Search Results

The ACCLARENT® ENT Navigation System is intended for use during intranasal and paranasal image-guided navigation procedures for patients who are eligible for sinus procedures.

The ACCLARENT® ENT Navigation System is intended to be used during intranasal and paranasal surgical procedures to help ENT physicians to track and display the real-time location of the tip of navigated instruments relative to pre-acquired reference images, such as CT.

The ACCLARENT® ENT Navigation System enables ENT physicians to access sphenoid, frontal, and maxillary sinuses by using the system magnetic tracking technology, identical to the predicate device.

The system incorporates a Navigation Console, Field Ring, Instrument Hub, Patient Tracker, Registration Probe, Field Ring and Holder, Workstation and accessories. A magnetic field generated by the Field Ring induces a current in the magnetic sensor embedded in the tip of the flexible navigated tool, which helps to accurately calculate the tool tip position. A CT image is imported and registered to the patient coordinates and a tool tip icon is displayed on top of the registered

The provided document is a 510(k) premarket notification for the Acclarent® ENT Navigation System. It primarily focuses on demonstrating substantial equivalence to a predicate device (CARTO® ENT Navigation System, K161701) rather than presenting a standalone study with a novel AI model's performance.

Therefore, many of the requested details regarding acceptance criteria, sample sizes for AI model training/testing, expert ground truth establishment, and MRMC studies are not applicable or not explicitly detailed in this type of regulatory submission. This document describes a medical device, not an AI/ML diagnostic or prognostic algorithm.

However, I can extract the relevant information regarding the performance testing that was conducted:

Here's a breakdown of the available information:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of "acceptance criteria" for an AI model's performance in terms of metrics like sensitivity, specificity, or AUC, as it's a navigation system. Instead, it describes non-clinical tests performed to ensure the system functions according to design specifications and demonstrates safety and effectiveness.

2. Sample Size Used for the Test Set and Data Provenance

• Test Set Sample Size: Not explicitly stated in terms of number of cases or patients. For the "Location Accuracy tests," it refers to "the entire navigation volume," suggesting a comprehensive evaluation within the system's operational space. For "Simulated use accuracy test" and "Pre-clinical (cadaver) tests," the number of cadavers or simulated procedures is not specified.
• Data Provenance: The tests are "nonclinical" and "pre-clinical (cadaver) tests." This suggests controlled laboratory and cadaveric environments, which do not typically involve patient data from specific countries in the way an AI model would. There's no indication of retrospective or prospective patient data collection for these specific performance tests.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications

• Number of Experts: Not applicable, as the "ground truth" for a navigation system's performance is established through physical measurements (e.g., comparison to a robot system for location accuracy) and functional assessments, not subjective expert annotations of medical images for diagnostic purposes.
• Qualifications of Experts: Not specified or applicable in the context of hardware/software functional and accuracy testing.

4. Adjudication Method for the Test Set

• Adjudication Method: Not applicable. Performance is measured against engineering specifications and physical accuracy metrics, not through expert consensus on AI outputs.

5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study Was Done

• MRMC Study: No, an MRMC comparative effectiveness study was not performed. This type of study is typically done for diagnostic imaging AI algorithms to assess their impact on human reader performance. The Acclarent ENT Navigation System is a surgical navigation device.
• Effect Size of Human Readers Improvement with AI vs. Without AI Assistance: Not applicable, as this is not an AI diagnostic assistance tool.

6. If a Standalone (i.e., Algorithm Only Without Human-in-the-Loop Performance) Was Done

• Standalone Performance: The non-clinical tests (electrical, location accuracy, software functional, safety, EMC, mechanical) represent standalone performance of the device's components and system accuracy against established engineering parameters. The "Pre-clinical (cadaver) tests" involved human interaction but were qualitative assessments of workflow and clinical accuracy, not a comparative "human-in-the-loop" study in the AI sense.

7. The Type of Ground Truth Used

• Ground Truth:
  • Engineering Specifications: For electrical, software functional, safety, EMC, and mechanical tests, the ground truth is defined by the device's design specifications and relevant industry/regulatory standards.
  • Precise Robotic Measurements: For "Location Accuracy tests," the ground truth was provided by a "very accurate robot system."
  • Simulated Clinical Workflows: For "Simulated use accuracy test" and "Pre-clinical (cadaver) tests," the ground truth involves assessing the system's ability to accurately guide instruments relative to pre-acquired CT images within a controlled, mimicked surgical environment. This is less about a single "ground truth" label and more about functional validation.

8. The Sample Size for the Training Set

• Training Set Sample Size: Not applicable. This document describes a medical device, not an AI model that undergoes a training phase with a specific dataset.

9. How the Ground Truth for the Training Set Was Established

• Ground Truth for Training Set: Not applicable, as this is not an AI model.

Ask a specific question about this device