Search Results

The Catapult Guide Sheath is indicated to be used for introduction of interventional and diagnostic devices into the peripheral (and coronary) vasculature.

The COMPASS Guiding Introducer Sheath is indicated to be used for introduction of interventional and diagnostic devices into the peripheral (and coronary) vasculature. The device is also intended to be used within a pediatric population.

The Fortress Introducer Sheath System is intended to provide access and to facilitate percutaneous introduction of guide wres, catheters and other devices into the femoral, popliteal and infrapopliteal arteries while maintaining haemostasis during diagnostic and interventional procedures.

The Introducer Sheath System devices consist of a coil reinforced introducer sheath with hemostasis valve and side port, as well as a dilator with a tapered tip and luer lock at the proximal end. The main introducer sheath tubing is connected at the proximal end to a hemostasis valve with side port tubing that is connected to a plastic color coded 3-way stopcock valve. The side port is used for flushing the introducer sheath. The sheath is introduced into the vascular system with the aid of the dilator. The hemostasis valve at the proximal end of the introducer sheath conforms and seals around guide wires and catheters to reduce blood leakage from the introducer sheath. A radiopaque marker helps identify the distal end of the introducer sheath. The introducer sheath has a lubricious hydrophilic coating on the outer surface in length of 20cm on the distal portion.

The System consists of the following components:

• A One Introducer Sheath with hemostasis valve
• A One or two dilator(s)

The provided text describes a 510(k) premarket notification for a medical device called the Catapult Guide Sheath / Introducer Sheath System. It details the device, its intended use, comparison to a predicate device, and the performance testing conducted to demonstrate substantial equivalence.

However, the questions you've asked are typical for the evaluation of AI/ML-driven medical devices, especially related to diagnostic or classification tasks (e.g., image analysis for disease detection). The device described in the document (Catapult Guide Sheath) is a physical medical device (an introducer sheath system) used for physical introduction of interventional and diagnostic devices into the vasculature, not an AI/ML software device.

Therefore, the provided document does not contain the information requested in your prompt regarding acceptance criteria and study proving device meets acceptance criteria for an AI/ML device. Many of the questions (e.g., sample size for test set, number of experts for ground truth, MRMC study, standalone performance, training set details) are irrelevant to the type of device being reviewed in this FDA submission.

Here's why and what information is available:

• Type of Device: The Catapult Guide Sheath is a Class II physical medical device (introducer catheter). It's a tool, not a diagnostic or AI algorithm.
• Purpose of Submission (510(k)): This submission is to demonstrate "substantial equivalence" to a legally marketed predicate device (Catapult Guide Sheath Introducer Sheath System, K240957). This is a common pathway for physical devices with modifications or new physical devices that are very similar to existing ones. The core of the substantial equivalence argument relies on demonstrating that the new device performs similarly to the predicate device, especially after a material change (insourced HVA).
• "Acceptance Criteria" for this device: For this type of device, "acceptance criteria" are related to mechanical performance, biocompatibility, sterilization, and shelf-life, ensuring the device functions as intended and is safe. These are detailed in Table 2, listing the tests performed and the applicable standards.
• "Study that proves the device meets the acceptance criteria": The document lists a series of non-clinical (laboratory) tests that were performed. These tests are the "study" demonstrating the device meets the performance requirements for substantial equivalence.

Therefore, I cannot fill out the detailed table and answer the specific questions about AI/ML device evaluation based on the provided text. The text focuses on the mechanical, material, and safety performance of a physical device, not the diagnostic or predictive performance of an AI algorithm.

If your intention was to ask about the evaluation of a physical medical device, I can re-frame the answer based on the provided document.

Assuming you are asking for information relevant to the physical medical device described, here's an attempt to interpret your questions in that context, recognizing that most are geared towards AI/ML:

Device: Catapult Guide Sheath / Introducer Sheath System

1. Acceptance Criteria and Reported Device Performance

For this physical device, "acceptance criteria" relate to meeting specifications derived from regulatory standards and predicate device performance. The "reported device performance" are the results of the listed tests that demonstrated compliance.

