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 FlowTriever2 Catheter is indicated for:
• The non-surgical removal of emboli and thrombi from peripheral blood vessels.
• Injection, infusion, and/or aspiration of contrast media and other fluids into or from a blood vessel.
The FlowTriever2 Catheter is intended for use in the peripheral vasculature and for the treatment of pulmonary embolism (PE).

The Inari FlowTriever Retrieval/Aspiration System is a single-use, sterile medical device comprised of the following components, each packaged separately:
• FlowTriever2 Catheter - Model 11-102
• Triever20® - Model 21-101
• Triever24® - Model 22-101
• Triever16® - Model 25-101

The FlowTriever2 Catheter is used to engage and retrieve emboli and thrombi. It consists of a coaxial catheter assembly with an outer Delivery Catheter and an inner catheter having a flexible shaft attached to distal self-expanding wireform element. A "Y" connector with a rotatable hemostatic valve and stopcock is attached to the proximal end of the outer Delivery Catheter. Radiopaque markers are positioned near the distal tip of the Delivery Catheter and at the proximal and distal ends of the self-expanding FlowTriever element to aid with fluoroscopic visualization.

The Triever20 and Triever24 (packaged separately) provides a conduit for FlowTriever2 Catheter deployment, aspiration, and clot removal. It consists of a single lumen catheter with a proximal hemostasis valve and stopcock with flush port. A radiopaque marker is positioned near the distal tip to aid with fluoroscopic visualization. A Dilator compatible with a 0.035" guidewire is provided for the Triever20 and Triever24 to aid insertion.

Alternatively, the Triever16 can be tracked through the Triever Catheter (20 or 24 Fr) over the pre-inserted guidewire to a location proximal to the targeted thrombus. Thrombus is removed via aspiration using the Triever16, after which it can be withdrawn and flushed to remove residual thrombus, leaving the Triever Catheter in place as a conduit for subsequent thrombectomy passes. The user may elect to perform a thrombectomy pass using the FlowTriever2 Catheter or through the Triever16 using aspiration alone.

The Inari FlowTriever Retrieval/Aspiration System has not been evaluated for use in the neurovasculature.

The provided text is related to the FDA 510(k) premarket notification for the FlowTriever2 Catheter, specifically for an expanded indication for the treatment of pulmonary embolism (PE). This document focuses on demonstrating substantial equivalence to a predicate device based on non-clinical and clinical testing.

The information primarily describes the device, its indications for use, comparison with a predicate device, and the specifics of a clinical study (FLARE-FT2) to support the expanded indication. However, it does not delineate specific acceptance criteria with reported device performance in a table format as requested. Furthermore, it does not specify details about sample sizes for test sets, ground truth establishment methods for test/training sets, or specific information about MRMC studies, as the device is not an AI/ML diagnostic system.

Based on the provided text, here's an attempt to extract the requested information, with notable limitations due to the nature of the document:

1. Table of Acceptance Criteria and Reported Device Performance:

The document describes the primary safety and effectiveness endpoints of the FLARE-FT2 clinical study. These endpoints serve as the "acceptance criteria" and the study results are the "reported device performance."

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

• Sample Size (Test Set): A total of 50 patients were enrolled in the FLARE-FT2 clinical study.
• Data Provenance: The study was a prospective, single-arm, multicenter confirmatory study. The country of origin is not explicitly stated, but clinical studies are generally conducted in a controlled, multi-center environment, likely within the US given FDA submission.

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

The document describes a clinical study for a medical device (catheter) used for embolectomy/thrombectomy, not an AI/ML diagnostic software. Therefore, the concept of "ground truth" established by experts for a "test set" in the context of an algorithm's performance is not directly applicable here. The outcomes measured in the clinical study (SAE, changes in pulmonary arterial pressure) are direct physiological measurements or clinical events, not classifications requiring expert interpretation for ground truth.

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

As this is a clinical trial evaluating a medical device, not an AI/ML diagnostic, adjudication methods like N+1 consensus are not detailed for establishing ground truth of image interpretations. Clinical trials typically have a different structure for reviewing and adjudicating adverse events and clinical outcomes, often involving independent clinical event committees (CECs) or data safety monitoring boards (DSMBs), but the specifics are not included in this 510(k) summary.

