Search Results

The G-EYE® colonoscope is intended to be used with a compatible video processor (including light source), documentation equipment, monitor, endotherapy device such as a biopsy forceps, and other ancillary equipment for endoscopy and endoscopic surgery within the lower gastrointestinal tract including the anus, rectum, sigmoid colon, colon and ileocecal valve. It incorporates a balloon at the colonoscope to maintain central positioning within the lumen and help control the endoscope's view field and/or endoscope positioning.

The G-EYE® System comprises the G-EYE® Colonoscope and the NaviAid™ SPARKC ("SPARKC") inflation pump. The G-EYE® Colonoscope includes a reprocessable, reusable balloon (the G-EYE® balloon) that is attached to a standard, commercially available colonoscope which is remanufactured by Smart Medical to include the balloon at its bending section. The balloon onto the standard colonoscope is considered remanufacturing of the standard colonoscope by Smart Medical, which assumes responsibility for the final device including the G-EYE® balloon and the remanufactured colonoscope. The G-EYE® balloon is inflated by the dedicated SPARKC inflation system, which enables automatic control of the required balloon pressure in one of several user-selected, system-controlled pressure levels such that the balloon conforms to the colonic lumen diameter. The G-EYE® Colonoscope is advanced by the endoscopist with the balloon deflated, which essentially preserves the standard colonoscope's diameter and insertion technique. At the cecum, the balloon is inflated to engage the colon walls, and the colonoscope is then withdrawn by the endoscopist using standard withdrawal technique. Withdrawal of the inflated balloon mechanically straightens the colonic folds and anatomic flexures, centers the colonoscope optics within the colonic lumen, and minimizes uncontrolled bowel slippage during withdrawal, therefore maintaining the endoscope's field of view

The provided text (FDA 510(k) summary for the G-EYE® System) does not contain detailed information about acceptance criteria and a study proving the device meets these criteria in the format requested. Specifically, it lacks:

• A table of acceptance criteria and reported device performance.
• Sample sizes used for a test set specifically for evaluating the AI component (as the device described is not an AI/software as a medical device in the typical sense but rather a physical colonoscope system with a balloon).
• Data provenance for a test set.
• Details on expert involvement, ground truth establishment, or adjudication methods for a test set.
• Information on MRMC studies or effect sizes of human reader improvement with AI assistance.
• Standalone algorithm performance.
• Type of ground truth used.
• Sample size for a training set or how its ground truth was established.

The document discusses performance data in the context of demonstrating substantial equivalence to a predicate device, focusing on verification bench testing, reprocessing validation, biocompatibility, software verification/validation, and electrical safety/EMC. It also mentions three clinical studies conducted outside the United States that further support safety and performance, but these are noted as "not required to demonstrate substantial equivalence" and are presented at a high level.

Therefore, many of the requested points cannot be answered from the provided text because the device is a hardware system, not an AI software, and the document focuses on regulatory clearance via substantial equivalence rather than a detailed AI performance study.

However, I can extract the information that is present regarding performance and its acceptance:

Acceptance Criteria and Device Performance (as inferred from the text)

The document doesn't explicitly list quantitative "acceptance criteria" for a study in a table, but it states that various tests "met its acceptance criteria, supporting substantial equivalence to the predicate."

Here's a summary of the performance "studies" and what they aimed to achieve in terms of acceptance:

Other Requested Information:

Since this is a filing for a physical medical device (colonoscope system) and not an AI/software device, much of the requested information (especially points 2-5, 8-9) is not applicable or not provided in the context of an AI performance study.

1. Sample size used for the test set and the data provenance: Not applicable in the context of an "AI test set." For the clinical studies (which were supplementary and not primary for 510(k) clearance): "over 1000 subjects" combined across three studies. Data provenance is "outside the United States." It's not specified if they were retrospective or prospective, but clinical studies are typically prospective.
2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable as this is not an AI/diagnostic imaging device requiring expert ground truth in this manner for its 510(k). The clinical studies involved medical professionals using the device.
3. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable for this type of device and regulatory submission.
4. 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 assistance tool for human readers.
5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable.
6. The type of ground truth used (expert consensus, pathology, outcomes data, etc): For the clinical studies, the "ground truth" was essentially the observed performance of the device in facilitating procedures, absence of adverse events, and aiding visualization. These are clinical outcomes rather than a "ground truth" for an AI diagnostic task.
7. The sample size for the training set: Not applicable. This is not an AI device trained on data.
8. How the ground truth for the training set was established: Not applicable.

Ask a specific question about this device