Search Results

The Advance Serenity 18 Hydrophilic PTA Balloon Dilatation Catheter is indicated for Percutaneous Transluminal Angioplasty (PTA) of the peripheral vasculature in the iliac, femoral, popliteal, infrapopliteal, and renal arteries, and for the treatment of obstructive lesions of native or synthetic arteriovenous dialysis fistulae.

The Advance Serenity™ 18 Hydrophilic PTA Balloon Dilatation Catheter is a coaxial catheter with a semi compliant balloon near the distal tip. It is an Over-the-Wire (OTW) Percutaneous Transluminal Anqioplasty (PTA) device with various shaft lengths. The balloon has two radiopaque markers that aid in the placement of the balloon within the stenosis. The clearance between the inner and outer shafts acts as the passage for the inflation medium for balloon expansion. The proximal end of the catheter has a bifurcated manifold & strain relief that allows for the 0.018" guidewire and the attachment of a balloon inflation device via a standard luer connector. The inflation device is used to inflate and deflate the balloon with a contrast medium. The device is used by positioning the balloon catheter over a guidewire. The balloon is aligned under fluoroscopy in the diseased vessel at the area to be treated. The balloon is then inflation media to pressures ranging between the nominal and the rated burst pressure to dilate the occluded area. On completion the balloon is then deflated under vacuum and removed from the patient. The Advance Serenity™ 18 Hydrophilic PTA Balloon Dilatation Catheter is to be provided sterile (via ethylene oxide, EtQ) and is intended for single use only.

The provided text is an FDA 510(k) clearance letter and its associated summary for a medical device: the "Advance Serenity™ 18 Hydrophilic PTA Balloon Dilatation Catheter." This document focuses on demonstrating substantial equivalence to a predicate device, rather than proving the safety and effectiveness of a novel device through clinical trials and rigorous statistical validation against predefined acceptance criteria.

Therefore, the information regarding acceptance criteria, study design for proving device performance, sample sizes for test sets, establishment of ground truth, expert adjudication, MRMC studies, standalone performance, training set details, and ground truth for training data is not present in the provided text.

The document primarily outlines:

• Acceptance Criteria (Implicit via Substantial Equivalence): The implicit acceptance criterion for this 510(k) submission is that the device must be shown to be "substantially equivalent" to a legally marketed predicate device. This means it has the same intended use, similar technological characteristics, and any differences do not raise new questions of safety or effectiveness.
• Reported Device Performance: Instead of a detailed table of acceptance criteria and performance against them, the document lists bench tests performed to demonstrate that the small changes (expanded matrix of balloon sizes) compared to the predicate device do not compromise safety or effectiveness.

Here's a breakdown of what is available and what is missing from your request based on the provided text:

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

• Acceptance Criteria: Not explicitly stated as pass/fail thresholds for specific performance metrics in a table. The overall acceptance criterion is "substantial equivalence" to the predicate.

• Reported Device Performance: The document lists bench tests performed, indicating that the results "demonstrate that the technological differences identified do not raise new questions of safety or effectiveness." Specific quantitative results or acceptance criteria for these bench tests are not provided.

  Performed Bench Tests (as listed):

  • Rated burst pressure (RBP)
  • Inflation & deflation time
  • Balloon diameters at nominal pressure to RBP
  • Simulated use - Pushability & Trackability & Sheath Compatibility
  • Coating integrity (b)
  • Multiple inflation/fatigue & leak test
  • Tensile strength Balloon to Shaft (proximal bond)
  • Particulate
  • Balloon Length & Marker Band Position (Leveraged from predicate)
  • Radiopacity (Leveraged from predicate)
  • Ancillary Tool Compatibility (Guidewire) (Leveraged from predicate)
  • Catheter Effective Length (Leveraged from predicate)
  • Tensile Strength Manifold to Shaft (Manifold Bond) (Leveraged from predicate)
  • Tensile Strength (Distal / Tip Bond) (Leveraged from predicate)
  • Tip Profile (Geometry of the catheter most distal tip) (Leveraged from predicate)
  • Simulated Use, Push & Track (Leveraged from predicate)
  • Flexibility & Kink (Leveraged from predicate)
  • Coating Lubricity (Leveraged from predicate)
  • Coating Integrity (a) (Leveraged from predicate)
  • Torque Strength (Leveraged from predicate)

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

• Sample Sizes: Not specified. This document refers to bench testing of a medical device, which typically involves a number of units tested to engineering specifications, but these numbers are not disclosed.
• Data Provenance: The tests are bench tests, not clinical data, so country of origin/retrospective/prospective doesn't apply in the same way. The manufacturer is based in Ireland (Creagh Medical Ltd. dba Surmodics, Inc.).