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 document does not mention an MRMC study. The device is a physical catheter for thrombectomy and embolectomy, not an AI/ML-driven diagnostic or assistive software requiring comparison of human reader performance with and without AI assistance.

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

No. This question is irrelevant as the device is a physical catheter, not an algorithm.

7. The type of ground truth used:

The "ground truth" in the context of this device's clinical study refers to directly measured safety and effectiveness outcomes in patients.

• Safety: Incidence of Serious Adverse Events (SAE), including device-related mortality, major bleeding, and intra-procedural adverse events. These are clinical outcomes directly observed and recorded.
• Effectiveness: Change in mean and systolic pulmonary arterial pressure (a physiological measurement).

8. The sample size for the training set:

As this is a physical medical device and its clearance is based on a clinical trial for effectiveness and safety, not on an AI/ML model for which a "training set" would be used, this concept is not applicable here. The 50 patients in the FLARE-FT2 study represent the clinical evaluation data.

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

Not applicable, as no AI/ML model with a separate training set is described. The "ground truth" for the clinical study was established through direct patient observation and physiological measurements.

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

The ClotTriever Thrombectomy System is indicated for:

• · The non-surgical removal of thrombi and emboli from blood vessels.
• · Injection, infusion, and/or aspiration of contrast media and other fluids into or from a blood vessel.
  The ClotTriever Thrombectomy System is intended for use in the peripheral vasculature including deep vein thrombosis (DVT).

The ClotTriever Thrombectomy System is a single-use, sterile medical device system designed to remove thrombi and emboli from the peripheral vasculature. The ClotTriever XL Catheter is intended for vessels 10 to 28 mm in the peripheral vasculature. The ClotTriever Thrombectomy System consists of the 16Fr ClotTriever Sheath ("ClotTriever Sheath"), Protrieve Sheath and the ClotTriever XL Catheter ("Catheter"), each packaged separately.
The ClotTriever XL Catheter is a coaxial catheter assembly with a distal coring element and collection bag for retrieving thrombus. The proximal handle controls the expansion of the collection bag via the inner catheter. The outer shaft constrains the coring element and collection bag prior to deployment. Stopcocks and Luer connectors are provided for de-airing the ClotTriever XL Catheter shafts.
To aid in fluoroscopic visualization, the distal tip is radiopaque and radiopaque marker bands are located on the intermediate catheter to identify the proximal end of the coring element, and on the outer catheter to identify the distal end of ClotTriever XL outer catheter.

This document is a 510(k) summary for the Inari Medical ClotTriever XL Catheter (41-102). It describes a labeling correction to the Instructions for Use (IFU) for the device. As such, the submission focuses on verifying that the labeling changes do not alter performance or safety, rather than providing extensive de novo performance data.

Here's an analysis of the provided information regarding acceptance criteria and supporting studies:

1. Table of Acceptance Criteria and Reported Device Performance

Explanation: The document states that "In accordance with the design failure modes and effects analysis, design validation testing was only performed on the attributes impacted by the IFU modifications." This suggests that the acceptance criteria for the "Simulated Use – Clot Burden" and "Simulated Use – Tensile Testing" would have been established based on ensuring the device continues to function as intended and safely, despite the labeling changes. However, the specific numerical or qualitative criteria for these tests are not detailed in the provided text. The conclusion of substantial equivalence implies that these criteria were met.

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

Due to the nature of this submission being a labeling correction rather than a new device submission or significant modification, the concept of a "test set" for performance evaluation in the typical sense (e.g., a clinical trial cohort or a dataset for AI model testing) is not directly applicable.

• Sample Size for Non-Clinical Testing: Not explicitly provided for the "Simulated Use – Clot Burden" and "Simulated Use – Tensile Testing." These tests would have used an appropriate number of devices to demonstrate reproducibility and robustness, but the specific count is not mentioned.
• Data Provenance: The non-clinical testing was conducted by Inari Medical, Inc. The data is prospective for this specific submission, as it was generated to support the labeling updates. No information is provided regarding country of origin for the data, but it would typically be conducted in the country of the manufacturer (USA, in this case).

