Search Results

These devices are intended for the lower digestive tract, specifically for the observation, diagnosis, and endoscopic treatment of the rectum and large intestine.

FUJIFILM Endoscope Models EC-600HL and EC-600LS are lower gastrointestinal endoscopes that capture images when used in combination with a video processor and light source. Light travels from the light source, through the glass fiber bundles in the endoscopes, and out the tip of the insertion portion to illuminate the body cavity. This provides enough light to the CMOS image sensor to capture an image and display it on the monitor.

This document describes the 510(k) premarket notification for the FUJIFILM Endoscope Models EC-600HL and EC-600LS. The submission aims to demonstrate substantial equivalence to a previously cleared predicate device (K162622). As such, the study performed is a performance testing of the device itself rather than a study on an AI algorithm. Therefore, many of the typical questions for AI/ML study design (e.g., sample size for test/training sets, data provenance, ground truth establishment, MRMC studies) are not applicable in this context.

Here's an analysis of the provided information concerning the device's performance and acceptance criteria:

1. Table of Acceptance Criteria and Reported Device Performance

The document states that "In all cases, the devices met the pre-defined acceptance criteria for the test." However, the exact quantitative acceptance criteria for each test are not explicitly provided in the submitted text. The performance data section lists the parameters tested, but not the specific thresholds for acceptance.

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

This is a physical device performance test rather than an AI/ML algorithm evaluation. The document does not specify the sample size of devices used for testing. It also does not specify data provenance as it's not a data-driven AI study.

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

This information is not applicable. The performance testing is for physical device characteristics, not for diagnostic accuracy requiring expert interpretation.

4. Adjudication Method for the Test Set

This information is not applicable as this is not an AI/ML study requiring expert adjudication of results.

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 is a performance evaluation of a physical endoscope, not an AI-assisted diagnostic tool. Therefore, an MRMC study is not relevant.

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

No. This approval is for an endoscope as a physical medical device, not an algorithm.

7. The type of ground truth used

The "ground truth" here would be the physical and functional specifications of the endoscope. For example, for "Field of view," the ground truth would be the expected angular range, and the device's measurement would need to fall within the accepted tolerance of that specification. The document implies these are established engineering specifications rather than clinical ground truth (e.g., pathology).

8. The sample size for the training set

Not applicable. There is no AI model or training set involved in this device approval.

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

Not applicable. There is no AI model or training set involved. The ground truth for this device's performance would be engineering and design specifications.

Ask a specific question about this device