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)

• This is not part of a bench test evaluation for a substantial equivalence determination. Experts are not typically used to establish "ground truth" for physical device performance metrics like burst pressure.

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

• Not applicable to bench testing.

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 MRMC study was done. This device is a physical catheter, not an AI/software device that assists human readers.
• The document explicitly states: "No clinical studies were required for the Advance Serenity 18 Hydrophilic PTA Balloon Dilatation Catheter."

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

• Not applicable as it's not an AI/software device.

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

• Not applicable. Performance is measured against engineering specifications and industry standards for physical device properties, not against "ground truth" derived from clinical data or expert consensus.

8. The sample size for the training set

• Not applicable; there is no training set for a physical medical device. (This is relevant for AI models).

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

• Not applicable; there is no training set.

In summary, the provided FDA document is a 510(k) clearance letter for a physical medical device, based on demonstrated "substantial equivalence" through bench testing, not clinical studies or AI model validation. Therefore, most of the detailed information requested regarding clinical study design, data characteristics, expert involvement, and AI model evaluation (points 2-9) is not found in this type of submission.

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 Surmodics™ Pounce™ XL 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 delivery catheter, a basket wire and a funnel catheter. The system also includes a basket loading tool accessory for loading the basket wire into the delivery catheter. The system contains the necessary radiopaque components to conduct the procedure and the system should be introduced through a minimum 7 Fr guide sheath.

The Delivery Catheter is flexible and designed to deliver the Basket Wire to the location of the thrombus. Incorporated in the catheter is a radiopaque marker band located at the distal tip.

The Basket Wire is comprised of two distal self-expanding baskets mounted on a core wire for capturing thrombus. The distal capture baskets have integral radiopaque markers mounted on the struts of the basket for basket visibility under fluoroscopy.

The Funnel Catheter is used for thrombus collection and retrieval in conjunction with the Basket Wire. The Funnel Catheter is comprised of an inner funnel catheter and an outer delivery catheter. The two catheters work together to allow unsheathing and sheathing of the slider button on the integrated handle.

The provided text is a 510(k) summary for the Surmodics Pounce XL Thrombectomy System. This document outlines the device's technical specifications, indications for use, and a summary of testing conducted to demonstrate substantial equivalence to predicate devices. It does not describe a study involving human-in-the-loop performance with AI assistance, nor does it detail a standalone AI algorithm performance study. The device described is a mechanical thrombectomy system, not an AI-powered diagnostic or therapeutic device.

Therefore, many of the requested details, such as "acceptance criteria," "sample size for test set," "number of experts," "adjudication method," "MRMC study," "standalone study," "type of ground truth," "sample size for training set," and "how ground truth for training set was established" are not applicable to this document as they pertain to the evaluation of AI/ML-based medical devices or diagnostic studies, not the mechanical thrombectomy system described here.

The document focuses on the mechanical performance and biocompatibility of the device, comparing it to existing predicate devices.

However, I can extract the information relevant to the mechanical device's acceptance criteria and the summary of studies performed to prove it meets them, based on the provided text.

Here's a breakdown of the requested information, adapted to what is present in the document:

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

The document states: "All test results met documented acceptance criteria and did not raise new questions of safety or effectiveness." It lists the types of tests conducted but does not provide the specific numerical acceptance criteria or the numerical results for each test. Instead, it offers a high-level statement of compliance.