2. Sample Size for the Test Set and Data Provenance

For a physical device, "test set" refers to the number of units tested. The specific sample sizes for each mechanical test are not detailed in this summary (they would be in the full submission). The data provenance is from non-clinical (laboratory) testing conducted by the manufacturer and external laboratories. It is not patient data, so "country of origin of the data," "retrospective or prospective" do not apply.

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

This question is not applicable. "Ground truth" in the context of AI/ML diagnostic devices refers to a definitive diagnosis or finding. For a physical device, the "ground truth" is established by the specifications and performance requirements derived from engineering principles and relevant ISO standards. No human experts are used to "establish ground truth" in this context; instead, engineers and technicians conduct specified physical and chemical tests.

4. Adjudication Method for the Test Set

Not applicable. There's no "adjudication" (e.g., consensus among readers) needed for a physical device's performance testing. Test results are quantitative measurements against defined criteria.

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

Not applicable. MRMC studies are for evaluating human reader performance, typically with and without AI assistance, for diagnostic tasks. This device is not an AI diagnostic tool.

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

Not applicable. This is a physical device, not an algorithm. Its "standalone performance" refers to its mechanical and material properties as tested in the lab.

7. The Type of Ground Truth Used

For this physical device, the "ground truth" for performance is defined by:

• International standards (ISO, AAMI, ASTM, EN): These standards define acceptable limits and testing methodologies for medical device properties (e.g., leakage, tensile strength, biocompatibility, sterility).
• Predicate device performance: The previously cleared predicate device provides a benchmark for expected performance characteristics of the new device.
• Manufacturer's internal design specifications and risk analysis: Derived from the intended use and safety considerations.

8. The Sample Size for the Training Set

Not applicable. This device does not involve a "training set" as it's not an AI/ML algorithm.

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

Not applicable. There is no "training set" or "ground truth" for training in the AI/ML sense for this device.

Ask a specific question about this device

The Catapult TM Guide Sheath is indicated to be used for introduction of interventional and diagnostic devices into the peripheral (and coronary) vasculature.

The Catapult ™ Guide Sheath consists of a coil reinforced introducer sheath with hemostasis valve and side port, as well as a dilator with a tapered tip and luer lock at the proximal end. The main introducer sheath tubing is connected at the proximal end to a hemostasis valve with side port tubing that is connected to a plastic color coded 3-way stopcock valve. The side port is used for flushing the introducer sheath. The sheath is introduced into the vascular system with the aid of the dilator. The hemostasis valve at the proximal end of the introducer sheath conforms and seals around guide wires and catheters to reduce blood leakage from the introducer sheath. A radiopaque marker helps identify the distal end of the introducer sheath. The introducer sheath has a lubricious hydrophilic coating on the outer surface of its distal 20cm.

The Catapult ™ Guide Sheath was previously cleared under K221914 in 4 French, 5 French, 7 French and 8 French sizes, each with effective lengths of 15 cm, 60 cm or 90 cm. This 510(k) adds a 130 cm length which is available in 4 French, 5 French and 6 French sizes.

The provided text does not contain information about the acceptance criteria and study proving a device meets them in the context of an AI/ML-driven device. Instead, it describes characteristics and performance tests for a conventional medical device, the "Catapult Guide Sheath," for which a 510(k) premarket notification was submitted.

The request asks for specific details related to AI/ML device studies (e.g., sample size for test set and training set, ground truth establishers, MRMC studies, standalone performance), which are not applicable to the non-AI device described in the document.

Therefore, I cannot fulfill the request as it pertains to an AI/ML device. The provided text details the 510(k) submission for a medical device that is not an AI/ML device.

Ask a specific question about this device

The Catapult Guide Sheath is indicated to be used for introduction of interventional and diagnostic devices into the peripheral (and coronary) vasculature.

The Catapult Guide Sheath consists of a coil reinforced introducer sheath with hemostasis valve and side port, as well as a dilator with a tapered tip and luer lock at the proximal end. The main introducer sheath tubing is connected at the proximal end to a hemostasis valve with side port tubing that is connected to a plastic color coded 3-way stopcock valve. The side port is used for flushing the introducer sheath. The introducer sheath is introduced into the vascular system with the aid of the dilator. The hemostasis valve at the proximal end of the introducer sheath conforms and seals around guide wires and catheters to reduce blood leakage from the introducer sheath. A radiopaque marker helps identify the distal end of the introducer sheath. The introducer sheath has a lubricious hydrophilic coating on the outer surface up to 20cm on the distal portion.

