Search Results

The Pounce™ Sheath is intended to introduce therapeutic or diagnostic devices into the vasculature.

The Pounce™ Sheath 16Fr is a single-use, sterile introducer sheath intended for the introduction of therapeutic or diagnostic devices within the vasculature. The Pounce™ Sheath 16Fr includes the following features:

• Braided nitinol, self-expanding funnel at the sheath's distal end
• Handle assembly with slider button to actuate the funnel's deployment
• Hub and hemostasis valve assembly to allow for device introduction and removal
• Aspiration assembly including tubing, a stopcock, and connection for a 60 cc syringe

Additional components provided within the packaging include:

• 0.035" guidewire compatible pre-dilator for access site preparation
• 0.035" guidewire compatible dilator designed for atraumatic introduction of the sheath
• 60 cc locking syringe, compatible with the sheath's aspiration assembly

A radiopaque marker band is located at the distal tip of the sheath during introduction and removal, when the funnel is sheathed. When the funnel is unsheathed, the radiopaque marker band is located proximally to the funnel. The funnel is sheathed and unsheathed with the actuation of a slider button located on the handle assembly. The hemostasis valve can be actively defeated (opened), during device introduction or removal, by pressing down on the base of the surrounding hub. This action is designed to minimize device contact across the hemostatic valve during the introduction or removal of devices. The aspiration assembly also aids in the delivery of contrast or saline.

N/A

Ask a specific question about this device

The Pounce sheath is intended to introduce therapeutic devices into the vasculature.

The Pounce™ Sheath is a single-use, sterile introducer sheath intended for the introduction of therapeutic or diagnostic devices within the vasculature. The Pounce™ Sheath includes the following features:

• . Braided nitinol, self-expanding funnel at the sheath's distal end
• Handle assembly with slider button to actuate the funnel's deployment
• Hub and hemostasis valve assembly to allow for device introduction and removal .
• Aspiration assembly to include tubing, a stopcock, and connection for a 60 cc syringe .
  Additional components provided within the packaging include:
• . 0.035" guidewire compatible dilator designed for atraumatic introduction of the sheath
• . 60 cc locking syringe, compatible with the sheath's aspiration assembly
  A radiopaque marker band is located at the distal tip of the sheath during introduction and removal, when the funnel is sheathed. When the funnel is unsheathed, the radiopaque marker band is located proximally to the funnel is sheathed and unsheathed with the actuation of a slider button located on the handle assembly.
  The hemostasis valve can be actively defeated (opened), prior to device introduction or removal, by pressing down on the base of the surrounding hub. This action is designed to minimize device contact across the hemostatic valve during the introduction or removal of devices. The aspiration assembly also aids in the delivery of contrast or saline.

The provided text is a 510(k) summary for the Pounce™ Sheath, a medical device. This document focuses on demonstrating substantial equivalence to a predicate device rather than presenting a standalone study proving a device meets specific acceptance criteria in the context of an AI/ML algorithm or a complex diagnostic device.

Therefore, the information required to answer questions 1-9 is largely not present in this document. The 510(k) process for a device like the Pounce™ Sheath (a catheter introducer) relies heavily on bench testing (performance, biocompatibility, sterilization) to show that a new device is as safe and effective as a legally marketed predicate device. It does not involve the types of studies typically conducted for AI/ML algorithms, such as MRMC studies, expert ground truthing, or large-scale clinical trials (unless specifically mandated for a higher risk classification or novel technology).

Here's a breakdown based on the provided text, and where the requested information is absent:

1. A table of acceptance criteria and the reported device performance

• Acceptance Criteria: The document generically states, "All test results met documented acceptance criteria." It does not provide the specific numerical acceptance criteria for each bench test (e.g., minimum tensile strength, maximum insertion force).
• Reported Device Performance: Similarly, it states, "The subject device has been evaluated through the following categories of testing... All test results met documented acceptance criteria." However, the actual performance values are not reported. For example, it lists "Funnel Radial Force" as a test but doesn't provide the measured radial force.

