Search Results

FUJIFILM Endoscope Model EG-740N is intended for the upper digestive tract, specifically for the observation, diagnosis, and endoscopic treatment of the esophagus, stomach, and duodenum. The device can be inserted orally or transnasally.

FUJIFILM Endoscope Model EG-740N is comprised of three general sections: a control portion, an insertion portion and an umbilicus. The control portion controls the angulation of the endoscope. This portion also controls the flexibility of the distal end in the endoscope. The insertion portion contains glass fiber bundles, several channels and a complementary Charge-Coupled Device (CCD) image sensor in its distal end. The channels in the insertion portion assist in delivering air/suction as well as endoscope accessories, such as forceps. The glass fiber bundles allow light to travel through the endoscope and emit light from the tip of the insertion portion to illuminate the body cavity. This provides enough light to the CCD image sensor to capture an image and display it on the monitor. The umbilicus consists of electronic components needed to operate the endoscope when plugged in to the video processor and the light source. The endoscope is used in combination with FUJIFILM's video processors, light sources and peripheral devices such as monitor, printer, foot switch, and cart.

The provided document is a 510(k) premarket notification for a medical device, the FUJIFILM Endoscope Model EG-740N. This type of submission focuses on demonstrating substantial equivalence to a legally marketed predicate device rather than proving clinical efficacy or superiority through extensive clinical studies, especially those involving AI algorithms or human reader performance.

Therefore, much of the requested information regarding AI algorithm performance, multi-reader multi-case studies, and detailed ground truth establishment methods for large datasets is not applicable to this specific submission. The document primarily reports on bench testing, electrical safety, and biocompatibility to demonstrate that the new device performs similarly and is as safe as the predicate devices.

Here's a breakdown of the requested information based on the provided text, highlighting what is and is not present:

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

The document states that the subject device met performance specifications in various tests. While it lists the categories, it does not provide specific numerical acceptance criteria or reported performance values in a table format. It simply states that the device "met performance specifications" or that "bench testing data demonstrated that the subject device is substantially equivalent in performance to the predicate devices."

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

The document refers to "bench testing" and "comparative bench testing" without specifying a sample size in terms of number of patients or images. These tests would involve physical testing of the device prototypes. Data provenance and whether it's retrospective or prospective are not relevant for this type of physical device testing.

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)

This is not applicable. The "ground truth" for this device's testing relates to engineering specifications (e.g., does the endoscope bend to the correct angle, is the resolution within specification, does it pass the electrical safety tests). It does not involve human expert interpretation of medical images or clinical outcomes data.

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

This is not applicable. Adjudication methods are used to establish ground truth in clinical data interpretation, typically in studies involving human readers or AI algorithms assessing medical conditions. This submission focuses on engineering and safety performance.

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

This is not applicable. This submission is for a physical endoscope, not an AI-powered diagnostic or assistive tool. Therefore, no MRMC study or assessment of human reader improvement with AI assistance was performed or reported.

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

This is not applicable. This device is a physical endoscope, not a standalone algorithm.

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

The "ground truth" for this submission are the engineering specifications, consensus standards (e.g., ISO, IEC, AAMI), and regulatory guidance documents used for electrical safety, biocompatibility, software validation, and reprocessing validation. For example, the device must meet the specified lumens for light output or specific angles for bending capability, which are objective engineering parameters.

8. The sample size for the training set

This is not applicable. This is a 510(k) for a physical endoscope, not a machine learning or AI algorithm. Therefore, there is no "training set" in the context of data used for algorithm development.

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

This is not applicable for the same reasons as #8.

Ask a specific question about this device