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

This question is not applicable to this submission. The device is a physical medical device (catheter) for thrombus removal, not an AI or diagnostic device that requires expert-established ground truth on a test set. The validation for this submission focuses on non-clinical performance and safety based on changes to the instructions for use.

4. Adjudication Method for the Test Set

This question is not applicable for the same reasons as point 3.

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

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not done. This type of study is typically associated with diagnostic imaging devices or AI-powered clinical decision support systems where human readers interpret medical data. The ClotTriever XL Catheter is a therapeutic device, and this particular submission concerns a labeling correction, not a comparative effectiveness study of the device itself.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was Done

No, a standalone performance study was not done. This question is primarily relevant for AI algorithms. The ClotTriever XL Catheter is a physical medical device, not an algorithm.

7. The Type of Ground Truth Used

For the non-clinical testing ("Simulated Use – Clot Burden" and "Simulated Use – Tensile Testing"), the "ground truth" would be established by engineering specifications, design requirements, and industry standards for device performance and safety. For example, for tensile testing, the ground truth would be breaking strength exceeding a specified threshold. For simulated clot burden, the ground truth would be successful and complete removal of simulated clots according to a predefined metric. This differs from expert consensus, pathology, or outcomes data which are relevant for diagnostic or AI-based devices.

8. The Sample Size for the Training Set

This question is not applicable. The ClotTriever XL Catheter is a physical medical device, not an AI algorithm that requires a training set.

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

This question is not applicable for the same reasons as point 8.

Ask a specific question about this device

The Removal System Large Bore 60 cc Syringe is used with the Removal Catheters to inject fluids into or withdraw fluids and/or tissues from the body. It can be used for aspiration removal of fluid and/or tissue in the form of abscess fluid, infected materials, etc.

The Removal System Large Bore 60 cc Syringe is a general piston syringe constructed using a barrel, plunger, plunger seal, and large bore Toomey tip adapter that acts as a quick-release connector. The quick-release connector is compatible with the Removal System Catheters' sideport connector to establish an airtight seal. The twist-to-lock plunger with barrel tabs maintains the retracted position of the plunger.

The provided text describes information about the Inari Medical, Inc. Removal System Large Bore 60 cc Syringe (K233069).

Based on the provided document, this device is a simple piston syringe. The information about "acceptance criteria" and "study that proves the device meets the acceptance criteria" refers to non-clinical performance testing for mechanical integrity, biocompatibility, and sterilization, rather than a clinical study involving human patients or complex AI algorithms. Therefore, many of the requested categories (like MRMC studies, expert ground truth for imaging, training/test set sample sizes for AI, etc.) are not applicable to this type of device submission.

Here's the breakdown of the relevant information from the document:

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

The document does not provide a direct table of specific numerical acceptance criteria alongside quantitative performance results for each test. Instead, it lists the types of tests conducted and states that "Test results demonstrated that all acceptance criteria were met; therefore, the device conforms to established product specifications." This indicates a qualitative summary of successful performance against predefined criteria internally established by the manufacturer, rather than reportable numerical results for public review.

Here's a summary of the types of performance tests mentioned:

