Search Results

The proposed SpyGlass Direct Visualization Probe is intended to provide direct visualization for diagnostic and therapeutic applications during endoscopic procedures in the pancreatico-biliary system including the hepatic ducts.

The proposed SpyGlass Direct Visualization Probe a fiberoptic endoscope. The proposed device is used through the SpyScope Access and Delivery Catheter (K051504) which provides stability for steering the device. The delivery catheter/probe is inserted into the working channel of a duodenoscope for entry into the duodenum for access to the indicated site.

The provided document is a 510(k) summary for the Boston Scientific SpyGlass™ Direct Visualization Probe. It details a submission for substantial equivalence to a predicate device, not a study performing comparative effectiveness or standalone performance with specific acceptance criteria in the typical sense of a novel algorithm or AI device.

Therefore, many of the requested elements (like sample size for test/training sets, number of experts for ground truth, adjudication methods, MRMC studies, standalone performance with acceptance criteria, ground truth types for training) are not applicable or cannot be extracted from this type of FDA submission.

Here's a breakdown of what can be extracted based on the document:

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

The document states: "A comparison of the optical performance and image quality specifications was made between the proposed and predicate SpyGlass™ Direct Visualization Probe." It also mentions "Electrical safety testing was performed in accordance with industry standards."

This indicates that the acceptance criteria were based on:

• Equivalence in optical performance and image quality to the predicate device (K050403). Specific quantitative metrics for these "specifications" are not provided in this summary.
• Compliance with industry standards for electrical safety. The specific standards are not listed.

Since this is a submission for substantial equivalence to an existing device, the "reported device performance" is essentially that it met these equivalence and safety benchmarks, making it like the predicate. No specific performance metrics (e.g., sensitivity, specificity, accuracy) are reported because it's not a new performance claim but an equivalence claim.

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. This 510(k) does not describe a clinical study with a test set of data (e.g., patient cases) to evaluate an algorithm's performance. Instead, it describes a technical comparison of the physical device and its components to a predicate device.

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. No ground truth establishment by experts for a test set of data is described in this submission. The comparison is technical.

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

• Not Applicable. No test set or associated adjudication method is described.

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. This document describes a traditional medical device (a mini-endoscope), not an AI or imaging diagnostic algorithm requiring an MRMC study.

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

• No. This is not an algorithm, but a physical medical device. Standalone performance as described (algorithm only) is not applicable.

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

• Not Applicable. No "ground truth" in the context of diagnostic accuracy against a reference standard is used or described. The "ground truth" for this submission would be the verifiable specifications and performance of the predicate device and relevant industry safety standards.

8. The sample size for the training set:

• Not Applicable. No training set, as would be relevant for an AI/ML model, is described.

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

• Not Applicable. No training set or associated ground truth establishment is described.

Ask a specific question about this device