Search Results

FX SPS is intended to be used as an information tool to assist in the preoperative surgical planning and visualization of a primary total shoulder replacement.

FX SPS is a preoperative standalone web-based medical software used for the planning of primary shoulder replacement from CT-images. It comprises a secure database which enables the patient's cases management and the access to the planning interface. Preliminary to the planning, a manual segmentation needs to be performed from the patient's CT-images. The segmentation process consists in building 3D bone models of the patient's shoulder and positioning anatomic landmarks on it. Once these data are generated, their compliance is checked. They are then imported into the FX SPS's database making the planning available for the surgeon. The planning step involves virtually positioning of the shoulder prosthesis on the 3D reconstruction of the patient's shoulder. On that purpose, the surgeon chooses implants from a library of implants. Afterwards, he selects the size of the implant more suitable to the joint and he can move prosthesis components in all directions. Once the positioning of the implant is satisfying, he validates the planning to generate a planning report. During surgery, he will have at its disposal the planning report comprising preoperative and planned parameters.

The provided text describes the 510(k) summary for the Pixee Medical FX SPS device, focusing on its substantial equivalence to a predicate device (e-ortho Shoulder Software). While it details the device's function, intended use, and comparison to the predicate, it does not contain information about acceptance criteria or a specific study proving the device meets those criteria with detailed performance metrics.

The "Non-Clinical Performance Data" section generically states that:

• "Software verification and validation testing were conducted as required by IEC 62304..."
• "All performance testing demonstrated that FX SPS performs according to its specifications and functions as intended."
• "Concerning the angle or gap measurements, software verification and validation testing were conducted. All performance testing demonstrated that FX SPS performs according to its specifications and functions as intended to ensure the required angle accuracy of 1 degree and gap measurement accuracy of 1 mm."
• "User needs validation The software was validated with intended users through a human factor test series to ensure the user needs and intended use requirements were met, in accordance with IEC 62366-1. All requirements were met and no new issues of safety or effectiveness were raised."

This summary indicates that testing was performed and the device met its specifications, but it does not provide the specific "acceptance criteria" table and "reported device performance" as requested in the prompt, nor does it detail a specific study with sample sizes, data provenance, ground truth establishment, or expert involvement.

Therefore, for aspects related to a specific performance study (sample size, experts, ground truth, MRMC, effect size, standalone performance, training set details), the provided document does not contain this information.

Based on the information available in the document, here's what can be inferred or stated about the device's validation:

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

   • Acceptance Criteria (inferred/stated specifications):
     • Angle accuracy: 1 degree
     • Gap measurement accuracy: 1 mm
     • Software performs according to its specifications.
     • Software functions as intended.
     • User needs and intended use requirements are met (human factors).
   • Reported Device Performance:
     • "All performance testing demonstrated that FX SPS performs according to its specifications and functions as intended."
     • "All performance testing demonstrated that FX SPS performs according to its specifications and functions as intended to ensure the required angle accuracy of 1 degree and gap measurement accuracy of 1 mm."
     • "All requirements were met and no new issues of safety or effectiveness were raised."

2. Sample sizes used for the test set and the data provenance: Not specified in the provided text. The document refers to "software verification and validation testing" and "human factor test series" but does not detail the number of cases or the origin of the data (country, retrospective/prospective).

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not specified in the provided text. The "human factor test series" implies involvement of "intended users" (surgeons), but details on the number or their qualifications are not provided.

4. Adjudication method for the test set: Not specified in the provided text.

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 specified in the provided text. The device is described as an "information tool to assist in the preoperative surgical planning," but no MRMC study comparing human performance with and without the tool is detailed.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: The document states "software verification and validation testing were conducted," which would typically include standalone performance against internal specifications (like the angle and gap accuracy). However, detailed results of such a standalone study beyond a general statement of compliance are not provided. The device itself is described as a "standalone web-based medical software."

7. The type of ground truth used: For the stated accuracy metrics (angle and gap), the ground truth would likely be derived from precisely measured simulated data or a highly accurate reference standard established during software development and testing. For human factors, the "ground truth" would be the fulfillment of user needs and intended use requirements assessed by users. Specific details are not provided.

8. The sample size for the training set: Not applicable/Not specified. The device performs 3D reconstruction and planning based on CT images and a library of implants. It's not explicitly described as an AI/machine learning device that requires a large "training set" in the conventional sense for model building. The software development likely involved well-defined algorithms, rather than data-driven learning. If there was a machine learning component for, e.g., segmentation (though it states manual segmentation), training set details are not provided.

9. How the ground truth for the training set was established: Not applicable/Not specified, for the same reasons as point 8.

Ask a specific question about this device