• Sensitization
• Acute Systemic Toxicity
• Intracutaneous Reactivity
• Material-Mediated Pyrogenicity | "The passing results demonstrate that the subject device meets the biological safety requirements per ISO 10993-1." |
  | Sterilization Validation | EtO sterilization to achieve a Sterility Assurance Level (SAL) of 10^-6 in accordance with ISO 11135:2014/Amd 1:2018 and AAMI TIR 28:2016. | "The Removal System is sterilized using EtO to achieve a sterility assurance level (SAL) of 10^-6 using a validated sterilization process..." |
  | Non-Clinical Performance Tests | - Packaging Inspection
• Leak Testing Syringe to Quick-Connect Adapter
• Vacuum Testing Syringe to Quick-Connect Adapter
• Air Leakage
• Simulated Pus Analog Removal
• Tensile Testing - Large Bore Syringe to Connector
• General, ISO 7886-1, Clause 6.1
• Limits for Acidity or Alkalinity, ISO 7886-1, Clause 6.2 & Annex A
• Limits for Extractable Metals, ISO 7886-1, Clause 6.3 & Annex A
• Lubricant, ISO 7886-1, Clause 7 (Paragraph 1)
• Tolerance on Graduated Capacity, ISO 7886-1, Clause 8
• Scale, ISO 7886-1, Clause 9.1
• Numbering of Scales, ISO 7886-1, Clause 9.2
• Overall Length of Scale, ISO 7886-1, Clause 9.3
• Position of Scale, ISO 7886-1, Clause 9.4
• Barrel Flanges, ISO 7886-1, Clause 10.2
• Design, ISO 7886-1, Clause 11.1
• Position of Nozzle on End of Barrel, ISO 7886-1, Clause 12.2
• Nozzle Lumen, ISO 7886-1, Clause 12.3
• Freedom from Liquid Leakage Past Plunger, guided by ISO 7886-1, Clause 13.2 & Annex D
• Freedom from Air Leakage Past Plunger, ISO 7886-1, Clause 13.2 & Annex B
• Force to Operate the Piston, ISO 7886-1, Clause 13.3 & Annex E
• Fit of Stopper/Plunger in Barrel, ISO 7886-1, Clause 13.4
• Particulate Matter | "Test results demonstrated that all acceptance criteria were met; therefore, the device conforms to established product specifications." |
  | Leveraged Performance Tests | - Pouch Seal Visual Inspection (from K191368 and K231848)
• Bubble Leak (from K231848)
• Dye Penetration (from K231848)
• Pouch Peel, Seal Strength (from K231108)
• Packaging Usability Evaluation for Aseptic Presentation (from K230494)
• Vacuum Testing Large Bore Syringe (from K191710)
• Simulated Use, Tensile Large Bore Syringe (from K191710) | "Test results demonstrated that all acceptance criteria were met; therefore, the device conforms to established product specifications." |

Regarding the other points:

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

• Sample Size: The document does not specify the exact sample sizes (number of syringes) used for each individual non-clinical performance test. This level of detail is typically found in the full test reports referenced by the submission, not the summary itself.
• Data Provenance: The tests are performance tests of a physical medical device. "Data provenance" as in geographic origin or retrospective/prospective data collection is not applicable here, as it pertains to clinical data or AI data sets. These are laboratory-based engineering tests.

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

• Not Applicable. This question relates to studies establishing "ground truth" for clinical diagnoses, typically in the context of AI or diagnostic imaging. For a physical device like a syringe, "ground truth" is established by engineering specifications, international standards (e.g., ISO 7886-1, ISO 10993-1, ISO 11135), and successful outcomes of validated test methods performed by qualified personnel in a laboratory setting. Experts would logically be engineers, material scientists, and sterilization specialists.

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 resolving discrepancies in expert interpretations of clinical data (e.g., in radiology studies). This is not relevant for physical device performance testing. The "adjudication" for these tests would involve ensuring that the test methods are followed correctly and that results are objectively measured against predefined acceptance 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. MRMC studies are specific to evaluating diagnostic performance, particularly with AI assistance in clinical imaging. This device is a manual piston syringe and does not involve AI or human "readers" in its primary function or evaluation for this submission. The document explicitly states: "Clinical testing was not required for the determination of substantial equivalence."

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

• Not Applicable. This question relates to AI algorithm performance. This device is a physical, non-AI medical device.

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

• Engineering Specifications and International Standards: The "ground truth" for this device's performance is whether it meets predefined engineering specifications (e.g., dimensions, materials, leak rates, force to operate) and complies with relevant international standards (e.g., ISO 7886-1 for sterile hypodermic syringes, ISO 10993 for biocompatibility, ISO 11135 for sterilization). The tests are designed to verify these physical and biological characteristics.

8. The sample size for the training set:

• Not Applicable. This question relates to AI model training. This device does not use AI.

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

• Not Applicable. This question relates to AI model training. This device does not use AI.

In summary: The provided FDA 510(k) summary is for a Class II manual medical device (piston syringe). The "acceptance criteria" and "study that proves the device meets the acceptance criteria" refer to a series of non-clinical, laboratory-based performance, biocompatibility, and sterilization validation tests conducted to demonstrate that the device meets established engineering specifications and international standards, thereby supporting its substantial equivalence to a predicate device. Clinical studies or AI-related evaluations were explicitly stated as "not required" for this submission.