2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

• Sample Size: Not specified for any of the bench tests.
• Data Provenance: Not applicable in the context of bench testing for a physical device. Data is generated in a lab setting, not from patient populations.
• Retrospective/Prospective: Not applicable.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

• Not applicable. This device is not an AI/ML algorithm or a diagnostic tool that requires expert interpretation for ground truth establishment. Bench testing relies on engineering specifications and physical measurements, not expert human assessment of images or clinical data.

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

• Not applicable. No human interpretation or adjudication is involved in the bench testing described.

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. This is a physical medical device (catheter introducer), not an AI algorithm for diagnostic imaging. Therefore, no MRMC study was conducted.

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

• No. This is not an algorithm. Bench tests evaluate the physical performance of the device itself.

7. The type of ground truth used (expert concensus, pathology, outcomes data, etc)

• Engineering Specifications/Physical Standards: For bench tests, the "ground truth" or reference is typically defined by engineering design specifications, industry standards (e.g., ISO for biocompatibility and sterilization), and regulatory requirements. It is a measurement against a predefined acceptable range, not a "diagnosis."

8. The sample size for the training set

• Not applicable. This device does not use a training set as it's not an AI/ML algorithm or a data-driven model.

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

• Not applicable. As above, no training set is used.

Summary regarding the device and its studies:

The document states:

• "Results of successful design verification testing demonstrate the safety and effectiveness of the Pounce Sheath and that the technological differences identified do not raise new questions of safety or effectiveness compared to the predicate device."
• "All test results met documented acceptance criteria."

The studies performed were:

• Performance Bench Testing: A long list of physical and mechanical tests (e.g., Dimensional, Funnel Radial Force, Insertion Force, Hemostasis Valve Leakage, Radiopacity, Torque Strength).
• Biocompatibility: Tests performed according to ISO 10993-1, including Cytotoxicity, Irritation, Sensitization, Acute Systemic Toxicity, Material Mediated Pyrogenicity, Hemocompatibility (ASTM Hemolysis Assay, SC5b Complement Activation Assay, Partial Thromboplastin Time (PTT), Heparinized Platelet and Leukocyte Count Assay, In Vivo Thrombogenicity).
• Sterilization: Demonstrated compliance with ISO 11135.

Crucially, the document explicitly states:

• "No animal testing data was required for the Pounce Sheath."
• "No clinical data was required for the Pounce Sheath."

This indicates that the FDA deemed the bench testing sufficient to establish substantial equivalence given the nature of the device and its predicate.

Ask a specific question about this device

The Pounce™ Thrombectomy System is intended for the non-surgical removal of thrombi and emboli from the peripheral arterial vasculature.

The Pounce™ Thrombectomy System is a percutaneous catheter system designed to facilitate mechanical thrombus removal in the peripheral arterial vasculature. The system is comprised of three separate components: a 5Fr Basket Delivery Catheter, a Basket Wire Assembly, and a Trumpet Assembly. The system also includes a Basket Loading Tool accessory for loading the Basket Wire Assembly into the Basket Delivery Catheter. The system contains the necessary radiopaque components to conduct the procedure and the system should be introduced through a minimum 7Fr guide sheath.

The Basket Delivery Catheter is a flexible 5Fr catheter designed to deliver the Basket Wire Assembly to the location of the thrombus.

The Basket Wire Assembly is comprised of two distal self-expanding baskets mounted in series on a wire for capturing thrombus.

The Trumpet Assembly is used for thrombus collection and retrieval. The Trumpet Assembly is made of an inner trumpet catheter and an outer trumpet delivery catheters work together to allow deployment and retraction of the trumpet feature.

The provided text describes a 510(k) premarket notification for the Pounce™ Thrombectomy System, which is intended for the non-surgical removal of thrombi and emboli from the peripheral arterial vasculature. This is not the type of device (e.g., an AI/Machine Learning diagnostic or assistive device) that would typically have acceptance criteria presented in the format requested, nor would it involve the detailed study design (sample sizes, expert adjudication, MRMC studies, ground truth establishment for AI models) as outlined in the prompt's requirements.

