Search Results

Intended for the endovascular embolization of:

• Intracranial aneurysms. .
• Other neurovascular abnormalities such as arteriovenous . malformations and arteriovenous fistulae.
• Arterial and venous embolizations in the peripheral vasculature. .

The Boston Scientific Neurovascular Guglielmi Detachable Coil (GDCTM) is a device which facilitates endovascular embolization of intracranial aneurysms and other vascular abnormalities. The GDCTM Detachable Coil is a platinum/tungsten alloy coil attached to a stainless steel delivery wire. The GDCTM Detachable Coil is detached (using the GDCTM Power Supply) by electrolytically dissolving a small portion of the delivery wire upon its desired placement within an aneurysm or other vascular site via a microcatheter. Multiple coils can be delivered into an aneurysm or other vascular site through the same microcatheter until the aneurysm or other vascular site is densely packed.

The acceptance criteria for the Guglielmi Detachable Coil (GDC™) are implicitly met by demonstrating substantial equivalence to the predicate device, specifically regarding an expanded indication for use. The primary basis for this expanded indication is the results of the International Subarachnoid Aneurysm Trial (ISAT).

Here's the breakdown of the information requested:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size: The International Subarachnoid Aneurysm Trial (ISAT) included 2143 patients.
• Data Provenance: The study was an "International Subarachnoid Aneurysm Trial." While specific countries are not listed in the provided text, the name "International" suggests data from multiple countries. The study is a prospective, randomized trial, comparing two treatment methods.

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

The provided summary of the ISAT study focuses on the clinical outcomes of the patients rather than the establishment of a "ground truth" for diagnostic purposes by experts in a specific image interpretation scenario. The study's design as a randomized controlled trial inherently establishes the "truth" through patient outcomes (dependency or death at 1 year) following different interventions.

Therefore, the concept of "number of experts used to establish ground truth" with specific qualifications in the context of interpreting medical images for device performance validation (as one might see in an AI/imaging device submission) is not directly applicable here. The "ground truth" is the observed clinical outcome of the patients in the trial, determined by standard clinical follow-up and assessment, not by expert consensus on a set of images.

4. Adjudication Method for the Test Set

The document does not explicitly describe an adjudication method for the test set in the way it might for a diagnostic study. As a clinical trial comparing two interventions and their outcomes, the "adjudication" would refer to how patient outcomes (dependency or death) were assessed and classified during follow-up. While not detailed, such large-scale clinical trials typically employ:

• Standardized outcome measures: e.g., modified Rankin Scale for dependency.
• Blinded assessment (if feasible): Assessors of outcomes (e.g., neurologists) might be blinded to the initial treatment arm (coiling vs. clipping), though this is often challenging in interventional trials due to visible procedural scars or imaging findings that reveal the treatment.
• Independent monitoring committees: These committees often review adverse events and critical outcomes to ensure proper reporting and adherence to the study protocol.

The specific "2+1, 3+1" adjudication methods are typically for image interpretation tasks, which is not the primary focus of this clinical effectiveness study.

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

This was not an MRMC comparative effectiveness study in the traditional sense of evaluating human reader performance with or without AI assistance. The ISAT study was a direct clinical trial comparing two different medical interventions (endovascular coiling vs. neurosurgical clipping) in patients with ruptured intracranial aneurysms. It evaluated the effectiveness of the GDC™ device itself against the predicate surgical clipping, not a diagnostic algorithm's impact on human readers.

Therefore, the effect size of how much human readers improve with AI vs. without AI assistance is not applicable to this study.

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

This was not a standalone performance study of an algorithm. The GDC™ is a physical medical device (detachable coil) for embolization, not a diagnostic algorithm. Its performance is intrinsically linked to the interventional procedure performed by a human clinician.

7. The Type of Ground Truth Used

• Clinical Outcomes Data: The ground truth used was patient clinical outcomes at 1 year post-treatment, specifically the rates of dependency or death. This is based on direct observation of patient health status following the intervention.

8. The Sample Size for the Training Set

The concept of a "training set" is not directly applicable to this premarket notification as it pertains to a physical medical device and a clinical trial. The ISAT study is a pivotal clinical trial designed to test the device's expanded indication, not to train an algorithm. Previous clinical experience and trials would have informed the development and initial indications of the GDC™, but ISAT is the primary evidentiary support mentioned for this specific submission.

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

As explained above, a "training set" in the context of algorithm development is not relevant here. The ISAT study provides the evidence (the "truth" in a clinical trial sense) for the device's performance regarding an expanded indication. This "truth" was established through the rigorous methodology of a randomized controlled clinical trial, where patient characteristics, interventions, and outcomes were systematically recorded and analyzed by the ISAT Collaborative Group.

Ask a specific question about this device

See table below

Please refer to Table 1 (Page 10)

The provided text is a 510(k) summary for various medical devices by Target Therapeutics. It primarily focuses on demonstrating substantial equivalence to predicate devices based on functional, chemical, biocompatibility, and sterile barrier tests.

This document does not contain information on acceptance criteria and a study that proves the device meets those criteria in the context of AI/ML performance.

Instead, it details laboratory-based testing for physical and chemical properties and refers to section 6 of the submission for further details on these tests. There is no mention of a study involving human readers, ground truth established by experts, or AI performance metrics.

Therefore, I cannot fulfill your request for information related to AI/ML acceptance criteria and studies based on the provided text. The document is for a traditional medical device submission, not an AI/ML-driven one.

Ask a specific question about this device