Search Results

The InThrill™ Thrombectomy System is indicated for:

• The non-surgical removal of emboli and thrombi from blood vessels, including arteriovenous fistulae and arteriovenous grafts for dialysis access, and synthetic grafts.
• Injection, infusion, and/or aspiration of contrast media and other fluids into or from a blood vessel/graft.

The InThrill™ Sheath is indicated for use as a conduit for the insertion of endovascular devices into the peripheral vasculature while minimizing blood loss associated with such insertions.

The InThrill™ Thrombectomy System is intended for use in the peripheral vasculature.

The InThrill™ Thrombectomy System is not intended for use in deep vein thrombosis (DVT) treatment.

The InThrill™ Thrombectomy System is a single-use, over-the-wire, catheter-based system for the minimally invasive treatment of thromboemboli in the peripheral vasculature, including arteriovenous fistulae and arteriovenous grafts for dialysis access, and synthetic grafts. The system comprises two main components packaged separately:

• InThrill Sheath (8 Fr)
• InThrill Thrombectomy Catheter (8 Fr)

The InThrill Sheath is placed in the target vessel, and, after its funnel is expanded, the InThrill Catheter is inserted through the sheath and advanced past the thrombus. The InThrill Catheter coring element is deployed, providing wall-to-wall contact to engage the clot, and is then retracted into the InThrill Sheath to capture the targeted thrombus. Additional clot may be removed by aspiration through the sheath with a syringe (not provided). After the procedure is complete, the InThrill Catheter and InThrill Sheath are removed from the patient.

I'm sorry, but based on the provided FDA 510(k) clearance letter for the InThrill™ Thrombectomy System, there is no information available about acceptance criteria and a study that proves the device meets specific performance criteria for AI/ML-based medical devices.

This document describes a medical device (thrombectomy system) which is a physical, mechanical device, not an AI/ML-based software device. The entire document focuses on the substantial equivalence of the InThrill™ Thrombectomy System to a predicate device, based on non-clinical performance and biocompatibility testing.

Therefore, I cannot fulfill your request for the specific points related to AI/ML device testing, such as:

• A table of acceptance criteria and reported device performance related to AI/ML metrics.
• Sample size and data provenance for an AI/ML test set.
• Number of experts and their qualifications for AI/ML ground truth.
• Adjudication method for AI/ML test set.
• MRMC comparative effectiveness study for AI assistance.
• Standalone (algorithm only) performance for AI.
• Type of ground truth used for AI/ML.
• Sample size for training set and how ground truth was established for AI/ML.

The "Performance Tests" section in the document refers to engineering and functional performance tests for the physical device (e.g., tensile strength, luer connections, clot burden removal efficacy of the mechanical device), not the performance of an AI algorithm in interpreting medical images or data.

If you have a document pertaining to an AI/ML medical device, I would be happy to analyze it for the criteria you've outlined.

Ask a specific question about this device

The Artix™ MT thrombectomy device is indicated for:

· The non-surgical removal of emboli and thrombi from blood vessels

· Injection, infusion, and/or aspiration of contrast media and other fluids into or from a blood vessel.

The Artix™ MT thrombectomy device is intended for use in the peripheral vasculature.

The Artix™ Thin-Walled Sheath is indicated for:

· The non-surgical removal of emboli and thrombi from blood vessels.

· Injection, infusion, and/or aspiration of contrast media and other fluids into or from a blood vessel.

· Use as a conduit for endovascular devices.

· Use in facilitating the insertion and guidance of an intravascular catheter into a selected blood vessel. The funnel provides temporary vascular occlusion during these and other angiographic procedures.

The Artix™ Thin-Walled Sheath is intended for use in the peripheral vasculature.

The Artix™ MT is a single-use, over-the-wire catheter device used for the minimally invasive treatment of thromboemboli in the peripheral vasculature. The Artix MT is packaged with the following components: Artix MT (3-6 mm or 4-8 mm) Cleaning accessory 1-Way Stopcock The Artix MT is inserted over-the-wire through a compatible sheath (such as the Artix Thin-Walled Sheath) and advanced until its proximal marker band is distal to the target thrombus. The self-expanding element is deployed by retracting the delivery catheter. Thrombus is engaged and removed by retracting the Artix MT into the sheath and out of the patient. Once the procedure is complete, the system is completely withdrawn from the patient.

