(22 days)
TMIN® Miniature Robotic System is indicated as a stereotaxic instrumentation system for total knee replacement (TKA) surgery. It is to assist the surgeon by providing software-defined spatial boundaries for orientation and reference information to identifiable anatomical structures for the accurate placement of knee implant components.
The robotic device placement is performed relative to anatomical landmarks as recorded using the system intraoperatively and based on a surgical plan determined preoperatively using CT based surgical planning tools.
The targeted population has the same characteristics as the population that is suitable for the implant(s) compatible with the TMINI® Miniature Robotic System. The TMINI® Mimiature Robotic System is to be used with the following knee replacement system(s) in accordance with the indications and contraindications:
- · Enovis™ EMPOWR Knee System®
- · Ortho Development® BKS® and BKS TriMax® Knee System
- · Total Joint Orthopedics Klassic® Knee System
- · United® U2™ Knee Total Knee System
- · Medacta® GMK® Sphere / SpheriKA Knee Systems
- · Zimmer Biomet Anterior & Posterior Referencing Persona® Knee
Like its predicate, the TMIN® Miniature Robotic System (Additional Knee System) consists of three primary components: a three-dimensional, graphical, Preoperative Planning Workstation (TPLAN Planning Station), an Optical Tracking Navigation Console (TNav) and a robotically controlled hand-held tool (TMINI Robot) that assists the surgeon in preparing the bone for implantation of TKA components.
The TPLAN Planning Station uses preoperative CT scans of the operative leg to create 3D surface models for case templating and intraoperative registration purposes. The Planning Workstation contains a library of 510(k) cleared knee replacement implant(s) available for use with the system. The surgeon can select an implant model from this library. The planner/surqeon can manipulate the 3D representation of the implant in relation to the bone model to optimally place the implant. The surgeon reviews and approves the case plan once the surgeon is satisfied with the implant selection, location and orientation. The data from the approved plan is written to a file that is used to guide the robotically controlled hand-held tool.
The hand-held robotic tool is optically tracked relative to optical markers placed in both the femur and tibia and articulates in two degrees-of-freedom, allowing the user to place bone pins in a planar manner in both bones. Mechanical quides are clamped to the bone pins, resulting in subsequent placement of cut slots and drill guide holes such that the distal femoral and proximal tibial cuts can be made in the pre-planned positions and orientations, and such that the implant manufacturer's multi-planer cutting block can be placed relative to drilled distal femoral pilot holes. If the surgeon needs to change the plan during surgery, it can be changed intraoperatively.
The provided document is a 510(k) premarket notification for the TMINI Miniature Robotic System, focusing on adding compatibility with two new knee implant systems. It explicitly states that the subject device is substantially equivalent to a previously cleared predicate device (K241031) and that no new questions of safety or effectiveness have been raised. Therefore, the study described is not a primary clinical validation study of a novel device, but rather a verification and validation (V&V) exercise to demonstrate equivalence for an updated device.
The document does not describe an AI-driven diagnostic device that would typically involve establishing ground truth from expert consensus or pathology, or MRMC studies. Instead, it describes a surgical robotic system where "accuracy" refers to the robotic system's ability to precisely place instruments based on a pre-planned surgical model.
Based on the provided text, here's an analysis against your questions:
1. A table of acceptance criteria and the reported device performance:
The document mentions that "The verification and validation activities were successfully completed, and all pre-determined acceptance criteria were met." However, it does not provide a detailed table of quantitative acceptance criteria or corresponding reported device performance values for specific metrics like cutting accuracy, pin & block placement accuracy, or system gap balance accuracy. It only states "Passed" for these categories, implying that the predefined, but unstated, acceptance criteria were satisfied.
