Search Results

The React™ 71 Catheter is indicated for the introduction of interventional devices into the peripheral and neuro vasculature.

The React™ 71 Catheter is a single lumen, flexible, variable stiffness composite catheter with a nitinol structure that is jacketed with various durable polymer outer layers. A lubricious, polytetrafluoroethylene liner and Engage™ inner layer is used to create a structure that has both proximal stiffness and distal flexibility. The React™ 71 Catheter is also designed with an encapsulated radiopaque distal platinumiridium marker band which is used for visualization under fluoroscopy. The React™ 71 Catheter is introduced into the vasculature through the Split-Y Introducer Sheath. The proximal end of the React™ 71 Catheter is designed with a green thermoplastic elastomer strain relief and a clear hub. The distal end of the React™ 71 Catheter is coated with a Surmodics Serene™ Coating.

The provided text describes a 510(k) submission for the React™ 71 Catheter, focusing on demonstrating substantial equivalence to a predicate device after a change in device length. The information primarily covers non-clinical bench testing.

Here's an analysis of the provided information against your requested categories:

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

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

• Sample Size: Not explicitly stated. The text mentions "non-clinical bench testing was conducted," but does not provide details on the number of devices tested for each criterion.
• Data Provenance: Not specified. "Non-clinical bench testing" typically implies laboratory-based tests. The country of origin of the data is not mentioned. The data is prospective in the sense that new tests were conducted for this submission, but it's not clinical human data.

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 section is not applicable as the study described is non-clinical bench testing, not a study involving human or animal data requiring expert ground truth for interpretation.

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

This section is not applicable as the study described is non-clinical bench testing against predefined performance criteria, not a study involving subjective interpretations requiring 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, an MRMC comparative effectiveness study was not done. This submission is for a percutaneous catheter, not an AI-powered diagnostic device.

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

No, a standalone algorithm performance study was not done. This submission is for a physical medical device (catheter), not an algorithm or software.

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

For the non-clinical bench tests, the "ground truth" is defined by the acceptance criteria established in the test methods, based on FDA Guidance 1757 and FDA Recognized Consensus Standards 5-125 & 5-129. These are objective engineering and performance standards, not clinical ground truths like pathology or expert consensus.

8. The sample size for the training set

This section is not applicable. This is a 510(k) submission for a physical medical device, not a machine learning or AI algorithm that requires a training set.

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

This section is not applicable for the reasons stated in point 8.

Ask a specific question about this device

Axium™ Detachable Coil:

Axium™ Detachable Coils are intended for the endovascular embolization of intracranial aneurysms. Axium™ Detachable Coils are also intended for the embolization of other neuro vascular abnormalities such as arteriovenous malformations and arteriovenous fistulae.

Axium™ Prime Detachable Coil:

(Models: APB-X-Y-3D-ES, APB-X-Y-3D-SS, APB-X-Y-HX-ES, APB-X-Y-HX-SS)

The Axium™ Prime Detachable Coils are intended for the endovascular embolization of intracranial aneurysms. The Axium™ Prime Detachable Coils are also intended for the embolization of other neuro vascular abnormalities such as arteriovenous malformations and arteriovenous fistulae.

Axium™ Prime Detachable Coil:

(Models: FC-X-Y-3D)

The Axium™ Prime Detachable Col is intended for the endovascular embolization of intracranial aneurysms and other neurovascular abnormalities, such as arteriovenous malformations and arteriovenous fistulae. The Axium™ Prime Detachable Coils are also intended for arterial and venous embolizations in the peripheral vasculature.

The Axium™ Detachable Coil and Axium™ Prime Detachable Coil consist of a platinum embolization coil attached to a composite implant delivery pusher with a radiopaque positioning marker and a hand-held Instant Detacher (I.D.) which when activated detaches the coil from the delivery pusher tip. The I.D. is sold separately.

The document provided focuses on the substantial equivalence of the "Axium™ Detachable Coil" and "Axium™ Prime Detachable Coil" with the addition of fluorosafe markers. The primary purpose of the submission is to demonstrate that these changes do not raise new questions of safety and effectiveness compared to the predicate devices. Therefore, the "device" in question is not an AI/ML powered diagnostic device, but rather a neurovascular embolization device with a minor design change.