Ask a specific question about this device

The VenaCore Thrombectomy Catheter is indicated for:
· The non-surgical removal of thrombi and emboli from blood vessels.
• Injection, infusion, and/or aspiration of contrast media and other fluids into or from blood vessels.
The VenaCore Thrombectomy Catheter is intended for use in the peripheral vasculature.

The VenaCore Thrombectomy Catheter is a single-use, sterile, over-the-wire catheter used for the minimally invasive treatment of thromboemboli in the peripheral vasculature. The VenaCore Thrombectomy Catheter is designed to remove thrombi and emboli in the peripheral vasculature. The VenaCore Thrombectomy Catheter consists of a distal laser-cut nitinol coring element, three coaxial catheter shafts (inner, middle, and outer), and a handle with a diameter control knob and a lever. The proximal handle controls the expansion and collapse of the coring element via the handle knob and lever. The outer shaft constrains the coring element prior to deployment. To aid in fluoroscopic visualization, the distal tip is radiopaque, and a radiopaque tip is located on the outer catheter to identify the distal end of the outer catheter.

This looks like a 510(k) submission for a medical device called the "VenaCore Thrombectomy Catheter." The provided text describes the device, its intended use, and a comparison to a predicate device. It also details the non-clinical testing performed to demonstrate substantial equivalence.

Here's an analysis of the acceptance criteria and the study information based only on your provided text:

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

The document states, "Test results demonstrated that all acceptance criteria were met; therefore, the device conforms to established product specifications." However, the specific quantitative acceptance criteria for each test and the corresponding reported device performance values are not provided in the text. The document lists the types of tests performed but not the pass/fail thresholds or the numerical results.

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 lists "Non-Clinical Testing" which means these were laboratory or bench tests, not tests on human subjects. Therefore, terms like "test set," "data provenance," "country of origin," and "retrospective or prospective" are not applicable in their usual clinical sense. The specific sample sizes for each non-clinical test (e.g., how many catheters were tested for tensile strength) are not detailed.

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 question is not applicable. The testing described is non-clinical (bench testing), not a clinical study involving expert assessment of patient data.

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

This question is not applicable. Adjudication methods are typically used in clinical studies where multiple human readers assess data and discrepancies need to be resolved. This document describes non-clinical engineering and material property 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 comparative effectiveness study was done. The document explicitly states: "Clinical testing was not required for the determination of substantial equivalence." Furthermore, this is a thrombectomy catheter, not an AI-powered diagnostic device, so the concept of AI assistance for human readers is irrelevant.

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

This question is not applicable. The device is a mechanical thrombectomy catheter, not a software algorithm.

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

For the non-clinical tests, the "ground truth" would be established engineering specifications, material standards (e.g., ISO standards), and physical measurements. For example, for "Tensile Testing," the ground truth would be defined by a maximum allowable force before breakage according to the design specification. The specific standards or target values are not explicitly given in the text.

8. The sample size for the training set

This question is not applicable. The device does not involve machine learning or AI models that require a training set.

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

This question is not applicable for the same reason as point 8.

Ask a specific question about this device

The ClotTriever Thrombectomy System is indicated for:
• The non-surgical removal of thrombi and emboli from blood vessels.
• Injection, infusion, and/or aspiration of contrast media and other fluids into or from a blood vessel.
The ClotTriever Thrombectomy System is intended for use in the peripheral vasculature including deep vein thrombosis (DVT).
The ClotTriever Sheaths are indicated for use as a conduit for the insertion of endovascular devices into the vasculature while minimizing blood loss associated with such insertions.

The ClotTriever Thrombectomy System ("ClotTriever System") is a single-use over-the-wire catheter-based system used for the minimally invasive treatment of thromboemboli in the peripheral vasculature. The system consists of ClotTriever Catheters, ClotTriever Sheaths and Protrieve Sheath, each packaged separately. The ClotTriever Sheath consist of a polymeric shaft with a distal self-expanding nitinol mesh funnel, a proximal hub with a hemostasis valve and a sideport tubing. The mesh funnel is deployed by retracting the slide actuator back until it snaps into place. The mesh funnel self-expands to the diameter of the vessel and serves as a backstop as clot is removed through the lumen of the sheath. A hemostasis valve is integrated into the proximal hub of the sheath to prevent blood loss from devices passing through it. The sideport tubing has a large-bore stopcock and a terminal quick-disconnect coupling for connection to the Large Bore 60 cc Syringe for the aspiration of clot. A pre-dilator is provided with the ClotTriever Sheaths, to expand the target vessel prior to sheath insertion. A dilator is provided to aid insertion and positioning of the sheath, while the loading tool facilitates insertion of the mesh funnel into the dilator.

