of patient leg length, offset, and acetabular cup angle during Total Hip Arthroplasty (THA) procedures. The system is composed of an infrared Camera, Tracker, computer workstation, software, and bone fixation instruments/hardware.
The intellijoint HIP® Generation 2A System is an update to the intellijoint HIP® System previously cleared in 510(k) K151364. The updates include revised software to support THA procedures performed using the Direct Anterior Approach, modified methods of patient registration, and leg position measurement.
The Intellijoint HIP Generation 2A System is an imageless optical navigation system intended for intra-operative measurements to aid in the selection and positioning of orthopaedic implant system components, particularly for Total Hip Arthroplasty (THA). This 510(k) summary provides information on the device's acceptance criteria and the studies conducted to demonstrate its performance.
1. Table of Acceptance Criteria and Reported Device Performance
The submission details three main categories of tests: Tracking System Accuracy and Robustness, Benchtop Accuracy, and Software Functional and Unit Tests under "Verification"; and Anatomical Phantom Simulated Use and Clinical Accuracy and Cadaver Simulated Use under "Validation."
| Acceptance Criteria Category | Specific Criteria/Description | Reported Device Performance |
|---|---|---|
| Verification | ||
| Tracking System Accuracy and Robustness | Accuracy verified according to ASTM F2554-10. Testing simulated normal conditions, worst-case use scenarios, and realistic tracking disturbances. | "All accuracy specifications and robustness requirements were met." |
| Benchtop Accuracy | Verified clinical accuracy requirements using calibrated benchtop test fixtures. The specific numerical accuracy targets are not provided in this summary but are implied to be part of the "clinical accuracy requirements." | "All accuracy requirements were met." |
| Software Functional and Unit Tests | Verified that the software application satisfies functional requirements and performs as intended. Algorithms and measurement calculations were also verified. | "Software satisfied all requirements and specifications." |
| Validation | ||
| Anatomical Phantom Simulated Use and Clinical Accuracy | Simulated use testing on bone models by orthopaedic surgeons following a typical workflow. This test validated that the device satisfies user needs, intended use, and clinical accuracy requirements. Accuracy was assessed by comparing simulated use measurements with ground truth values. Specific numerical accuracy targets are not provided. | "All user needs and clinical accuracy requirements were met." |
| Cadaver Simulated Use | Simulated use testing in a cadaver lab. This test validated that the device satisfies clinical use requirements and performs as intended when operated by a surgeon, used on human specimens, and used in a realistic OR environment. | "All clinical use requirements were met." |
2. Sample Sizes Used for the Test Set and Data Provenance
- Tracking System Accuracy and Robustness: The document does not specify a distinct "test set" sample size in terms of number of cases or subjects. The testing involved simulating "normal conditions, and a variety of worst-case use scenarios and realistic tracking disturbances." This implies a varied set of conditions rather than a fixed number of "samples."
- Benchtop Accuracy: Not specified. Testing used "calibrated benchtop test fixtures," implying a controlled laboratory environment.
- Anatomical Phantom Simulated Use and Clinical Accuracy: Not specified in terms of the number of phantom models or simulated procedures. Data provenance is implied to be laboratory-based (simulated use on bone models), likely in North America (Canada, given the company's location). This was a prospective simulation.
- Cadaver Simulated Use: Not specified in terms of the number of cadavers or simulated procedures. Data provenance is implied to be laboratory-based (cadaver lab), likely in North America. This was a prospective simulation.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
- Tracking System Accuracy and Robustness: Ground truth would likely be established by a reference tracking system or measurement standard, not human experts.
- Benchtop Accuracy: Ground truth would be established by "calibrated" measurement systems and fixtures, not human experts.
- Anatomical Phantom Simulated Use and Clinical Accuracy: Orthopaedic surgeons performed the simulated use. Their number and specific qualifications (e.g., years of experience) are not specified. It is reasonable to assume they were experienced in THA. The "ground truth values" for accuracy comparison would not be established by these surgeons but by precision measurement tools on the phantom models.