As such, many of the typical acceptance criteria and study details relevant to AI/ML powered devices, such as sample size for test sets, data provenance, number of experts for ground truth, adjudication methods, MRMC studies, standalone performance, and training set details, are not applicable or provided in this document. The provided text describes bench testing and biocompatibility testing for the physical device itself.

However, I can extract the relevant "acceptance criteria" and "reported device performance" as presented for the specific tests conducted for this submission.

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size: Not explicitly stated for each test, but standard for device verification and validation. For biocompatibility, animal models were used (guinea pig, rabbit, mice). For bench tests, "devices" (plural) were evaluated, implying a sample size greater than one but not specified numerically.
• Data Provenance: Not applicable in the context of AI/ML data sets. These are laboratory tests on physical devices.

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. The "ground truth" for this device modification is established through physical and objective measures against predefined specifications and recognized international standards (e.g., ISO 10993, USP 151) and user needs (for marker visibility). The "clinical users" who evaluated fluorosafe marker visibility are mentioned, but their number and specific qualifications are not detailed.

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

• Not applicable. Adjudication methods are typically for subjective assessments (e.g., image interpretation). These tests involve objective measurements and evaluations against specified criteria and standards.

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 submission is for a physical medical device (embolization coil) with a minor design change (adding fluorosafe markers), not an AI-powered diagnostic tool. No MRMC study was conducted.

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.

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

• The "ground truth" here is based on objective measurements against established engineering specifications, chemical/biological compatibility standards (ISO 10993, USP 151), and documented user needs. For example, meeting the criteria for "non-cytotoxic" or demonstrating "no corrosion."

8. The sample size for the training set

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

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

• Not applicable. There is no "training set."

Ask a specific question about this device

Phenom™ Catheters are intended for the introduction of interventional devices or diagnostic agents into the neuro, peripheral, and coronary vasculatures.

The Phenom™ Catheters are variable stiffness, single lumen catheters designed to access small, tortuous vasculature. They are available in a variety of lengths, stiffness and inner and outer diameters. The outer surface of the catheter is coated to enhance navigation in the vessel. The Phenom™ 17, 21, and 27 Catheters have a hydrophilic coating that spans the distal 100cm. The Phenom™ Plus Catheters have a hydrophilic coating that spans the distal 90cm. The catheter also incorporates a liner to facilitate movement of introduction devices passing through its lumen. The distal tip has radiopaque marker(s) to aid visualization and positioning under fluoroscopy. The Phenom™ Catheter is packaged with a shaping mandrel and may be accompanied with a split introducer sheath.

The provided text describes the regulatory clearance for the "Phenom Catheters" and includes performance data from bench testing. However, it does not describe any study involving AI, human readers, or the establishment of ground truth for such a study. Therefore, I cannot fulfill your request for information related to AI or human-in-the-loop performance.

The document focuses on demonstrating substantial equivalence to predicate devices through non-clinical bench testing. There is no mention of acceptance criteria or performance metrics in the context of an AI-based device, a multi-reader multi-case (MRMC) study, or standalone algorithm performance.

Here's a breakdown of the information that is present in the document, framed against your request:

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

The document provides a table of "Tests" with "Test Method Summary" and "Results." The "Results" column implicitly indicates that the acceptance criteria were met for each test, as it states "The Phenom™ Catheters met the acceptance criteria for..." or "acceptable friction force," "compatible for use," etc.

Regarding the other points of your request, the document does not provide this information because it's for a medical device (catheter) and not an AI-based system:

• 2. Sample size used for the test set and the data provenance: Not applicable. The testing described is bench testing of physical devices, not a test set of data.
• 3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. Ground truth for data interpretation is not relevant for this type of device submission.
• 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. This device is not an AI system.
• 6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable. This device is not an algorithm.
• 7. The type of ground truth used (expert consensus, pathology, outcomes data, etc): Not applicable. The "ground truth" for the catheter is its ability to perform according to engineering specifications and biocompatibility standards.
• 8. The sample size for the training set: Not applicable. This is not an AI model requiring a training set.
• 9. How the ground truth for the training set was established: Not applicable.

In summary, the provided document details the regulatory clearance of a physical medical device (catheter) based on non-clinical performance and biocompatibility testing, not an AI software/device.

Ask a specific question about this device