Summary of Studies Performed (Relevant to mechanical device performance):

The device was evaluated through the following tests, with all results meeting documented acceptance criteria:

• Dimensional evaluations
• Radiopacity
• Tensile Strength
• Freedom from leakage
• Hub/Luer connector compatibility
• Removal Force
• Radial Force
• Kink Resistance
• Torque Strength
• Ancillary Device Compatibility
• Atraumatic Surfaces
• Simulated Use
• Basket Wire Fatigue
• Biocompatibility

2. Sample sized used for the test set and the data provenance

The document does not specify sample sizes for any of the performance or bench tests (e.g., how many devices were tested for tensile strength or fatigue). It also does not discuss "data provenance" in the context of clinical data (e.g., country of origin, retrospective/prospective) because these are benchmarking/engineering tests of a physical device, not clinical trials or AI model validation studies.

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

Not applicable. "Ground truth" in this context would refer to engineering specifications and performance benchmarks, not expert medical consensus on imaging or clinical outcomes, as this is a mechanical device, not an AI system. The "experts" would be the engineers and technicians performing the tests and comparing results against design specifications.

4. Adjudication method for the test set

Not applicable. Adjudication methods like "2+1" or "3+1" are used in clinical trials or expert review of data (e.g., radiology reads) to resolve discrepancies in interpretation. These are bench tests against engineering 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

Not applicable. This is a mechanical thrombectomy device, not an AI-powered diagnostic or assistance tool for human readers.

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

Not applicable. This relates to AI algorithm performance.

7. The type of ground truth used

For the mechanical device performance tests, the "ground truth" would be established engineering specifications, design requirements, and recognized industry standards for medical device performance (e.g., biocompatibility standards, tensile strength requirements for catheters).

8. The sample size for the training set

Not applicable. This refers to the training of an AI model, which is not the subject of this document.

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

Not applicable, for the same reason as above.

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 distal end. The catheter is available in working lengths of 135 cm and 150 cm to facilitate access to various target sites.

The provided text is a 510(k) clearance letter from the FDA for a microcatheter, not an AI/ML device. Therefore, it does not contain any of the information requested regarding acceptance criteria, study details, sample sizes, expert ground truth, or MRMC studies for an AI/ML device.

The document states:

• The device is a "Microcatheter" (Trade/Device Name).
• Its classification is "Percutaneous catheter" (Regulation Name, Class II, Product Code DQY).
• It's a medical device for use in coronary and peripheral vasculatures.
• "No clinical studies were required for the Surmodics Microcatheter." (Section 8.5)
• Performance testing focused on "Coating Integrity (Particulate, Track Force), Simulated Use (part of track force testing), Pinch testing lubricity, and Biocompatibility." (Section 8.4)

Since this document pertains to a physical medical device (microcatheter) and explicitly states no clinical studies were required, the questions regarding AI/ML device performance, ground truth, expert adjudication, and comparative effectiveness studies are not applicable and cannot be answered from this source.

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 LP Thrombectomy System is indicated for use in vessels ranging from 2 mm in diameter.

The Surmodics 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 Delivery Catheter, a Basket Wire, the Funnel Catheter, and cleaning tool accessories. The system contains radiopaque components to conduct the procedure and is intended to be introduced through appropriately sized guide sheath.

The Delivery Catheter is flexible and designed to deliver the Basket Wire to the location of the thrombus. Incorporated in the catheter is a radiopaque marker band located at the distal tip.

The Basket Wire is comprised of two distal self-expanding baskets mounted a core wire for capturing thrombus. The distal capture baskets have integral radiopaque markers mounted on the struts of the basket for basket visibility under fluoroscopy.

The Funnel Catheter is used for thrombus collection and retrieval in conjunction with the Basket Wire. The Funnel Catheter is comprised of an inner funnel catheter and an outer delivery catheter. The two catheters work together to allow unsheathing of the funnel using the slider button on the integrated handle.

The provided document describes the Pounce™ Thrombectomy System, specifically the Pounce LP Thrombectomy System, for which Surmodics Inc. sought 510(k) clearance (K231022). This submission is for modifications to an existing predicate device (Pounce™ Thrombectomy System, K220501) to extend its use to smaller vessels.

The document explicitly states: "No clinical studies were required for the Pounce Thrombectomy System."

Therefore, the following information regarding acceptance criteria, device performance, and study details is not available in the provided text, as the clearance was based on bench testing and a determination of substantial equivalence to a predicate device, rather than a clinical study demonstrating performance against specific acceptance criteria.