The System consists of the following components:

• A One Introducer Sheath) with hemostasis valve
• A One dilator or
• A Two dilators for 15 cm version

The shaft and hemostasis valve are pre-assembled and packaged together with a dilator. Each shaft and each dilator are placed in a separate protection tube, the protection tubes are fixated onto a packaging pad. Products are sealed inside a medical grade Tyvek pouch on which a product label is placed. Devices are packaged in labeled packers containing five units and one Instruction for Use (IFU) booklet.

The Catapult Guide Sheath is a sterile, disposable device. It is a prescription medical device that is used only in healthcare facilities or hospitals. The device is suitable for placement in patients for up to 24 hours.

Devices are sterilized using ethylene oxide. Maximum levels of remaining tested sterilant residuals meet requirement limits EO

The provided document is a 510(k) summary for the Catapult Guide Sheath, a medical device. It describes the device, its intended use, comparison to a predicate device, and performance data. However, the document does not contain any information about an AI/ML-based device.

Therefore, I cannot provide an answer to your request regarding acceptance criteria and a study that proves an AI/ML device meets them, as the provided text pertains to a traditional medical device (Catheter Introducer).

If you can provide a document that describes the acceptance criteria and study for an AI/ML medical device, I would be happy to assist you.

Ask a specific question about this device

The Fortress Introducer Sheath System is intended to provide access and to facilitate percutaneous introduction of guide wires, catheters and other devices into the femoral, popliteal arteries while maintaining hemostasis during diagnostic and interventional procedures.

The Fortress Introducer Sheath System consists of an introducer sheath with hemostasis valve and side port, as well as a dilator with a tapered tip and luer lock at the proximal end. The main introducer sheath tubing is connected at the proximal end to a hemostasis valve with side port tubing that is connected to a plastic color coded 3-way stopcock valve. The side port is used for flushing the introducer sheath. The introducer sheath is introduced into the vascular system with the aid of the dilator. The hemostasis valve at the proximal end of the introducer sheath conforms and seals around guide wires and catheters to reduce blood leakage from the introducer sheath. A radiopaque marker helps identify the distal end of the introducer sheath. The introducer sheath has a hydrophobic silicone coating on the outer surface of the distal 30cm portion.

The provided text describes the regulatory clearance for the Fortress Introducer Sheath System (7F and 8F sizes) and does not contain information about an AI/ML powered medical device. Therefore, a table of acceptance criteria and reported device performance related to AI/ML capabilities, or details about a study evaluating such a device, cannot be extracted from this document.

The document discusses the substantial equivalence of the Fortress Introducer Sheath System (7F and 8F) to a predicate device (6F Fortress Introducer Sheath System, K153197). The performance data presented are for non-clinical tests related to the mechanical properties, biocompatibility, sterilization, and shelf-life of the physical device.

Here's an analysis of what can be extracted from the document, recognizing that it doesn't pertain to an AI/ML device:

1. Table of Acceptance Criteria and Reported Device Performance (as non-AI/ML)

Since this is a non-AI/ML device, "acceptance criteria" here refers to specific tests and relevant standards the device must meet. The "reported device performance" is that the device met these criteria, demonstrating substantial equivalence to the predicate.

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

• Test Set Sample Size: Not explicitly stated for each test, but it is implied that sufficient samples were tested to meet the requirements of the standards listed. These are physical device tests, not data-driven AI/ML tests.
• Data Provenance: The tests are non-clinical (laboratory-based) and conducted to international and internal standards. Provenance is therefore the testing conducted by the manufacturer and/or external laboratories. The country of origin for the device manufacturer is Germany.

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 the document describes physical device testing, not an AI/ML product requiring expert ground truth for image or data analysis. Usability evaluation (IEC 62366-1:2015) would involve human users, but the number and qualifications of those users are not specified, nor are they "experts establishing ground truth" in the AI/ML sense.

