Search Results

The SpyCatch™ Stone Retrieval Basket is used endoscopically to entrap and remove stones from the biliary system. The SpyCatch Stone Retrieval Basket is designed to be used through the working channel of a delivery device accessing the biliary system.

The proposed SpyCatch is a stone retrieval device designed to pass through the working channel of a scope with a working channel of >1.1mm and retrieve stones inside the biliary duct.

The provided text is a 510(k) summary for the SpyCatch™ Stone Retrieval Basket. It addresses a medical device, not a an AI/ML device, and therefore the acceptance criteria and study information typically sought for AI/ML devices (e.g., sample sizes of test/training sets, ground truth establishment, expert qualifications, MRMC studies) are not applicable or available in this document.

The 510(k) process is primarily focused on demonstrating substantial equivalence to a legally marketed predicate device through engineering and performance testing.

Here's a breakdown of the information that is available, and why certain AI/ML-specific questions cannot be answered from this document:

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

The document states:

• "Design Verification testing has been conducted to confirm that the proposed basket meets its intended use."
• "The SpyCatch™ Stone Retrieval Basket represents the same fundamental scientific technology as the currently marketed Biliary Flat Wire Baskets, K925879."

This implies that the acceptance criteria are likely related to standard engineering performance specifications for stone retrieval baskets (e.g., basket strength, flexibility, deployment/retraction reliability, stone capture effectiveness in a benchtop model, biocompatibility). However, the specific acceptance criteria and the numerical results of these tests are not detailed in this 510(k) summary. These details would typically be found in the full 510(k) submission, not the publicly available summary.

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

• Not applicable / Not provided. For a mechanical device like a stone retrieval basket, "test sets" in the AI/ML sense (e.g., a set of patient images) are not relevant. Testing would involve benchtop simulations, material testing, and potentially animal or cadaver studies, but the sample sizes for these types of engineering tests are not disclosed in this summary. Data provenance is also not applicable for this type of device submission.

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 / Not provided. Ground truth, in the context of expert consensus, is not relevant for the performance evaluation of a mechanical stone retrieval basket. Device performance is assessed against engineering specifications, often validated by engineers or technicians, rather than clinical experts establishing a "ground truth."

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

• Not applicable / Not provided. Adjudication methods are typically associated with resolving discrepancies in expert interpretations (e.g., in an AI/ML study). This concept does not apply to the performance testing of a mechanical device.

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 or screening devices (often AI-powered) where human readers are interpreting cases. This device is a surgical tool, not a diagnostic one, and does not involve human "readers" or AI assistance in interpretation.

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

• Not applicable. This question pertains to AI algorithms. The SpyCatch™ is a physical surgical tool; it does not have an "algorithm" component.

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

• Not applicable / Engineering Specifications. As explained above, for a mechanical device, ground truth as clinical data is not the primary assessment. The device's "truth" is its ability to meet predefined engineering and functional specifications (e.g., ability to deploy, capture, and retrieve a stone in a simulated environment).

8. The sample size for the training set

• Not applicable. This question is specific to AI/ML models. There is no "training set" for a mechanical device.

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

• Not applicable. See point 8.

Summary for the SpyCatch™ Stone Retrieval Basket:

The K071066 submission for the SpyCatch™ Stone Retrieval Basket is for a Class II mechanical medical device. The regulatory pathway is a 510(k), which requires demonstration of "substantial equivalence" to a predicate device (Boston Scientific Corporation's Biliary Flat Wire Baskets, K925879).

The "study" referenced in the document is Design Verification testing. This testing is conducted to "confirm that the proposed basket meets its intended use." The basis for equivalence is the "same fundamental scientific technology" as the predicate device.

To reiterate, the questions regarding AI/ML device evaluation criteria (sample sizes, ground truth establishment by experts, adjudication, MRMC studies, standalone performance, training sets) are not applicable to this type of device submission. The 510(k) summary provides evidence of substantial equivalence through technological characteristics and design verification testing, rather than clinical efficacy trials or AI performance metrics.

Ask a specific question about this device