(21 days)
ARVIS® Shoulder is indicated for assisting the surgeon in the positioning and alignment of implants relative to reference alignment axes and landmarks in stereotactic orthopedic surgery.
The system aids the surgeon in making intraoperative measurements and locating anatomical structures of the shoulder joint based on the patient's preoperative imaging.
The system is intended to be used with the head mounted ARVIS® Eyepiece display for augmented reality visualization and information, such as visualization of the preoperative plan and display of instrument and implant alignment information. The augmented/ virtual displayed information should not be relied upon solely for absolute positional/alignment information and should always be used in conjunction with the displayed stereotaxic information.
ARVIS® Shoulder is indicated for total shoulder arthroplasty using the Enovis AltiVate, LimaCorporation PRIMA, and LimaCorporation SMR implant systems.
ARVIS® Shoulder is a computer-controlled navigation system for shoulder arthroplasty. It aids the surgeon in making intra-operative measurements and locating anatomical structures of the shoulder joint based on the patient's preoperative imaging to assist with selection and positioning of orthopedic implant components. The system consists of software, electronic hardware and surgical instruments.
The ARVIS® Eyepiece is mounted on the surgeon's head and contains tracking cameras that locate the positions of trackers on the patient and instruments. All system measurements, instructions, prompts, and alerts are shown to the surgeon on the Eyepiece display. The Eyepiece communicates with the Belt Pack which is worn by the surgeon around their waist and houses the computer module that runs the ARVIS® Shoulder application software.
The device's workflow involves CT based preoperative planning followed by intraoperative navigation and execution. The preoperative planning software enables 3D virtual implant positioning based on the patient's CT reconstructed digital bone model and bony landmarks. The shoulder navigation software then matches the patient's digital bone model and landmarks to the intraoperative landmarks registered by the surgeon, allowing an image-based navigation to follow. The surgeon uses the plan data as guidance to navigate and help position shoulder instruments and implants.
The provided text does not contain details about acceptance criteria or a study proving the device meets those criteria for the ARVIS® Shoulder system.
The document is an FDA 510(k) clearance letter and a 510(k) Summary. These documents primarily focus on demonstrating substantial equivalence to a predicate device, rather than providing detailed acceptance criteria and performance study data as would be found in a clinical study report or a more comprehensive technical document.
While the document mentions "AI-based automatic image segmentation and landmarking algorithms" and states that "The algorithms and the data used to train and test these remain unchanged from the original submission," it does not provide the specific acceptance criteria or the reported performance metrics for these algorithms. It only broadly states that the data was "labeled and validated in advance by trained experts."
Therefore, I cannot fulfill your request for the detailed table and study information based solely on the provided text.
Here is a breakdown of what can be extracted or inferred, and what cannot:
What can be extracted/inferred:
- Sample size for the training set: 240 CT scans (from 240 patients).
- Sample size for the test set: 60 CT scans (20% of 300, derived from 300 total scans with 80% for training).
- Data provenance for training and test sets: CT scans from candidates for shoulder joint replacement surgery, acquired from 300 patients. The text doesn't explicitly state the country of origin but implies a single cohort. It's retrospective (pre-existing scans).
- How the ground truth for training and test sets was established: "labeled and validated in advance by trained experts."
- Type of ground truth used: Expert consensus on image segmentation and landmarking.
- Standalone performance: The mention of "AI-based automatic image segmentation and landmarking algorithms" being "unchanged" implies these algorithms have standalone performance characteristics, but the details are not provided.
What cannot be extracted from the provided text:
- A table of acceptance criteria and reported device performance: This crucial information is missing.
- Number of experts used to establish the ground truth: Not specified.
- Qualifications of those experts: Only "trained experts" is mentioned, no specific qualifications (e.g., radiologist with 10 years of experience).
- Adjudication method for the test set: Not specified (e.g., 2+1, 3+1, none).
- If a multi-reader multi-case (MRMC) comparative effectiveness study was done: Not mentioned.
- Effect size of human readers improving with AI vs. without AI assistance: Not mentioned.
In summary, the provided document describes the regulatory clearance process and confirms the device's substantial equivalence, but it does not detail the specific performance study results and acceptance criteria for the AI components. These details would typically be found in a more technical report submitted as part of the 510(k) submission, but not usually in the public-facing summary or clearance letter.
§ 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).