The document primarily focuses on demonstrating substantial equivalence to a predicate device (Pounce™ Thrombectomy System K192814) by showing that a revised contraindication (for a smaller native vessel size) did not impact safety or effectiveness.

Therefore, I cannot fulfill the request as formatted, because the provided text does not contain the information relevant to a study proving a device meets acceptance criteria related to AI/ML performance, human reader improvement with AI assistance, or detailed ground truth methodologies for training and test sets.

Instead, the document states:

• Nonclinical Performance Testing Summary: "Test results demonstrated that all pre-defined acceptance criteria were met. Therefore, conforms to established product specifications and intended use and no new questions of safety and effectiveness were raised."

  • This indicates that internal acceptance criteria, likely related to engineering performance (e.g., basket cage radial force, simulated use), were met, but these are not the type of clinical performance criteria (e.g., sensitivity, specificity, AUC) typically associated with AI/ML devices that would involve large human reader studies.

• Clinical Data: "No clinical data was required to demonstrate substantial equivalence."

  • This explicitly states that a clinical study (like the one implied by the prompt's questions) was not necessary for this 510(k) submission, as substantial equivalence was demonstrated through nonclinical bench testing and prior animal testing information from the predicate device.

To directly answer the prompt's specific questions using the available information, where possible:

1. A table of acceptance criteria and the reported device performance:

   • The document states: "Test results demonstrated that all pre-defined acceptance criteria were met."
   • The specific criteria mentioned are:
     • Basket Cage Radial Force
     • Thrombectomy System Simulated Use
   • No quantitative performance values or a detailed table are provided in this regulatory summary.

2. Sample sizes used for the test set and the data provenance: Not applicable. No clinical test set data from human subjects or images were used for this substantial equivalence determination. The "test set" in this context refers to non-clinical bench tests.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. Ground truth as typically understood for AI/ML performance evaluation (e.g., expert consensus on medical images) was not established for this device's submission.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable. This refers to clinical image interpretation by multiple readers, which was not part of this submission.

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: Not applicable. An MRMC study was not performed, as implicitly stated by "No clinical data was required."

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable. This is a thrombectomy system, not an algorithm.

7. The type of ground truth used (expert concensus, pathology, outcomes data, etc): Not applicable in the context of clinical images and human interpretation. For the non-clinical tests, "ground truth" would be the engineering specifications and performance targets for the device's physical function.

8. The sample size for the training set: Not applicable. This is not an AI/ML device requiring a training set.

9. How the ground truth for the training set was established: Not applicable. This is not an AI/ML device requiring ground truth for a training set.

Ask a specific question about this device

The Thrombus Retrieval System is intended for the non-surgical removal of thrombi and emboli from the arterial peripheral vasculature.

The Pounce™ Thrombus Retrieval System is a percutaneous catheter system designed to facilitate mechanical thrombus removal in the peripheral arterial vasculature. The system is comprised of three separate components; a 5Fr Basket Delivery Catheter, a Basket Wire Assembly and a Trumpet Assembly. The system also includes a Basket Loading Tool accessory for loading the Basket Wire Assembly into the Basket Delivery Catheter. The system contains the necessary radiopaque components to conduct the procedure and the system should be introduced through a minimum 7Fr guide sheath.

This document describes the Surmodics Pounce™ Thrombus Retrieval System, a medical device intended for the non-surgical removal of thrombi and emboli from the arterial peripheral vasculature. The information provided is from a 510(k) summary submitted to the FDA. The following aims to extract details regarding acceptance criteria and the study proving the device meets them, based solely on the provided text.

Based on the provided FDA 510(k) summary, the Pounce™ Thrombus Retrieval System underwent various performance bench tests, packaging tests, biocompatibility tests, and an animal study to demonstrate substantial equivalence to its predicate devices. The document explicitly states that "All test results met documented acceptance criteria and/or included justification of values."

1. A table of acceptance criteria and the reported device performance

The document does not explicitly present a table of specific numerical acceptance criteria alongside corresponding numerical reported device performance for each test. Instead, it states that "All test results met documented acceptance criteria and/or included justification of values," indicating qualitative compliance. The tests performed are listed, implying that the device successfully met the undisclosed acceptance criteria for each.

