Search Results

Smith & Nephew's VISIONAIRE UK Patient Matched Cutting Guides are intended to be used as patient-specific surgical instrumentation to assist in the positioning of knee replacement components intra-operatively and in guiding the marking. of bone before cutting provided that anatomic landmarks necessary for alignment and positioning of the implant are identifiable on patient imaging scans.

The Smith & Nephew VISIONAIRE UK Patient Matched Cutting Guides are intended for use with the following existing Smith & Nephew, Inc. Knee Systems and their cleared indications for use:

• JOURNEY II Unicompartmental Knee (JOURNEY II UK) System

The Smith & Nephew VISIONAIRE UK Patient Matched Cutting Guides are intended for single use only.

The VISIONAIRE Unicompartmental Knee (UK) Patient Matched Cutting Guides are to be used as patient-specific surgical instrumentation to assist in the positioning of partial knee replacement implant components intra-operatively and in guiding the marking of bone before cutting. The subject device is designed and manufactured from patient imaging data (i.e. MRI, X-Ray) using additive manufacturing of Nylon 12 material to create the patientmatched guides. The blocks achieve mechanical alignment via an intimate fit with the patient's proximal tibia or distal femur. This fit is achieved by reconstructing the patient's bony and cartilaginous anatomy from the MRI scans of the patient's knee. The VISIONAIRE UK Patient Matched Cutting Guides are intended to be used for medial femoral and tibia resections in conjunction with previously cleared Smith & Nephew JOURNEY II Unicompartmental Knee (JOURNEY II UK) System (K190085).

The provided document does not contain information about acceptance criteria or a study that proves the device meets those criteria in the context of device performance metrics like sensitivity, specificity, accuracy, or other similar quantitative measures typically associated with AI/ML diagnostic or measurement devices.

The document is a 510(k) summary for the "VISIONAIRE UK Patient Matched Cutting Guides," which are patient-specific surgical instruments. The assessment for this type of device focuses on substantial equivalence to existing predicate devices, functional performance in a surgical context, and safety.

Here's a breakdown of the information that is available in the document, framed against your requested points:

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

This information is not provided in the document in the format of quantitative performance metrics for AI/ML. The device is a physical surgical guide, not a diagnostic AI.

The document states: "Smith & Nephew conducted cadaveric testing of the VISIONAIRE UK Patient Matched Cutting Guides. The results of this testing demonstrated that the patient matched cutting blocks/guides designed using the case processing applications perform equivalent to the predicate devices listed in the Table 5.1 below."

This implies that the acceptance criteria for the cadaveric testing would have been equivalence to the predicate devices in guiding bone cuts, likely in terms of accuracy of bone resection or component positioning. However, the specific criteria (e.g., "within X degrees of alignment," "within Y mm of cut depth") and the actual performance results (e.g., "average deviation was Z mm/degrees") are not detailed.

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

The document mentions "cadaveric testing," which serves as the "test set" for the physical guides.

• Sample size for the test set: Not specified.
• Data provenance: Cadaveric testing. Country of origin not specified, but typically conducted in-house or at a specialized lab. This is a prospective test, as the testing was conducted specifically for this submission.

The patient imaging data (MRI, X-Ray) used to design the guides for this testing would have been retrospective if taken from existing cadaveric scans or prospective if new scans were performed. This detail is not given.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

This information is not provided. For cadaveric testing of surgical guides, ground truth would likely be established by direct measurement of the bone cuts or implant placement by qualified engineers or surgeons, but the specific details are absent.

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

Not applicable and not done. This device is a surgical cutting guide, not an AI/ML diagnostic or measurement tool that assists human readers in interpreting images.

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

Not applicable. The device is a physical cutting guide, designed using "VISIONAIRE Patient Matched Technology" (which involves software applications, not a standalone AI for diagnosis). The performance evaluation focuses on the physical guide's ability to facilitate accurate surgical cuts, assisted by human surgeons. The software itself is assessed for safety and effectiveness in its role of manufacturing the guide, not as a standalone diagnostic algorithm. The document states: "All changes are made to the non-medical device software as part of the subject device submission. There are no changes required to the previously cleared VISIONAIRE Patient Matched Cutting Blocks software (Secondary Predicate - K200826) that are involved in creating the VISIONAIRE UK Patient Matched Cutting Guides."

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

For the cadaveric testing, the ground truth would likely be physical measurements of the achieved bone resection or implant alignment compared to the planned resection/alignment, performed by engineers or surgeons after the cuts were made using the guides. The document does not specify how this ground truth was measured or established.

8. The sample size for the training set

Not applicable for a typical AI/ML training set. The "training" for this device involves the design and manufacturing process based on patient imaging data. The document mentions "patient imaging data (i.e. MRI, X-Ray)" being used to design and manufacture the guides. There isn't a "training set" in the sense of a machine learning model learning from a dataset. The software uses these scans to generate a patient-specific guide.

9. How the ground truth for the training set was established

Not applicable. There isn't a "training set" in the AI/ML context. The patient's own anatomy, as captured by the MRI scans, serves as the basis for the design of their individual guide. The "ground truth" here is the patient's actual anatomical features.

In summary, the provided document is a regulatory submission for a physical medical device (surgical guide), not an AI/ML software as a medical device. Therefore, many of the requested criteria related to AI/ML performance studies are not relevant or addressed in the document. The key study mentioned is "cadaveric testing" to demonstrate equivalence to predicate devices in the context of guiding surgical cuts.

Ask a specific question about this device