Search Results

The Paragon 28 Patient Specific Marking Guide is intended to be used as a surgical instrument to assist in preoperative planning and/or in guiding the marking of bone and/or in guiding surgical instruments in non-acute, non-joint replacing osteotomies for adult patients in the foot ankle. The Patient Specific Guide is not intended to directly guide the cutting of bone. The device is single use only.

The Paragon 28 Patient Specific Marking Guides are designed and additively manufactured based on an individual patient's CT scan(s). In surgery, these guides, templates, or anatomical models are used to assist a surgeon in guiding the marking of a bone and/or guiding a surgical instrument for placement (i.e., placing a k-wire). The guides are not used for cutting bone. All guides are patient specific and utilize a CT scanning protocol previously cleared in K180239 (Paragon 28 formerly Additive Orthopaedics). The anatomical landmarks necessary for the design and creation of the Patient Specific Marking Guides must be present and identifiable on computed tomography scan.

The Paragon 28 Patient Specific Marking Guides are additively manufactured from biocompatible nylon (PA 2200 - polyamide 12 white) and produced by laser sintering. The Patient Specific Marking Guides are optional for surgeons to help visualize and plan osteotomies in the foot and ankle and are for single use only.

The provided text is a 510(k) summary for the Paragon 28 Patient Specific Marking Guides. It describes the device, its intended use, and substantial equivalence to a predicate device, supported by various performance tests. However, it does not contain the specific details requested regarding acceptance criteria for device performance, a study proving those criteria were met, sample sizes for test or training sets, data provenance, number or qualifications of experts, adjudication methods, multi-reader multi-case studies, standalone performance, or how ground truth was established for training data.

Therefore, I cannot fulfill your request for that specific information based solely on the provided text.

The closest information provided related to performance is:

1. A table of acceptance criteria and the reported device performance
No explicit table of acceptance criteria or quantitative reported device performance is provided in the document. The general statement is that "a cadaver lab were conducted to prove the subject device performs in accordance with its intended use."

2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
The document mentions a "Cadaver Study" but does not specify the sample size (number of cadavers or cases) or the provenance of the data.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)
This information is not provided.

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
This information is not provided. The device is a physical instrument, not an AI-assisted diagnostic tool, so an MRMC study in this context would be unlikely.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
This information is not provided. The device is a surgical guide, not a standalone algorithm.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
For the cadaver study, the "ground truth" would implicitly be the actual anatomical marking or instrument placement achieved by the surgeon using the guide, compared to the intended pre-operative plan. However, the specific method of establishing this ground truth (e.g., measurement, expert verification) is not described.

8. The sample size for the training set
This device is designed based on individual patient CT scans. There is no "training set" in the traditional machine learning sense, as it's a patient-specific physical device, not an algorithm being trained. Each guide is custom-made based on one patient's data.

9. How the ground truth for the training set was established
As there isn't a traditional training set, this question is not applicable. The design of each guide is based on the anatomical data from the specific patient's CT scan.

Ask a specific question about this device