Search Results

VERASENSE is indicated for any medical condition in which primary or revision Total Knee Arthroplasty (TKA) would be indicated.

For use as a tool for adjustment of the femoral knee implant to reduce instability from flexion gap asymmetry.

VERASENSE is sterile, for single patient use.

The VERASENSE device is an intelligent disposable tibial insert trial that measures dynamic loads in the medical and lateral compartments of the knee and wirelessly transmits the measured load data to the LinkStation MINI and LinkStation MINI Evaluation Kit with VERASENSE Software Application (VSA). The VSA provides the surgeon with a graphical and numerical presentation of the load magnitude and center of load (COL) location (weighted average) of the femoral to the tibial component in each of the medial and lateral compartments of the knee for reference only. Individual VERASENSE devices are packaged sterile, for single patient use with a shim set for thickness adjustments.

This document describes a 510(k) premarket notification for the VERASENSE for Stryker Triathlon device. It is a re-submission for a device that has previously been cleared for other implant systems (VERASENSE for Zimmer Biomet Persona, K180459). Therefore, the provided text focuses on demonstrating substantial equivalence to existing predicate devices, rather than a full de novo acceptance criteria and performance study for a novel device.

As a result, many of the typical elements of an acceptance criteria and performance study (like specific performance metrics from a clinical study, sample size for testing, expert validation process, MRMC studies) are not present in this document, as the primary goal is to show that the modified device functions similarly and safely to already-cleared devices.

However, I can extract the information that is present and highlight what is not available based on the request.

Acceptance Criteria and Device Performance (Based on Substantial Equivalence)

The acceptance criteria for this 510(k) submission are not expressed as specific performance thresholds for a new clinical trial, but rather as demonstrating substantial equivalence to predicate devices. The "performance" is demonstrated by showing that the subject device meets the same specifications and standards as the predicate devices, despite minor technological differences.

Table of Acceptance Criteria (vs. Predicate Device) and Reported Device Performance:

Identified Technological Differences (and justification for substantial equivalence):

Study Details (Based on Substantial Equivalence Demonstration Documentation)

Given this is a 510(k) submission for substantial equivalence based on prior clearances and design modifications, the "study" is primarily a verification and validation (V&V) assessment of the changes, rather than a prospective clinical trial proving de novo performance.

1. Sample size used for the test set and the data provenance:

   • The document does not specify a sample size in terms of clinical cases or patients for a test set. The "test set" here refers to engineering and bench testing to verify the changes and demonstrate that the device still meets its specifications, rather than a clinical dataset.
   • Data Provenance: Not explicitly stated as "country of origin" for data, but the V&V activities align with FDA regulations for device modification. The studies mentioned are verification and validation activities for compliance with 21 CFR 820.30 design controls. These would typically be internal testing data (bench, pre-clinical if necessary) to support the safety and effectiveness of the modified device. These are retrospective in the sense that they are conducted on the modified device to confirm its performance against established specifications, not prospective in gathering new clinical outcome data.

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

   • This information is not provided in the document. Ground truth, in the context of device performance for substantial equivalence, relies on the device meeting its established technical specifications (e.g., load accuracy, battery life, communication range) rather than expert interpretation of clinical outcomes for a new clinical efficacy claim.

3. Adjudication method (e.g. 2+1, 3+1, none) for the test set:

   • This information is not applicable/provided. Adjudication methods are typically for clinical studies involving human interpretation (e.g., image reading), which is not the primary focus of this type of 510(k) submission for substantial equivalence based on technical specifications. The V&V activities would involve engineering and quality assurance reviews against defined acceptance criteria.

4. 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 device is an intraoperative mechanical assessment tool, not an AI-assisted diagnostic imaging device requiring human reader improvement studies. Its function is to provide force and load data to a surgeon, not to interpret images or assist in diagnosis.

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

   • The device itself provides objective measurements (load data). The algorithm in the software (VSA) processes this data to display force vectors and positional data. The document states that the Load Range and Accuracy is 5-40 lbf $\leq$ 3.5 lbf, demonstrating a standalone performance metric for the sensor and its associated processing. However, a dedicated "standalone performance study" as would be defined for an AI diagnostic algorithm is not described, as the device's role is to provide real-time data during surgery for human decision-making, not to replace it.

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

   • The "ground truth" for demonstrating substantial equivalence and device performance in this context is primarily derived from engineering specifications, bench testing, and conformity to recognized standards (e.g., IEC standards). For mechanical and functional aspects, this would involve validated measurement equipment and calibration standards. For software, it would involve software verification and validation against requirements and design specifications. There is no mention of clinical outcomes data, expert consensus, or pathology as a ground truth, as the submission is for substantial equivalence of modifications, not a de novo clinical claim.

7. The sample size for the training set:

   • This information is not applicable and not provided. This device is not an AI/ML algorithm that is "trained" on data in the traditional sense. It is a sensor-based device with a fixed algorithm for processing sensor data.

8. How the ground truth for the training set was established:

   • This information is not applicable and not provided for the same reason as point 7.

Ask a specific question about this device