However, based on the provided information, we can infer some aspects relevant to a hypothetical acceptance criteria and the type of study conducted (bench testing) to support the device's substantial equivalence.

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

Since no clinical study was performed and the clearance was based on substantial equivalence to a predicate, there isn't a table of clinical acceptance criteria and device performance in the traditional sense for this submission. The "acceptance criteria" here would be the successful completion of various bench tests demonstrating that the modified device performs similarly to the predicate and meets engineering specifications.

Study that proves the device meets the acceptance criteria:

The study that "proves the device meets the acceptance criteria" in this context is the Performance Bench Testing listed on page 5 of the document. These tests evaluated mechanical properties, device functionality, material integrity, and compatibility with the intended use environment.

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: The document does not specify the sample sizes used for each of the bench tests.
• Data Provenance: Not applicable. These were bench tests, not clinical data from patients. They would have been conducted within Surmodics Inc. (an American company) or contracted labs.
• Retrospective or Prospective: Not applicable, as these were non-clinical, controlled bench tests.

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. For bench testing, "ground truth" is typically established by engineering specifications, validated test methods, and industry standards, rather than expert clinical consensus.

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

Not applicable. Adjudication methods like 2+1 or 3+1 are used for clinical trial endpoints or image interpretation where human judgment is involved. Bench tests rely on objective measurements and established pass/fail criteria.

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. No clinical studies were required or performed for this submission. The device is a mechanical thrombectomy system, not an AI-assisted diagnostic or therapeutic device that would involve human readers or AI improvement.

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

Not applicable. The device is a mechanical thrombectomy system, not an algorithm.

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

Not applicable for the bench testing. The "ground truth" for each bench test was defined by the specified engineering requirements and performance parameters that the device was designed to meet, often in accordance with ISO or ASTM standards.

8. The sample size for the training set

Not applicable. As a physical medical device, there is no "training set" in the context of machine learning or AI.

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

Not applicable. See point 8.

Ask a specific question about this device

The Sublime™ Microcatheter is intended to access the peripheral vasculature in order to facilitate the placement and/or the exchange of guidewires. The Sublime Microcatheter is also intended to provide a conduit for the delivery of saline solutions or diagnostic contrast agents.

The Sublime Microcatheter is a sterile, single-use, disposable intravascular catheter with an atraumatic distal tip and a proximal hub with a luer fitting. The Sublime Microcatheter is a single lumen support catheter, compatible with 014", 018", and 035" guide wire platforms and a 4F guide catheter. It has a working length of up to 200 cm, and both straight and angled tip configurations. The catheter has a stainless-steel braid supported construction with hydrophilic coating. The distal end of the catheter includes a radiopaque markerband to facilitate visualization under fluoroscopy.

This document is a 510(k) Premarket Notification from the U.S. Food and Drug Administration (FDA) for the Sublime™ Microcatheter. It describes the device, its intended use, and the studies conducted to demonstrate its substantial equivalence to a legally marketed predicate device.

Here's an analysis of the acceptance criteria and the study proving the device meets them, based on the provided text:

Important Note: This document pertains to a medical device (Microcatheter), not an AI/software device. Therefore, many of the typical questions for AI/software such as "Number of experts used to establish ground truth," "Adjudication method," "MRMC study," "Standalone performance," "Training set sample size," and "How ground truth for training set was established" are not applicable in this context. The acceptance criteria and studies are for a physical medical device's performance characteristics.

Acceptance Criteria and Reported Device Performance

The document states that "All test results met documented acceptance criteria." However, it does not explicitly list the quantitative acceptance criteria for each test. It only lists the tests performed, implying that specific criteria were defined and met internally by the manufacturer.

Table 1: Acceptance Criteria and Reported Device Performance (as inferred from the text)

Study Details

As this is a physical medical device, the "study" primarily consists of design verification testing rather than clinical performance studies typically seen with diagnostic or AI devices. The goal is to demonstrate "substantial equivalence" to a predicate device based on performance characteristics.