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

• This is not applicable as the document describes physical device testing. The results are determined by compliance with specified test methods and acceptance criteria rather than expert 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:

• This is not applicable as the device is a physical medical introducer sheath system, not an AI/ML product intended to assist human readers.

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

• This is not applicable as the device is a physical medical introducer sheath system, not an AI/ML algorithm.

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

• This is not applicable as the document describes physical device testing. The "ground truth" or reference for evaluating performance against is defined by the technical specifications outlined in the referenced international standards and internal requirements.

8. The sample size for the training set:

• This is not applicable as the device is a physical medical introducer sheath system and does not involve AI/ML requiring a training set.

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

• This is not applicable as the device is a physical medical introducer sheath system and does not involve AI/ML requiring a training set.

Ask a specific question about this device

The DuraSheath Introducer Sheath System is indicated to be used for introduction of interventional and diagnostic devices into the peripheral (and coronary) vasculature. The device is also intended to be used within a pediatric population.

The DuraSheath Introducer Sheath System is a sterile, disposable device consisting of (a) a coil reinforced shaft with an atraumatic tip at the distal end; (b) a hemostasis valve with a side port and color coded 3-way stopcock; and (c) a tapered tip dilator with snap-fit hub at the proximal end.

The provided text describes a 510(k) premarket notification for a medical device called the DuraSheath Introducer Sheath System. It details the device's design, materials, indications for use, and a comparison to predicate devices, along with non-clinical performance data.

However, the document does not contain acceptance criteria or study details in the format requested, which typically relates to performance metrics for AI/ML devices or clinical endpoints for studies proving substantial equivalence. Instead, it lists various engineering and biological tests conducted to demonstrate the safety and effectiveness of the device as a whole, rather than specific performance metrics against pre-defined acceptance thresholds for an AI algorithm.

The document mainly focuses on proving the new device is substantially equivalent to existing, legally marketed devices. It details a comprehensive set of non-clinical tests (mechanical, biocompatibility, sterilization, accelerated aging, packaging integrity, simulated use, and usability) to demonstrate this equivalence and the device's safety and effectiveness.

Given the nature of the device (an introducer sheath system, which is a physical medical device, not an AI/ML algorithm or a diagnostic tool with specific performance metrics like sensitivity/specificity), the requested information regarding "acceptance criteria and the study that proves the device meets the acceptance criteria" in terms of AI performance, expert ground truth, adjudication methods, MRMC studies, and standalone algorithm performance is not applicable.

Therefore, I cannot populate the table and answer the specific questions (2-9) about acceptance criteria, test set sample size, expert qualifications, adjudication, MRMC studies, standalone performance, ground truth types, and training set details because this information is not present in the provided FDA document, as it pertains to a mechanical medical device, not an AI/ML diagnostic or therapeutic device.

The closest information to "acceptance criteria" is the list of standards the device testing conformed to, indicating that meeting these standards served as the "acceptance criteria" for demonstrating safety and effectiveness of a physical medical device. The "study that proves the device meets the acceptance criteria" is the collection of all the non-clinical tests listed in the "PERFORMANCE DATA" section.

Here's what can be extracted from the provided text, recognizing the constraints:

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

2. Sample size used for the test set and the data provenance: Not applicable in the context of an AI/ML device. For the mechanical device, the number of units tested for each specific non-clinical test (e.g., how many sheaths were subjected to pull-out testing) is not explicitly stated, although it is implied that sufficient units were tested to meet the requirements of the listed standards. There was feedback from 16 clinical cases in Germany, but this was for European CE certification and not a formal clinical trial for this 510(k).

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 the AI/ML context, does not apply to this mechanical device.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable.

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.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc): Not applicable. The "ground truth" for this physical device is successful performance according to engineering and biocompatibility standards.

8. The sample size for the training set: Not applicable.

9. How the ground truth for the training set was established: Not applicable.

Ask a specific question about this device

The Fortress Introducer Sheath System is intended to provide access and to facilitate percutaneous introduction of guide wires, catheters and other devices into the femoral, popliteal arteries while maintaining hemostasis during diagnostic and interventional procedures.

