(29 days)
The TSolution One® Total Knee Application is intended for use as a device that uses diagnostic images of the patient acquired specifically to assist the physician with preoperative planning and to provide orientation and reference information during intraoperative procedures. The robotic surgical tool, under the direction of the surgeon, precisely implements the presurgical software plan.
The preoperative planning software and robotic surgical tool are used as an alternative to manual planning and resecting techniques for the distal femur and proximal tibia preparation in primary total knee arthroplasty (TKA).
The TSolution One® Total Knee Application is indicated for orthopedic procedures in which resecting techniques used for the distal femur and proximal tibia may be considered to be safe and effective and where references to rigid anatomical structures may be made.
The TSolution One® Total Knee Application is also intended to assist the surgeon in determining reference alignment axes in relation to anatomical and instrumentation structures during stereotactic orthopedic surgical procedures. The TSolution One® Total Knee Application facilitates accurate positioning of TKA implants, relative to these alignment axes.
The TSolution One® Total Knee Application is compatible with the following Knee Implant Systems:
- · Zimmer Persona™ Knee System
- · Corin Unity Knee System
- Aesculap Columbus Knee System
- · DJO Surgical® EMPOWR 3D Knee® System
The TSolution One® Total Knee Application is a three-dimensional, graphical, preoperative planning workstation and implementation tool for treatment of patients who require total joint arthroplasty. The device is intended as an alternative to manual template planning and preparation of the bone with patients requiring primary total knee arthroplasty (TKA).
The TSolution One® Total Knee Application consists of TPLAN and TCAT. TPLAN is a three-dimensional (3D) preoperative planning workstation that aids a surgeon in planning the position and orientation of the implant components relative to 3D models of the patient's anatomy. TCAT consists of an electromechanical arm, an arm base including control electronics and computer, a display monitor, operating software, pendant control, and tools and accessories, for the implementation of the preoperative plan. TCAT and TPLAN when used according to the instructions for use, make submillimeter precision bone preparation possible before and during TKA surgical procedures.
This document describes a 510(k) premarket notification for the TSolution One® Total Knee Application by Think Surgical, Inc. The submission is a "Special 510(k)" because it concerns modifications to a previously cleared device (K191369). The primary modifications are the addition of compatibility with three new knee implant systems (Corin Unity Knee System, Aesculap Columbus Knee System, and DJO Surgical® EMPOWR 3D Knee® System) and corresponding labeling changes.
Here's an analysis of the provided information concerning acceptance criteria and device performance:
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly present a table of specific numerical acceptance criteria. Instead, it refers to prior testing and states that the current device met all test criteria and specifications and passed various tests. The claim of equivalence is based on the new device performing similarly to the predicate device, which had already met specified criteria.
| Performance Metric | Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|---|
| Cutting Accuracy Verification | "similar test methods and acceptance criteria to those used for the predicate device" | "Passed" |
| Cadaver Lab Validation Testing | "methods and acceptance criteria similar to that used for the predicate device" | "Passed" |
| Software Testing | (Implied to be sufficient for proper function) | "Passed" |
2. Sample Size Used for the Test Set and Data Provenance
The document states:
- Cutting Accuracy Verification: "Performance testing to verify the cutting accuracy of the subject device was conducted following similar test methods and acceptance criteria to those used for the predicate device." No specific sample size (e.g., number of tests, number of bone samples) is provided for this testing.
- Cadaver Lab Validation Testing: "Validation testing, with methods and acceptance criteria similar to that used for the predicate device, was conducted using simulated surgical testing in a cadaver model and all test criteria were met." No specific sample size (e.g., number of cadavers, number of procedures) is provided.
The data provenance is not explicitly stated in terms of country of origin. The study appears to be prospective in nature, as new testing was conducted specifically for this submission to verify the modifications.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
The document mentions "simulated surgical testing in a cadaver model" and that the robotic surgical tool operates "under the direction of the surgeon." While this implies clinical involvement, it does not specify the number of experts, their qualifications, or their role in establishing ground truth for the test set used for regulatory submission. The focus is on the device's ability to precisely implement a presurgical plan, rather than on expert interpretation of outcomes for ground truth.
4. Adjudication Method for the Test Set
The document does not describe any adjudication method. The testing described (cutting accuracy, cadaver lab validation, software testing) suggests objective, quantifiable measurements against engineering specifications or predetermined surgical plans, rather than a subjective assessment requiring adjudication.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size
No MRMC comparative effectiveness study is mentioned in this document. The submission is a Special 510(k) for modifications to an existing device, focusing on demonstrating that the changes do not negatively impact safety or effectiveness. There's no comparative study presented on human reader performance with or without AI assistance. The device is an AI/robotic system assisting surgeons, but its comparative effectiveness against unaided human surgeons is not described here.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
The document describes the TSolution One® Total Knee Application as consisting of:
- TPLAN: "a three-dimensional (3D) preoperative planning workstation that aids a surgeon in planning the position and orientation of the implant components relative to 3D models of the patient's anatomy."
- TCAT: "an electromechanical arm... for the implementation of the preoperative plan."
The core function is a "robotic surgical tool, under the direction of the surgeon, precisely implements the presurgical software plan." This clearly indicates a "human-in-the-loop" system.
However, the "Cutting Accuracy Verification" and "Software Testing" could be considered "standalone" tests of the algorithm's and robotic arm's mechanical precision and software functionality in a controlled environment, even if the overall system is always used with a surgeon. The cadaver lab testing also evaluates the system's performance, but still within the context of a simulated surgical procedure involving a human operator.
7. The Type of Ground Truth Used
Based on the description of performance testing:
- Cutting Accuracy Verification: The ground truth would likely be engineering specifications or predefined geometric targets. The robotic arm's actual cut surfaces or trajectory would be compared against these targets.
- Cadaver Lab Validation Testing: The ground truth for this would likely be the preoperative plan generated by TPLAN. The actual resections performed by the TCAT robotic arm on cadaver bone would be measured and compared against the planned resections (e.g., bone resection depth, angle, implant position). This would be an objective, quantifiable ground truth based on the software's plan.
- Software Testing: Ground truth for software testing generally involves verifying that the software functions according to its design specifications and requirements, producing expected outputs for given inputs.
8. The Sample Size for the Training Set
This document describes a device modification and substantial equivalence comparison, not the development of a novel machine learning algorithm from scratch. Therefore, information about a "training set" for an AI model is not provided. The TSolution One system uses CT images to create 3D models and a "library of FDA cleared components" for planning, but this is not described as a traditional machine learning training set.
9. How the Ground Truth for the Training Set Was Established
As no "training set" is mentioned or implied for a machine learning model, information on how its ground truth was established is not applicable to this document. The system's functionality relies on engineering principles, image processing, and pre-defined surgical planning rules.
§ 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).