- Cadaver Simulated Use: Orthopaedic surgeons operated the system. Their number and specific qualifications are not specified. Ground truth for clinical use requirements would be determined by whether the system performed as intended under realistic conditions, likely evaluated by the surgeons and study coordinators against established protocols, rather than individual "ground truth" measurements like accuracy.
4. Adjudication Method for the Test Set
The document does not describe any adjudication method (e.g., 2+1, 3+1) for establishing ground truth from multiple human readers/experts. For the accuracy tests, ground truth appears to be based on objective physical measurements or comparisons to established standards. For simulated use, the assessment of "satisfaction of user needs" and "clinical use requirements" would likely be based on pre-defined criteria and possibly surgeon feedback rather than an adjudication process of subjective interpretations.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, What was the effect size of how much human readers improve with AI vs without AI assistance?
No MRMC comparative effectiveness study is described in this summary. The Intellijoint HIP Generation 2A System is an optical navigation system that provides intra-operative measurements. It's a tool for surgeons, not an AI system that directly assists human readers (like radiologists interpreting images). Therefore, an MRMC study in the traditional sense of comparing human reader performance with and without AI assistance is not applicable to this device's reported testing. The testing focuses on the system's own accuracy and its ability to meet clinical requirements during surgery.
6. If a Standalone (i.e. algorithm only without human-in-the loop performance) Was Done
The device is an "imageless optical navigation system intended to provide intra-operative measurements to a surgeon." Its function is inherently "human-in-the-loop," as it provides information to a surgeon to aid in decision-making and positioning. Therefore, a purely standalone (algorithm-only) performance evaluation would not be directly applicable to its intended use in surgery. However, the "Tracking System Accuracy and Robustness" and "Benchtop Accuracy" tests essentially evaluate the core capabilities of the system (including its algorithms for measurement and tracking) in a controlled, objective manner, which could be considered a form of standalone evaluation of its measurement accuracy, even if its ultimate application requires human interaction.
7. The Type of Ground Truth Used
- Tracking System Accuracy and Robustness: Ground truth was established against reference standards according to ASTM F2554-10, likely using a highly accurate measurement system (e.g., a coordinate measuring machine or a more precise optical tracking system).
- Benchtop Accuracy: Ground truth was established using "calibrated benchtop test fixtures," implying objective, known, and precise measurements.
- Anatomical Phantom Simulated Use and Clinical Accuracy: Ground truth was established through "ground truth values" on the phantom models, which would have been precisely measured and known references. This is objective, physical measurement ground truth.
- Cadaver Simulated Use: Ground truth for meeting "clinical use requirements" would be assessed based on the system's ability to perform its functions as intended by a surgeon in a realistic surgical environment on human specimens. This focuses more on functional performance and user satisfaction rather than a single, objective "ground truth" measurement.
8. The Sample Size for the Training Set
The document does not provide information about a separate "training set" sample size. This device is an optical navigation system with specific algorithms for measurement and tracking, not a machine learning or AI model in the sense of requiring a large, labeled training dataset for pattern recognition. The software "algorithms and measurement calculations were also verified" implying deterministic or rule-based algorithms, or algorithms trained on smaller, controlled datasets, but not a "training set" in the context of deep learning.
9. How the Ground Truth for the Training Set Was Established
As no specific "training set" is described for machine learning, the concept of establishing ground truth for it is not applicable here. The algorithms' accuracy and functionality would be verified through rigorous engineering testing (as suggested by the "Software Functional and Unit Tests") against known mathematical principles and validated reference data, rather than a labeled training set derived from expert consensus on medical cases.
§ 882.4560 Stereotaxic instrument.
(a)
Identification. A stereotaxic instrument is a device consisting of a rigid frame with a calibrated guide mechanism for precisely positioning probes or other devices within a patient's brain, spinal cord, or other part of the nervous system.(b)
Classification. Class II (performance standards).