Search Results

The Endo SmartCap™ is intended to be used with an air or CO2 source and/or a pump along with a sterile water source to supply air or CO2 and sterile water to an endoscope during endoscopic procedures.

The Endo SmartCap™ supplies sterile water and either air or CO2 to an endoscope during endoscopic procedures when connected to a sterile water source and an air or CO2 source. Two tubes are arranged coaxially; air or CO2 supplied through the outer tube pressurizes the sterile water container, forcing water up through the inner tube and to the endoscope. The proximal end of the tube set includes a bottle cap for attachment to a user-provided sterile water container; the Endo SmartCap™ is compatible with all major brands of sterile water containers. The proximal end of the tube set terminates in a tube weight which keeps the tip of the tubing submerged. A pinch clip prevents water from dripping from the tube's distal end when the device is detached from the endoscope. The distal end of the tube set terminates in a connector which mates with the corresponding brand of endoscope; Endo SmartCap™ models are available for all major brands of endoscopes. The device is provided sterile (EtO). The device is fabricated from metals, plastics, and elastomers. The Endo SmartCap™ is intended for 24 hour multi-patient use and should be discarded daily. No portion of the device comes in direct contact with patients.

The provided text is a 510(k) Premarket Notification for the "Endo SmartCap™" device. This document focuses on demonstrating substantial equivalence to a predicate device, rather than proving that an AI/ML device meets specific performance criteria. The document describes a medical device accessory, not an AI/ML system.

Therefore, many of the requested details about acceptance criteria for AI/ML performance, study design, sample sizes for test/training sets, expert involvement, and ground truth establishment cannot be found in this document because the device is a physical accessory (Endoscope and Accessories), not an AI/ML software.

However, I can extract the information related to the device's functional performance testing.

Here's what can be extracted from the document:

1. Table of Acceptance Criteria and Reported Device Performance (for functional testing):

2. Sample size used for the test set and the data provenance:

• Sample Size: Not explicitly stated as a number of devices/tests, but implies multiple production samples for the flow rate test ("average mean flow of the 100551-production sample").
• Data Provenance: The document does not specify the country of origin of the data. The tests conducted are functional performance tests of the device itself, not data-driven performance. The tests are retrospective in the sense that they were conducted for the 510(k) submission.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

• This is not applicable as the device is a physical accessory undergoing functional engineering tests (flow rate, backflow prevention), not an AI/ML algorithm requiring expert interpretation of medical images or data for ground truth. The "ground truth" here is the objective measurement of physical properties.

4. Adjudication method for the test set:

• Not applicable for functional engineering tests. The results are objective measurements against predefined engineering specifications.

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 device is a physical medical accessory, not an AI/ML system for diagnostic assistance. No human reader studies with or without AI were conducted or are relevant.

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

• Not applicable. This is not an algorithm. The reported tests are for the standalone physical device's functional performance.

7. The type of ground truth used:

• For flow rate and backflow prevention tests, the "ground truth" is established by engineering specifications and direct physical measurement. For example, for flow rate, it would involve direct measurement of water/gas volume over time. For backflow, it's the observation of whether water backflows into the insufflator.

8. The sample size for the training set:

• Not applicable. This is not an AI/ML device, so there is no training set.

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

• Not applicable. As there is no training set for an AI/ML algorithm, there is no ground truth for a training set.

In summary, this document is for a traditional medical device accessory (Endo SmartCap™) seeking 510(k) clearance based on substantial equivalence. The "study that proves the device meets the acceptance criteria" in this context refers to engineering performance testing rather than the clinical validation or AI algorithm performance studies typically associated with the detailed questions provided.

Ask a specific question about this device