The Fortress Introducer Sheath System is a sterile, disposable device. It is a prescription medical device that is used only in healthcare facilities or hospitals. The device is placed in patients for up to 24 hours.

The Fortress Introducer Sheath System consists of an introducer sheath with hemostasis valve and side port, as well as a dilator with a tapered tip and luer lock at the proximal end. The main introducer sheath tubing is connected at the proximal end to a hemostasis valve with side port tubing that is connected to a plastic 3-way stopcock valve. The side port is used for flushing the introducer sheath. The introducer sheath is introduced into the vascular system with the aid of the dilator. The hemostasis valve at the proximal end of the introducer sheath conforms and seals around guide wires and catheters to reduce blood leakage from the introducer sheath. A radiopaque marker helps identify the distal end of the introducer sheath. The introducer sheath (5F and 6F sizes) has a hydrophobic silicone coating on the outer surface of the distal 30cm portion.

The System consists of the following components:

• A One Introducer Sheath with hemostasis valve
• A Two dilators: 5F and 6F 100cm version
• A One dilator: 5F and 6F 45cm version

This document is a 510(k) Premarket Notification from the FDA regarding the Fortress Introducer Sheath System. It details the device's indications for use, comparison to a predicate device, and the testing performed to demonstrate substantial equivalence.

Here's the breakdown of the acceptance criteria and study information provided:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for each test are implicitly stated as "Passed," indicating that the device met the pre-defined requirements for each test. The actual numerical or descriptive criteria for "passing" are not explicitly listed in this summary, but the "Test Result" column confirms that all tests were successfully completed according to their respective acceptance criteria.

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

The document does not explicitly state the sample sizes used for each of the tests. The tests performed are primarily performance and safety tests on the device itself (e.g., mechanical testing, material compatibility, sterilization), not clinical studies with human subjects. Therefore, typical data provenance details like "country of origin" or "retrospective/prospective" are not applicable in the way they would be for a clinical trial. The testing appears to be laboratory-based verification and validation.

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

Not applicable. The tests performed are laboratory-based engineering and biological compatibility tests, not evaluations requiring expert consensus on clinical imagery or patient data. The "ground truth" for these tests would be established by the industry standards and methodologies followed (e.g., ISO standards, ASTM standards, FDA guidance documents) by qualified laboratory personnel.

4. Adjudication Method for the Test Set

Not applicable. The tests are objective measurements and evaluations against pre-defined engineering and safety specifications, not subjective assessments requiring adjudication among multiple observers.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, and effect size

No, an MRMC comparative effectiveness study was not done. The document focuses on demonstrating substantial equivalence through non-clinical performance and safety testing. The device is an introducer sheath system, which is a physical medical device, not an AI software or imaging diagnostic tool that would typically undergo MRMC studies.

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

Not applicable. The Fortress Introducer Sheath System is a physical medical device, not an algorithm or AI software. Therefore, the concept of "standalone algorithm performance" (without human-in-the-loop) does not apply.

7. The Type of Ground Truth Used

The ground truth used for these tests is based on established engineering principles, material science, biological compatibility standards, and regulatory guidance documents. For instance:

• Mechanical tests: "Ground truth" is defined by the device's design specifications and performance limits (e.g., strength, kink resistance, insertion force) derived from engineering analysis and comparison to predicate devices, verified through physical measurements.
• Biological tests (Cytotoxicity, LAL, Sterilization): "Ground truth" is defined by accepted biological safety standards and validated testing protocols to ensure the device is non-toxic, non-pyrogenic, and sterile.
• Visibility under X-ray: "Ground truth" is the device's observable radiopacity under X-ray imaging.

8. The Sample Size for the Training Set

Not applicable. This device is a physical medical instrument, not an AI or machine learning model. Therefore, there is no "training set" in the context of data-driven model development.

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

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

Ask a specific question about this device

The DuraSheath Introducer Sheath System is indicated to be used for introduction of interventional and diagnostic devices into the human vasculature, including but not limited to femoral access via a contralateral approach to access the popliteal and infrapopliteal arteries.

