Search Results

The Indy OTW™ Vascular Retriever is intended to snare a foreign body and withdraw it to a peripheral vascular location.

The Indy OTW™ Vascular Retriever consists of a 4-loop nitinol wire snare attached to an inner catheter (which is attached proximally to a metal cannula) and includes an outer Flexor sheath. The device is compatible with a 0.035 inch wire guide for over-the-wire introduction. The Flexor sheath has a radiopaque band incorporated within the sheath material to identify the location of the sheath's distal tip.

The provided text describes the Cook Incorporated Indy OTW™ Vascular Retriever, a medical device for snaring and retrieving foreign bodies in the vascular system. However, it does not contain the specific information requested about the acceptance criteria or a study proving the device meets those criteria, particularly in the context of an AI/human-in-the-loop system.

The document is a 510(k) summary for a medical device cleared by the FDA. It focuses on demonstrating substantial equivalence to a predicate device through manufacturing and performance testing, not on the performance of a software algorithm or AI.

Therefore, I cannot fulfill your request for the specific points listed (AI performance, sample sizes for test/training sets, ground truth establishment, MRMC studies, standalone performance) based on the provided text.

The closest information related to "acceptance criteria" and "device performance" in this document is in Section VII, "PERFORMANCE DATA". It lists various types of engineering and materials testing performed, but these are for the physical device itself, not an AI component.

Here's what can be extracted from the provided text regarding "acceptance criteria" and "device performance" for the physical device, recognizing it does not apply to an AI system:

1. Table of Acceptance Criteria and Reported Device Performance (as much as can be inferred from the text):

Regarding the other requested information (which is specific to AI/software performance):

• 2. Sample sized used for the test set and the data provenance: Not applicable to the provided document, as it describes a physical medical device, not an AI system.
• 3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable.
• 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.
• 8. The sample size for the training set: Not applicable.
• 9. How the ground truth for the training set was established: Not applicable.

The document details the evaluation of a physical vascular retriever based on mechanical, material, and simulated use tests designed to establish its safety and effectiveness and substantial equivalence to a predicate device. It does not involve any artificial intelligence or machine learning components.

Ask a specific question about this device

Alight™ 16 Superselective Microwire Guides are intended for use in facilitating delivery of percutaneous catheters into the peripheral vasculature.

Alight™ 16 Superselective Microwire Guides are 0.016 inches (0.41 mm) in diameter and are available in a variety of lengths and configurations. The core mandril of the Alight Superselective Microwire Guides is made of nitinol with a polymer coating and spans the entire length of the device to help facilitate flexibility and torqueability. The distal length of the device is covered with a hydrophilic coating.

This document describes the testing and acceptance criteria for the Alight™ 16 Superselective Microwire Guides.

1. Table of Acceptance Criteria and Reported Device Performance

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

The provided document does not explicitly state the numerical sample size used for the test set for each individual test. It consistently refers to "all test articles" being subjected to the tests, implying that the entire batch of samples prepared for testing was used without presenting specific numerical counts.
The data provenance (country of origin, retrospective/prospective) is not mentioned in the provided text. It can be inferred that the testing was prospective as it was conducted specifically for this premarket notification.

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

The provided text describes performance testing of a medical device (microwire guide). For such physical and biocompatibility testing, "ground truth" is typically established through adherence to standardized testing protocols and validated measurement techniques, rather than expert consensus on interpretive data. There is no mention of experts being used to establish a "ground truth" in the way that would apply to interpretative diagnostic studies (e.g., radiologists interpreting images). The "ground truth" here is the physical measurement against set engineering and biocompatibility standards.

4. Adjudication Method for the Test Set

Not applicable. As described above, the tests are primarily objective performance measurements against predetermined engineering and biocompatibility criteria, not subjective interpretations requiring adjudication.

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

No. The provided document relates to the premarket notification for a medical device (microwire guide), not a diagnostic or interpretative AI system. Therefore, an MRMC comparative effectiveness study involving human readers and AI assistance is not relevant or described.

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

Yes, in a sense. The testing described is entirely "standalone" in that it assesses the device's inherent physical and biological performance characteristics without integration into a human workflow or requiring human interpretation for its primary function. The device's performance is evaluated intrinsically.

7. The Type of Ground Truth Used

The ground truth for the performance tests described (Torque Response, Lubricity, Flexing, Fracture, Torque Strength, Tensile, Biocompatibility) is based on:

• Engineering Specifications and Predetermined Acceptance Criteria: These are set values or conditions that the device must meet, derived from design requirements, industry standards (e.g., ISO 11070:2009 for tensile evaluation, ISO 10993-1 for biocompatibility), and internal quality controls.
• Objective Measurements: Laboratory instruments and standardized procedures are used to objectively measure the device's physical properties (e.g., rotational response, peak force, absence of flaking/fracture, tensile strength).
• Standardized Biocompatibility Assays: Established biological tests (e.g., for cytotoxicity, sensitization) with predefined positive and negative controls and interpretation criteria.

8. The Sample Size for the Training Set

Not applicable. This document describes the evaluation of a physical medical device. There is no mention of a "training set" as would be used for machine learning or AI algorithms. The device's design and manufacturing processes are refined through engineering and material science, not through AI training on data.

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