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 does not specify the sample sizes used for each of the bench tests, packaging tests, or biocompatibility tests. It also does not provide details on the data provenance for these tests, such as country of origin or whether they were retrospective or prospective.

For the animal study, it states: "The Thrombus Retrieval System device was subjected to an acute animal GLP study to evaluate and confirm the substantially equivalent performance and safety of the Pounce Thrombus Retrieval System device use within an arterial vasculature system." However, the number of animals or specific details of the study design (e.g., prospective) are not mentioned.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

The document makes no mention of experts being used to establish ground truth for any of the tests, nor does it specify their qualifications. The tests conducted (bench, packaging, biocompatibility) are typically objective engineering and scientific evaluations that do not rely on expert consensus for "ground truth" in the same way clinical image interpretation might. The animal study would involve veterinary professionals, but their specific roles in establishing "ground truth" are not detailed.

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

The document does not describe any adjudication methods used for the test set. This is consistent with the nature of the tests performed, which are primarily objective and do not typically involve human interpretation needing adjudication.

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 multi-reader, multi-case (MRMC) comparative effectiveness study was done. The document explicitly states: "No Clinical data is being submitted for the Thrombus Retrieval System." This device is a mechanical thrombus retrieval system, not an AI-assisted diagnostic or interpretative tool, so an MRMC study comparing human readers with and without AI assistance is not applicable.

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

This question is not applicable as the Pounce™ Thrombus Retrieval System is a physical medical device for mechanical thrombus removal, not an algorithm or AI system. Therefore, standalone algorithm performance without human-in-the-loop is not relevant.

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

The types of "ground truth" used for the various tests are inherent to the nature of those tests:

• Performance Bench Testing: Engineering specifications, material properties, and functional design requirements serve as the ground truth. For example, a "burst" test would have an acceptance criterion for the pressure it withstands, which is its engineered breaking point.
• Packaging Testing: Compliance with ISO 11607-1 standards and internal design specifications for package integrity.
• Biocompatibility Tests: Compliance with ISO 10993-1 series standards for biological safety, with established limits for various toxicological endpoints.
• Sterilization Evaluation: Compliance with ISO 11135 standards for ethylene oxide sterilization.
• Animal Testing: Physiological and histological assessments in an animal model to evaluate device performance and safety in a living system. The "ground truth" here would be the biological response and observable effects.

8. The sample size for the training set

This question is not applicable. This device is a physical medical device, not a software algorithm that requires a training set.

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

This question is not applicable as there is no training set for a physical medical device.

Ask a specific question about this device

The Guide Sheath is intended to introduce therapeutic devices into the vasculature, excluding the coronary and neuro vasculature.

The Surmodics Guide Sheath is designed to perform as a guide sheath and/or introducer sheath. The sheath is braid reinforced with an embedded radiopague marker band to identify the distal tip. It also has a hydrophilic coating over the working length to provide a lubricious surface to ease insertion. The device comes packaged with a dilator, which is either .018" or .035" guidewire compatible.

This highly flexible, braid reinforced sheath is designed to resist kinking and maximize strength while keeping a minimized profile. Incorporated in the sheath is a radiopaque marker band located approximately 5mm from the distal tip. The Guide Sheath has an atraumatic tip and has a hydrophilic coating over the working length.

The dilator hub is designed to snap into the Guide Sheath cross cut valve cap. Additionally, the dilator shaft design allows for simultaneous movement of the sheath and dilator assembly. The dilator features an atraumatic tip, which is designed to extend beyond the sheath tip by approximately 5 cm. The dilator shaft is radiopaque.

The Guide Sheath features a custom designed cross cut valve that is integrated into the sheath hub and includes a 3-way stopcock with sidearm extension tubing. No assembly is required.

The sheath is packaged in a dual sterile barrier configuration. The sheath and dilator will be placed individually in high density polyethylene (HDPE) coiled hoops, which are then placed in a poly-tyvek pouch within a shelf box.

I apologize, but the provided text from the FDA 510(k) summary for the Surmodics Guide Sheath does not contain information related to a study proving a device meets acceptance criteria for an AI/software device.

