Search Results

EG-530UT2 and EG-530UR2 are intended to provide ultrasonic images of submucosal and peripheral organs of the upper gastrointestinal tract for observation, diagnosis, and endoscopic treatment. The product is intended to be used with a Fujifilm ultrasonic processor. This product is not intended for use on children and infants.

FUJIFILM Ultrasonic Endoscopes EG-530UT2 and EG-530UR2 are upper gastrointestinal endoscopes that emit ultrasound waves and scan the reflected signals to provide ultrasonic images when used in combination with an ultrasonic processor.

The provided text describes a 510(k) premarket notification for FUJIFILM Ultrasonic Endoscopes EG-530UT2 and EG-530UR2. This document focuses on demonstrating substantial equivalence to a predicate device, rather than proving that a new AI/software device meets specific performance criteria through a clinical study.

Therefore, the requested information regarding acceptance criteria for an AI/software device and a study to prove it meets them cannot be fully extracted from this document. The document lists performance tests for the physical endoscopic devices (e.g., field of view, bending capability, resolution, air/water supply rates), but these are for hardware performance, not AI/software performance.

However, I can extract the information related to the device performance and acceptance criteria for the physical endoscopy device as described in the document.

Here's a breakdown of what can be extracted and what cannot be, based on the provided text:

What Can Be Extracted (for the physical endoscope device):

1. A table of acceptance criteria and the reported device performance:
   The document states: "Fujifilm conducted the following performance testing on the proposed devices EG-530UT2 and EG-530UR2 to ensure that the modified devices perform equivalently to the predicate devices:

   • Field of view
   • Viewing direction
   • Bending capability
   • Resolution
   • Air supply rate
   • Water supply rate
   • Axial resolution
   • LG output
   • Suction rate
   • Working length
   • Lateral resolution
   • Penetration depth
   • Forceps channel diameter

   In all cases, the devices met the pre-defined acceptance criteria for the test."

   Therefore, the table would look like this (specific values are not provided in the document, only the claim of meeting criteria):

   Acceptance Criteria (Measured Parameter)	Reported Device Performance
   Field of view	Met pre-defined criteria
   Viewing direction	Met pre-defined criteria
   Bending capability	Met pre-defined criteria
   Resolution	Met pre-defined criteria
   Air supply rate	Met pre-defined criteria
   Water supply rate	Met pre-defined criteria
   Axial resolution	Met pre-defined criteria
   LG output	Met pre-defined criteria
   Suction rate	Met pre-defined criteria
   Working length	Met pre-defined criteria
   Lateral resolution	Met pre-defined criteria
   Penetration depth	Met pre-defined criteria
   Forceps channel diameter	Met pre-defined criteria

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

   • Sample Size: Not explicitly stated for each performance test. The document refers to "the proposed devices EG-530UT2 and EG-530UR2" performing these tests, suggesting testing on the physical devices themselves rather than a separate dataset of patient cases.
   • Data Provenance: Not specified. This is a pre-market submission, and the tests are likely internal lab/bench testing of the device hardware.

What Cannot Be Extracted (as it's not an AI/software performance study):

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. Ground truth for physical device performance typically comes from engineering specifications and measurements, not expert human interpretation of medical images.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable.
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. This document does not describe an AI-assisted diagnostic device or an MRMC study.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable, as this is not an AI algorithm.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.): Not applicable for an AI/software context. Ground truth for physical device specs (like resolution, field of view) is based on engineering measurements against design specifications.
8. The sample size for the training set: Not applicable. This document is not about AI training.
9. How the ground truth for the training set was established: Not applicable.

In summary: The provided FDA 510(k) clearance document for FUJIFILM Ultrasonic Endoscopes EG-530UT2 and EG-530UR2 pertains to demonstrating substantial equivalence of a physical medical device (endoscope) to a predicate, primarily through engineering performance testing (e.g., field of view, bending capability, resolution, fluid rates), electrical safety, and biocompatibility. It is not a document describing the validation of an AI/software device, and therefore the specific criteria related to AI performance studies cannot be found within it.

Ask a specific question about this device