Here's an analysis of the provided FDA 510(k) summary regarding the ClotTriever Sheath, focusing on "acceptance criteria" and "study that proves the device meets the acceptance criteria."

Important Note: The provided document is a 510(k) clearance letter and summary for a medical device (ClotTriever Sheath). It is not a typical AI/Software as a Medical Device (SaMD) submission that would involve performance metrics like sensitivity, specificity, AUC, or a comparative effectiveness study with human readers assisting AI. Therefore, most of the requested information (sample size for test set, expert qualifications, MRMC study, standalone performance, training set details) will either be explicitly stated as "not applicable" or inferred from the nature of the device submission.

The "device" in this context is a physical medical device (catheter sheath), not an AI algorithm. The "acceptance criteria" and "performance" relate to its physical and functional characteristics, and its "study" refers to non-clinical (bench) testing, not clinical trials with human readers or AI algorithms.

Acceptance Criteria and Device Performance for ClotTriever Sheath

The acceptance criteria for the ClotTriever Sheath, as described in this 510(k) submission, are primarily centered around demonstrating substantial equivalence to a predicate device (Protrieve Sheath) through non-clinical performance characteristics, and the safety and effectiveness of the device for its indicated uses.

1. Table of Acceptance Criteria and Reported Device Performance

Since this is a physical device and not an AI algorithm, the "acceptance criteria" are typically defined by engineering specifications, material properties, and functional performance benchmarks to ensure safety and effectiveness for its intended use. The "reported device performance" is demonstrated through verification testing.

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

• Sample Size: Not applicable. For a physical device like a sheath, the "test set" would typically refer to the number of devices or components tested during non-clinical verification. This number is not specified in the provided summary, as it's typically found in detailed test reports, not the 510(k) summary itself. The summary only refers to "Verification testing provided in K180329 and K192036."
• Data Provenance: Not applicable in the context of human data. The testing mentioned in the previous 510(k)s (K180329 and K192036) would be non-clinical (bench and potentially animal) testing.

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

• Not applicable. This submission is for a physical medical device, not an AI/SaMD. "Ground truth" in this context refers to engineering specifications and performance benchmarks, not expert annotations of medical images or data.

4. Adjudication Method for the Test Set

• Not applicable. This relates to expert review for AI/SaMD and is not relevant for this physical device submission.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, and the effect size (e.g., human readers improve with AI vs without AI assistance)

• No, not applicable. This is a physical device, not an AI-assisted diagnostic tool.

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

• No, not applicable. This is a physical device, not a standalone algorithm.

7. The Type of Ground Truth Used

• Engineering specifications and documented performance characteristics. For medical devices, the "ground truth" for non-clinical testing refers to established engineering standards, material properties, functional requirements, and safety benchmarks (e.g., burst pressure, tensile strength, flow rates, biocompatibility results), along with performance observed in simulated-use environments (e.g., flow models). The comparison to the predicate device also establishes a "ground truth" of already cleared and accepted performance.

8. The Sample Size for the Training Set

• Not applicable. There is no "training set" as this is not an AI/Machine Learning device.

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

• Not applicable. There is no "training set" as this is not an AI/Machine Learning device.

In summary, this 510(k) pertains to a non-active, physical medical device (catheter sheath). The "acceptance criteria" and "proof" primarily stem from demonstrating substantial equivalence to a legally marketed predicate device (Protrieve Sheath) based on shared intended use, similar technological characteristics, and prior non-clinical verification testing, without raising new questions of safety or effectiveness. The questions about AI-specific validation metrics are not applicable here.

Ask a specific question about this device

The Intri24 Introducer Sheath is indicated to provide a conduit for the insertion of endovascular devices into the vasculature while minimizing blood loss associated with such insertions.