The Artix™ Thin-Walled Sheath ("Artix Sheath") is a single-use, over-the-wire system designed to facilitate the insertion and guidance of an intravascular catheter into a selected peripheral blood vessel and act as a conduit for endovascular devices. The Artix Sheath also non-surgically aspirates thromboemboli from selected vessels and is capable of infusion/aspiration of fluids into or from a selected vessel. The Artix Sheath is packaged with the following components: Artix Thin-Walled Sheath (65 cm or 90 cm) Sheath Dilator (0.035" guidewire compatibility) Funnel Catheter and Funnel Catheter Dilator (0.035" guidewire compatibility) Funnel Loading Tool (2) Large Bore Syringe, 30 mL The Artix Sheath is inserted over-the-wire and advanced to a desirable position. Any compatible endovascular device, such as the Artix MT, can then be inserted through the Artix Sheath for access into the peripheral vasculature. The provided funnel catheter accessory can also be inserted through the Sheath and deployed to provide flow occlusion of the vessel during the procedure to aid with the system's clot ingestion. Compatible endovascular devices, such as the Artix MT, can be used through the 6 Fr inner diameter of the funnel catheter as well. The provided 30 mL syringe can be used to aspirate clot in the vessel or Sheath and infuse contrast media and other fluids as required. Once the procedure is complete, the funnel catheter (if used) is removed prior to withdrawal of the entire system from the patient, and standard 7 Fr closure devices can be used.

The provided document describes the 510(k) premarket notification for two devices: Artix™ MT and Artix™ Thin-Walled Thrombectomy Sheath. The document focuses on demonstrating substantial equivalence to predicate devices through non-clinical testing. It does not contain information about acceptance criteria or studies involving human expert performance (such as MRMC studies, specific ground truth established by experts, or sample sizes for test/training sets relevant to AI/software performance).

Therefore, I cannot fulfill the request for information on acceptance criteria and a study proving device meets those criteria in the context of AI/software performance with human-in-the-loop. The document exclusively discusses the substantial equivalence of physical medical devices based on their design, materials, and non-clinical performance (e.g., burst strength, tensile strength, simulated use, biocompatibility).

The "study" mentioned in the document refers to a series of non-clinical tests conducted to demonstrate that the devices perform as intended and are as safe and effective as their predicate devices. These tests are not related to AI or human reader performance.

Here's an overview of the information that is available in the document, which primarily concerns the physical characteristics and performance of the devices:

1. Table of Acceptance Criteria and Reported Device Performance:

The document does not present acceptance criteria in a quantitative table with reported device performance in the way one might expect for AI or software. Instead, it lists various non-clinical tests (e.g., Biocompatibility, Sterilization, Packaging Testing, Visual and Dimensional Inspections, Simulated Use Testing, Hemostasis, Burst, Corrosion, Radiopacity, Radial Force, Chronic Clot Analog for Artix MT; and similar tests for Artix Thin-Walled Sheath) and states that "The passing results demonstrate that the subject device meets biological safety requirements" (for biocompatibility) and that "verification and validation testing were identified to support the substantial equivalence" and "The testing provided supports the Artix MT's substantial equivalence." This implies that the devices met their internal acceptance criteria for these physical and functional tests. However, the specific numerical acceptance criteria and performance outcomes for each test are not detailed in this summary.

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

• Test Set (Non-clinical): The document does not specify the sample sizes for the individual non-clinical tests conducted (e.g., how many units were tested for burst strength, or simulated use).
• Data Provenance: Not applicable in the context of device performance data presented, as it refers to non-clinical, lab-based testing of the physical devices.

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

• Not applicable. The "ground truth" for the performance of these physical medical devices is established through engineering specifications, material science, and physical testing protocols, not through expert consensus on interpretation of medical images or patient outcomes.

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

• Not applicable. This concept typically applies to human reader studies where disagreements in interpretations need to be resolved. For non-clinical device testing, results are typically objective measurements against pre-defined specifications.

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. The document explicitly states: "Neither animal testing nor clinical testing were required for the determination of substantial equivalence." This means no human-in-the-loop or clinical studies were performed or are discussed here. MRMC studies are not relevant to this submission.

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

• Not applicable. These are physical thrombectomy devices, not AI algorithms.

7. The type of ground truth used:

• For the non-clinical tests ("verification and validation testing"), the "ground truth" is defined by engineering specifications, material properties, and performance benchmarks established through industry standards and the predicate device's known performance. For example, a "burst" test would have a pre-defined pressure or force target that the device must withstand to pass.

8. The sample size for the training set:

• Not applicable. This concept is for machine learning models. These devices are physical products.

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

• Not applicable.

In summary, the provided FDA 510(k) summary is for physical medical devices and does not describe acceptance criteria or studies related to AI performance or human reader studies. The "studies" mentioned are non-clinical verification and validation tests to ensure the physical device meets its design specifications and is substantially equivalent to existing predicate devices.

Ask a specific question about this device