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

   • Sample Size: The document does not specify the sample sizes used for each of the listed tests (e.g., number of catheters tested for flow rate, tensile strength, etc.).
   • Data Provenance: This would typically be from laboratory bench testing and simulated use, conducted by the manufacturer (Surmodics Inc.). The country of origin is implied to be the USA, as the company is based in Eden Prairie, Minnesota, and submitting to the US FDA. The testing is prospective in nature, as it's part of the premarket notification process for a new device.

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

   • This question is not applicable for this type of medical device clearance. "Ground truth" in this context refers to engineering specifications and performance standards established by the manufacturer and recognized industry standards (e.g., ISO standards for medical devices). The expertise would be in materials science, mechanical engineering, and quality control, rather than medical interpretation by radiologists.

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

   • This is not applicable for engineering bench testing. Adjudication methods are typically for human interpretation of medical images or clinical outcomes. Deviations from expected test results would be handled through a non-conformance process and investigation by engineers and quality personnel.

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:

   • This is not applicable. This is a physical microcatheter, not an AI software. No human reader studies (MRMC) were conducted or required for this type of device clearance.

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

   • This is not applicable. This is a physical medical device, not an algorithm.

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

   • The "ground truth" (or more appropriately, the reference standard) for these tests is based on defined engineering specifications, performance standards (e.g., ISO standards for catheters), and validation methods for each physical characteristic (e.g., a calibrated flow meter for flow rate, a universal testing machine for tensile strength, a pressure gauge for burst testing). Biocompatibility is assessed against established biological safety standards.

7. The sample size for the training set:

   • This is not applicable. This is a physical medical device, not a machine learning model that requires a training set.

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

   • This is not applicable for the same reason as above.

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 Surmodics 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 Delivery Catheter, a Basket Wire with a preloaded loading tool, and the Funnel Catheter. The system contains radiopaque components to conduct the procedure and is intended to be introduced through a minimum 7Fr guide sheath.

The Delivery Catheter is a flexible 5Fr catheter designed to deliver the Basket Wire to the location of the thrombus. Incorporated in the catheter is a radiopaque marker band located at the distal tip.

The Basket Wire is comprised of two distal self-expanding baskets mounted a core wire for capturing thrombus. The distal capture baskets have integral radiopaque markers mounted on the struts of the basket for basket visibility under fluoroscopy.

The Funnel Catheter is used for thrombus collection and retrieval in conjunction with the Basket Wire. The Funnel Catheter is comprised of an inner funnel catheter and an outer delivery catheter. The two catheters work together to allow unsheathing and sheathing of the funnel using the slider button on the integrated handle.

This document is a 510(k) premarket notification for the Surmodics Pounce™ Thrombectomy System. It outlines the device's description, indications for use, and a comparison to a predicate device.

Here's an analysis of the acceptance criteria and study information:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state acceptance criteria in a quantitative format, nor does it present device performance against specific targets for efficacy. Instead, it describes a series of bench tests conducted to demonstrate substantial equivalence to the predicate device after modifications. The reported performance is a qualitative statement of meeting these testing requirements.

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

The document does not specify sample sizes for the bench tests. The tests are described as "design verification" and "biocompatibility testing." These are typically laboratory-based engineering tests, not clinical studies involving human or animal subjects. Therefore, the concept of "data provenance" (country of origin, retrospective/prospective) as it applies to clinical data is not relevant here.

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

Not applicable. This report details bench testing, not a study requiring expert-established ground truth for a test set.

4. Adjudication Method for the Test Set

Not applicable. There was no clinical test set requiring adjudication in this 510(k) submission.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size of Human Reader Improvement

No. The document explicitly states: "No clinical studies were required for the Pounce Thrombectomy System." Therefore, no MRMC study was conducted.

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

Not applicable. This device is a medical instrument (thrombectomy system), not an AI algorithm, so standalone performance in that context is not relevant.

7. Type of Ground Truth Used (Expert Consensus, Pathology, Outcomes Data, etc.)

For the bench testing, the "ground truth" would be the engineering specifications and established standards for performance and biocompatibility for medical devices. The device was tested against these predefined criteria to ensure it met the necessary performance characteristics and was safe for its intended use, demonstrating substantial equivalence to its predicate.

8. 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.

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