The Intri24 Introducer Sheath is a single-use over-the-wire system intended for use in vessels > 9 mm and is a conduit for the insertion of diagnostic or endovascular devices into the peripheral vasculature. The Intri24 Introducer Sheath consists of a Sheath and Dilator. The Sheath is comprised of a single lumen catheter with a hydrophilic coating, a proximal hemostasis valve, and stopcock with flush port. A radiopaque marker is positioned near the distal tip of the sheath to aid with fluoroscopic visualization. The Dilator is 0.035" guidewire compatible and attaches to the hemostasis valve on the Sheath. The Dilator has a tapered edge to aid in the dilation of the target vessel for insertion and positioning of the Sheath.

The provided text describes a medical device, the Intri24 Introducer Sheath, and its regulatory clearance. However, it does not include information about acceptance criteria or a study that proves the device meets those criteria in the context of AI/ML performance.

The document is a 510(k) premarket notification summary, which focuses on demonstrating substantial equivalence to a legally marketed predicate device. The tests described are primarily related to mechanical performance, biocompatibility, and sterilization of a physical medical device, not the performance of an AI algorithm or model.

Therefore, I cannot provide the information requested in your prompt based on the given text.

Specifically:

1. Table of acceptance criteria and reported device performance: This information is not present for AI/ML performance. The document lists non-clinical performance tests for the physical introducer sheath (e.g., visual inspection, dimensional inspection, tensile testing, fluid leak tests), but these are not related to an AI/ML device's performance.
2. Sample size for test set and data provenance: Not applicable, as there's no AI/ML test set discussed.
3. Number of experts used to establish ground truth and qualifications: Not applicable.
4. Adjudication method: Not applicable.
5. Multi-reader multi-case (MRMC) comparative effectiveness study: Not applicable.
6. Standalone (algorithm-only) performance: Not applicable.
7. Type of ground truth used: Not applicable.
8. Sample size for training set: Not applicable.
9. How ground truth for training set was established: Not applicable.

The document discusses "design verification testing" and lists various mechanical and functional tests for the introducer sheath, but these are for a traditional hardware device, not an AI/ML-powered one.

Ask a specific question about this device

The Talon Transseptal Sheath is used for the percutaneous introduction of various types of cardiovascular catheters and guidewires to all heart chambers, including the left atrium via transseptal perforation/puncture.

The Talon Transseptal Sheath (“Sheath”) provides a conduit for catheterization and angiography of specific heart chambers and locations. It consists of a single lumen catheter with a proximal hemostasis valve and stopcock with flush port. A radiopaque marker is positioned near the distal tip to aid with fluoroscopic visualization. The Sheath is packaged with a dilator and two 60 cc syringes. The dilator is compatible with a 0.035" guidewire and has a tapered tip which aids insertion and positioning of the Sheath. The dilator attaches to the Sheath hemostasis valve, and a Y-connector with hemostasis valve connects to the dilator luer connector. A quick-release syringe is provided to connect to the Sheath sideport, and a standard VacLok syringe is provided to connect to the Sheath flush port and dilator connector.

The provided text describes the regulatory clearance for the Talon Transseptal Sheath. It focuses on demonstrating substantial equivalence to a predicate device rather than presenting a study with acceptance criteria and device performance in the context of an AI/human reader study.

Therefore, many of the requested categories (e.g., sample size for test set, number of experts for ground truth, adjudication method, MRMC study, effect size, standalone performance, training set details) are not applicable or not provided in this document, as they relate to the evaluation of AI-driven diagnostic devices, which the Talon Transseptal Sheath is not.

Here's the information that can be extracted from the provided text, primarily focusing on the non-clinical testing section, which serves as the "study" for this device's regulatory submission:

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

The document states that "Test results demonstrated that all acceptance criteria were met," but it does not provide specific numerical acceptance criteria or reported device performance metrics for each test. It simply lists the types of tests performed.

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

• Sample Size: Not specified for any of the non-clinical tests.
• Data Provenance: Not applicable in the context of device performance testing. These are laboratory/bench tests, not studies involving human data.

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

• Not Applicable. This device is not an AI diagnostic device that relies on expert interpretation to establish ground truth for a test set. Its performance is evaluated through engineering and biological testing.