The DuraSheath Introducer Sheath System is a sterile, disposable device consisting of (a) a coil reinforced shaft with an atraumatic tip at the distal end; (b) a hemostasis valve with a side port and color coded 3-way stopcock; and (c) a tapered tip dilator with snap-fit hub at the proximal end. The distal end of the sheath contains a radiopaque marker. Lubricous coating is applied to the distal end of the sheath. The system is packaged inside a sealed Tyvek pouch.

The DuraSheath Introducer Sheath System is a prescription medical device that is used only in healthcare facilities or hospitals. The device is placed in patients for up to 24 hours.

This document is a 510(k) Premarket Notification from the FDA regarding the DuraSheath Introducer Sheath System. It details the device's indications for use, comparison to predicate devices, and performance data provided for substantial equivalence, but it does not contain the acceptance criteria or a study proving the device meets specific acceptance criteria in the manner you've requested for AI/diagnostic devices.

Instead, this document focuses on demonstrating that the DuraSheath Introducer Sheath System is "substantially equivalent" to legally marketed predicate devices, meaning it performs similarly and raises no new questions of safety or effectiveness. The performance data provided is primarily non-clinical and related to the physical and material properties of the device, rather than diagnostic accuracy or clinical outcomes as would be seen in studies for AI-powered diagnostic tools.

Therefore, many of your requested points cannot be answered based on the provided text.

Here's how the available information relates to your request:

1. Table of acceptance criteria and the reported device performance

N/A. The document does not provide a table of explicit acceptance criteria with numerical targets for clinical performance (e.g., sensitivity, specificity, AUC) or the device's measured performance against those criteria. Instead, it refers to "non-clinical tests" and "performance data" to demonstrate substantial equivalence to predicate devices in terms of safety and effectiveness, rather than meeting specific quantifiable performance benchmarks.

The "performance data" mentioned falls into these categories:

• Mechanical testing: Including tests required under relevant international standards, coating adhesion, particulate testing, and transportation integrity testing. Reported Performance: Performed to verify and validate the design and to demonstrate process capability, with results demonstrating comparable performance to predicates.
• Biocompatibility testing: Full range of tests. Reported Performance: Demonstrated biocompatibility.
• Sterilization Validation Adoption: To confirm sterility of the device upon exposure to the selected sterilization cycle. Reported Performance: Confirmed sterility.
• Accelerated age testing: To confirm product performance and end of shelf life. Reported Performance: Confirmed product performance and end of shelf life.

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

N/A. The document describes non-clinical engineering and material tests, not tests on patient data sets. Therefore, there is no "test set" in the context of clinical data, sample size, or data provenance (country of origin, retrospective/prospective). These tests are typically conducted in a laboratory setting on manufactured device samples.

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

N/A. Since this isn't a diagnostic device and there's no clinical "test set" involving patient data, there's no ground truth established by medical experts in the way that would apply to, for example, an AI image analysis tool.

4. Adjudication method for the test set

N/A. As there is no clinical test set requiring expert adjudication, this is not applicable.

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

N/A. This device (an introducer sheath system) is a physical medical instrument, not an AI-powered diagnostic tool. Therefore, MRMC studies, human reader improvement with AI, or effect sizes are not relevant to its evaluation.

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

N/A. This device does not involve an algorithm.

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

The "ground truth" for this device's evaluation is based on engineering standards, material science, and manufacturing quality control. For example, the ground truth for mechanical testing would be the specified strength or flexibility required by relevant standards, and for biocompatibility, it would be the absence of adverse biological reactions. It's not a clinical "ground truth" derived from patient diagnosis.

8. The sample size for the training set

N/A. The concept of a "training set" applies to machine learning models. This device does not involve AI or machine learning.

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

N/A. As there is no training set, this is not applicable.

In summary: The provided document is an FDA 510(k) clearance letter and summary for a medical device (an introducer sheath). The evaluation framework for such a device focuses on "substantial equivalence" to existing predicate devices, primarily through non-clinical performance data (mechanical, biocompatibility, sterilization, aging). This is fundamentally different from the evaluation criteria and study types used for AI-powered diagnostic tools, which would involve clinical data, ground truth establishment by experts, and statistical performance metrics.

Ask a specific question about this device