The table on page 5-6 lists various technological characteristics and performance testing categories, with the "Conclusion" indicating "SAME" or "Substantially Equivalent" for each.
| Category | TMINI® Miniature Robotic System (Additional Knee System) Performance | TMINI™ Miniature Robotic System (Predicate) Performance | Conclusion |
|---|---|---|---|
| Full System Run | Passed | Passed | SAME |
| Cutting Accuracy | Passed | Passed | SAME |
| - Pin & Block Placement Accuracy | Passed | Passed | SAME |
| - Cadaver Lab Validation Testing | Passed | Passed | SAME |
| - System Gap Balance Accuracy | Passed | Passed | SAME |
| Biocompatibility (Cytotoxicity, Sensitization, Intracutaneous Reactivity, Acute Systemic Toxicity, Pyrogenicity) | *Passed | Passed | SAME |
Note: The asterisk on Biocompatibility indicates "There are no material changes to any of the direct patient contact components... therefore, no additional biocompatibility testing was required." The "Passed" refers to the predicate device's prior testing.
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 states "Verification and validation activities were performed... Throughout all testing performed, test samples were representative of the production product." It explicitly mentions "Cadaver Lab Validation Testing."
However, the document does not specify the sample size (number of cadavers or test instances) used for the cadaver lab validation or other performance testing.
It also does not specify the country of origin of the data or whether the study was retrospective or prospective. Given it's a cadaver lab, it would inherently be a prospective experimental study, but details are not provided.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
This device is a surgical robotic system, not an AI diagnostic system. The "ground truth" for its performance testing (e.g., accuracy of cuts or pin placement) would be established by
- Predefined surgical plans based on CT scans.
- Precise metrology (measurement) of the physical results against those plans.
- This is not a human expert interpretation task.
Therefore, the concept of "experts" establishing ground truth in the context of an AI diagnostic device (like radiologists interpreting images for disease presence) does not directly apply here.
The document does not mention experts being used to establish a subjective "ground truth" for the test set. The surgical plan is derived from CT data and the system's software, and its accuracy is measured against physical outcomes.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
As the ground truth is based on physical measurements against a pre-planned surgical model, adjudication methods typically used for subjective clinical assessments in AI diagnostic studies (like 2+1 radiologist review) are not relevant here. The document does not describe any such adjudication method.
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. This type of study is relevant for AI diagnostic systems where human readers interpret medical images. The TMINI Miniature Robotic System is a surgical robot that assists the surgeon in the physical execution of a total knee replacement, it does not interpret images for diagnosis or assist human readers in making diagnostic decisions. The document focuses on the validated accuracy of the robotic system itself in performing physical tasks (e.g., placing pins, guiding cuts) based on the surgical plan.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
The device is a "robotically controlled hand-held tool" that "assists the surgeon." Its operation inherently involves a human surgeon. The performance metrics listed (cutting accuracy, pin & block placement accuracy, cadaver lab validation testing, system gap balance accuracy) relate to the system's ability to achieve predefined surgical parameters, which implies a standalone assessment of the system's mechanical and software precision. The document doesn't explicitly separate "algorithm only" performance from system performance with the surgeon as an operator, but the tests performed (e.g., cadaver lab) would evaluate the combined system's precision in accurately executing the surgical plan.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
The ground truth for the performance testing of this robotic surgical system would be:
- The preoperatively determined surgical plan: Based on CT scans and software templating, defining the precise locations and orientations for cuts and implant placement.
- Precise metrological measurements: Physical measurements taken on the cadaver (or test jig) after the robotic assistance to determine how closely the actual executed actions (e.g., pin placement, cut planes) match the planned actions. This is an engineering/physical measurement ground truth, not a clinical ground truth like pathology or expert consensus on a diagnosis.
8. The sample size for the training set:
The document does not refer to "training sets" in the context of machine learning. The device described appears to be a deterministic robotic system based on pre-programmed algorithms and optical tracking, not a machine learning model that learns from large datasets. Therefore, the concept of a "training set" as understood in AI/ML is not applicable here and is not mentioned.
9. How the ground truth for the training set was established:
Since the document does not mention "training sets" or machine learning, this question is not applicable. The system's functionality is based on engineering principles and pre-programmed surgical planning, not on learning from a labeled training dataset.
§ 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).