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

• Not Applicable. See explanation above.

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. An MRMC study was not done as this is a medical device (transseptal sheath), not an AI-driven diagnostic or imaging aid.

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

• Not Applicable. This is not an algorithm or AI device. Its "standalone" performance is measured by its physical and biological properties.

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

• For Biocompatibility: Standards (ISO 10993-1) and validated laboratory test methodologies.
• For Sterilization: Standards (ISO 11135:2014/Amd 1:2018, AAMI TIR 28:2016) and validated sterilization processes.
• For Performance Tests: Established product specifications, engineering standards, and functional requirements, identified through a Design Failure Modes and Effects Analysis. The "ground truth" is adherence to these predefined criteria.

8. The sample size for the training set

• Not Applicable. This device does not use a training set as it is not an AI/machine learning product.

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

• Not Applicable. See explanation above.

Ask a specific question about this device

The Triever20 Curve (21-201) is used coaxially within the Triever24 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 Triever20 Curve (21-201) is intended for use in the peripheral vasculature and for the treatment of pulmonary embolism.
The Triever20 Curve (21-201) Catheter is not indicated for use with FlowTriever Catheters.
Triever20 Curve (21-201) is also intended for use in treating clot in transit in the right atrium, but not in conjunction with FlowTriever Catheters.
The Triever20 Curve (21-201) must be used within the Triever24.

Triever20 Curve, Model 21-201 is a single-use over-the-wire catheter used for the minimally invasive treatment of thromboemboli in the peripheral vasculature and the treatment of pulmonary embolism. A Dilator is provided with the Triever20 Curve Catheter to assist in its advancement over a preplaced 0.035" guidewire to the proximal end of the obstruction (thrombus). The Triever24 Catheter is inserted through an introducer sheath (not provided). After Triever24 Catheter placement, the Dilator is removed. The Triever20 Curve Catheter is then inserted through the Triever24 Catheter and advanced to the thrombus. Thrombus is removed by aspiration with the provided 60 cc Large Bore Syringe.

The provided text is a 510(k) summary for the Triever20 Curve (21-201) device, which is an embolectomy catheter. The document focuses on demonstrating substantial equivalence to a predicate device (Inari FlowTriever Retrieval/Aspiration System K213402) and a reference device (Inari Medical, Triever20 Curve K203333), highlighting physical and material modifications.

The vast majority of the "study" described in this document is non-clinical bench testing to verify the device's physical and functional properties. It is not an AI/ML-based device, so the sections on ground truth, MRMC studies, training/test sets, and expert adjudication are not applicable here.

Here's an analysis based on the available information:

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

The document doesn't provide a typical "acceptance criteria vs. performance" table in the context of clinical outcomes or AI model performance. Instead, it lists numerous non-clinical tests and states that "Test results demonstrated that all acceptance criteria were met; the device conforms to established product specifications."

Here are examples of the non-clinical tests mentioned, and what their acceptance criteria would generally imply:

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

• Sample Size: Not explicitly stated for each test, but it would be physical samples of the device and its components. For bench testing, sample sizes are typically determined by statistical methods or industry standards.
• Data Provenance: The study described is non-clinical (bench testing). There is no patient data involved, therefore no country of origin or retrospective/prospective distinction.

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

This information is not applicable as this is a non-clinical device that does not use AI/ML. The "ground truth" for the tests would be based on engineering specifications, physical measurements, and functional benchmarks. No human experts are establishing "ground truth" in the clinical imaging interpretation sense.

4. Adjudication method for the test set:

Not applicable as this is a non-clinical device. Bench test results are typically recorded and verified by engineers according to test protocols.

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), not an AI/ML diagnostic tool. Therefore, MRMC studies are not relevant.

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

Not applicable. This is a physical medical device.

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

The "ground truth" (or more accurately, the reference standard) for this device's performance is based on engineering specifications, physical measurements, and functional performance benchmarks established through design validation testing. For example, a "clot burden removal validation" test would use a standardized clot model and measure the amount of clot removed, with the "ground truth" being the pre-defined effectiveness threshold.

8. The sample size for the training set:

Not applicable. There is no AI/ML component, so no "training set."

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

Not applicable. There is no AI/ML component.

Ask a specific question about this device