(87 days)
Knee+ is a stereotaxic system including an intraoperative software as a medical device and surgical instruments. Knee+ is intended for primary Total Knee Replacement, to assist the surgeon in determining reference alignment axes in relation to anatomical landmarks, in order to position the cutting computed mechanical axis. The Knee+ includes smart glasses as a Head Mounted Device (HMD) for displaying information to the user intraoperatively. The smart glasses should not be relied upon solely and should always be used in conjunction with traditional methods.
Knee+ is a navigation system dedicated to orthopaedic kneePlus software and KneeTools reusable surgical instruments.
The main purpose of Knee+ is to assist the surgeon during primary Total Knee Arthroplasty (TKA) interventions.
Knee+ provides information to help locate and orientate the main femoral and tibial cutting planes as required during TKA. Knee+ allows the surgeon to adjust the orientation of the cutting plane orientation and the level of resection by collecting anatomical references during the TKA procedure using surgical instruments. The software frame the instruments which include markers. All collected coordinates are treated by software algorithms to provide the surgeon with relevant orientation and location of the tracked cutting guide. Knee+ software is installed on a wearable Head Mounted Device (HMD) which includes a camera, a computer and displays intraoperative information to the user. A near-eye display allows the HMD screen when needed.
The provided document [K243975](https://510k.innolitics.com/search/K243975) is a 510(k) Premarket Notification from Pixee Medical for their device, Knee+. This document claims substantial equivalence to a previously cleared version of the same device (K233899). As such, it does not detail a new study proving the device meets new acceptance criteria, but rather demonstrates that modifications to the device do not negatively impact its performance or raise new safety/effectiveness concerns, maintaining the performance established by the predicate.
Therefore, much of the requested information regarding "acceptance criteria" and "the study that proves the device meets the acceptance criteria" in the context of a new clinical study for FDA clearance is not present, as this is a 510(k) submission showing substantial equivalence of a modified device.
However, based on the non-clinical testing summaries provided, I can infer and construct answers to some of your questions relevant to the performance demonstration for the modified device in comparison to the predicate, and how its established performance was maintained.
Here's an attempt to answer your questions based on the available information:
1. A table of acceptance criteria and the reported device performance
The document states: "Precision and accuracy of the device remain unchanged compared to previous version when measured according to the same methods." It also mentions "Bench testing was conducted in order to demonstrate that Knee+ performs according to its requirements and specifications. In particular, repeatability and accuracy were tested according to ASTM F2554."
Since this is a 510(k) for a modified device, the "acceptance criteria" would primarily be maintaining the performance established by the predicate. Explicit numerical acceptance criteria and reported device performance for these specific modifications are not provided in this public summary. However, the statement "All performance testing demonstrates that Knee+ performs according to its specifications and functions as intended" implies that the device met internal specifications.
| Performance Metric | Acceptance Criteria (Inferred from "unchanged performance") | Reported Device Performance (Inferred from "demonstrates... performs according to its specifications") |
|---|---|---|
| Precision | Consistent with predicate (K233899) | Achieved consistency with predicate |
| Accuracy | Consistent with predicate (K233899) | Achieved consistency with predicate |
| Repeatability | Meets requirements (via ASTM F2554) | Met requirements |
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 does not specify test set sample sizes for the non-clinical bench testing (e.g., how many measurements were taken for repeatability and accuracy). It primarily relies on bench testing and human factors testing.
- Non-Clinical Testing Providence: France (Pixee Medical is based in Besançon, France). The testing performed is described as "Bench testing" and "Human factors." These are typically prospective tests.
- Clinical Data: "Clinical testing is not applicable." This indicates no new clinical studies were conducted for this 510(k) submission as the device is substantially equivalent to its predicate.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
Not applicable for this 510(k) as the submission primarily relies on non-clinical bench testing and human factors assessment, not on a new clinical study requiring ground truth established by medical experts for performance evaluation.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
Not applicable. As this is a 510(k) submission based on substantial equivalence, there's no mention of a clinical study that would require adjudication of expert opinions for a test set.
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
No, an MRMC comparative effectiveness study was not done. The device is a stereotaxic system for guiding Total Knee Replacement, not a diagnostic AI system requiring reader studies. Clinical testing was deemed "not applicable" for this 510(k).
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The performance testing described (repeatability and accuracy via ASTM F2554) would be considered a standalone assessment of the device's measurement capabilities. However, this is for the surgical guidance aspect, not an AI algorithm generating a diagnostic output to be evaluated independently in isolation from clinical context. The device is intended to be used with human clinicians: "The Knee+ includes smart glasses as a Head Mounted Device (HMD) for displaying information to the user intraoperatively. The smart glasses should not be relied upon solely and should always be used in conjunction with traditional methods."
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
For the non-clinical bench testing for accuracy and repeatability, the "ground truth" would be established by the precise measurements of a calibrated reference system or phantom used in the testing (e.g., known distances or angles on a test fixture). This is standard for evaluating the accuracy of navigation or measurement systems.
8. The sample size for the training set
Not applicable. This document is for a medical device (stereotaxic instrument), not a machine learning/AI algorithm that requires a training set in the conventional sense for a diagnostic output. While the device does use "software algorithms" to process collected coordinates, there's no indication of a machine learning model that requires an external training dataset in the context typically discussed for AI/ML-driven medical devices.
9. How the ground truth for the training set was established
Not applicable, as there's no mention of a training set for an AI/ML model for which "ground truth" would need to be established in this context.
§ 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).