The document describes the acceptance criteria and performance of a physical medical device (catheter introducer) through various bench tests, packaging tests, and biocompatibility tests. It demonstrates substantial equivalence to a predicate device, as opposed to an AI or software product.

Therefore, I cannot fulfill your request for information regarding an AI device's acceptance criteria, data provenance, expert ground truth establishment, MRMC studies, or training set details, as these concepts are not applicable to the content provided.

Ask a specific question about this device

The Surmodics Microcatheter is intended to provide support to facilitate the placement of guidewires in the coronary and peripheral vasculatures and can be used to exchange one guidewire for another. This microcatheter is also intended to assist in the delivery of contrast media into the coronary and peripheral vasculatures.

Do not use this microcatheter other than for use in the coronary and peripheral vasculatures.

The Surmodics Microcatheter is a sterile, single use, percutaneous device intended to provide support to facilitate the placement of guidewires in the coronary and peripheral vasculature. Additionally, the microcatheter can be used for contrast media injection.

The catheter is a single-lumen microcatheter with a 1.9 Fr distal outer diameter, a 2.6 Fr proximal outer diameter and is compatible with a 0.014" guidewire. The proximal end of the catheter shaft has a larger inner diameter, outer diameter and wall thickness and tapers to the catheter is available in lengths of 135 cm and 150 cm in length to facilitate access to various target sites.

The provided text describes a 510(k) premarket notification for a medical device called the "Surmodics Microcatheter." This type of submission focuses on demonstrating substantial equivalence to a legally marketed predicate device rather than conducting effectiveness studies akin to AI/ML device studies. Therefore, many of the requested elements for AI/ML device evaluations (such as human readers, ground truth establishment, training set details, or comparative effectiveness studies with AI assistance) are not applicable or not present in this document.

However, I can extract and structure the available information regarding acceptance criteria and testing:

Acceptance Criteria and Device Performance Study for Surmodics Microcatheter (K173560)

This submission establishes substantial equivalence to a predicate device (ASAHI Caravel, K152447) based on design, intended use, principles of use, materials, sizes, and sterility. The "acceptance criteria" here refer to the performance thresholds met during design verification and biocompatibility testing. The "study" refers to the conducted design verification tests and biocompatibility assessments.

1. Table of Acceptance Criteria and Reported Device Performance

The document states that "All test results met documented acceptance criteria and did not raise new questions of safety or effectiveness." Specific quantitative performance values or detailed acceptance criteria are not provided in this regulatory document. The table below lists the types of tests performed.

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

The document does not specify the sample sizes for each individual test or the data provenance (e.g., country of origin, retrospective/prospective). These details are typically contained in the full test reports referenced in such a submission, but not in the summary provided.

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

Not applicable. For a 510(k) submission for a non-AI/ML device, "ground truth" as typically understood in AI/ML performance evaluation (e.g., expert consensus on medical images) is not established. Device performance is assessed against engineering specifications, material properties, and regulatory standards.

4. Adjudication Method for the Test Set

Not applicable. This is not an AI/ML device and does not involve adjudication of expert interpretations for a test set.

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

No, an MRMC comparative effectiveness study was not performed. This is a 510(k) submission for a microcatheter, not an AI/ML device, and thus does not involve human readers or AI assistance.

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

Not applicable. This is not an AI/ML algorithm. The device performance testing is akin to "standalone" in the sense that the device's physical and functional characteristics are tested directly without human intervention in the device's core function.

7. The Type of Ground Truth Used

The "ground truth" for this device's performance is established by engineering specifications, material science standards, and regulatory requirements (e.g., ISO standards) for medical devices. For example, a "tensile strength" test has a defined pass/fail criterion based on mechanical properties required for the device's intended use. Similarly, biocompatibility tests are assessed against established biological response limits.

8. The Sample Size for the Training Set

Not applicable. This is a conventional medical device; there is no "training set" in the context of machine learning. The device design is based on engineering principles and iterative development, not data-driven machine learning training.

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

Not applicable, as there is no training set for this device.

Ask a specific question about this device